Axera develops high-performance AI System-on-Chips (SoCs) that utilize hybrid precision processing and pixel-level AI imaging technology to enhance edge computing applications in smart IoT, autonomous driving, and robotics. Their solutions address the need for efficient, high-quality data processing and imaging in complex environments, enabling advanced functionalities in various edge devices.
Funding
$398.4M raised to dateRaised to date based on public sources. This may differ from the amount the company actually raised and is based only on what is publicly available on the internet.
CCCICLCLGCHC+8Founders
Product
Problem
Edge computing applications in smart IoT, autonomous driving, and robotics require efficient, high-quality data processing and imaging in complex environments. Existing solutions often struggle to balance performance, power consumption, and image quality, hindering the development of advanced functionalities in edge devices.
Solution
Axera develops high-performance AI System-on-Chips (SoCs) that leverage hybrid precision processing and pixel-level AI imaging technology to enhance edge computing capabilities. Their chips are designed to deliver a balance of computational power and energy efficiency. By integrating an AI-ISP (Image Signal Processor) that utilizes pixel-level AI processing, Axera's SoCs enhance image quality in various complex application scenarios, providing high-quality image and video data for subsequent intelligent processing. The hybrid precision NPU (Neural Processing Unit) efficiently supports mixed-precision algorithms and Transformer models, providing a foundation for large language model (LLM) applications on edge devices.
Target Audience
The primary target audience includes developers and manufacturers of smart IoT devices, autonomous vehicles, robots, and AR/VR systems seeking high-performance, energy-efficient edge computing solutions.
Features
- Hybrid precision NPU with operator-as-atomic-instruction-set AI compute processor
- Native support for Transformer models
- AI-ISP utilizing pixel-level AI processing technology to enhance image quality
- Single-chip full-stack autonomous driving solutions
- SoCs supporting 4K black light vision processing with low power consumption
- SoCs supporting 5M black light vision processing with ultra-low power consumption