criterion performance measurements

overview

want to understand this report?

|V|=4039 |E|=88234 |SCC|=4039/AM-alga

200
205
210
215
220
225
230
235
|V|=4039 |E|=88234 |SCC|=4039/AM-alga time densities
mean
2
3
4
5
6
1 iters
500
750
0 s
250 ms
1 s
1.25
1.5
regression
|V|=4039 |E|=88234 |SCC|=4039/AM-alga times
lower bound estimate upper bound
OLS regression 202 ms 217 ms 258 ms
R² goodness-of-fit 0.915 0.980 1.000
Mean execution time 203 ms 209 ms 225 ms
Standard deviation 1.01 ms 12.7 ms 17.8 ms

Outlying measurements have moderate (14.7%) effect on estimated standard deviation.

|V|=4039 |E|=88234 |SCC|=4039/AIM-alga

170
175
180
185
190
195
200
|V|=4039 |E|=88234 |SCC|=4039/AIM-alga time densities
mean
2
3
4
5
6
1 iters
400
600
800
0 s
200 ms
1 s
1.2
regression
|V|=4039 |E|=88234 |SCC|=4039/AIM-alga times
lower bound estimate upper bound
OLS regression 167 ms 182 ms 220 ms
R² goodness-of-fit 0.916 0.975 1.000
Mean execution time 171 ms 176 ms 190 ms
Standard deviation 2.01 ms 11.7 ms 16.5 ms

Outlying measurements have moderate (15.0%) effect on estimated standard deviation.

|V|=4039 |E|=88234 |SCC|=4039/KL-alga

432
433
433
434
434
435
435
436
436
|V|=4039 |E|=88234 |SCC|=4039/KL-alga time densities
mean
1
2
2
3
3
4
4
0.5 iters
2
0 s
500 ms
1 s
1.5
regression
|V|=4039 |E|=88234 |SCC|=4039/KL-alga times
lower bound estimate upper bound
OLS regression 430 ms 436 ms 443 ms
R² goodness-of-fit 1.000 1.000 1.000
Mean execution time 432 ms 434 ms 435 ms
Standard deviation 738 μs 1.50 ms 1.98 ms

Outlying measurements have moderate (18.8%) effect on estimated standard deviation.

|V|=81306 |E|=1768149 |SCC|=12248/AM-alga

7.35
7.4
7.45
7.50
|V|=81306 |E|=1768149 |SCC|=12248/AM-alga time densities
mean
1
2
2
3
3
4
4
0.5 iters
5
10
15
20
25
30
35
0 s
regression
|V|=81306 |E|=1768149 |SCC|=12248/AM-alga times
lower bound estimate upper bound
OLS regression 7.32 s 7.44 s 7.70 s
R² goodness-of-fit 1.000 1.000 1.000
Mean execution time 7.36 s 7.44 s 7.49 s
Standard deviation 38.0 ms 74.0 ms 103 ms

Outlying measurements have moderate (18.7%) effect on estimated standard deviation.

|V|=81306 |E|=1768149 |SCC|=12248/AIM-alga

4.35
4.40
4.45
4.5
4.55
4.6
4.65
|V|=81306 |E|=1768149 |SCC|=12248/AIM-alga time densities
mean
1
2
2
3
3
4
4
0.5 iters
5
10
15
20
0 s
regression
|V|=81306 |E|=1768149 |SCC|=12248/AIM-alga times
lower bound estimate upper bound
OLS regression 4.21 s 4.29 s 4.43 s
R² goodness-of-fit 1.000 1.000 1.000
Mean execution time 4.39 s 4.47 s 4.62 s
Standard deviation 8.07 ms 134 ms 167 ms

Outlying measurements have moderate (18.8%) effect on estimated standard deviation.

|V|=81306 |E|=1768149 |SCC|=12248/KL-alga

58
59
60
61
62
58.5
59.5
60.5
61.5
|V|=81306 |E|=1768149 |SCC|=12248/KL-alga time densities
mean
1
2
2
3
3
4
4
0.5 iters
50
100
150
200
250
0 s
regression
|V|=81306 |E|=1768149 |SCC|=12248/KL-alga times
lower bound estimate upper bound
OLS regression 49.2 s 57.5 s 61.4 s
R² goodness-of-fit 0.995 0.997 1.000
Mean execution time 58.3 s 60.7 s 61.6 s
Standard deviation 102 ms 1.64 s 2.01 s

Outlying measurements have moderate (18.8%) effect on estimated standard deviation.

understanding this report

In this report, each function benchmarked by criterion is assigned a section of its own. The charts in each section are active; if you hover your mouse over data points and annotations, you will see more details.

Under the charts is a small table. The first two rows are the results of a linear regression run on the measurements displayed in the right-hand chart.

We use a statistical technique called the bootstrap to provide confidence intervals on our estimates. The bootstrap-derived upper and lower bounds on estimates let you see how accurate we believe those estimates to be. (Hover the mouse over the table headers to see the confidence levels.)

A noisy benchmarking environment can cause some or many measurements to fall far from the mean. These outlying measurements can have a significant inflationary effect on the estimate of the standard deviation. We calculate and display an estimate of the extent to which the standard deviation has been inflated by outliers.