Performance Design Discussion #323
kusumachalasani
started this conversation in
Ideas
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Validation & Experiment Runs:
- RECCE: Using the default configuration, calculate the no.of warmups required by doing a long run. Look into each cycle data to check till how many warmup cycles are needed. Measure variance/CI range is accepted.
- Baseline
- Experiment Run
Few design points from the discussion:
1. average values in 3 iterations. ( has only 3 data points)
2. individual data points from measurement cycles in iterations. (has 9 data points)
3. per iteration variance - to confirm is the warmup enough
Beta Was this translation helpful? Give feedback.
All reactions