We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
I think we just have to copy the units from the base metric into, e.g.:
https://github.com/AMDResearch/omniperf/blob/8af6efc0be5288dadd2e758556154e52f7406e5d/src/omniperf_analyze/configs/gfx90a/1800_L2_cache_per_channel.yaml#L207
The text was updated successfully, but these errors were encountered:
Could you elaborate @arghdos. Per your screenshot, I'm reading metrics 18.1.1 - 18.1.7 all as "...req per $normUnit". Which seems correct to me
Am I missing something?
Sorry, something went wrong.
I guess it's sort of implied by the metric being "L1-L2 read req(uests)", but the unit would actually be "requests per wave" or "cycles per wave" (e.g., this one: https://github.com/AMDResearch/omniperf/blob/8af6efc0be5288dadd2e758556154e52f7406e5d/src/omniperf_analyze/configs/gfx90a/1800_L2_cache_per_channel.yaml#L921) not just "per wave". At a glance, it looks like all the request ones have this. Low priority issue tho
Merge pull request #146 from JoseSantosAMD/enhancement_133
b5b7f50
Enhancement #133
Patch merged into dev. Closing issue.
dev
JoseSantosAMD
No branches or pull requests
I think we just have to copy the units from the base metric into, e.g.:
https://github.com/AMDResearch/omniperf/blob/8af6efc0be5288dadd2e758556154e52f7406e5d/src/omniperf_analyze/configs/gfx90a/1800_L2_cache_per_channel.yaml#L207
The text was updated successfully, but these errors were encountered: