← Back to context Comment by p1esk 1 day ago Theoretical FP32 performance of AMD EPYC 9965 is double that of A100: 41.2 TFLOP/s vs 19.5 TFLOP/s 1 comment p1esk Reply fc417fc802 20 hours ago Isn't that because the A100 is optimizing for memory bandwidth per TF?
Isn't that because the A100 is optimizing for memory bandwidth per TF?