#gtc22 — Public Fediverse posts

#nVidia #GTC22 is over

#nVidia #GTC22 - nVidia #cnx 100

#nVidia #GTC22 - nVidia announced #omniverse cloud and omniverse view

#nVidia #GTC22 - #robots and #simulations

#nVidia #GTC22 - #isaac for #amrs

#nVidia #GTC22 - #clara #holoscan

#nVidia #GTC22 - nVidia drive map

#nVidia #GTC22 - nVidia #drive

#nVidia #GTC22 - #robotics and #ai

#nVidia #GTC22 - #Synthetic #Biology

#nVidia #GTC22 - #omniverse explained

#nVidia #GTC22 - # ovx and spectrum-4 https://t.co/94Sro74DSW

#nVidia #GTC22 - # H100 SXM5 specs

- 4th Gen #NVLink and #PCle Gen 5
- 8 GPCs, 66 TPCs, 2 SMs/#TPC, 132 SMs per GPU
- 128 FP32 #CUDA Cores per SM, 16,896 FP32 CUDA Cores per GPU
- 50 MB L2$
- 4 4th Gen Tensor Cores per SM, 528 per GPU
- 80 GB HBM3, 5 HBM3 stacks, 10 512-bit MCs

#nVidia #GTC22 - #omniverse https://t.co/xETiCD141K

#nVidia #GTC22 - #Research and software tools you depend on a digital twin https://t.co/SlNlq4BuHX

nVidia #GTC22 - NVIDIA DGX H100

Paper
https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/nvidia-dgx-h100-datasheet.pdf https://t.co/eb9kwGu4BB

#nVidia #GTC22 - nvidia #hopper specs revealed https://t.co/Ru0Ldu6keJ

#nVidia #GTC22 - #nvlink and pcie 5.0 https://t.co/MwVkcNIcOE

#nVidia #GTC22 - #grace #hopper #cpu with only 500W

#nVidia #GTC22 - #hopper #h100 performance

#nVidia #GTC22 - #eos to be the fastest supercomputer in the world

#nVidia #GTC22 - #dgx and #hbm3

#nVidia #GTC22 - #hopper directly supports #deeplearning

#nVidia #GTC22 - #hopper Confidential computing with #dpx

#nVidia #GTC22 - #h100 - #Hopper 700W monster

#nVidia #GTC22 - #Digital DNA and #AI

#nVidia #GTC22 - #translation via #Maxine in real-time

#nVidia confirms #Hopper for #gtc22