view release on metacpan or  search on metacpan

lib/Bencher/Scenario/ArraySamplePartition.pm  view on Meta::CPAN

=over

=item * 1/10

=item * 5/10

=item * 1/100

=item * 10/100

=item * 50/100

=item * 1/1000

=item * 10/1000

=item * 100/1000

=item * 500/1000

=back

=head1 BENCHMARK SAMPLE RESULTS

=head2 Sample benchmark #1

Run on: perl: I<< v5.34.0 >>, CPU: I<< Intel(R) Core(TM) i7-4770 CPU @ 3.40GHz (4 cores) >>, OS: I<< GNU/Linux LinuxMint version 19 >>, OS kernel: I<< Linux version 5.3.0-68-generic >>.

Benchmark command (default options):

 % bencher -m ArraySamplePartition

Result formatted as table:

 #table1#
 | dataset  | rate (/s) | time (μs) | pct_faster_vs_slowest | pct_slower_vs_fastest |  errors | samples |
 |----------+-----------+-----------+-----------------------+-----------------------+---------+---------|
 | 500/1000 |    8650   |  116      |                 0.00% |             14836.87% | 5.3e-08 |      20 |
 | 100/1000 |   28900   |   34.6    |               234.18% |              4369.68% |   1e-08 |      34 |
 | 10/1000  |   61200   |   16.3    |               607.56% |              2011.04% | 6.5e-09 |      21 |
 | 1/1000   |   68900   |   14.5    |               695.89% |              1776.76% | 5.6e-09 |      28 |
 | 50/100   |   83954.7 |   11.9112 |               870.43% |              1439.20% | 5.8e-12 |      26 |
 | 10/100   |  257240   |    3.8874 |              2873.47% |               402.34% | 5.8e-12 |      20 |
 | 1/100    |  492000   |    2.03   |              5590.87% |               162.47% | 8.3e-10 |      20 |
 | 5/10     |  620000   |    1.6    |              7061.39% |               108.58% | 3.3e-09 |      20 |
 | 1/10     | 1300000   |    0.77   |             14836.87% |                 0.00% | 1.2e-09 |      21 |


The above result formatted in L<Benchmark.pm|Benchmark> style:

                 Rate  500/1000  100/1000  10/1000  1/1000  50/100  10/100  1/100  5/10  1/10 
  500/1000     8650/s        --      -70%     -85%    -87%    -89%    -96%   -98%  -98%  -99% 
  100/1000    28900/s      235%        --     -52%    -58%    -65%    -88%   -94%  -95%  -97% 
  10/1000     61200/s      611%      112%       --    -11%    -26%    -76%   -87%  -90%  -95% 
  1/1000      68900/s      700%      138%      12%      --    -17%    -73%   -86%  -88%  -94% 
  50/100    83954.7/s      873%      190%      36%     21%      --    -67%   -82%  -86%  -93% 
  10/100     257240/s     2883%      790%     319%    272%    206%      --   -47%  -58%  -80% 
  1/100      492000/s     5614%     1604%     702%    614%    486%     91%     --  -21%  -62% 
  5/10       620000/s     7150%     2062%     918%    806%    644%    142%    26%    --  -51% 
  1/10      1300000/s    14964%     4393%    2016%   1783%   1446%    404%   163%  107%    -- 
 
 Legends:
   1/10: dataset=1/10
   1/100: dataset=1/100
   1/1000: dataset=1/1000
   10/100: dataset=10/100
   10/1000: dataset=10/1000
   100/1000: dataset=100/1000
   5/10: dataset=5/10
   50/100: dataset=50/100
   500/1000: dataset=500/1000

The above result presented as chart:

=begin html

<img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAtAAAAH4CAMAAABUnipoAAAJJmlDQ1BpY2MAAEiJlZVnUJNZF8fv8zzphUASQodQQ5EqJYCUEFoo0quoQOidUEVsiLgCK4qINEWQRQEXXJUia0UUC4uCAhZ0gywCyrpxFVFBWXDfGZ33HT+8/5l7z2/+c+bec8/5cAEgiINlwct7YlK6wNvJjhkYFMwE3yiMn5...

=end html


=head2 Sample benchmark #2

Benchmark command (benchmarking module startup overhead):

 % bencher -m ArraySamplePartition --module-startup

Result formatted as table:

 #table2#
 | participant              | time (ms) | mod_overhead_time | pct_faster_vs_slowest | pct_slower_vs_fastest |  errors | samples |
 |--------------------------+-----------+-------------------+-----------------------+-----------------------+---------+---------|
 | Array::Sample::Partition |         7 |                 3 |                 0.00% |                64.41% | 0.00025 |      21 |
 | perl -e1 (baseline)      |         4 |                 0 |                64.41% |                 0.00% | 0.00014 |      27 |


The above result formatted in L<Benchmark.pm|Benchmark> style:

                          Rate  AS:P  perl -e1 (baseline) 
  AS:P                 142.9/s    --                 -42% 
  perl -e1 (baseline)  250.0/s   75%                   -- 
 
 Legends:
   AS:P: mod_overhead_time=3 participant=Array::Sample::Partition
   perl -e1 (baseline): mod_overhead_time=0 participant=perl -e1 (baseline)

The above result presented as chart:

=begin html

<img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAtAAAAH4CAMAAABUnipoAAAJJmlDQ1BpY2MAAEiJlZVnUJNZF8fv8zzphUASQodQQ5EqJYCUEFoo0quoQOidUEVsiLgCK4qINEWQRQEXXJUia0UUC4uCAhZ0gywCyrpxFVFBWXDfGZ33HT+8/5l7z2/+c+bec8/5cAEgiINlwct7YlK6wNvJjhkYFMwE3yiMn5...

=end html


To display as an interactive HTML table on a browser, you can add option C<--format html+datatables>.

=head1 CONTRIBUTOR

=for stopwords perlancar (on pc-home)