New AI-Native Processor For Edge Applications Offers 100X Power And Performance Improvements Over 32-Bit Mcus
This technology enables a neural network model's matrix-multiply operations and activation flows to be mapped directly to in-memory analog compute blocks, a structure which eliminates the wasted cycles and overheads of a conventional processor's general-purpose instruction set.
As a result, the GPX10 Pro performs common edge AI functions such as voice recognition, keyword spotting, low-frequency computer vision and intelligent sensing much faster and at much lower power than today's MCUs, NPUs or GPUs can.
GP Singh, CEO of Ambient Scientific, said: "Today's MCUs and NPUs are hamstrung by their conventional silicon architecture when they try to run AI models. It's like hitting a baseball with a tennis racket – it's the wrong tool for the job. The GPX10 Pro shows what's possible when you build your architecture natively for AI – 100s of GOPs of AI performance at microwatts of power."
Integrated logic, inference and sensor fusion capabilities
The GPX10 Pro is a highly integrated SoC which enables local AI inference in edge and endpoint devices, even those powered by just a single coin cell battery.
AI processing is performed in two sets of five MX8 AI cores in two separate power domains. One set is in an always-on block which supports ultra-lower power sensor interfacing and fusion – for instance, when performing always-on keyword spotting, the chip consumes less than 100μW. The 10 MX8 cores perform up to 2,560 multiply-accumulate (MAC) operations per cycle, producing total peak AI throughput of 512 GOPs.
The GPX10 Pro's compute function is supported by 2MB of on-chip SRAM – ten times more than in the existing GPX10 – to enable implementation of larger and more complex AI models.
The GPX10 Pro also features an Arm® Cortex®-M4F CPU core for classic control functions. Integrated analog functionality includes an ultra-low power ADC, enhanced I2S logic, and interfaces for up to eight simultaneous analog and 20 digital sensors.
Ambient Scientific provides the comprehensive NebulaTM AI enablement toolchain to accelerate the training, development and deployment of AI models to the GPX10 and GPX10 Pro. It is compatible with leading model training frameworks including TensorFlow, Keras and ONNX. The chip's AI cores, which are programmable in the Nebula toolchain, give designers the flexibility to adapt to evolving AI model types and topologies.
Ambient Scientific also provides the SenseMeshTM hardware sensor fusion layer, which enables low-latency sensor fusion by connecting multiple sensors to a core via a tightly-coupled mesh. This produces instant responses to trigger events, and ultra-low Idle mode power, as it offloads sensor polling from the CPU.
Ambient Scientific is demonstrating various on-device AI applications running on coin cell batteries, including fall detection, voice recognition and face ID, at its booth 5.E31 at Electronica (17-19 September, Bangalore, India).
The GPX10 Pro is available for sampling now. Volume production is forecast to start in Q1 2026.
About Ambient Scientific
Ambient Scientific is a fabless semiconductor company pioneering AI native compute architecture DigAn®, that combines the efficiency of analog with the scalability of digital to bring breakthrough AI performance with sustained efficiency to an entire roadmap of processors from Edge to Cloud. Our technology stack including CubicCore compute, SenseMesh multimodal fusion and Nebula toolchains redefine how compute, memory, sensing fusion and software are co-designed for Energy Aware Intelligence. Headquartered in Santa Clara, with a growing global footprint, Ambient Scientific is on a mission to bring sustainable intelligence to every device – from the tiniest sensor to the largest hyperscale servers. To learn more about our products, visit or follow Ambient Scientific on LinkedIn .
Photo:
SOURCE Ambient Scientific

Legal Disclaimer:
MENAFN provides the
information “as is” without warranty of any kind. We do not accept
any responsibility or liability for the accuracy, content, images,
videos, licenses, completeness, legality, or reliability of the information
contained in this article. If you have any complaints or copyright
issues related to this article, kindly contact the provider above.
Most popular stories
Market Research

- Pluscapital Advisor Empowers Traders To Master Global Markets Around The Clock
- Invromining Expands AI Quant Infrastructure To Broaden Access To Digital Asset Strategies
- Cartesian Launches First Outsourced Middle-Back-Office Offering For Digital Asset Funds
- Permissionless Data Hub Baselight Taps Walrus To Activate Data Value Onchain
- PLPC-DBTM: Non-Cellular Oncology Immunotherapy With STIPNAM Traceability, Entering A Global Acquisition Window.
- Primexbt Launches Empowering Traders To Succeed Campaign, Leading A New Era Of Trading
Comments
No comment