Synaptics Incorporated has extended its award-winning Synaptics Astra artificial intelligence (AI)-Native platform with the SR-Series high-performance adaptive microcontroller units (MCUs) for scalable context-aware Edge AI. The series features three tiers of operation: performance (100 GOPS), efficiency and ultra-low-power (ULP) always-on (AON) to deliver intelligence at every power level. Based on an Arm Cortex-M55 core and the Arm Ethos-U55 neural processing unit (NPU), the SR-Series is supported by the Astra Machina Micro development kit and open-source SDK. It is optimised for multimodal consumer, enterprise and industrial Internet of Things (IoT) workloads with accelerators and adaptive vision, audio and voice algorithms. The small-form-factor MCUs have a rich set of peripherals—including multiple camera interfaces—to help minimise system cost, power and footprint while enabling integration into a wide range of devices, such as battery-operated security cameras, sensors, appliances, point-of-sale, digital signage and scanners.
Announced at EW2024 with the SL-Series MPUs, the Synaptics Astra AI-Native compute platform for the IoT combines scalable, low-power compute silicon for the device Edge with open-source, easy-to-use software and tools and Veros wireless connectivity. The platform was built upon Synaptics’ foundation in neural networks, field-hardened AI hardware and compiler design expertise for the IoT, and refined, in-house support of a broad base of modalities.
“We believe we are at an inflection point in Edge AI where embedded developers have a unique opportunity to redefine human-machine interaction through multimodal processing and contextual awareness,” said Vikram Gupta, the senior vice president and general manager of IoT processors and the chief product officer at Synaptics. “Unlocking this potential requires a new class of embedded compute silicon. As part of our Astra family, the SR-Series extends our Edge AI processing roadmap with intelligence optimised for various power levels. It allows the development of cognitive IoT devices that seamlessly adapt to their surroundings, from ultra-low-power always-on sensing to high-performance edge inference.”
“Enabling ultra-low-power AI processing at the edge will revolutionise emerging applications across various markets, including retail and smart home, where we are seeing greater performance demands,” said Paul Williamson, the senior vice president and the general manager of IoT line of business at Arm. “With the new SR-Series, built on the Arm compute platform, Synaptics is delivering the real-time intelligence and innovation needed to scale edge AI deployments.”
“Meeting the needs of future intelligent edge devices requires solutions capable of multimodal processing to achieve situational awareness,” said Jim McGregor, the principal analyst at TIRIAS Research. “Synaptics’ SR-Series of AI MCUs offers a scalable solution that maximises IoT device awareness while simplifying integration and optimising power and performance.”
Technical highlights
The SR-Series comprises three MCUs, the SR110, SR105, and SR102, each with its respective features and benefits that cater to a range of multimodal application requirements. All three MCUs use a Cortex-M55 core with Arm Helium technology running up to 400 MHz. The SR110 also has a Cortex-M4 core and Arm Ethos-U55 NPU and is sampling now; the SR105 has an Ethos-U55 NPU; and the SR102 is a single Cortex-M55 device. Other SR-Series features include:
- Up to 4 MB of system memory, including ULP AON memory.
- Streaming vision and audio processing.
- MIPI-CSI camera input and passthrough.
- Low-power image signal processing.
- Secure OTP, TRNG, AES-256, RSA-4096, SHA-512.
The Machina Micro kit maintains Astra’s signature “out-of-the-box” AI development experience for beginners and experts alike.
Comment on this article via X: @IoTNow_ and visit our homepage IoT Now
