undefined | Better HN

0 pointsaschleck2y ago0 comments

1979 16 bit flops on an H100 is with sparsity. See footnote 2 on https://www.nvidia.com/en-us/data-center/h100/. You should be halving it for non-sparse flops.

0 comments

YetAnotherNick2y ago

GP is correct. With sparsity it is 3958. 1979 Tflop/s is without sparsity.

emu2y ago

No, it is not. That's the sparse fp8 flop number, but you need to ignore sparsity and compare bf16 flops not fp8 flops for the comparison the ancestor post is making.

j / k navigate · click thread line to collapse

0 comments

YetAnotherNick2y ago

GP is correct. With sparsity it is 3958. 1979 Tflop/s is without sparsity.

emu2y ago

No, it is not. That's the sparse fp8 flop number, but you need to ignore sparsity and compare bf16 flops not fp8 flops for the comparison the ancestor post is making.

j / k navigate · click thread line to collapse