Nvidia unveils AI supercomputer the size of a credit card

Mini AI supercomputer measures in at 70x45mm

Nvidia has unveiled an AI supercomputer the size of a credit card for embedded edge computing devices.

Dubbed Xavier NX, the diminutive device delivers performance of up to 21 TOPs and can consume as little as 10 watts of power when running modern AI workloads.

Nvidia claimed the micro-module is the “world’s smallest, most powerful AI supercomputer” for devices at the edge.

The supercomputer will serve high-performance applications constrained by size and weight, such as small commercial robots drones, or high-resolution industrial IoT sensors.

“AI has become the enabling technology for modern robotics and embedded devices that will transform industries,” said Deepu Talla, vice president and general manager of Edge Computing at NVIDIA.

“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.”

Performance

The less-than-pint-sized powerhouse is fitted with a Nvidia Volta GPU with 384 Nvidia CUDA cores and 48 Tensor cores, 8GB of memory, two 4K video encoders and decoders and up to six CSI cameras.

In practice, this means Jetson Xavier NX delivers up to 14 TOPS (at 10W) or 21 TOPS (at 15W) when running multiple neural networks in parallel and processing data from several high-res sensors.

“Our goal is to dramatically increase the quality and accuracy of our optical inspection system and accelerate our move towards industry 4.0,” said Otsuka Hiroshi, CEO of Musashi Seimitsu.

“NVIDIA Jetson Xavier NX gives us the compute capabilities to improve our visual inspection capabilities without increasing the size and power of our optical inspection system.”

Jetson Xavier NX costs $399 and will be available in March from Nvidia distribution channels.