Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
partially addresses #762
I'm adding
argmin
first because it's a major hotspot when constructing index. See attached perf report.I extracted
create_file
function fromvector_index
bench, ran it in a binary, and recorded with perf. The result shows that we spend 17% of the time inargmin
function.The total time of the program is 14s + some change. It took 1+ second alone to generate and write the data to disk before index begone. Discounting the data generation overhead, we can safely say that
argmin
is about 20% of the time spent when build an index.I will follow up with AVX and Neon implementation of
argmin
.