arrow

ARROW-12032: [Rust] Optimize comparison kernels

This adds a function `from_trusted_len_iter_bool` to speed up the creation of an array for booleans.

Benchmarks are a bit noisy, but seems to be ~10-20% faster for comparison kernels. This also has some positive effect on DataFusion queries, as they contain quite some (nested) comparisons in filters. For example, executing tpch query 6 in memory is ~7% faster.

```
Gnuplot not found, using plotters backend
eq Float32              time:   [54.204 us 54.284 us 54.364 us]
                        change: [-29.087% -28.838% -28.581%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 6 outliers among 100 measurements (6.00%)
  5 (5.00%) low mild
  1 (1.00%) high mild

eq scalar Float32       time:   [43.660 us 43.743 us 43.830 us]
                        change: [-30.819% -30.545% -30.269%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
  4 (4.00%) high mild
  1 (1.00%) high severe

neq Float32             time:   [68.726 us 68.893 us 69.048 us]
                        change: [-14.045% -13.772% -13.490%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 1 outliers among 100 measurements (1.00%)
  1 (1.00%) high mild

neq scalar Float32      time:   [46.251 us 46.322 us 46.395 us]
                        change: [-12.204% -11.952% -11.702%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 6 outliers among 100 measurements (6.00%)
  1 (1.00%) low mild
  5 (5.00%) high mild

lt Float32              time:   [50.264 us 50.438 us 50.613 us]
                        change: [-21.300% -20.964% -20.649%] (p = 0.00 < 0.05)
                        Performance has improved.

lt scalar Float32       time:   [48.847 us 48.929 us 49.013 us]
                        change: [-10.132% -9.9180% -9.6910%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 5 outliers among 100 measurements (5.00%)
  4 (4.00%) high mild
  1 (1.00%) high severe

lt_eq Float32           time:   [46.105 us 46.198 us 46.282 us]
                        change: [-21.276% -20.966% -20.703%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 18 outliers among 100 measurements (18.00%)
  2 (2.00%) low severe
  13 (13.00%) low mild
  1 (1.00%) high mild
  2 (2.00%) high severe

lt_eq scalar Float32    time:   [47.359 us 47.456 us 47.593 us]
                        change: [+0.2766% +0.5240% +0.7821%] (p = 0.00 < 0.05)
                        Change within noise threshold.
Found 10 outliers among 100 measurements (10.00%)
  8 (8.00%) high mild
  2 (2.00%) high severe

gt Float32              time:   [57.313 us 57.363 us 57.412 us]
                        change: [-18.328% -18.177% -18.031%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 100 measurements (3.00%)
  2 (2.00%) low severe
  1 (1.00%) low mild

gt scalar Float32       time:   [44.091 us 44.132 us 44.175 us]
                        change: [-9.4233% -9.2747% -9.1273%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 7 outliers among 100 measurements (7.00%)
  4 (4.00%) low mild
  3 (3.00%) high mild

gt_eq Float32           time:   [55.856 us 55.932 us 56.007 us]
                        change: [-7.4997% -7.2656% -7.0334%] (p = 0.00 < 0.05)
                        Performance has improved.
Found 3 outliers among 100 measurements (3.00%)
  1 (1.00%) low mild
  2 (2.00%) high mild

gt_eq scalar Float32    time:   [42.365 us 42.419 us 42.482 us]
                        change: [+0.5289% +0.7174% +0.9116%] (p = 0.00 < 0.05)
                        Change within noise threshold.
Found 5 outliers among 100 measurements (5.00%)
  2 (2.00%) high mild
  3 (3.00%) high severe
```

Closes #9759 from Dandandan/optimize_comparison

Authored-by: Heres, Daniel <danielheres@gmail.com>
Signed-off-by: Andrew Lamb <andrew@nerdnetworks.org>