Live and recent posts from across the Fediverse tagged #pcle, aggregated by home.social.
#pcle
#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