Nvidia Jetson Solutions Provide High Performance on AI Workloads

November 18, 2019 0 By Reyjon Oregas

Nvidia is pushing the envelope of supercomputers with the introduction of its Jetson Xavier NX, the world’s smallest, most powerful AI supercomputer for robotics and embedded computing devices at the edge.

The Jetson Xavier NX, even with its size that’s smaller than a credit card, packs server-class performance and can hit up to 21 TOPS. It’s a perfect module for running modern AI workloads with extensive uptime or for implementations to systems with low power budgets since it only consumes 10 watts of power. These include, but not limited to, small commercial robots, drones, intelligent high-resolution sensors for factory logistics and production lines, optical inspection, network video recorders, and portable medical devices.

Nvidia’s Jetson Xavier NX opens a new door for embedded computing devices that requires top-notch performance but are constrained by size, weight, power budgets, or cost.

Jetson Xavier NX module specifications:

• GPU: NVIDIA Volta with 384 NVIDIA CUDA cores and 48 Tensor Cores, plus 2x NVDLA
• CPU: 6-core Carmel Arm 64-bit CPU, 6MB L2 + 4MB L3
• Video: 2x 4K30 Encode and 2x 4K60 Decode
• Camera: Up to six CSI cameras (36 via virtual channels); 12 lanes (3×4 or 6×2) MIPI CSI-2
• Memory: 8GB 128-bit LPDDR4x; 51.2GB/second
• Connectivity: Gigabit Ethernet
• OS Support: Ubuntu-based Linux
• Module Size: 70x45mm

“AI has become the enabling technology for modern robotics and embedded devices that will transform industries. Many of these devices, based on small form factors and lower power, were constrained from adding more AI features. Jetson Xavier NX lets our customers and partners dramatically increase AI capabilities without increasing the size or power consumption of the device.” -Deepu Talla, vice president and general manager of Edge Computing at NVIDIA

As part of NVIDIA’s one software architecture approach, Jetson Xavier NX is supported by NVIDIA JetPackTM software development kit, which is a complete AI software stack that can run modern and complex AI networks, accelerated libraries for deep learning as well as computer vision, computer graphics, multimedia and more.