samueleresca commented on issue #1343: URL: https://github.com/apache/arrow-go/issues/1343#issuecomment-5919336874
From a first look: - `arrow/bitutil`, `arrow/memory` migration matches hand-written assembly on average. It requires three-index slicing at each Load/Store call site to avoid compiler bound checks. - `arrow/math` (Sum) is already benchmarked: ~17% slower on average. This is likely due to the missing `ReduceSum` operation. It needs re-testing. - `internal/utils` min/max operations are also slower for small-to-mid sizes due to the missing reduce primitive. It needs re-testing. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
