NVIDIA A100 benchmarks as world’s fastest GPU

NVIDIA’s Ampere A100 GPU has been named the fastest graphics processor in the world after returning some impressive results in OctaneRender’s OctaneBench tests.

The A100 posted an Octanebench score of 446 (standard Linux OB4 benchmark, RTX off, recompiled for CUDA11, ref. 980=102 OB), which is roughly 43% faster than #Turing, even with/ #RTX off!

To put the achievement in context, here are the scores of a few Turing-based cards:

  • Nvidia Titan V: 401 points (11%)
  • Quadro RTX 8000: 328 points (35%)
  • GeForce RTX 2080 Ti: 302 points (48%)

The Ampere A100 is a bit of a monster – 6,912 CUDA cores, 432 Tensor cores, 40 GB of HBM2e memory, and a bandwidth of up to 1,555 Gbps.

NVIDIA has competition at the top-end – AMD’s Big Navi is in the pipeline, as is Intel’s Xe architecture – and it should be noted that the Octanebench only runs on NVIDIA hardware, but it’s always good to win an accolade to keep the development teams motivated to do even better.

Source: Tech Report