Ambiq Micro, a recognized leader in ultra-low-power semiconductor solutions for edge AI, today announced Atomiq, the highly anticipated system-on-chip (SoC) integrating a Neural Processing Unit (NPU) designed to enable real-time, always-on artificial intelligence at the edge. Built on Ambiq’s Subthreshold Power Optimized Technology (SPOT) platform, Atomiq aims to establish a new benchmark for energy efficiency in demanding edge AI applications.
High performance meets power efficiency
As AI models continue to grow in complexity, manufacturers face a critical challenge: scaling device intelligence without compromising battery life or increasing thermal and system costs. Atomiq is architected to address this challenge at a system level, optimizing compute performance and power consumption to enable sustained AI processing at the edge.
Key features
- World’s first SPOT-optimized NPU: Atomiq is the first SoC to leverage sub- and near-threshold voltage operation for AI acceleration, delivering industry-leading energy efficiency for complex edge AI workloads.
- >200 GOPS of on-device AI performance: Integration of the Arm Ethos-U85 NPU supports sparsity and on-the-fly decompression, enabling compute-intensive workloads, including computer vision, multilingual speech recognition, and sensory models, directly on-device.
- Dynamic power scaling for always-on intelligence: SPOT-based ultra-wide range dynamic voltage and frequency scaling (DVFS) enables operation at lower voltage and lower power than previously possible, making room in the power budget for unprecedented levels of intelligence.
- Robust software platform for faster time-to-market: Ambiq’s Helia AI platform, together with its AI development kits (ADK), and the modular neuralSPOT SDK, delivers a tightly integrated hardware-software stack that is designed to enable higher performance in a smaller memory footprint at much lower power, significantly shorten development cycles, and provide energy-optimized AI deployment out of the box.
The manufacturer advantage
The Atomiq SoC expands Ambiq’s edge AI portfolio by enabling a new class of high-performance, battery-powered devices that were previously impractical due to power and thermal constraints. Representative use cases include:
- Smart cameras & security: Always-on, high-resolution object recognition and tracking without frequent recharging or active cooling.
- AR glasses & wearables: Conversational voice-based interfaces with on-board text-to-speech synthesis for all-day use.
- Industrial edge & robotics: High-fidelity semantic audio processing and advanced data analysis on the factory floor, operating independently of cloud connectivity or fixed power sources.
Executive remarks
“The Atomiq product family represents a step-change in energy-efficient edge AI,” says CTO and Founder, Dr. Scott Hanson. “By combining the Atomiq system architecture with Arm’s Ethos-U85, we enable significantly larger AI models at the edge with industry-leading energy efficiency, powered by our SPOT platform. Together, these capabilities form the foundation for true ambient intelligence.”
“From smart cameras to wearables, edge devices now require increasing levels of AI performance within extreme power and thermal constraints,” said Lionel Belnet, senior director of hardware product management, Edge AI Business Unit at Arm. “Built on the Arm compute platform, Ambiq’s Atomiq SoC shows what’s possible when AI acceleration is designed specifically for the edge, enabling richer audio, vision, and reasoning directly on-device for a new class of intelligent, battery-powered edge systems.”