Alliance for OpenUSD

NVIDIA® MGX Server Reference Design for Accelerated Computing NVIDIA MGX server reference design is a scalable and open accelerated computing server architecture Helps system manufacturers quickly and cost-effectively build more than 100 server variations to address diverse AI, HPC and Omniverse applications Slashes development costs by up to three-quarters and reduces development time by two-thirds to just six months Extends NVIDIA accelerated computing into virtually every server segment of the $1T installed base of data center infrastructure Will be adopted by ASRock Rack, ASUS, GIGABYTE, Pegatron, QCT and Supermicro

View entire presentation