Aitech, a manufacturer of rugged computers for military, aerospace and space applications, has used Nvidia’s Jetson TX2i system-on-module (SoM) for a new radiation-characterized system, he announced recently. The Aitech S-A1760 Venus is a Commercial Standard System (COTS) that can be used for spacecraft and small satellites and takes advantage of around 1 FP32 TFLOPS of “AI performance,” as Nvidia puts it.
There is a growing need for advanced imaging and data processing in various space applications, but equipping a small satellite with a high-performance, radiation-hardened computer is extremely expensive, as tiny satellites are said to be light and tiny. . This is where Aitech’s S-A1760 Venus system comes in.
According to Aitech, the S-A1760 Venus is intended for “short duration space flights” as well as near Earth orbit (NEO) and low Earth orbit (LEO) satellite applications. Its best use is “video and signal processing in distributed systems”.
At the heart of Nvidia SoM Jetson TX2i is the company’s Tegra X2 system-on-chip (SoC) which integrates two or four Cortex-A57s for general use Processor cores. It also uses the GP10B GPU, based on Nvidia’s Pascal architecture with 256 CUDA cores delivering performance up to 1.26 FP32 TFLOPS (around 1 TFLOPS in the case of the S-A1760 Venus) for AI or processing. of images. The Tegra X2 can also connect up to six cameras (12 via virtual channels) and encode / decode up to 1/2 4Kp60 or 4/20 1080p60 HEVC video stream simultaneously.
Nvidia’s Tegra X2 SoC is not radiation resistant, but with proper protection it can still be used for some space applications. Aitech’s S-A1760 Venus Small Form Factor System has passed the 300 Series Level Qualification Standard which identifies the radiation tolerance requirements of space components and systems not used in deep space or in the long distance applications.
The Jetson TX2i module for industrial applications and harsh environments packs 8 GB of 128-bit LPDDR4 memory and 32 GB of eMMC 5.1 storage, which seems to be sufficient for space applications which tend to be personalized and spend resources economically. Meanwhile, Aitech’s S-A1760 Venus has GbE, UART Serial, USB 2.0, CANbus and DVI / HDMI output. Video capture capabilities include HD-SDI input with a H.264 encoder and eight composite RS-170A (NTSC) / PAL channels.
“With the growing need for advanced imaging and data processing in all space applications, transitioning our powerful GPGPU-based AI supercomputers into this industry was a logical choice,” said Dan Mor, line manager. of video and GPGPU products at Aitech, in a statement. “By validating these COTS-based space systems with a clearly defined and recognized level of qualification, we are helping to lead the charge in the development of commercial space applications and innovations of small satellite clusters.
Nvidia in space
One interesting thing to note about Aitech’s S-A1760 Venus system is that it will be the first Nvidia SoC-based solution that will power devices such as satellites. But this isn’t the first time we’ve seen Nvidia tech ready for space.
Some Lenovo ThinkPads are certified for use on the International Space Station, and historically these PCs have used graphics processors from ATI Technologies (now AMD) and Nvidia. Of course, displaying graphics and maybe doing simulations is different from powering a satellite or a unit in a spacecraft.