Supergate’s Deep-learning Microcontroller (DMC) first silicon was received in February 2023 with the immediate bring up and successful execution of test networks on the NMP-300 IP licensed from Aim Future
On-floor demonstration will showcase ultra-low-power object detection for consumer electronics.
The DMC is an ideal solution for a broad range of application including the home consumer, robotics, smart toy, and artificial intelligence of things (AIoT)
Product will be available for purchase from August 2023.
Seoul, Korea, and San Jose, CA, May 22, 2023 – SUPERGATE announced today they will demonstrate their newest product, the Deep-learning Microcontroller (DMC), at the 2023 Embedded Vision Summit, the premier event for practical, deployable computer vision and visual AI, for product creators who want to bring visual intelligence to products. This year’s Summit takes place May 22 – 24, 2023, in Santa Clara, California. This annual event brings together a global audience of technology professionals from companies developing computer vision and edge AI-enabled products including embedded systems, cloud solutions and mobile applications. Supergate also announced it has licensed the NMP-300 processor from AiM Future. The NMP-300 is the smallest member of the NeuralMosAIc Processor family optimized to enable ultra-low-power microcontrollers for intelligent sensors and control systems in a variety of applications including home consumer, robotics, toys, and the broad artificial intelligence of things (AIoT). Supergate will showcase its DMC-based computer vision demo in Booth #801 and AiM Future will showcase concurrent multimodal inferencing of objects on the NeuroMosAIc Processor in Booth #802.
“Our customers continue to redefine consumer expectations by delivering advanced interactive devices which stretch the imagination”, says Seungpil Shim, Chief Executive Officer of Supergate. “AiM Future has proven to be a strategic partner in enabling the DMC to address intelligent end-device applications made possible by its NeuroMosAIc Processor technology. The DMC introduces a new level of on-device AI capability previously unseen at the cost and power constraints of smart AIoT.”
“We are delighted Supergate chose to partner with AiM Future on this innovative new Deep-learning Microcontroller product. They licensed the NMP-300 as a production-proven solution to accelerate the advanced edge AI workloads their customers demand”, said ChangSoo Kim, Chief Executive Officer of AiM Future. “The small size and low power of NMP-300 presents an ideal match to the applications targeted by Supergate’s DMC resulting in a compelling advantage over traditional microcontrollers.”
Supergate Deep-learning Microcontroller Highlights
DMC is a 32-bit RISC-V-based Microcontroller for low-cost AI inference applications. DMC integrates the highly optimized NMP-300 for Neural Networks in general and Convolutional Neural Networks (CNN) in particular. DMC is best suited for Tiny Machine Learning (TinyML) and Artificial Intelligence of Things (AIoT) applications. The combination of TinyML and AIoT enables the development of intelligent, connected devices that can perform complex tasks with minimal power consumption and latency. For example, a TinyML model can be deployed on a low-power microcontroller in a smart home device, such as a thermostat, to optimize temperature control based on user preferences and patterns. The device could then be connected to an AIoT platform that collects data from multiple devices in the home and uses machine learning algorithms to optimize energy usage and improve overall efficiency.
NeuroMosAIc Processor Family Highlights
The NMP-300 is an ideal match for machine learning applications in ultra-low power, far-edge devices such as wearables and environmental and image sensors. It offers 0.5 TOPS while consuming microwatts on common at-sensor applications.
The NMP-500 targets applications requiring performance efficiency, such as smartphones, drones, AR/VR, and high-end home appliances. It delivers up to 4 TOPS or may be scaled down to 2 TOPS to match the power and area constraints of cost-sensitive applications.
The NMP-700 is the highest-performance member of the family targeting edge gateways, servers, robotics, and UAVs. It delivers 8 or 16 TOPS where performance is the primary design objective.
Software Enables End-User Applications
The co-designed NeuroMosAIc Studio provides developers with a comprehensive set of tools to run pre-trained machine-learning models on the NMP hardware. This includes a sophisticated hardware-aware model converter, mapper, and profiler to produce maximum efficiency. Support for industry-standard frameworks, such as ONNX, PyTorch, and TensorFlow Lite, offer ML engineers flexibility while also leveraging GLOW and TensorFlow XLA compilers to achieve highly optimized models. This equates to a production-ready hardware and software solution generating the highest performance and lowest power computation of edge AI applications.
Availability and Additional Reference
- The DMC is available to sample by lead customers today.
- For more information, please contact us at [email protected].
- The NeuroMosAIc Processor IP and Studio are commercially available today.
- For more information, please contact [email protected].
Supergate is a dedicated turn-key design company that delivers wafers or chips by using unique SoC frameworks and solutions, covering automotive self-driving, high-performance computing, and the artificial intelligence of things. Learn more at http://www.supergate.cc
About AiM Future
Based in Seoul, South Korea, the company was founded in late 2020 with LG Electronics as a strategic investor. Subsequently, it attracted a seed round investment from a group of leading venture capital firms We Ventures, KB Investment, and D.Camp. The company is focused on the development of neural network hardware accelerator IP and compiler software. Its flagship NeuroMosAIc architecture achieved commercialization in 2019 and the company has executed several license agreements with partners around the world. Learn more at https://www.aimfuture.ai.