ARROW PR 38394: Dictionary ChunkedArray hash kernels optimization benchmark

pr38394.txt

### Before
-----------------------------------------------------------------------------------------
Benchmark                               Time             CPU   Iterations UserCounters...
-----------------------------------------------------------------------------------------
ValueCountsDictionaryChunks/0     8112938 ns      8112013 ns           87 bytes_per_second=4.81539Gi/s items_per_second=517.048M/s null_percent=0 num_unique=100
ValueCountsDictionaryChunks/1     8563428 ns      8563225 ns           82 bytes_per_second=4.56166Gi/s items_per_second=489.804M/s null_percent=0.1 num_unique=100
ValueCountsDictionaryChunks/2     9591335 ns      9590370 ns           72 bytes_per_second=4.0731Gi/s items_per_second=437.345M/s null_percent=1 num_unique=100
ValueCountsDictionaryChunks/3    12068706 ns     12066611 ns           55 bytes_per_second=3.23724Gi/s items_per_second=347.596M/s null_percent=10 num_unique=100
ValueCountsDictionaryChunks/4    22068866 ns     22068960 ns           32 bytes_per_second=1.77002Gi/s items_per_second=190.054M/s null_percent=50 num_unique=100
ValueCountsDictionaryChunks/5    10474824 ns     10474596 ns           66 bytes_per_second=3.72926Gi/s items_per_second=400.426M/s null_percent=99 num_unique=100
ValueCountsDictionaryChunks/6     8641591 ns      8641564 ns           81 bytes_per_second=4.5203Gi/s items_per_second=485.364M/s null_percent=100 num_unique=100
ValueCountsDictionaryChunks/7   537463756 ns    537447624 ns            1 bytes_per_second=74.4259Mi/s items_per_second=7.80412M/s null_percent=0 num_unique=100k
ValueCountsDictionaryChunks/8   506843630 ns    506775330 ns            1 bytes_per_second=78.9304Mi/s items_per_second=8.27646M/s null_percent=0.1 num_unique=100k
ValueCountsDictionaryChunks/9   526191657 ns    526113873 ns            1 bytes_per_second=76.0292Mi/s items_per_second=7.97224M/s null_percent=1 num_unique=100k
ValueCountsDictionaryChunks/10  533948000 ns    533932498 ns            1 bytes_per_second=74.9158Mi/s items_per_second=7.85549M/s null_percent=10 num_unique=100k
ValueCountsDictionaryChunks/11  485905496 ns    485851582 ns            2 bytes_per_second=82.3297Mi/s items_per_second=8.63289M/s null_percent=50 num_unique=100k
ValueCountsDictionaryChunks/12   54465167 ns     54459173 ns           12 bytes_per_second=734.495Mi/s items_per_second=77.0174M/s null_percent=99 num_unique=100k
ValueCountsDictionaryChunks/13    8587787 ns      8587147 ns           81 bytes_per_second=4.54895Gi/s items_per_second=488.44M/s null_percent=100 num_unique=100k

### After
-----------------------------------------------------------------------------------------
Benchmark                               Time             CPU   Iterations UserCounters...
-----------------------------------------------------------------------------------------
ValueCountsDictionaryChunks/0     7966614 ns      7966261 ns           91 bytes_per_second=4.90349Gi/s items_per_second=526.509M/s null_percent=0 num_unique=100
ValueCountsDictionaryChunks/1     8320302 ns      8320284 ns           85 bytes_per_second=4.69485Gi/s items_per_second=504.106M/s null_percent=0.1 num_unique=100
ValueCountsDictionaryChunks/2     9323569 ns      9323436 ns           75 bytes_per_second=4.18971Gi/s items_per_second=449.867M/s null_percent=1 num_unique=100
ValueCountsDictionaryChunks/3    12000566 ns     11998826 ns           59 bytes_per_second=3.25553Gi/s items_per_second=349.56M/s null_percent=10 num_unique=100
ValueCountsDictionaryChunks/4    21641714 ns     21640423 ns           32 bytes_per_second=1.80507Gi/s items_per_second=193.818M/s null_percent=50 num_unique=100
ValueCountsDictionaryChunks/5    10142759 ns     10142761 ns           67 bytes_per_second=3.85127Gi/s items_per_second=413.527M/s null_percent=99 num_unique=100
ValueCountsDictionaryChunks/6     8591046 ns      8590837 ns           81 bytes_per_second=4.547Gi/s items_per_second=488.23M/s null_percent=100 num_unique=100
ValueCountsDictionaryChunks/7   134303597 ns    134301041 ns            5 bytes_per_second=297.838Mi/s items_per_second=31.2306M/s null_percent=0 num_unique=100k
ValueCountsDictionaryChunks/8   137137643 ns    137135458 ns            5 bytes_per_second=291.682Mi/s items_per_second=30.5851M/s null_percent=0.1 num_unique=100k
ValueCountsDictionaryChunks/9   136837967 ns    136828316 ns            5 bytes_per_second=292.337Mi/s items_per_second=30.6538M/s null_percent=1 num_unique=100k
ValueCountsDictionaryChunks/10  140485423 ns    140485416 ns            5 bytes_per_second=284.727Mi/s items_per_second=29.8558M/s null_percent=10 num_unique=100k
ValueCountsDictionaryChunks/11  102110513 ns    102109071 ns            7 bytes_per_second=391.738Mi/s items_per_second=41.0767M/s null_percent=50 num_unique=100k
ValueCountsDictionaryChunks/12   13535453 ns     13534458 ns           52 bytes_per_second=2.88615Gi/s items_per_second=309.898M/s null_percent=99 num_unique=100k
ValueCountsDictionaryChunks/13    8598628 ns      8598517 ns           81 bytes_per_second=4.54293Gi/s items_per_second=487.794M/s null_percent=100 num_unique=100k