Make the compiler inline the hot RE2::DFA loop.

Right now the compiler does not inline the function and all branches are evaluated at each iteration of the loop.

By templating the function instead of relying on compiler heuristics to
do the constant folding, we force the compiler to create a separate
optimized copy of the code for each case.

This makes RE2 searching roughly 5 to 100% faster !

Detailed Benchmarks:

```
name                                                old speed               new speed               delta
Search_Easy0_CachedDFA/8/threads:1                   196MB/s ± 2%            187MB/s ± 3%    -4.64%          (p=0.009 n=6+6)
Search_Easy0_CachedDFA/8/threads:2                   197MB/s ± 0%            189MB/s ± 2%    -4.01%          (p=0.002 n=6+6)
Search_Easy0_CachedDFA/8/threads:4                   192MB/s ± 2%            185MB/s ± 9%      ~             (p=0.329 n=5+6)
Search_Easy0_CachedDFA/8/threads:8                   100MB/s ± 1%            112MB/s ± 1%   +11.68%          (p=0.016 n=4+5)
Search_Easy0_CachedDFA/8/threads:12                 98.4MB/s ± 5%          109.6MB/s ± 1%   +11.38%          (p=0.004 n=6+5)
Search_Easy0_CachedDFA/64/threads:1                 1.46GB/s ± 2%           1.51GB/s ± 1%    +3.41%          (p=0.008 n=5+5)
Search_Easy0_CachedDFA/64/threads:2                 1.42GB/s ± 2%           1.43GB/s ± 4%      ~             (p=0.662 n=6+5)
Search_Easy0_CachedDFA/64/threads:4                 1.38GB/s ± 1%           1.41GB/s ±20%      ~             (p=0.429 n=5+6)
Search_Easy0_CachedDFA/64/threads:8                  677MB/s ± 5%            767MB/s ± 1%   +13.31%          (p=0.002 n=6+6)
Search_Easy0_CachedDFA/64/threads:12                 667MB/s ± 4%            739MB/s ± 3%   +10.80%          (p=0.002 n=6+6)
Search_Easy0_CachedDFA/512/threads:1                7.90GB/s ± 1%           7.92GB/s ± 4%      ~             (p=0.818 n=6+6)
Search_Easy0_CachedDFA/512/threads:2                7.85GB/s ± 6%           8.02GB/s ± 4%      ~             (p=0.485 n=6+6)
Search_Easy0_CachedDFA/512/threads:4                6.77GB/s ±13%           7.53GB/s ±11%      ~             (p=0.093 n=6+6)
Search_Easy0_CachedDFA/512/threads:8                3.60GB/s ± 9%           3.86GB/s ±11%      ~             (p=0.132 n=6+6)
Search_Easy0_CachedDFA/512/threads:12               3.47GB/s ± 4%           3.66GB/s ± 1%    +5.50%          (p=0.004 n=6+5)
Search_Easy0_CachedDFA/4k/threads:1                 15.7GB/s ± 2%           16.0GB/s ± 0%    +2.04%          (p=0.002 n=6+6)
Search_Easy0_CachedDFA/4k/threads:2                 15.0GB/s ± 3%           15.4GB/s ± 2%    +2.49%          (p=0.015 n=6+6)
Search_Easy0_CachedDFA/4k/threads:4                 13.4GB/s ±15%           14.0GB/s ± 8%      ~             (p=0.792 n=6+5)
Search_Easy0_CachedDFA/4k/threads:8                 8.63GB/s ± 5%           8.58GB/s ± 4%      ~             (p=1.000 n=6+6)
Search_Easy0_CachedDFA/4k/threads:12                8.48GB/s ± 2%           8.44GB/s ± 3%      ~             (p=0.589 n=6+6)
Search_Easy0_CachedDFA/32k/threads:1                15.3GB/s ± 1%           15.4GB/s ± 1%      ~             (p=0.937 n=6+6)
Search_Easy0_CachedDFA/32k/threads:2                15.1GB/s ± 1%           15.1GB/s ± 1%      ~             (p=0.937 n=6+6)
Search_Easy0_CachedDFA/32k/threads:4                15.0GB/s ± 1%           14.9GB/s ± 3%      ~             (p=0.548 n=5+5)
Search_Easy0_CachedDFA/32k/threads:8                10.2GB/s ± 2%           10.2GB/s ± 4%      ~             (p=0.485 n=6+6)
Search_Easy0_CachedDFA/32k/threads:12               10.1GB/s ± 2%           10.0GB/s ± 1%      ~             (p=0.589 n=6+6)
Search_Easy0_CachedDFA/256k/threads:1               10.3GB/s ± 1%           10.4GB/s ± 1%      ~             (p=0.485 n=6+6)
Search_Easy0_CachedDFA/256k/threads:2               10.2GB/s ± 4%           10.3GB/s ± 1%      ~             (p=0.537 n=6+5)
Search_Easy0_CachedDFA/256k/threads:4               9.33GB/s ±16%          10.29GB/s ± 1%   +10.29%          (p=0.004 n=6+5)
Search_Easy0_CachedDFA/256k/threads:8               6.16GB/s ± 6%           6.24GB/s ± 1%      ~             (p=0.537 n=6+5)
Search_Easy0_CachedDFA/256k/threads:12              6.03GB/s ± 2%           6.11GB/s ± 3%      ~             (p=0.240 n=6+6)
Search_Easy0_CachedDFA/2M/threads:1                 7.16GB/s ± 1%           7.14GB/s ± 1%      ~             (p=0.240 n=6+6)
Search_Easy0_CachedDFA/2M/threads:2                 7.11GB/s ± 0%           7.09GB/s ± 1%      ~             (p=0.699 n=6+6)
Search_Easy0_CachedDFA/2M/threads:4                 6.88GB/s ± 3%           6.88GB/s ± 4%      ~             (p=1.000 n=6+6)
Search_Easy0_CachedDFA/2M/threads:8                 5.10GB/s ± 1%           5.10GB/s ± 0%      ~             (p=0.841 n=5+5)
Search_Easy0_CachedDFA/2M/threads:12                4.91GB/s ± 1%           4.88GB/s ± 1%      ~             (p=0.485 n=6+6)
Search_Easy0_CachedDFA/16M/threads:1                6.49GB/s ± 0%           6.45GB/s ± 1%      ~             (p=0.310 n=6+6)
Search_Easy0_CachedDFA/16M/threads:2                6.32GB/s ± 0%           6.26GB/s ± 2%      ~             (p=0.662 n=5+6)
Search_Easy0_CachedDFA/16M/threads:4                6.10GB/s ± 2%           5.99GB/s ± 3%      ~             (p=0.126 n=5+6)
Search_Easy0_CachedDFA/16M/threads:8                4.63GB/s ± 0%           4.62GB/s ± 0%      ~             (p=0.421 n=5+5)
Search_Easy0_CachedDFA/16M/threads:12               4.50GB/s ± 2%           4.55GB/s ± 0%      ~             (p=0.429 n=6+5)
Search_Easy1_CachedDFA/8/threads:1                   195MB/s ± 1%            189MB/s ±11%      ~             (p=0.818 n=6+6)
Search_Easy1_CachedDFA/8/threads:2                   193MB/s ± 3%            194MB/s ± 2%      ~             (p=0.937 n=6+6)
Search_Easy1_CachedDFA/8/threads:4                   192MB/s ± 3%            191MB/s ± 3%      ~             (p=0.662 n=6+5)
Search_Easy1_CachedDFA/8/threads:8                   100MB/s ± 3%            108MB/s ± 0%    +7.03%          (p=0.016 n=5+4)
Search_Easy1_CachedDFA/8/threads:12                 96.6MB/s ± 2%          105.6MB/s ± 2%    +9.30%          (p=0.002 n=6+6)
Search_Easy1_CachedDFA/64/threads:1                 1.21GB/s ± 5%           1.32GB/s ± 0%    +9.42%          (p=0.004 n=6+5)
Search_Easy1_CachedDFA/64/threads:2                 1.20GB/s ± 4%           1.30GB/s ± 4%    +8.24%          (p=0.002 n=6+6)
Search_Easy1_CachedDFA/64/threads:4                 1.17GB/s ± 5%           1.21GB/s ±18%      ~             (p=0.180 n=6+6)
Search_Easy1_CachedDFA/64/threads:8                  613MB/s ± 6%            691MB/s ± 6%   +12.73%          (p=0.004 n=5+6)
Search_Easy1_CachedDFA/64/threads:12                 603MB/s ± 2%            682MB/s ± 5%   +13.03%          (p=0.004 n=5+6)
Search_Easy1_CachedDFA/512/threads:1                5.97GB/s ± 1%           6.62GB/s ± 2%   +10.83%          (p=0.004 n=5+6)
Search_Easy1_CachedDFA/512/threads:2                6.70GB/s ± 7%           7.40GB/s ± 3%   +10.49%          (p=0.002 n=6+6)
Search_Easy1_CachedDFA/512/threads:4                6.27GB/s ± 4%           6.73GB/s ± 2%    +7.47%          (p=0.010 n=6+4)
Search_Easy1_CachedDFA/512/threads:8                3.33GB/s ± 8%           3.70GB/s ± 2%   +11.04%          (p=0.002 n=6+6)
Search_Easy1_CachedDFA/512/threads:12               3.04GB/s ± 2%           3.39GB/s ± 2%   +11.55%          (p=0.002 n=6+6)
Search_Easy1_CachedDFA/4k/threads:1                 11.8GB/s ± 1%           13.4GB/s ± 0%   +13.87%          (p=0.004 n=6+5)
Search_Easy1_CachedDFA/4k/threads:2                 11.7GB/s ± 1%           13.1GB/s ± 2%   +12.21%          (p=0.010 n=4+6)
Search_Easy1_CachedDFA/4k/threads:4                 11.1GB/s ± 2%           12.2GB/s ± 5%   +10.16%          (p=0.004 n=5+6)
Search_Easy1_CachedDFA/4k/threads:8                 6.05GB/s ± 5%           6.77GB/s ± 3%   +11.96%          (p=0.002 n=6+6)
Search_Easy1_CachedDFA/4k/threads:12                5.96GB/s ± 1%           6.65GB/s ± 3%   +11.68%          (p=0.002 n=6+6)
Search_Easy1_CachedDFA/32k/threads:1                11.3GB/s ± 1%           13.0GB/s ± 1%   +15.04%          (p=0.002 n=6+6)
Search_Easy1_CachedDFA/32k/threads:2                11.1GB/s ± 1%           12.8GB/s ± 1%   +14.85%          (p=0.008 n=5+5)
Search_Easy1_CachedDFA/32k/threads:4                10.2GB/s ±14%           12.5GB/s ± 2%   +21.94%          (p=0.004 n=6+5)
Search_Easy1_CachedDFA/32k/threads:8                6.34GB/s ± 0%           7.29GB/s ± 2%   +15.00%          (p=0.004 n=5+6)
Search_Easy1_CachedDFA/32k/threads:12               6.24GB/s ± 4%           7.13GB/s ± 2%   +14.30%          (p=0.002 n=6+6)
Search_Easy1_CachedDFA/256k/threads:1               7.36GB/s ± 1%           7.46GB/s ± 1%    +1.42%          (p=0.009 n=5+6)
Search_Easy1_CachedDFA/256k/threads:2               7.24GB/s ± 1%           7.36GB/s ± 2%    +1.62%          (p=0.026 n=6+6)
Search_Easy1_CachedDFA/256k/threads:4               7.16GB/s ± 2%           6.62GB/s ± 6%    -7.52%          (p=0.004 n=5+6)
Search_Easy1_CachedDFA/256k/threads:8               4.25GB/s ± 0%           4.54GB/s ± 1%    +6.68%          (p=0.004 n=6+5)
Search_Easy1_CachedDFA/256k/threads:12              4.18GB/s ± 2%           4.43GB/s ± 1%    +5.78%          (p=0.002 n=6+6)
Search_Easy1_CachedDFA/2M/threads:1                 5.91GB/s ± 0%           5.91GB/s ± 2%      ~             (p=0.589 n=6+6)
Search_Easy1_CachedDFA/2M/threads:2                 5.89GB/s ± 0%           5.85GB/s ± 2%      ~             (p=0.699 n=6+6)
Search_Easy1_CachedDFA/2M/threads:4                 5.57GB/s ± 6%           5.44GB/s ± 9%      ~             (p=0.699 n=6+6)
Search_Easy1_CachedDFA/2M/threads:8                 3.88GB/s ± 1%           4.11GB/s ± 0%    +5.91%          (p=0.016 n=5+4)
Search_Easy1_CachedDFA/2M/threads:12                3.79GB/s ± 3%           3.98GB/s ± 1%    +5.28%          (p=0.002 n=6+6)
Search_Easy1_CachedDFA/16M/threads:1                5.48GB/s ± 1%           5.44GB/s ± 2%      ~             (p=0.699 n=6+6)
Search_Easy1_CachedDFA/16M/threads:2                5.34GB/s ± 2%           5.31GB/s ± 1%      ~             (p=0.589 n=6+6)
Search_Easy1_CachedDFA/16M/threads:4                5.09GB/s ± 3%           5.04GB/s ± 8%      ~             (p=0.937 n=6+6)
Search_Easy1_CachedDFA/16M/threads:8                3.67GB/s ± 4%           3.88GB/s ± 1%    +5.78%          (p=0.004 n=6+5)
Search_Easy1_CachedDFA/16M/threads:12               3.62GB/s ± 1%           3.79GB/s ± 1%    +4.78%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/8/threads:1                  140MB/s ± 2%            162MB/s ± 1%   +15.61%          (p=0.004 n=6+5)
Search_Medium_CachedDFA/8/threads:2                  140MB/s ± 1%            159MB/s ± 2%   +13.80%          (p=0.004 n=5+6)
Search_Medium_CachedDFA/8/threads:4                  138MB/s ± 1%            156MB/s ± 6%   +13.08%          (p=0.004 n=5+6)
Search_Medium_CachedDFA/8/threads:8                 77.9MB/s ± 5%           93.4MB/s ± 0%   +19.85%          (p=0.004 n=6+5)
Search_Medium_CachedDFA/8/threads:12                76.1MB/s ± 3%           91.5MB/s ± 2%   +20.29%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/64/threads:1                 266MB/s ± 1%            445MB/s ± 1%   +66.86%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/64/threads:2                 283MB/s ± 6%            444MB/s ± 1%   +56.67%          (p=0.004 n=6+5)
Search_Medium_CachedDFA/64/threads:4                 250MB/s ±12%            431MB/s ± 4%   +72.66%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/64/threads:8                 169MB/s ± 5%            312MB/s ± 1%   +84.73%          (p=0.004 n=6+5)
Search_Medium_CachedDFA/64/threads:12                167MB/s ± 3%            302MB/s ± 1%   +80.23%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/512/threads:1                364MB/s ± 0%            571MB/s ± 1%   +57.00%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/512/threads:2                373MB/s ± 0%            570MB/s ± 0%   +52.84%          (p=0.008 n=5+5)
Search_Medium_CachedDFA/512/threads:4                364MB/s ± 3%            534MB/s ±16%   +46.73%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/512/threads:8                206MB/s ± 5%            430MB/s ± 2%  +108.87%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/512/threads:12               209MB/s ± 2%            427MB/s ± 0%  +103.77%          (p=0.010 n=6+4)
Search_Medium_CachedDFA/4k/threads:1                 389MB/s ± 1%            592MB/s ± 1%   +52.03%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/4k/threads:2                 385MB/s ± 1%            590MB/s ± 1%   +52.96%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/4k/threads:4                 369MB/s ± 9%            559MB/s ± 7%   +51.32%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/4k/threads:8                 224MB/s ± 3%            458MB/s ± 0%  +104.42%          (p=0.016 n=5+4)
Search_Medium_CachedDFA/4k/threads:12                213MB/s ± 2%            455MB/s ± 1%  +113.74%          (p=0.004 n=6+5)
Search_Medium_CachedDFA/32k/threads:1                388MB/s ± 1%            593MB/s ± 1%   +52.68%          (p=0.004 n=5+6)
Search_Medium_CachedDFA/32k/threads:2                386MB/s ± 0%            593MB/s ± 0%   +53.68%          (p=0.004 n=5+6)
Search_Medium_CachedDFA/32k/threads:4                367MB/s ± 6%            559MB/s ± 4%   +52.38%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/32k/threads:8                220MB/s ± 2%            460MB/s ± 0%  +108.85%          (p=0.004 n=6+5)
Search_Medium_CachedDFA/32k/threads:12               211MB/s ± 0%            452MB/s ± 1%  +114.87%          (p=0.004 n=5+6)
Search_Medium_CachedDFA/256k/threads:1               387MB/s ± 1%            595MB/s ± 0%   +53.91%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/256k/threads:2               386MB/s ± 0%            592MB/s ± 1%   +53.50%          (p=0.008 n=5+5)
Search_Medium_CachedDFA/256k/threads:4               376MB/s ± 6%            583MB/s ± 2%   +55.28%          (p=0.008 n=5+5)
Search_Medium_CachedDFA/256k/threads:8               218MB/s ± 0%            458MB/s ± 0%  +110.03%          (p=0.008 n=5+5)
Search_Medium_CachedDFA/256k/threads:12              215MB/s ± 4%            455MB/s ± 1%  +112.24%          (p=0.004 n=6+5)
Search_Medium_CachedDFA/2M/threads:1                 387MB/s ± 0%            591MB/s ± 1%   +52.82%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/2M/threads:2                 385MB/s ± 0%            591MB/s ± 0%   +53.53%          (p=0.008 n=5+5)
Search_Medium_CachedDFA/2M/threads:4                 366MB/s ± 6%            546MB/s ± 8%   +49.28%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/2M/threads:8                 212MB/s ± 5%            456MB/s ± 1%  +115.43%          (p=0.004 n=6+5)
Search_Medium_CachedDFA/2M/threads:12                211MB/s ± 1%            446MB/s ± 1%  +111.65%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/16M/threads:1                385MB/s ± 0%            585MB/s ± 1%   +51.85%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/16M/threads:2                378MB/s ± 4%            578MB/s ± 3%   +52.88%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/16M/threads:4                356MB/s ± 9%            555MB/s ± 9%   +55.99%          (p=0.002 n=6+6)
Search_Medium_CachedDFA/16M/threads:8                218MB/s ± 1%            449MB/s ± 2%  +106.09%          (p=0.004 n=5+6)
Search_Medium_CachedDFA/16M/threads:12               211MB/s ± 2%            447MB/s ± 1%  +112.00%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/8/threads:1                    142MB/s ± 1%            163MB/s ± 0%   +14.91%          (p=0.004 n=6+5)
Search_Hard_CachedDFA/8/threads:2                    141MB/s ± 0%            160MB/s ± 3%   +13.24%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/8/threads:4                    128MB/s ±26%            145MB/s ±24%   +13.61%          (p=0.041 n=6+6)
Search_Hard_CachedDFA/8/threads:8                   79.8MB/s ± 0%           92.5MB/s ± 5%   +15.94%          (p=0.010 n=4+6)
Search_Hard_CachedDFA/8/threads:12                  77.1MB/s ± 2%           91.3MB/s ± 3%   +18.47%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/64/threads:1                   350MB/s ± 1%            447MB/s ± 1%   +27.59%          (p=0.004 n=6+5)
Search_Hard_CachedDFA/64/threads:2                   350MB/s ± 0%            442MB/s ± 1%   +26.09%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/64/threads:4                   340MB/s ± 3%            418MB/s ± 6%   +23.05%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/64/threads:8                   202MB/s ± 2%            307MB/s ± 1%   +52.18%          (p=0.004 n=6+5)
Search_Hard_CachedDFA/64/threads:12                  195MB/s ± 3%            305MB/s ± 0%   +56.09%          (p=0.004 n=6+5)
Search_Hard_CachedDFA/512/threads:1                  434MB/s ± 1%            573MB/s ± 0%   +31.92%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/512/threads:2                  428MB/s ± 1%            566MB/s ± 2%   +32.14%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/512/threads:4                  416MB/s ± 5%            530MB/s ± 8%   +27.29%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/512/threads:8                  243MB/s ± 5%            430MB/s ± 2%   +76.51%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/512/threads:12                 239MB/s ± 1%            427MB/s ± 1%   +78.38%          (p=0.004 n=5+6)
Search_Hard_CachedDFA/4k/threads:1                   445MB/s ± 0%            593MB/s ± 0%   +33.12%          (p=0.008 n=5+5)
Search_Hard_CachedDFA/4k/threads:2                   443MB/s ± 0%            590MB/s ± 1%   +33.17%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/4k/threads:4                   425MB/s ± 6%            579MB/s ± 2%   +36.49%          (p=0.004 n=6+5)
Search_Hard_CachedDFA/4k/threads:8                   258MB/s ± 1%            452MB/s ± 2%   +75.25%          (p=0.004 n=5+6)
Search_Hard_CachedDFA/4k/threads:12                  250MB/s ± 2%            452MB/s ± 1%   +80.80%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/32k/threads:1                  445MB/s ± 1%            595MB/s ± 0%   +33.78%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/32k/threads:2                  444MB/s ± 0%            590MB/s ± 1%   +33.04%          (p=0.004 n=5+6)
Search_Hard_CachedDFA/32k/threads:4                  430MB/s ± 9%            572MB/s ± 3%   +33.00%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/32k/threads:8                  249MB/s ± 4%            454MB/s ± 1%   +82.04%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/32k/threads:12                 251MB/s ± 1%            452MB/s ± 1%   +79.78%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/256k/threads:1                 445MB/s ± 1%            590MB/s ± 1%   +32.63%          (p=0.004 n=6+5)
Search_Hard_CachedDFA/256k/threads:2                 443MB/s ± 0%            587MB/s ± 3%   +32.47%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/256k/threads:4                 426MB/s ± 4%            570MB/s ± 4%   +33.78%          (p=0.004 n=5+6)
Search_Hard_CachedDFA/256k/threads:8                 256MB/s ± 2%            455MB/s ± 3%   +77.80%          (p=0.004 n=5+6)
Search_Hard_CachedDFA/256k/threads:12                252MB/s ± 3%            450MB/s ± 1%   +78.40%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/2M/threads:1                   443MB/s ± 1%            592MB/s ± 1%   +33.72%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/2M/threads:2                   442MB/s ± 0%            591MB/s ± 0%   +33.85%          (p=0.004 n=6+5)
Search_Hard_CachedDFA/2M/threads:4                   410MB/s ± 4%            564MB/s ± 2%   +37.63%          (p=0.008 n=5+5)
Search_Hard_CachedDFA/2M/threads:8                   256MB/s ± 2%            449MB/s ± 2%   +75.60%          (p=0.004 n=5+6)
Search_Hard_CachedDFA/2M/threads:12                  249MB/s ± 3%            449MB/s ± 2%   +80.22%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/16M/threads:1                  441MB/s ± 1%            586MB/s ± 0%   +32.76%          (p=0.004 n=6+5)
Search_Hard_CachedDFA/16M/threads:2                  439MB/s ± 0%            583MB/s ± 1%   +32.81%          (p=0.004 n=5+6)
Search_Hard_CachedDFA/16M/threads:4                  407MB/s ±14%            553MB/s ± 5%   +35.90%          (p=0.002 n=6+6)
Search_Hard_CachedDFA/16M/threads:8                  256MB/s ± 0%            452MB/s ± 0%   +76.89%          (p=0.008 n=5+5)
Search_Hard_CachedDFA/16M/threads:12                 248MB/s ± 2%            445MB/s ± 1%   +79.12%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/8/threads:1                  139MB/s ± 1%            167MB/s ± 1%   +20.07%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/8/threads:2                  137MB/s ± 1%            163MB/s ± 4%   +18.42%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/8/threads:4                  124MB/s ±13%            153MB/s ± 8%   +23.04%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/8/threads:8                 75.1MB/s ± 3%           91.0MB/s ± 0%   +21.18%          (p=0.010 n=6+4)
Search_Fanout_CachedDFA/8/threads:12                75.3MB/s ± 2%           88.4MB/s ± 2%   +17.28%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/64/threads:1                 335MB/s ± 1%            449MB/s ± 0%   +34.06%          (p=0.004 n=6+5)
Search_Fanout_CachedDFA/64/threads:2                 331MB/s ± 1%            446MB/s ± 1%   +34.84%          (p=0.004 n=5+6)
Search_Fanout_CachedDFA/64/threads:4                 297MB/s ±20%            437MB/s ± 6%   +46.83%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/64/threads:8                 183MB/s ± 4%            302MB/s ± 0%   +65.05%          (p=0.004 n=6+5)
Search_Fanout_CachedDFA/64/threads:12                182MB/s ± 4%            298MB/s ± 2%   +63.98%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/512/threads:1                422MB/s ± 0%            572MB/s ± 1%   +35.62%          (p=0.008 n=5+5)
Search_Fanout_CachedDFA/512/threads:2                417MB/s ± 1%            568MB/s ± 1%   +36.32%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/512/threads:4                402MB/s ± 3%            542MB/s ±11%   +34.72%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/512/threads:8                223MB/s ± 0%            434MB/s ± 2%   +94.32%          (p=0.010 n=4+6)
Search_Fanout_CachedDFA/512/threads:12               216MB/s ± 2%            429MB/s ± 1%   +98.82%          (p=0.004 n=6+5)
Search_Fanout_CachedDFA/4k/threads:1                 434MB/s ± 0%            593MB/s ± 0%   +36.48%          (p=0.004 n=6+5)
Search_Fanout_CachedDFA/4k/threads:2                 432MB/s ± 0%            590MB/s ± 0%   +36.49%          (p=0.004 n=6+5)
Search_Fanout_CachedDFA/4k/threads:4                 429MB/s ± 0%            567MB/s ± 8%   +32.05%          (p=0.004 n=5+6)
Search_Fanout_CachedDFA/4k/threads:8                 230MB/s ± 2%            459MB/s ± 0%   +99.35%          (p=0.016 n=5+4)
Search_Fanout_CachedDFA/4k/threads:12                221MB/s ± 2%            453MB/s ± 1%  +104.82%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/32k/threads:1                433MB/s ± 1%            595MB/s ± 0%   +37.25%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/32k/threads:2                431MB/s ± 0%            592MB/s ± 0%   +37.24%          (p=0.004 n=5+6)
Search_Fanout_CachedDFA/32k/threads:4                406MB/s ± 6%            574MB/s ± 4%   +41.29%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/32k/threads:8                232MB/s ± 3%            464MB/s ± 0%  +100.41%          (p=0.004 n=6+5)
Search_Fanout_CachedDFA/32k/threads:12               223MB/s ± 2%            459MB/s ± 1%  +106.09%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/256k/threads:1               428MB/s ± 1%            595MB/s ± 0%   +39.11%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/256k/threads:2               428MB/s ± 1%            593MB/s ± 0%   +38.53%          (p=0.004 n=6+5)
Search_Fanout_CachedDFA/256k/threads:4               399MB/s ±15%            574MB/s ± 4%   +43.77%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/256k/threads:8               232MB/s ± 5%            476MB/s ± 0%  +104.62%          (p=0.004 n=6+5)
Search_Fanout_CachedDFA/256k/threads:12              224MB/s ± 4%            477MB/s ± 1%  +112.81%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/2M/threads:1                 426MB/s ± 1%            594MB/s ± 1%   +39.51%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/2M/threads:2                 424MB/s ± 1%            590MB/s ± 1%   +39.21%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/2M/threads:4                 391MB/s ± 9%            580MB/s ± 2%   +48.19%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/2M/threads:8                 224MB/s ± 6%            491MB/s ± 0%  +119.10%          (p=0.004 n=6+5)
Search_Fanout_CachedDFA/2M/threads:12                220MB/s ± 1%            489MB/s ± 1%  +122.04%          (p=0.004 n=5+6)
Search_Fanout_CachedDFA/16M/threads:1                425MB/s ± 0%            587MB/s ± 1%   +38.32%          (p=0.004 n=5+6)
Search_Fanout_CachedDFA/16M/threads:2                422MB/s ± 1%            586MB/s ± 0%   +38.97%          (p=0.004 n=6+5)
Search_Fanout_CachedDFA/16M/threads:4                357MB/s ±15%            567MB/s ± 2%   +59.01%          (p=0.002 n=6+6)
Search_Fanout_CachedDFA/16M/threads:8                228MB/s ± 0%            483MB/s ± 2%  +112.06%          (p=0.010 n=4+6)
Search_Fanout_CachedDFA/16M/threads:12               223MB/s ± 2%            484MB/s ± 1%  +116.75%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/8/threads:1                  141MB/s ± 1%            162MB/s ± 1%   +14.86%          (p=0.004 n=6+5)
Search_Parens_CachedDFA/8/threads:2                  140MB/s ± 1%            158MB/s ± 4%   +12.51%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/8/threads:4                  138MB/s ± 4%            151MB/s ±15%      ~             (p=0.082 n=5+6)
Search_Parens_CachedDFA/8/threads:8                 78.0MB/s ± 6%           91.7MB/s ± 4%   +17.59%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/8/threads:12                77.6MB/s ± 2%           91.8MB/s ± 3%   +18.32%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/64/threads:1                 352MB/s ± 1%            445MB/s ± 0%   +26.58%          (p=0.008 n=5+5)
Search_Parens_CachedDFA/64/threads:2                 347MB/s ± 2%            441MB/s ± 2%   +27.05%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/64/threads:4                 336MB/s ± 5%            431MB/s ± 5%   +27.96%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/64/threads:8                 205MB/s ± 2%            309MB/s ± 1%   +50.83%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/64/threads:12                198MB/s ± 4%            303MB/s ± 2%   +52.95%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/512/threads:1                436MB/s ± 0%            572MB/s ± 1%   +31.03%          (p=0.004 n=5+6)
Search_Parens_CachedDFA/512/threads:2                430MB/s ± 1%            569MB/s ± 1%   +32.10%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/512/threads:4                417MB/s ± 8%            550MB/s ± 4%   +31.74%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/512/threads:8                251MB/s ± 2%            437MB/s ± 1%   +74.07%          (p=0.004 n=6+5)
Search_Parens_CachedDFA/512/threads:12               243MB/s ± 3%            428MB/s ± 1%   +76.19%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/4k/threads:1                 443MB/s ± 1%            594MB/s ± 0%   +34.04%          (p=0.004 n=6+5)
Search_Parens_CachedDFA/4k/threads:2                 443MB/s ± 0%            591MB/s ± 0%   +33.42%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/4k/threads:4                 410MB/s ± 9%            581MB/s ± 2%   +41.79%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/4k/threads:8                 255MB/s ± 6%            459MB/s ± 1%   +79.82%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/4k/threads:12                250MB/s ± 2%            450MB/s ± 1%   +79.51%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/32k/threads:1                444MB/s ± 1%            596MB/s ± 0%   +34.17%          (p=0.004 n=5+6)
Search_Parens_CachedDFA/32k/threads:2                443MB/s ± 0%            593MB/s ± 0%   +33.72%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/32k/threads:4                434MB/s ± 4%            567MB/s ± 5%   +30.67%          (p=0.004 n=5+6)
Search_Parens_CachedDFA/32k/threads:8                257MB/s ± 1%            459MB/s ± 2%   +78.28%          (p=0.004 n=5+6)
Search_Parens_CachedDFA/32k/threads:12               248MB/s ± 1%            453MB/s ± 1%   +82.71%          (p=0.004 n=5+6)
Search_Parens_CachedDFA/256k/threads:1               441MB/s ± 2%            597MB/s ± 0%   +35.16%          (p=0.004 n=6+5)
Search_Parens_CachedDFA/256k/threads:2               442MB/s ± 1%            594MB/s ± 0%   +34.41%          (p=0.004 n=6+5)
Search_Parens_CachedDFA/256k/threads:4               402MB/s ±18%            571MB/s ± 6%   +41.92%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/256k/threads:8               258MB/s ± 1%            453MB/s ± 2%   +75.68%          (p=0.004 n=5+6)
Search_Parens_CachedDFA/256k/threads:12              251MB/s ± 2%            452MB/s ± 1%   +80.04%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/2M/threads:1                 442MB/s ± 1%            592MB/s ± 2%   +33.92%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/2M/threads:2                 440MB/s ± 1%            591MB/s ± 0%   +34.24%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/2M/threads:4                 417MB/s ± 4%            583MB/s ± 1%   +39.74%          (p=0.008 n=5+5)
Search_Parens_CachedDFA/2M/threads:8                 251MB/s ± 5%            454MB/s ± 1%   +80.51%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/2M/threads:12                250MB/s ± 4%            447MB/s ± 1%   +78.84%          (p=0.002 n=6+6)
Search_Parens_CachedDFA/16M/threads:1                441MB/s ± 1%            585MB/s ± 1%   +32.65%          (p=0.004 n=5+6)
Search_Parens_CachedDFA/16M/threads:2                440MB/s ± 0%            585MB/s ± 0%   +33.11%          (p=0.004 n=6+5)
Search_Parens_CachedDFA/16M/threads:4                422MB/s ± 7%            553MB/s ± 1%   +31.13%          (p=0.004 n=6+5)
Search_Parens_CachedDFA/16M/threads:8                256MB/s ± 0%            452MB/s ± 1%   +76.70%          (p=0.004 n=6+5)
Search_Parens_CachedDFA/16M/threads:12               249MB/s ± 2%            448MB/s ± 0%   +79.67%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/8/threads:1                140MB/s ± 1%            159MB/s ± 2%   +13.66%          (p=0.008 n=5+5)
Search_BigFixed_CachedDFA/8/threads:2                135MB/s ± 5%            158MB/s ± 1%   +16.54%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/8/threads:4                123MB/s ±28%            146MB/s ±11%   +18.75%          (p=0.026 n=6+6)
Search_BigFixed_CachedDFA/8/threads:8               77.0MB/s ± 4%           86.5MB/s ± 4%   +12.35%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/8/threads:12              75.5MB/s ± 3%           86.8MB/s ± 0%   +15.09%          (p=0.004 n=6+5)
Search_BigFixed_CachedDFA/64/threads:1               350MB/s ± 2%            436MB/s ± 6%   +24.62%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/64/threads:2               346MB/s ± 2%            441MB/s ± 1%   +27.73%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/64/threads:4               336MB/s ± 7%            434MB/s ± 2%   +29.16%          (p=0.008 n=5+5)
Search_BigFixed_CachedDFA/64/threads:8               200MB/s ± 5%            298MB/s ± 1%   +48.94%          (p=0.004 n=6+5)
Search_BigFixed_CachedDFA/64/threads:12              199MB/s ± 3%            294MB/s ± 1%   +48.05%          (p=0.004 n=6+5)
Search_BigFixed_CachedDFA/512/threads:1              426MB/s ± 3%            533MB/s ± 6%   +25.20%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/512/threads:2              422MB/s ± 2%            511MB/s ± 3%   +21.16%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/512/threads:4              402MB/s ± 5%            479MB/s ± 3%   +19.30%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/512/threads:8              224MB/s ± 8%            283MB/s ± 7%   +26.30%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/512/threads:12             215MB/s ± 3%            272MB/s ± 1%   +26.68%          (p=0.004 n=5+6)
Search_BigFixed_CachedDFA/4k/threads:1               230MB/s ± 6%            229MB/s ±13%      ~             (p=0.699 n=6+6)
Search_BigFixed_CachedDFA/4k/threads:2               211MB/s ±12%            210MB/s ± 9%      ~             (p=0.937 n=6+6)
Search_BigFixed_CachedDFA/4k/threads:4               169MB/s ±11%            189MB/s ± 8%   +11.68%          (p=0.015 n=6+6)
Search_BigFixed_CachedDFA/4k/threads:8               126MB/s ± 2%            141MB/s ± 2%   +12.19%          (p=0.004 n=5+6)
Search_BigFixed_CachedDFA/4k/threads:12              127MB/s ± 3%            145MB/s ± 3%   +14.70%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/32k/threads:1              161MB/s ± 1%            168MB/s ± 0%    +4.46%          (p=0.004 n=6+5)
Search_BigFixed_CachedDFA/32k/threads:2              148MB/s ± 3%            153MB/s ± 2%    +3.39%          (p=0.009 n=6+6)
Search_BigFixed_CachedDFA/32k/threads:4              151MB/s ± 3%            156MB/s ± 3%    +3.45%          (p=0.041 n=6+6)
Search_BigFixed_CachedDFA/32k/threads:8              109MB/s ± 6%            124MB/s ± 6%   +14.70%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/32k/threads:12            90.4MB/s ± 3%          104.9MB/s ± 1%   +16.07%          (p=0.002 n=6+6)
Search_BigFixed_CachedDFA/256k/threads:1            93.9MB/s ± 7%           99.2MB/s ± 3%    +5.68%          (p=0.041 n=6+6)
Search_BigFixed_CachedDFA/256k/threads:2             464kB/s ± 4%            488kB/s ± 2%    +5.04%          (p=0.016 n=5+5)
Search_BigFixed_CachedDFA/256k/threads:4             300kB/s ± 9%            276kB/s ± 7%    -7.79%          (p=0.037 n=6+6)
Search_BigFixed_CachedDFA/256k/threads:8             126kB/s ± 6%            124kB/s ± 3%      ~             (p=0.368 n=6+6)
Search_BigFixed_CachedDFA/256k/threads:12           74.7kB/s ±12%           72.2kB/s ±12%      ~             (p=0.431 n=6+6)
Search_BigFixed_CachedDFA/1M/threads:1               668kB/s ± 2%            650kB/s ± 6%      ~             (p=0.076 n=6+6)
Search_BigFixed_CachedDFA/1M/threads:2               205kB/s ± 5%            201kB/s ± 2%      ~             (p=0.370 n=6+6)
Search_BigFixed_CachedDFA/1M/threads:4               100kB/s ± 9%            105kB/s ± 9%      ~             (p=0.416 n=6+6)
Search_BigFixed_CachedDFA/1M/threads:8              67.3kB/s ±11%           64.5kB/s ± 7%      ~             (p=0.524 n=6+6)
Search_BigFixed_CachedDFA/1M/threads:12             65.5kB/s ± 8%           63.2kB/s ± 9%      ~             (p=0.411 n=6+6)
Search_Success_CachedDFA/8/threads:1                 137MB/s ± 2%            160MB/s ± 1%   +16.01%          (p=0.002 n=6+6)
Search_Success_CachedDFA/8/threads:2                 136MB/s ± 2%            158MB/s ± 1%   +16.44%          (p=0.002 n=6+6)
Search_Success_CachedDFA/8/threads:4                 128MB/s ±12%            151MB/s ± 7%   +18.51%          (p=0.002 n=6+6)
Search_Success_CachedDFA/8/threads:8                76.8MB/s ± 4%           88.2MB/s ± 0%   +14.83%          (p=0.008 n=5+5)
Search_Success_CachedDFA/8/threads:12               73.1MB/s ± 2%           85.6MB/s ± 2%   +17.05%          (p=0.002 n=6+6)
Search_Success_CachedDFA/64/threads:1                334MB/s ± 0%            444MB/s ± 1%   +32.75%          (p=0.004 n=5+6)
Search_Success_CachedDFA/64/threads:2                332MB/s ± 0%            438MB/s ± 2%   +31.74%          (p=0.002 n=6+6)
Search_Success_CachedDFA/64/threads:4                324MB/s ± 6%            425MB/s ± 6%   +31.10%          (p=0.002 n=6+6)
Search_Success_CachedDFA/64/threads:8                184MB/s ± 1%            299MB/s ± 4%   +62.33%          (p=0.004 n=5+6)
Search_Success_CachedDFA/64/threads:12               177MB/s ± 1%            294MB/s ± 1%   +65.69%          (p=0.002 n=6+6)
Search_Success_CachedDFA/512/threads:1               420MB/s ± 1%            573MB/s ± 0%   +36.52%          (p=0.002 n=6+6)
Search_Success_CachedDFA/512/threads:2               417MB/s ± 0%            570MB/s ± 0%   +36.53%          (p=0.004 n=6+5)
Search_Success_CachedDFA/512/threads:4               406MB/s ± 8%            559MB/s ± 4%   +37.64%          (p=0.002 n=6+6)
Search_Success_CachedDFA/512/threads:8               225MB/s ± 3%            433MB/s ± 0%   +92.18%          (p=0.004 n=6+5)
Search_Success_CachedDFA/512/threads:12              216MB/s ± 1%            426MB/s ± 1%   +97.43%          (p=0.002 n=6+6)
Search_Success_CachedDFA/4k/threads:1                432MB/s ± 1%            595MB/s ± 0%   +37.56%          (p=0.004 n=6+5)
Search_Success_CachedDFA/4k/threads:2                430MB/s ± 1%            591MB/s ± 0%   +37.53%          (p=0.002 n=6+6)
Search_Success_CachedDFA/4k/threads:4                399MB/s ±18%            550MB/s ± 7%   +37.86%          (p=0.002 n=6+6)
Search_Success_CachedDFA/4k/threads:8                224MB/s ± 6%            458MB/s ± 1%  +104.32%          (p=0.004 n=6+5)
Search_Success_CachedDFA/4k/threads:12               221MB/s ± 3%            447MB/s ± 1%  +102.68%          (p=0.002 n=6+6)
Search_Success_CachedDFA/32k/threads:1               434MB/s ± 0%            595MB/s ± 1%   +37.16%          (p=0.004 n=5+6)
Search_Success_CachedDFA/32k/threads:2               431MB/s ± 0%            593MB/s ± 0%   +37.55%          (p=0.004 n=5+6)
Search_Success_CachedDFA/32k/threads:4               420MB/s ± 2%            575MB/s ± 3%   +36.71%          (p=0.004 n=5+6)
Search_Success_CachedDFA/32k/threads:8               230MB/s ± 1%            459MB/s ± 0%   +99.72%          (p=0.004 n=6+5)
Search_Success_CachedDFA/32k/threads:12              224MB/s ± 1%            456MB/s ± 1%  +103.42%          (p=0.004 n=6+5)
Search_Success_CachedDFA/256k/threads:1              427MB/s ± 1%            597MB/s ± 0%   +39.73%          (p=0.004 n=6+5)
Search_Success_CachedDFA/256k/threads:2              427MB/s ± 0%            593MB/s ± 0%   +38.77%          (p=0.008 n=5+5)
Search_Success_CachedDFA/256k/threads:4              406MB/s ± 6%            581MB/s ± 4%   +43.22%          (p=0.002 n=6+6)
Search_Success_CachedDFA/256k/threads:8              229MB/s ± 0%            458MB/s ± 0%  +100.03%          (p=0.010 n=4+6)
Search_Success_CachedDFA/256k/threads:12             224MB/s ± 2%            452MB/s ± 1%  +101.66%          (p=0.002 n=6+6)
Search_Success_CachedDFA/2M/threads:1                426MB/s ± 1%            595MB/s ± 0%   +39.88%          (p=0.004 n=6+5)
Search_Success_CachedDFA/2M/threads:2                425MB/s ± 1%            590MB/s ± 1%   +38.93%          (p=0.004 n=5+6)
Search_Success_CachedDFA/2M/threads:4                388MB/s ± 9%            574MB/s ± 4%   +48.15%          (p=0.002 n=6+6)
Search_Success_CachedDFA/2M/threads:8                229MB/s ± 1%            453MB/s ± 0%   +98.03%          (p=0.029 n=4+4)
Search_Success_CachedDFA/2M/threads:12               222MB/s ± 3%            451MB/s ± 1%  +102.69%          (p=0.002 n=6+6)
Search_Success_CachedDFA/16M/threads:1               423MB/s ± 1%            587MB/s ± 0%   +38.84%          (p=0.004 n=6+5)
Search_Success_CachedDFA/16M/threads:2               422MB/s ± 0%            585MB/s ± 0%   +38.64%          (p=0.004 n=6+5)
Search_Success_CachedDFA/16M/threads:4               394MB/s ± 7%            538MB/s ± 6%   +36.37%          (p=0.002 n=6+6)
Search_Success_CachedDFA/16M/threads:8               223MB/s ± 6%            451MB/s ± 0%  +102.34%          (p=0.002 n=6+6)
Search_Success_CachedDFA/16M/threads:12              220MB/s ± 2%            448MB/s ± 1%  +103.48%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/8/threads:1                140MB/s ± 1%            156MB/s ± 3%   +11.43%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/8/threads:2                139MB/s ± 1%            157MB/s ± 2%   +12.63%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/8/threads:4                131MB/s ± 6%            141MB/s ±17%      ~             (p=0.394 n=6+6)
Search_Success1_CachedDFA/8/threads:8               78.3MB/s ± 0%           88.1MB/s ± 0%   +12.50%          (p=0.016 n=4+5)
Search_Success1_CachedDFA/8/threads:12              76.1MB/s ± 3%           86.7MB/s ± 0%   +14.01%          (p=0.004 n=6+5)
Search_Success1_CachedDFA/64/threads:1               344MB/s ± 5%            439MB/s ± 4%   +27.46%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/64/threads:2               348MB/s ± 0%            438MB/s ± 1%   +25.57%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/64/threads:4               301MB/s ±26%            425MB/s ± 7%   +41.32%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/64/threads:8               206MB/s ± 3%            299MB/s ± 1%   +44.92%          (p=0.008 n=5+5)
Search_Success1_CachedDFA/64/threads:12              197MB/s ± 1%            293MB/s ± 1%   +48.46%          (p=0.004 n=5+6)
Search_Success1_CachedDFA/512/threads:1              446MB/s ± 2%            570MB/s ± 1%   +27.82%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/512/threads:2              443MB/s ± 1%            569MB/s ± 0%   +28.46%          (p=0.004 n=5+6)
Search_Success1_CachedDFA/512/threads:4              442MB/s ± 0%            531MB/s ±15%   +20.25%          (p=0.004 n=5+6)
Search_Success1_CachedDFA/512/threads:8              248MB/s ± 7%            429MB/s ± 2%   +72.71%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/512/threads:12             248MB/s ± 3%            426MB/s ± 1%   +71.91%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/4k/threads:1               461MB/s ± 1%            594MB/s ± 1%   +28.90%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/4k/threads:2               457MB/s ± 0%            591MB/s ± 0%   +29.28%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/4k/threads:4               404MB/s ±18%            580MB/s ± 1%   +43.56%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/4k/threads:8               254MB/s ± 4%            455MB/s ± 3%   +79.34%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/4k/threads:12              254MB/s ± 2%            451MB/s ± 1%   +77.21%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/32k/threads:1              460MB/s ± 1%            595MB/s ± 1%   +29.28%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/32k/threads:2              458MB/s ± 1%            593MB/s ± 0%   +29.40%          (p=0.004 n=6+5)
Search_Success1_CachedDFA/32k/threads:4              425MB/s ±18%            572MB/s ± 5%   +34.61%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/32k/threads:8              262MB/s ± 0%            455MB/s ± 2%   +73.79%          (p=0.010 n=4+6)
Search_Success1_CachedDFA/32k/threads:12             257MB/s ± 1%            453MB/s ± 1%   +76.24%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/256k/threads:1             460MB/s ± 1%            596MB/s ± 0%   +29.58%          (p=0.004 n=6+5)
Search_Success1_CachedDFA/256k/threads:2             458MB/s ± 0%            592MB/s ± 1%   +29.45%          (p=0.004 n=5+6)
Search_Success1_CachedDFA/256k/threads:4             436MB/s ± 3%            573MB/s ± 7%   +31.43%          (p=0.004 n=5+6)
Search_Success1_CachedDFA/256k/threads:8             258MB/s ± 7%            455MB/s ± 2%   +76.26%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/256k/threads:12            254MB/s ± 3%            453MB/s ± 1%   +78.27%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/2M/threads:1               461MB/s ± 1%            594MB/s ± 1%   +28.80%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/2M/threads:2               457MB/s ± 0%            592MB/s ± 0%   +29.42%          (p=0.004 n=6+5)
Search_Success1_CachedDFA/2M/threads:4               452MB/s ± 1%            562MB/s ±10%   +24.31%          (p=0.004 n=5+6)
Search_Success1_CachedDFA/2M/threads:8               263MB/s ± 2%            455MB/s ± 0%   +72.60%          (p=0.004 n=5+6)
Search_Success1_CachedDFA/2M/threads:12              255MB/s ± 4%            449MB/s ± 1%   +76.26%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/16M/threads:1              457MB/s ± 1%            588MB/s ± 0%   +28.58%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/16M/threads:2              453MB/s ± 1%            586MB/s ± 0%   +29.38%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/16M/threads:4              412MB/s ±11%            564MB/s ± 6%   +36.79%          (p=0.002 n=6+6)
Search_Success1_CachedDFA/16M/threads:8              260MB/s ± 7%            451MB/s ± 0%   +73.63%          (p=0.010 n=6+4)
Search_Success1_CachedDFA/16M/threads:12             251MB/s ± 4%            449MB/s ± 1%   +79.20%          (p=0.002 n=6+6)
Search_AltMatch_CachedDFA/8/threads:1                199MB/s ± 5%            222MB/s ± 1%   +11.27%          (p=0.004 n=6+5)
Search_AltMatch_CachedDFA/8/threads:2                200MB/s ± 1%            219MB/s ± 1%    +9.29%          (p=0.008 n=5+5)
Search_AltMatch_CachedDFA/8/threads:4                188MB/s ± 6%            198MB/s ±14%      ~             (p=0.699 n=6+6)
Search_AltMatch_CachedDFA/8/threads:8                114MB/s ± 1%            123MB/s ± 4%    +8.33%          (p=0.010 n=4+6)
Search_AltMatch_CachedDFA/8/threads:12               111MB/s ± 1%            121MB/s ± 0%    +8.74%          (p=0.004 n=6+5)
Search_AltMatch_CachedDFA/64/threads:1              1.62GB/s ± 1%           1.78GB/s ± 0%    +9.78%          (p=0.008 n=5+5)
Search_AltMatch_CachedDFA/64/threads:2              1.59GB/s ± 3%           1.74GB/s ± 2%    +9.53%          (p=0.002 n=6+6)
Search_AltMatch_CachedDFA/64/threads:4              1.51GB/s ± 9%           1.57GB/s ±10%      ~             (p=0.589 n=6+6)
Search_AltMatch_CachedDFA/64/threads:8               914MB/s ± 1%            997MB/s ± 0%    +9.08%          (p=0.004 n=6+5)
Search_AltMatch_CachedDFA/64/threads:12              880MB/s ± 1%            989MB/s ± 2%   +12.40%          (p=0.002 n=6+6)
Search_AltMatch_CachedDFA/512/threads:1             12.9GB/s ± 1%           14.1GB/s ± 0%    +9.34%          (p=0.004 n=6+5)
Search_AltMatch_CachedDFA/512/threads:2             12.9GB/s ± 0%           14.0GB/s ± 2%    +8.30%          (p=0.008 n=5+5)
Search_AltMatch_CachedDFA/512/threads:4             12.2GB/s ±11%           13.8GB/s ± 4%   +13.00%          (p=0.004 n=6+5)
Search_AltMatch_CachedDFA/512/threads:8             7.30GB/s ± 0%           8.01GB/s ± 0%    +9.67%          (p=0.016 n=5+4)
Search_AltMatch_CachedDFA/512/threads:12            7.13GB/s ± 2%           7.77GB/s ± 3%    +9.06%          (p=0.002 n=6+6)
Search_AltMatch_CachedDFA/4k/threads:1               104GB/s ± 0%            114GB/s ± 0%    +9.69%          (p=0.008 n=5+5)
Search_AltMatch_CachedDFA/4k/threads:2               103GB/s ± 1%            113GB/s ± 0%   +10.09%          (p=0.004 n=6+5)
Search_AltMatch_CachedDFA/4k/threads:4              98.6GB/s ± 5%          102.3GB/s ±12%      ~             (p=0.394 n=6+6)
Search_AltMatch_CachedDFA/4k/threads:8              59.3GB/s ± 2%           64.8GB/s ± 3%    +9.24%          (p=0.002 n=6+6)
Search_AltMatch_CachedDFA/4k/threads:12             57.2GB/s ± 2%           62.2GB/s ± 1%    +8.75%          (p=0.004 n=6+5)
Search_AltMatch_CachedDFA/32k/threads:1              827GB/s ± 1%            895GB/s ± 4%    +8.26%          (p=0.008 n=5+5)
Search_AltMatch_CachedDFA/32k/threads:2              811GB/s ± 3%            889GB/s ± 1%    +9.53%          (p=0.004 n=6+5)
Search_AltMatch_CachedDFA/32k/threads:4              754GB/s ± 9%            827GB/s ± 9%    +9.72%          (p=0.041 n=6+6)
Search_AltMatch_CachedDFA/32k/threads:8              466GB/s ± 0%            514GB/s ± 0%   +10.09%          (p=0.010 n=6+4)
Search_AltMatch_CachedDFA/32k/threads:12             460GB/s ± 1%            501GB/s ± 1%    +9.04%          (p=0.002 n=6+6)
Search_AltMatch_CachedDFA/256k/threads:1            6.59TB/s ± 1%           7.27TB/s ± 0%   +10.30%          (p=0.008 n=5+5)
Search_AltMatch_CachedDFA/256k/threads:2            6.60TB/s ± 0%           7.09TB/s ± 5%    +7.32%          (p=0.004 n=5+6)
Search_AltMatch_CachedDFA/256k/threads:4            6.13TB/s ± 4%           6.58TB/s ±12%      ~             (p=0.240 n=6+6)
Search_AltMatch_CachedDFA/256k/threads:8            3.73TB/s ± 1%           4.11TB/s ± 2%   +10.13%          (p=0.004 n=5+6)
Search_AltMatch_CachedDFA/256k/threads:12           3.64TB/s ± 3%           4.02TB/s ± 2%   +10.27%          (p=0.002 n=6+6)
Search_AltMatch_CachedDFA/2M/threads:1              53.1TB/s ± 1%           58.1TB/s ± 1%    +9.42%          (p=0.004 n=5+6)
Search_AltMatch_CachedDFA/2M/threads:2              51.9TB/s ± 2%           57.8TB/s ± 0%   +11.32%          (p=0.004 n=6+5)
Search_AltMatch_CachedDFA/2M/threads:4              47.7TB/s ± 6%           54.8TB/s ± 5%   +15.03%          (p=0.004 n=6+5)
Search_AltMatch_CachedDFA/2M/threads:8              29.3TB/s ± 4%           32.7TB/s ± 1%   +11.43%          (p=0.002 n=6+6)
Search_AltMatch_CachedDFA/2M/threads:12             29.1TB/s ± 3%           32.0TB/s ± 3%   +10.03%          (p=0.002 n=6+6)
Search_AltMatch_CachedDFA/16M/threads:1              417TB/s ± 7%            453TB/s ± 3%    +8.79%          (p=0.002 n=6+6)
Search_AltMatch_CachedDFA/16M/threads:2              415TB/s ± 4%            458TB/s ± 2%   +10.25%          (p=0.002 n=6+6)
Search_AltMatch_CachedDFA/16M/threads:4              406TB/s ± 4%            419TB/s ± 8%      ~             (p=0.589 n=6+6)
Search_AltMatch_CachedDFA/16M/threads:8              239TB/s ± 0%            262TB/s ± 0%    +9.79%          (p=0.008 n=5+5)
Search_AltMatch_CachedDFA/16M/threads:12             235TB/s ± 1%            256TB/s ± 1%    +8.78%          (p=0.008 n=5+5)
```

Change-Id: I09708dd9ae6c2e134460a59f690248b366a204e2
Reviewed-on: https://code-review.googlesource.com/c/re2/+/57510
Reviewed-by: Paul Wankadia <junyer@google.com>
1 file changed