NVIDIA announced — at the SC20 supercomputing conference — new products that deliver speed and performance for AI and scientific breakthroughs.
NVIDIA A100 80GB GPU – New NVIDIA data center GPU features twice the memory and over 2 terabytes per second of memory bandwidth to help researchers unlock the next wave of AI and scientific breakthroughs.
NVIDIA DGX Station A100 and NVIDIA DGX A100 640GB – The world’s first petascale workgroup server for AI and data science that plugs in anywhere, DGX Station A100 packs four of the new A100 80GB GPUs. See what’s inside in the video available here. GPU memory capacity doubles in the new DGX A100 640GB — the world’s most advanced AI platform — to tackle the largest data center AI, HPC and data science workloads with eight NVIDIA A100 GPUs per system.
NVIDIA Mellanox 400G InfiniBand – Seventh generation of Mellanox InfiniBand doubles data throughput with NDR 400Gb/s and adds new NVIDIA In-Network Computing engines to provide additional acceleration for AI supercomputing.