"According to Nvidia, the GPU on the designed-for-space Rubin Module is able to deliver up to 25 times the AI compute of an H100 GPU, perfect for "space-based inferencing, enabling next-generation compute for orbital datacenters, advanced geospatial intelligence processing and autonomous space operations.""
"It's not necessarily intended for processing data for ground-based systems - one of the major concerns with the feasibility of orbital datacenters - but is meant for processing of data gathered from other orbital sensors and spacecraft."
"Jetson Orin "enables real-time processing of vision, navigation and sensor data directly onboard spacecraft, reducing latency and optimizing bandwidth," per Nvidia."
Nvidia announced the Space-1 Vera Rubin Module at GTC, a GPU specifically engineered for size-, weight-, and power-constrained space environments like satellites and orbital datacenters. The module delivers up to 25 times the AI compute of an H100 GPU and processes data from orbital sensors and spacecraft rather than transmitting data to ground systems. Nvidia also promoted complementary systems including the IGX Thor edge computing unit for local sensor data processing and the Jetson Orin module for real-time vision, navigation, and sensor data processing onboard spacecraft. The RTX Pro 6000 Blackwell Server Edition GPU serves as a ground-based partner for geospatial imaging processing. These solutions address the computational demands of space-based operations while managing latency and bandwidth constraints.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]