Improved performance of checking offsets ~-64-73%

[ritchie46]

This PR ensures that check_offsets is auto-vectorized. A break in a tight loop often prevents this auto-vectorization, so we keep a variable around in the hot loop and we decide if we must return an error once we have processed the data.

Gnuplot not found, using plotters backend
check_offsets^10        time:   [212.92 ns 213.20 ns 213.53 ns]                             
                        change: [-73.878% -73.296% -72.720%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 2 outliers among 100 measurements (2.00%)
  2 (2.00%) high severe

check_offsets^12        time:   [857.28 ns 858.50 ns 859.97 ns]                              
                        change: [-66.556% -66.487% -66.419%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 100 measurements (3.00%)
  3 (3.00%) high mild

check_offsets^14        time:   [3.2819 µs 3.2895 µs 3.2976 µs]                              
                        change: [-69.058% -68.997% -68.927%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 7 outliers among 100 measurements (7.00%)
  1 (1.00%) low severe
  5 (5.00%) high mild
  1 (1.00%) high severe

check_offsets^16        time:   [13.689 µs 13.701 µs 13.715 µs]                              
                        change: [-64.854% -64.650% -64.446%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 9 outliers among 100 measurements (9.00%)
  1 (1.00%) low mild
  4 (4.00%) high mild
  4 (4.00%) high severe

check_offsets^18        time:   [59.150 µs 59.216 µs 59.300 µs]                             
                        change: [-61.642% -61.554% -61.465%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 100 measurements (3.00%)
  2 (2.00%) low mild
  1 (1.00%) high severe

check_offsets^20        time:   [238.54 µs 239.10 µs 239.75 µs]                             
                        change: [-64.237% -64.127% -64.026%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 7 outliers among 100 measurements (7.00%)
  1 (1.00%) low mild
  4 (4.00%) high mild
  2 (2.00%) high severe

[codecov]

Codecov Report

Base: 83.14% // Head: 83.14% // Decreases project coverage by -0.00% ⚠️

Coverage data is based on head (2dc1f3f) compared to base (368aacc).
Patch coverage: 95.00% of modified lines in pull request are covered.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #1305      +/-   ##
==========================================
- Coverage   83.14%   83.14%   -0.01%     
==========================================
  Files         369      369              
  Lines       40234    40245      +11     
==========================================
+ Hits        33454    33461       +7     
- Misses       6780     6784       +4     

Impacted Files	Coverage Δ
src/array/specification.rs	92.23% <95.00%> (-0.16%)	⬇️
src/array/utf8/mod.rs	84.75% <0.00%> (-0.92%)	⬇️
src/bitmap/immutable.rs	86.06% <0.00%> (-0.61%)	⬇️
src/io/ipc/read/schema.rs	95.58% <0.00%> (-0.30%)	⬇️
src/io/ipc/read/file.rs	97.32% <0.00%> (+0.44%)	⬆️
src/bitmap/utils/slice_iterator.rs	98.78% <0.00%> (+1.21%)	⬆️

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report at Codecov.
📢 Do you have feedback about the report comment? Let us know in this issue.