overview

schur / original

lower boundestimateupper bound
OLS regression92.0 ms94.3 ms95.8 ms
R² goodness-of-fit0.9990.9991.00
Mean execution time92.8 ms94.3 ms96.4 ms
Standard deviation686 μs2.93 ms4.69 ms

Outlying measurements have a slight (9.88%) effect on estimated standard deviation.

schur / hasktorch-cpu

lower boundestimateupper bound
OLS regression51.0 ms87.9 ms139 ms
R² goodness-of-fit0.5770.6940.996
Mean execution time51.4 ms59.2 ms81.9 ms
Standard deviation5.99 ms23.0 ms38.8 ms

Outlying measurements have a severe (90.1%) effect on estimated standard deviation.

schur / hasktorch-cuda

lower boundestimateupper bound
OLS regression22.6 ms22.9 ms23.3 ms
R² goodness-of-fit0.9990.9991.00
Mean execution time23.6 ms24.5 ms26.8 ms
Standard deviation540 μs2.94 ms5.04 ms

Outlying measurements have a severe (53.4%) effect on estimated standard deviation.

woodbury / original

lower boundestimateupper bound
OLS regression42.3 ms43.0 ms43.9 ms
R² goodness-of-fit0.9990.9991.00
Mean execution time42.5 ms42.9 ms43.7 ms
Standard deviation496 μs1.07 ms1.48 ms

Outlying measurements have a slight (6.63%) effect on estimated standard deviation.

woodbury / hasktorch-cpu

lower boundestimateupper bound
OLS regression54.1 ms60.7 ms68.9 ms
R² goodness-of-fit0.8740.9570.996
Mean execution time60.8 ms65.8 ms71.1 ms
Standard deviation6.02 ms9.12 ms14.8 ms

Outlying measurements have a moderate (43.9%) effect on estimated standard deviation.

woodbury / hasktorch-cuda

lower boundestimateupper bound
OLS regression814 μs816 μs818 μs
R² goodness-of-fit1.001.001.00
Mean execution time816 μs817 μs818 μs
Standard deviation3.13 μs4.03 μs5.02 μs

Outlying measurements have a slight (1.33%) effect on estimated standard deviation.

direct-inversion / original

lower boundestimateupper bound
OLS regression82.3 ms96.9 ms116 ms
R² goodness-of-fit0.8590.9390.986
Mean execution time65.1 ms73.3 ms84.4 ms
Standard deviation12.8 ms16.0 ms19.6 ms

Outlying measurements have a severe (68.4%) effect on estimated standard deviation.

direct-inversion / hasktorch-cpu

lower boundestimateupper bound
OLS regression74.6 ms86.5 ms103 ms
R² goodness-of-fit0.8540.9380.991
Mean execution time78.3 ms87.3 ms94.6 ms
Standard deviation8.78 ms14.2 ms21.6 ms

Outlying measurements have a severe (57.9%) effect on estimated standard deviation.

direct-inversion / hasktorch-cuda

lower boundestimateupper bound
OLS regression23.7 ms24.3 ms25.0 ms
R² goodness-of-fit0.9970.9991.00
Mean execution time25.2 ms26.4 ms29.2 ms
Standard deviation1.07 ms3.85 ms5.80 ms

Outlying measurements have a severe (61.6%) effect on estimated standard deviation.

indirect-inversion / original

lower boundestimateupper bound
OLS regression55.7 ms64.9 ms77.9 ms
R² goodness-of-fit0.8960.9520.992
Mean execution time52.0 ms58.2 ms63.0 ms
Standard deviation5.89 ms9.94 ms16.1 ms

Outlying measurements have a severe (56.8%) effect on estimated standard deviation.

indirect-inversion / hasktorch-cpu

lower boundestimateupper bound
OLS regression34.6 ms57.4 ms73.9 ms
R² goodness-of-fit0.6230.8260.975
Mean execution time49.8 ms56.7 ms64.3 ms
Standard deviation10.1 ms13.4 ms19.5 ms

Outlying measurements have a severe (73.7%) effect on estimated standard deviation.

indirect-inversion / hasktorch-cuda

lower boundestimateupper bound
OLS regression972 μs975 μs977 μs
R² goodness-of-fit1.001.001.00
Mean execution time975 μs977 μs979 μs
Standard deviation5.26 μs6.77 μs9.55 μs

Outlying measurements have a slight (1.39%) effect on estimated standard deviation.

dense-inversion / original

lower boundestimateupper bound
OLS regression62.4 ms65.0 ms67.5 ms
R² goodness-of-fit0.9930.9971.00
Mean execution time63.3 ms64.2 ms65.5 ms
Standard deviation1.39 ms1.94 ms2.45 ms

Outlying measurements have a slight (8.26%) effect on estimated standard deviation.

dense-inversion / hasktorch-cpu

lower boundestimateupper bound
OLS regression60.1 ms63.1 ms64.7 ms
R² goodness-of-fit0.9840.9951.00
Mean execution time59.9 ms61.6 ms62.7 ms
Standard deviation973 μs2.54 ms3.70 ms

Outlying measurements have a slight (7.80%) effect on estimated standard deviation.

dense-inversion / hasktorch-cuda

lower boundestimateupper bound
OLS regression23.5 ms23.9 ms24.4 ms
R² goodness-of-fit0.9980.9991.00
Mean execution time24.4 ms25.5 ms27.7 ms
Standard deviation86.4 μs3.30 ms5.16 ms

Outlying measurements have a severe (56.3%) effect on estimated standard deviation.