Summary of Day 96:

Today’s kernel: MSE Loss

Click Here to redirect to the code.

[!note]

1. GPU: H100
   • Performance: $5.41 \text{ TFLOPs}$
   • Runtime: $0.06 \text{ ms}$
2. GPU: L40S
   • Performance: $6.41 \text{ TFLOPs}$
   • Runtime: $0.08 \text{ ms}$