Rich-T-kid commented on PR #10317:
URL: https://github.com/apache/arrow-rs/pull/10317#issuecomment-5093583838
> just having a hard time determining if there are any performance
regressions or its just noise in the benchmarks 🤔
nothing logically should have changed right? just a couple extra boolean
checks for things like
```rust
let total_bytes = repeat_count
.checked_mul(bytes_per_copy)
.ok_or(MutableBufferError::LengthOverflow)?;
```
it is weird how `MutableBuffer::from_iter bool ` seem to regress over
multiple benchmark calls
```
MutableBuffer::from_iter bool 1.00 3.1±0.01ms ? ?/sec
1.36 4.2±0.04ms ? ?/sec
```
&
```
MutableBuffer::from_iter bool 1.00 3.1±0.01ms ? ?/sec
1.37 4.2±0.03ms ? ?/sec
```
but then again `bench_bool/bench_bool ` seems to have also flipped
**old**
```
bench_bool/bench_bool 1.00 296.1±0.40µs 1688.8
MB/sec 1.22 361.2±0.21µs 1384.3 MB/sec
```
**new**
```
bench_bool/bench_bool 1.24 362.6±1.56µs 1379.1
MB/sec 1.00 293.1±0.32µs 1706.1 MB/sec
```
--
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]
