Axiomtek – a world-renowned leader relentlessly devoted to the research, development, and manufacture of innovative, highly efficient, and reliable industrial computer products – is proud to announce Super Mode support on its NVIDIA® Jetson Orin™-based AIE series, including the compact and rugged AIE100-ONA and AIE110-ONA. Designed for real-time, high-throughput AI workloads in intelligent transportation and smart parking applications, the system now delivers unprecedented AI inference performance thanks to NVIDIA’s latest high-performance operating mode.
As demand for smarter, more responsive traffic and parking systems rises, system integrators are challenged to deploy edge AI solutions capable of simultaneously handling multi-stream video analytics, license plate recognition, object detection, and predictive insights—all with strict latency constraints. With the Super Mode feature enabled on NVIDIA Jetson Orin Nano™, Axiomtek’s AIE100-ONA and AIE110-ONA now provide a significant performance leap to address these real-world deployment needs.
Super Mode maximizes CPU and GPU utilization on the Orin Nano platform, enabling more advanced AI model execution with greater parallelism and efficiency. In practical terms, each edge device can now support more camera streams and heavier AI models—reducing infrastructure costs while enhancing detection accuracy and response speed.
Reimagining AI Deployment Efficiency
In response to the growing demand for smarter city deployments, Axiomtek's internal teams reevaluated performance-per-dollar across compact Edge AI systems. “Our clients are looking for more compact systems that can handle heavier AI workloads without raising system cost or complexity,” said Ken Pan, Product Manager.
This sparked a strategic shift in development focus. Robin Lin, Head of Intelligent Automation Software Department, noted, “We asked ourselves: what delivers more value per watt, per dollar, and per deployment cycle?” The result was a renewed focus on fully unlocking Super Mode as a key enabler of performance scaling.
To meet this challenge, Vincent Chen, Senior Engineer of the AI Software R&D Department, proposed leveraging Super Mode as a performance breakthrough to unlock more computing potential from the Jetson Orin platform.
“In our DeepStream SDK-based testing with optimized YOLO models via TensorRT, we observed a 1.5–2x increase in throughput with Super Mode enabled,” said Vincent Chen. “Workloads that previously required two devices can now run on a single AIE100-ONA, while maintaining real-time response. Alternatively, developers can swap in larger models (e.g., YOLOv8n → YOLOv8s) to gain further mAP improvements, without changing deployment topology. This translates to a more cost-effective and scalable strategy, helping customers maximize performance per device and reduce total system investment.”
Reflecting on the development journey, Robin Lin concluded, “Super Mode is more than a performance boost—it’s a strategic enabler for our customers. It allows them to run larger models, consolidate devices, and simplify deployments, all while maintaining real-time responsiveness. It’s how we turn cutting-edge AI into practical, scalable solutions at the edge.”
Proven Gains for AI Vision Workloads
In comparative benchmarks using YOLOv8 variants under TensorRT optimization, enabling Super Mode on AIE100-ONA resulted in measurable throughput increases across all model sizes. For example, YOLOv8n inference jumped from 91.5 FPS to 141.96 FPS, while YOLOv8s increased from 73.75 FPS to 116.47 FPS, with minimal impact on system stability (see attached chart). In addition to faster performance, Super Mode enables the deployment of larger models with higher accuracy—for instance, YOLOv8l achieves a mAP of 52%, while YOLOv8x reaches 53.9%.
Ideal for Smart Transportation and Parking Systems
In smart parking deployments, the AIE100-ONA running Super Mode can now handle more entry lane monitoring, integrate license plate recognition, vacant space prediction, and pedestrian tracking simultaneously, enhancing both coverage and deployment ROI. Traffic management operators can also perform real-time object detection, vehicle tracking, and traffic flow analytics on a single rugged device at the edge.
Designed for Scalable, Long-Term Deployment
Axiomtek’s AIE series edge AI systems feature industrial-grade design, PoE support, rich I/O, and seamless compatibility with DeepStream SDK and TensorRT. Paired with LTE, Wi-Fi, and NVMe expansion, they are built for always-on edge AI operations in harsh outdoor environments. The Orin Nano-based AIE series lineup—including the AIE100-ONA and AIE110-ONA—fully supports Super Mode, enabling customers to scale high-throughput, multi-stream AI vision applications with improved efficiency and reduced infrastructure costs.
With Super Mode, the AIE100-ONA and AIE110-ONA are no longer just compact edge systems—they are enablers of next-generation urban intelligence. To learn more about AIE100-ONA, AIE110-ONA, and Super Mode performance testing, please visit Axiomtek’s global website at www.axiomtek.com or contact our sales representatives at info@axiomtek.com.tw.
