To pick up on a couple of topics from the Pull Request.
1. I've found that keeping the raw data allows one to process it in other ways
in terms of { iteration: 1 runtime: .... } instead of only storing the
statistics ?
Different folks would want to do different statistics with the data and we may
not be able to specify all the statistics needed on day 1 and would need to
keep adding. By keeping raw data we are able to do the aggregation on a later
date across history.
2. This is a bit minor - but why are we refering to the tvm stack as "engine"
rather than just tvm ? Can we rename engine to tvm , engine_version to
tvm_version, engine_configuration to tvm_build_configuration or some such ?
Ramana
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/4304#issuecomment-557742808
