Boards/Backplanes

Single board computer beefs up AI processing performance

10th May 2021
Mick Elliott
0

The new NVIDIA Jetson TX2 NX single board computer (SBC) is in stock at Impulse Embedded. It delivers the next step in AI performance for entry-level embedded and edge products.

As with the Jetson Xavier NX, the TX2 NX shares the same form factor and pin compatibility as the Jetson Nano but offers more than twice the AI processing performance at 1.33TFlops compared to 487GFlops.

A combination of form-factor, performance and power advantage makes the Jetson TX2 NX a candidate for mass-market AI platforms.

The NVIDIA Jetson TX2 NX SBC combines a dual-core NVIDIA Denver 2 64-bit CPU, a quad-core ARM Cortex-A57 MPCore processor and a 256-core Pascal GPU that can reach 1.3GHz.

Furthermore, the SBC has 4GB of 128-bit LPDDR4 memory and 16GB of eMMC 5.1 flash storage along with PCI Express expansion, Gigabit Ethernet, a USB3.1 Gen 1 port and video output via HDMI or DisplayPort. The SBC is fully capable of encoding one 4K stream at 60fps in HEVC/H.265 or as many as 14 streams in 1080p @ 30fps in HEVC/H.264.

NVIDIA's JetPack is a comprehensive solution for building powerful AI applications.

All Jetson modules and developer kits, including the TX2 NX, are supported by the JetPack software stack, enabling companies and developers to develop AI solutions with confidence knowing they can deploy them anywhere on any Jetson device.

Robert Plant, Sales Director at Impulse Embedded, comments, “Developing the perfect industrial AI computing solution can be difficult, costly and time-consuming. With our Embedded Systems capabilities, we can create reliable, repeatable and robust systems to help reduce our customer’s costs and development time. With our team of in-house engineers and specialists, all with decades of experience, we can offer fully deployable embedded Edge AI computing solutions straight out of the box.”

Product Spotlight

Upcoming Events

View all events
Newsletter
Latest global electronics news
© Copyright 2024 Electronic Specifier