GreenWaves Technologies, a fabless semiconductor company based in Grenoble, France, has received the funding needed to support the production of its second-generation GAP9 processor. As demonstrated at CES 2023, this advanced AI processor revolutionizes the next generation of true wireless earbuds, hearables, and connected devices with ultra-low latency noise cancellation, neural network-based background elimination and 3D sound.
GreenWaves Technologies, a fabless semiconductor company based in Grenoble, France, has received the funding needed to support the production of its second-generation GAP9 processor. As demonstrated at CES 2023, this advanced AI processor revolutionizes the next generation of true wireless earbuds, hearables, and connected devices with ultra-low latency noise cancellation, neural network-based background elimination and 3D sound.
GreenWaves is a pioneer in RISC-V application processors for battery powered devices and a performance leader in ultra-low power AI and DSP. The company has recently received a 20 million Euros investment led by private investor Innovacom, together with Thales, Definvest (a fund managed by the French Ministry of Defense) and the French Tech Seed Fund, with the backing of historical shareholders Soitec and Zepp Health and other financings.
GreenWaves will use the funding to ramp up the production of its GAP9 processor which is enjoying significant market traction with tier one hearables vendors. GAP9 allows them to bring to market new audio features such as Neural Network based Noise Filtering and Adaptive Transparency, as the company showcased at CES 2023 in partnership with software and algorithm partners in this space.
The company's second generation processor enables advanced features in neural network steered ultra-low latency, active noise cancellation, neural network based noise reduction and 3D sound. The platform is exceptionally power efficient for voice and music processing, giving headroom in both energy and processing power that can be used to develop innovative new features in audio products, with no compromise in area, cost or energy.
The funding will also support the development of further programmability features of the next generation of earbuds and to enable new automotive applications, exploring the device's best-in-class CNN engine (NE16) for AI based or driven algorithms. GAP9 is also being designed into battery powered IoT products such as smart cameras, condition monitoring sensors and vital sign monitoring devices.
Neural Networks and DSP
GAP9 is a unique combination of a powerful low power microcontroller, a programmable compute cluster with a hardware neural network accelerator and sample by sample audio filtering unit. This combination of hom*ogeneous processing units with integrated hardware acceleration blocks achieves a perfect balance between ultra low power consumption and latency and flexibility and ease of use.
All the 10 cores in the GAP9 processor are based on the RISC-V Instruction Set Architecture extended with custom instructions automatically used by the GAP toolchain. The compute cluster is perfectly adapted to handling combinations of neural network and digital signal processing tasks delivering programmable compute power at extreme energy efficiency.
The architecture employs adjustable dynamic frequency and voltage domains and automatic clock gating to tune the available compute resources and energy consumed to the exact requirements at a particular point in time. GAP9’s unique Smart Filtering Unit is perfectly adapted to ultra low latency (1uS) PDM to PDM filtering tasks but so flexible that it can simultaneously be used as a block filtering coprocessor for tasks executing on the cores. Finally, the device features 3 Serial Audio Interfaces capable of handling up to 48 incoming or outgoing audio signals.
"We are delighted about the rate of customers adoption of GAP9, with a dozen design wins in hearables and IoT. Hearables is on its way to surpass smartphones in innovation and volume," says Loic Lietar, CEO of GreenWaves Technologies. "In IoT applications we serve the most demanding low power smart camera use cases, where GAP9 shines."
Available in a small WL-CSP package (3.7×3.7mm) for more compact form factors, GAP9 provides the ideal platform for companies requiring a combination of neural network, classic and ultra-low latency Digital Signal Processing capabilities in highly energy constrained products. GAP9 enables these applications while remaining highly flexible and easy to program, delivering the lowest energy consumption across all of the tests in the MLPerf Tiny v1.0 inference benchmark.
"The expertise of the GreenWaves Technologies team in both architecture and software tools has made it possible to develop a new generation of easily programmable processors whose performance is unmatched today. After 8 years of R&D, the company is now at an inflection point; we are happy to support GreenWaves Technologies in this new stage of its development, with a scaling up expected this year," adds Gwenael Hamon, Senior Investment Director of Bpifrance (French Tech Seed Fund).
www.greenwaves-technologies.com
