World’s Smallest AI Supercomputer For Embedded And Edge Systems

0
347

Despite small size, the computing system promises to offer powerful features for all types of AI – based applications

NVIDIA Jetson Xavier NX

For developing high-performance AI systems like drones, portable medical devices, robots, smart cameras, high-resolution sensors, automated optical inspection and IoT-based embedded systems, NVIDIA has launched the Jetson Xavier NX, claimed to be the world’s smallest AI supercomputer for Embedded and Edge systems.

Similar in size to the Jetson Nano, which is NVIDIA’s small SOM (System on Module) for low powered AI and IoT applications, the Jetson Xavier NX comes at 70 mm x 45 mm. The system offers 14 TOPS (Tera Operations Per Second) in 10 W and 21 TOPS in 15 W, making it ideal for power-constrained applications. It is also capable of running modern neural networks in parallel and process data from high resolution sensors. All this gives the Jetson Xavier exceptional performance and makes it ready for supporting all popular AI frameworks.

Technical specifications

Advertisement

For the 10 W variant, AI performance is 14 TOPS, GPU max frequency is 800 MHz, CPU max frequency is 1500 MHz (2-core) and 1200 MHz (4-core).

For the 15 W variant, AI performance is 21 TOPS, GPU max frequency is 1100 MHz, CPU max frequency is 1900 MHz (2-core) and 1400 MHz (4/6-core)

For both 10 W and 15 W variants, GPU is 384-core NVIDIA Volta GPU with 48 tensor cores, CPU is at 6-core NVIDIA Carmel ARM v8.2 64-bit, 6 MB L2 + 4 MB L3, memory at 8 GB 128-bit [email protected] MHz; 51.2GB/second, 2 multi-mode DP 1.4 /eDP 1.4/HDMI 2.0 display.

The Jetson Xavier NX will be commercially available from March 2020 for US$ 399. Developers who don’t wish to wait that long can download the software patch, install it on the Jetson Xavier AGX Developer Kit and start developing today.

READ
Award Winning Multiradio & Gateway Module Series

“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.”


Advertisement

SHARE YOUR THOUGHTS & COMMENTS

Please enter your comment!
Please enter your name here

Are you human? *