[start automated performance testsuite report]
Results for [d470d7b9e5196b112287e707dfd35b717f0aa324](https://github.com/dealii/dealii/commit/d470d7b9e5196b112287e707dfd35b717f0aa324)
===============
- permalink: https://dealii.org/performance_tests//reports/render.html?#!d470d7b9e5196b112287e707dfd35b717f0aa324.md
- report date: 2026-09-23 14:30:00+00:00
- revision: d470d7b9e5196b112287e707dfd35b717f0aa324 [github](https://github.com/dealii/dealii/commit/d470d7b9e5196b112287e707dfd35b717f0aa324)
- timestamp: 2026-09-23 15:34:48+02:00
- status: improvement
gcc-10/timing-step-3
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-step-3.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-step-3.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| make_grid | 0.621 ± 0.00204 (3.569) | 0.612 ± 0.00112 (0.054) -1.5σ | 0.617 ± 0.00147 (0.018) +1.0σ | 0.619 ± 0.00315 (0.012) +1.2σ | o.f. | OK |
| setup_system | 0.500 ± 0.00036 (2.458) | 0.504 ± 0.00068 (0.387) +0.8σ | 0.503 ± 0.00171 (0.524) -0.2σ | 0.507 ± 0.00452 (0.495) +0.5σ | OK | OK |
| solve | 19.255 ± 0.01951 (135.813) | 19.920 ± 0.02443 (11.535) +21.0σ | 19.833 ± 0.05063 (17.612) -1.5σ | 20.156 ± 0.16140 (14.451) +1.4σ | u.f. | OK |
| assemble_system | 0.558 ± 0.00034 (0.321) | 0.554 ± 0.00090 (0.411) -0.8σ | 0.553 ± 0.00163 (0.374) -0.3σ | 0.554 ± 0.00239 (0.139) -0.0σ | o.f. | OK |
| vmult | 5.925 ± 0.00337 (8.592) | 6.001 ± 0.00879 (8.231) +7.1σ | 6.003 ± 0.01813 (7.462) +0.1σ | 6.029 ± 0.02836 (3.765) +0.9σ | u.f. | OK |
| output_results | 0.657 ± 0.00100 (8.077) | 0.704 ± 0.00142 (1.225) +8.9σ | 0.700 ± 0.00276 (0.830) -0.8σ | 0.683 ± 0.00610 (0.520) -2.6σ | OK | OK |
clang-16/timing-step-3
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-step-3.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-step-3.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| make_grid | 0.616 ± 0.00172 (4.039) | 0.614 ± 0.00099 (0.083) -0.3σ | 0.619 ± 0.00151 (0.038) +0.8σ | 0.618 ± 0.00297 (0.026) +0.6σ | o.f. | OK |
| setup_system | 0.507 ± 0.00057 (4.914) | 0.547 ± 0.00082 (0.603) +7.9σ | 0.541 ± 0.00078 (0.097) -1.1σ | 0.538 ± 0.00147 (0.072) -1.6σ | o.f. | OK |
| solve | 19.157 ± 0.02622 (252.466) | 19.990 ± 0.03948 (40.658) +17.5σ | 20.260 ± 0.09463 (62.963) +2.6σ | 20.356 ± 0.22570 (49.142) +1.6σ | u.f. | OK |
| assemble_system | 0.556 ± 0.00030 (2.248) | 0.567 ± 0.00072 (2.239) +2.1σ | 0.565 ± 0.00092 (0.691) -0.5σ | 0.569 ± 0.00219 (0.378) +0.4σ | OK | OK |
| vmult | 5.852 ± 0.00398 (15.990) | 5.919 ± 0.01283 (21.055) +4.7σ | 5.968 ± 0.01955 (8.367) +2.0σ | 5.961 ± 0.04917 (15.179) +0.8σ | u.f. | OK |
| output_results | 0.702 ± 0.00083 (16.820) | 0.760 ± 0.00118 (1.450) +11.2σ | 0.753 ± 0.00118 (0.271) -1.5σ | 0.752 ± 0.00324 (0.313) -1.4σ | o.f. | OK |
gcc-10/timing-step_22
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-step_22.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-step_22.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| solve | 12.288 ± 0.00456 (168.479) | 12.783 ± 0.00850 (3.007) +45.5σ | 12.763 ± 0.01343 (0.915) -1.2σ | 12.792 ± 0.02916 (0.937) +0.3σ | OK | OK |
| output_results | 0.135 ± 0.00043 (119.937) | 0.119 ± 0.00026 (0.892) -3.2σ | 0.116 ± 0.00036 (0.335) -0.6σ | 0.115 ± 0.00096 (0.452) -0.8σ | o.f. | OK |
| refinement | 0.216 ± 0.00059 (240.255) | 0.207 ± 0.00032 (11.107) -1.9σ | 0.206 ± 0.00032 (1.755) -0.1σ | 0.206 ± 0.00026 (0.197) -0.2σ | OK | OK |
| assemble_system | 14.390 ± 0.00216 (1.033) | 14.739 ± 0.00258 (0.027) +57.8σ | 14.730 ± 0.00472 (0.017) -1.2σ | 14.711 ± 0.01251 (0.023) -2.0σ | o.f. | OK |
| setup_system | 1.213 ± 0.00173 (154.604) | 1.284 ± 0.00130 (4.255) +13.0σ | 1.275 ± 0.00052 (0.148) -1.7σ | 1.277 ± 0.00205 (0.379) -1.3σ | o.f. | OK |
clang-16/timing-step_22
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-step_22.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-step_22.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| solve | 9.682 ± 0.00841 (134.892) | 9.333 ± 0.01569 (25.696) -18.9σ | 9.347 ± 0.04319 (37.880) +0.3σ | 9.334 ± 0.11710 (46.554) +0.0σ | u.f. | OK |
| output_results | 0.121 ± 0.00024 (40.480) | 0.124 ± 0.00034 (2.712) +0.5σ | 0.122 ± 0.00031 (0.462) -0.4σ | 0.122 ± 0.00090 (0.853) -0.5σ | OK | OK |
| refinement | 0.223 ± 0.00079 (146.591) | 0.215 ± 0.00052 (3.163) -1.5σ | 0.216 ± 0.00077 (1.363) +0.3σ | 0.212 ± 0.00149 (1.001) -0.6σ | OK | OK |
| assemble_system | 14.653 ± 0.00604 (72.618) | 15.245 ± 0.00239 (0.666) +72.3σ | 15.239 ± 0.00421 (0.516) -0.9σ | 15.236 ± 0.00676 (0.387) -1.0σ | OK | OK |
| setup_system | 1.244 ± 0.00197 (24.294) | 1.399 ± 0.00139 (0.491) +27.9σ | 1.397 ± 0.00272 (0.370) -0.3σ | 1.397 ± 0.00703 (0.509) -0.2σ | o.f. | OK |
gcc-10/timing-step_37
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-step_37.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-step_37.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| matvec_double | 1.172 ± 0.00062 (30.754) | 1.142 ± 0.00105 (5.613) -5.7σ | 1.155 ± 0.00074 (0.557) +2.5σ | 1.154 ± 0.00093 (0.115) +2.2σ | OK | OK |
| grid | 0.477 ± 0.00021 (0.039) | 0.479 ± 0.00052 (0.019) +0.4σ | 0.478 ± 0.00105 (0.017) -0.3σ | 0.484 ± 0.00187 (0.009) +0.9σ | o.f. | OK |
| dofs | 0.721 ± 0.00043 (1.385) | 0.718 ± 0.00058 (0.127) -0.5σ | 0.723 ± 0.00083 (0.046) +1.0σ | 0.724 ± 0.00158 (0.035) +1.1σ | o.f. | OK |
| matrix_free | 0.510 ± 0.00031 (4.550) | 0.494 ± 0.00032 (0.301) -3.1σ | 0.496 ± 0.00061 (0.203) +0.4σ | 0.497 ± 0.00225 (0.571) +0.5σ | o.f. | OK |
| matvec_float | 0.753 ± 0.00019 (3.327) | 0.728 ± 0.00134 (1.234) -4.9σ | 0.710 ± 0.00170 (0.299) -3.3σ | 0.711 ± 0.00104 (0.024) -3.1σ | o.f. | IMP |
| smoother | 0.336 ± 0.00005 (0.703) | 0.336 ± 0.00016 (0.781) +0.0σ | 0.337 ± 0.00022 (0.265) +0.1σ | 0.337 ± 0.00051 (0.306) +0.2σ | o.f. | OK |
| transfer | 0.344 ± 0.00017 (3.117) | 0.341 ± 0.00033 (1.297) -0.6σ | 0.341 ± 0.00062 (1.204) -0.1σ | 0.345 ± 0.00119 (0.915) +0.7σ | OK | OK |
| solve | 2.510 ± 0.00060 (1.930) | 2.495 ± 0.00459 (1.970) -2.2σ | 2.453 ± 0.00249 (0.150) -5.7σ | 2.457 ± 0.00331 (0.051) -4.9σ | o.f. | IMP |
clang-16/timing-step_37
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-step_37.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-step_37.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| matvec_double | 1.654 ± 0.00268 (505.635) | 1.228 ± 0.00095 (0.281) -74.1σ | 1.237 ± 0.00140 (0.097) +1.8σ | 1.235 ± 0.00367 (0.110) +1.1σ | o.f. | OK |
| grid | 0.523 ± 0.00075 (0.069) | 0.545 ± 0.00195 (0.044) +4.0σ | 0.548 ± 0.00475 (0.055) +0.4σ | 0.563 ± 0.00878 (0.032) +1.8σ | o.f. | OK |
| dofs | 0.720 ± 0.00076 (0.390) | 0.718 ± 0.00197 (0.187) -0.4σ | 0.716 ± 0.00427 (0.198) -0.3σ | 0.726 ± 0.01271 (0.178) +0.6σ | o.f. | OK |
| matrix_free | 0.491 ± 0.00041 (0.678) | 0.480 ± 0.00106 (0.138) -2.2σ | 0.484 ± 0.00220 (0.090) +0.6σ | 0.480 ± 0.00403 (0.091) -0.0σ | o.f. | OK |
| matvec_float | 1.214 ± 0.00173 (231.188) | 0.787 ± 0.00073 (0.144) -80.0σ | 0.791 ± 0.00135 (0.102) +0.9σ | 0.785 ± 0.00162 (0.030) -0.2σ | o.f. | OK |
| smoother | 0.372 ± 0.00017 (1.867) | 0.367 ± 0.00048 (0.863) -0.9σ | 0.371 ± 0.00078 (0.345) +0.8σ | 0.374 ± 0.00057 (0.024) +1.3σ | o.f. | OK |
| transfer | 0.324 ± 0.00016 (0.583) | 0.323 ± 0.00033 (0.163) -0.2σ | 0.321 ± 0.00067 (0.127) -0.3σ | 0.323 ± 0.00102 (0.050) +0.1σ | o.f. | OK |
| solve | 3.366 ± 0.00542 (81.969) | 2.599 ± 0.00216 (0.058) -99.8σ | 2.599 ± 0.00419 (0.045) -0.1σ | 2.583 ± 0.00449 (0.011) -2.2σ | o.f. | OK |
gcc-10/timing-step_68
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-step_68.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-step_68.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| load_balance | 0.883 ± 0.00055 (20.300) | 0.882 ± 0.00058 (0.641) -0.2σ | 0.881 ± 0.00124 (0.613) -0.3σ | 0.878 ± 0.00062 (0.031) -0.7σ | OK | OK |
| sort | 0.886 ± 0.00031 (6.390) | 0.910 ± 0.00048 (0.440) +4.9σ | 0.908 ± 0.00069 (0.150) -0.4σ | 0.910 ± 0.00121 (0.087) -0.0σ | o.f. | OK |
| output | 0.086 ± 0.00005 (9.822) | 0.084 ± 0.00005 (1.881) -0.3σ | 0.084 ± 0.00011 (1.746) -0.0σ | 0.084 ± 0.00016 (0.439) -0.0σ | OK | OK |
| advect | 0.472 ± 0.00029 (19.140) | 0.477 ± 0.00044 (2.024) +0.9σ | 0.473 ± 0.00051 (0.619) -0.7σ | 0.473 ± 0.00109 (0.512) -0.8σ | OK | OK |
| generate_particles | 0.673 ± 0.00037 (0.147) | 0.675 ± 0.00075 (0.041) +0.3σ | 0.675 ± 0.00115 (0.020) +0.0σ | 0.674 ± 0.00270 (0.026) -0.1σ | o.f. | OK |
clang-16/timing-step_68
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-step_68.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-step_68.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| load_balance | 0.928 ± 0.00041 (0.935) | 0.934 ± 0.00106 (0.211) +1.1σ | 0.931 ± 0.00159 (0.080) -0.5σ | 0.930 ± 0.00333 (0.093) -0.6σ | o.f. | OK |
| sort | 0.951 ± 0.00043 (1.228) | 0.988 ± 0.00131 (0.256) +7.0σ | 0.992 ± 0.00235 (0.143) +0.7σ | 0.997 ± 0.00418 (0.082) +1.5σ | o.f. | OK |
| output | 0.056 ± 0.00003 (0.955) | 0.058 ± 0.00005 (0.388) +0.2σ | 0.058 ± 0.00009 (0.173) +0.1σ | 0.058 ± 0.00017 (0.110) +0.1σ | o.f. | OK |
| advect | 0.529 ± 0.00018 (0.810) | 0.538 ± 0.00073 (0.337) +1.7σ | 0.535 ± 0.00099 (0.121) -0.5σ | 0.534 ± 0.00120 (0.062) -0.6σ | o.f. | OK |
| generate_particles | 0.764 ± 0.00103 (0.090) | 0.769 ± 0.00327 (0.081) +0.8σ | 0.753 ± 0.00774 (0.137) -1.6σ | 0.788 ± 0.00799 (0.014) +1.9σ | o.f. | OK |
gcc-10/timing-mg_glob_coarsen
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-mg_glob_coarsen.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-mg_glob_coarsen.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| matvec_float | 0.760 ± 0.00046 (101.151) | 0.742 ± 0.00033 (0.174) -3.6σ | 0.746 ± 0.00039 (0.038) +0.8σ | 0.747 ± 0.00063 (0.018) +0.9σ | o.f. | OK |
| solve | 1.903 ± 0.00049 (18.731) | 1.952 ± 0.00365 (2.749) +7.8σ | 1.932 ± 0.00143 (0.076) -3.1σ | 1.930 ± 0.00316 (0.178) -3.1σ | o.f. | IMP |
| setup_transfer | 0.487 ± 0.00089 (71.853) | 0.502 ± 0.00024 (0.119) +2.9σ | 0.502 ± 0.00056 (0.115) +0.0σ | 0.503 ± 0.00149 (0.228) +0.3σ | o.f. | OK |
| setup_smoother | 1.446 ± 0.00037 (3.146) | 1.464 ± 0.00062 (0.157) +3.7σ | 1.462 ± 0.00099 (0.138) -0.4σ | 1.469 ± 0.00107 (0.016) +0.9σ | o.f. | OK |
| setup_dofs | 0.827 ± 0.00027 (1.001) | 0.831 ± 0.00059 (0.197) +0.8σ | 0.833 ± 0.00117 (0.139) +0.4σ | 0.835 ± 0.00298 (0.149) +0.5σ | o.f. | OK |
| setup_matrix_free | 1.000 ± 0.00083 (1.154) | 1.007 ± 0.00057 (0.053) +1.5σ | 1.009 ± 0.00111 (0.038) +0.4σ | 1.009 ± 0.00120 (0.011) +0.4σ | o.f. | OK |
| matvec_double | 1.128 ± 0.00017 (2.493) | 1.138 ± 0.00033 (0.040) +2.0σ | 1.139 ± 0.00069 (0.030) +0.2σ | 1.137 ± 0.00132 (0.031) -0.2σ | o.f. | OK |
| setup_coarse_grids | 0.742 ± 0.00065 (51.356) | 0.725 ± 0.00161 (21.630) -3.2σ | 0.721 ± 0.00285 (13.532) -0.6σ | 0.766 ± 0.00196 (0.233) +7.2σ | u.f. | dev |
| embed_dg_and_error | 0.643 ± 0.00051 (32.253) | 0.647 ± 0.00140 (7.065) +0.7σ | 0.642 ± 0.00091 (1.045) -0.9σ | 0.646 ± 0.00191 (0.706) -0.3σ | OK | OK |
| compute_rhs | 0.956 ± 0.00042 (1.555) | 0.985 ± 0.00110 (0.512) +5.6σ | 0.980 ± 0.00260 (0.661) -0.9σ | 0.995 ± 0.00538 (0.189) +1.5σ | OK | OK |
| setup_grid | 0.430 ± 0.00021 (0.082) | 0.428 ± 0.00063 (0.084) -0.5σ | 0.426 ± 0.00092 (0.046) -0.4σ | 0.430 ± 0.00198 (0.033) +0.3σ | o.f. | OK |
clang-16/timing-mg_glob_coarsen
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-mg_glob_coarsen.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-mg_glob_coarsen.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| matvec_float | 1.149 ± 0.00197 (1288.980) | 0.777 ± 0.00050 (0.395) -68.8σ | 0.781 ± 0.00136 (0.471) +0.7σ | 0.788 ± 0.00101 (0.022) +2.2σ | OK | OK |
| solve | 2.556 ± 0.00301 (157.691) | 1.991 ± 0.00168 (0.160) -93.0σ | 1.992 ± 0.00101 (0.013) +0.1σ | 1.992 ± 0.00280 (0.025) +0.1σ | o.f. | OK |
| setup_transfer | 0.533 ± 0.00141 (83.244) | 0.538 ± 0.00075 (0.898) +1.0σ | 0.537 ± 0.00149 (0.646) -0.1σ | 0.536 ± 0.00392 (0.964) -0.3σ | OK | OK |
| setup_smoother | 1.531 ± 0.00094 (18.165) | 1.408 ± 0.00062 (0.161) -24.1σ | 1.407 ± 0.00105 (0.140) -0.2σ | 1.415 ± 0.00253 (0.047) +1.3σ | o.f. | OK |
| setup_dofs | 0.847 ± 0.00045 (0.232) | 0.836 ± 0.00104 (0.082) -2.1σ | 0.831 ± 0.00203 (0.081) -0.9σ | 0.833 ± 0.00403 (0.083) -0.5σ | o.f. | OK |
| setup_matrix_free | 0.994 ± 0.00055 (0.835) | 0.987 ± 0.00084 (0.269) -1.3σ | 0.987 ± 0.00164 (0.248) -0.1σ | 0.988 ± 0.00602 (0.585) +0.1σ | o.f. | OK |
| matvec_double | 1.488 ± 0.00210 (459.286) | 1.170 ± 0.00066 (0.443) -58.1σ | 1.170 ± 0.00153 (0.542) -0.0σ | 1.174 ± 0.00363 (0.471) +0.6σ | OK | OK |
| setup_coarse_grids | 0.654 ± 0.00061 (0.746) | 0.675 ± 0.00199 (0.079) +3.8σ | 0.678 ± 0.00375 (0.059) +0.4σ | 0.675 ± 0.00499 (0.033) -0.1σ | o.f. | OK |
| embed_dg_and_error | 0.701 ± 0.00037 (83.222) | 0.710 ± 0.00107 (6.076) +1.7σ | 0.712 ± 0.00246 (7.941) +0.4σ | 0.710 ± 0.00698 (4.949) +0.1σ | u.f. | OK |
| compute_rhs | 0.996 ± 0.00077 (43.210) | 0.991 ± 0.00461 (16.914) -0.7σ | 1.028 ± 0.01229 (22.820) +2.6σ | 0.972 ± 0.00628 (1.851) -2.1σ | u.f. | OK |
| setup_grid | 0.456 ± 0.00051 (0.061) | 0.473 ± 0.00114 (0.032) +3.2σ | 0.475 ± 0.00196 (0.021) +0.3σ | 0.474 ± 0.00363 (0.014) +0.2σ | o.f. | OK |
gcc-10/timing-navier_stokes
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-navier_stokes.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-navier_stokes.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| write_output | 0.263 ± 0.00009 (0.733) | 0.264 ± 0.00024 (0.704) +0.2σ | 0.263 ± 0.00032 (0.307) -0.1σ | 0.264 ± 0.00085 (0.364) +0.0σ | o.f. | OK |
| rk_step_fb_update | 0.338 ± 0.00005 (2.822) | 0.340 ± 0.00014 (0.371) +0.5σ | 0.341 ± 0.00029 (0.341) +0.0σ | 0.341 ± 0.00051 (0.241) +0.0σ | o.f. | OK |
| setup_grid | 0.034 ± 0.00003 (0.017) | 0.036 ± 0.00016 (0.022) +0.4σ | 0.035 ± 0.00033 (0.021) -0.1σ | 0.035 ± 0.00056 (0.014) -0.1σ | o.f. | OK |
| rk_step_cellbased | 1.462 ± 0.00024 (2.497) | 1.475 ± 0.00068 (0.966) +2.6σ | 1.480 ± 0.00130 (0.776) +0.8σ | 1.477 ± 0.00311 (1.155) +0.2σ | OK | OK |
| rk_step_facebased | 1.453 ± 0.00039 (22.099) | 1.422 ± 0.00034 (0.239) -6.0σ | 1.419 ± 0.00050 (0.116) -0.6σ | 1.419 ± 0.00060 (0.031) -0.6σ | o.f. | OK |
| analyze_solution | 0.098 ± 0.00006 (11.111) | 0.100 ± 0.00022 (3.920) +0.4σ | 0.100 ± 0.00015 (0.402) -0.1σ | 0.100 ± 0.00044 (0.873) -0.1σ | OK | OK |
| rk_step_fb_loop | 1.113 ± 0.00043 (42.874) | 1.081 ± 0.00029 (0.368) -6.4σ | 1.078 ± 0.00028 (0.086) -0.6σ | 1.078 ± 0.00035 (0.022) -0.6σ | o.f. | OK |
| setup_matrix_free | 0.699 ± 0.00058 (0.863) | 0.699 ± 0.00079 (0.139) -0.1σ | 0.700 ± 0.00102 (0.051) +0.3σ | 0.701 ± 0.00128 (0.019) +0.4σ | o.f. | OK |
| project_initial | 0.036 ± 0.00003 (29.458) | 0.036 ± 0.00008 (39.124) -0.0σ | 0.035 ± 0.00008 (10.518) -0.0σ | 0.035 ± 0.00023 (3.313) -0.1σ | u.f. | OK |
| setup_dofs | 0.013 ± 0.00001 (0.019) | 0.013 ± 0.00002 (0.009) +0.0σ | 0.013 ± 0.00003 (0.007) -0.0σ | 0.013 ± 0.00006 (0.004) -0.0σ | o.f. | OK |
clang-16/timing-navier_stokes
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-navier_stokes.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-navier_stokes.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| write_output | 0.280 ± 0.00012 (0.229) | 0.281 ± 0.00044 (0.168) +0.2σ | 0.283 ± 0.00092 (0.104) +0.3σ | 0.284 ± 0.00124 (0.031) +0.6σ | o.f. | OK |
| rk_step_fb_update | 0.338 ± 0.00005 (1.011) | 0.340 ± 0.00017 (0.402) +0.3σ | 0.339 ± 0.00041 (0.365) -0.0σ | 0.345 ± 0.00239 (0.139) +0.9σ | o.f. | OK |
| setup_grid | 0.033 ± 0.00002 (0.009) | 0.033 ± 0.00009 (0.011) +0.0σ | 0.033 ± 0.00025 (0.017) +0.0σ | 0.033 ± 0.00040 (0.009) +0.0σ | o.f. | OK |
| rk_step_cellbased | 1.291 ± 0.00029 (0.635) | 1.307 ± 0.00107 (0.381) +3.2σ | 1.307 ± 0.00260 (0.360) -0.1σ | 1.309 ± 0.00753 (0.367) +0.2σ | o.f. | OK |
| rk_step_facebased | 1.361 ± 0.00112 (29.230) | 1.443 ± 0.00059 (0.482) +15.9σ | 1.442 ± 0.00095 (0.398) -0.2σ | 1.451 ± 0.00590 (0.204) +1.0σ | o.f. | OK |
| analyze_solution | 0.091 ± 0.00003 (0.457) | 0.093 ± 0.00021 (0.420) +0.5σ | 0.093 ± 0.00033 (0.295) -0.1σ | 0.093 ± 0.00129 (0.498) +0.0σ | o.f. | OK |
| rk_step_fb_loop | 1.020 ± 0.00107 (50.757) | 1.102 ± 0.00048 (0.621) +16.0σ | 1.102 ± 0.00074 (0.508) -0.1σ | 1.105 ± 0.00378 (0.309) +0.4σ | OK | OK |
| setup_matrix_free | 0.751 ± 0.00092 (0.151) | 0.744 ± 0.00185 (0.046) -1.4σ | 0.743 ± 0.00652 (0.136) -0.2σ | 0.759 ± 0.00886 (0.036) +1.4σ | o.f. | OK |
| project_initial | 0.032 ± 0.00003 (16.293) | 0.032 ± 0.00005 (0.670) -0.0σ | 0.032 ± 0.00008 (1.027) -0.0σ | 0.036 ± 0.00066 (0.039) +0.7σ | OK | OK |
| setup_dofs | 0.016 ± 0.00003 (0.141) | 0.016 ± 0.00005 (0.042) -0.0σ | 0.016 ± 0.00013 (0.050) +0.0σ | 0.016 ± 0.00025 (0.038) +0.0σ | o.f. | OK |
gcc-10/timing-matrix_free_kokkos
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-matrix_free_kokkos.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-bullseye-gcc-10/timing-matrix_free_kokkos.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| mf_vmult | 0.654 ± 0.00038 (10.175) | 0.680 ± 0.00060 (0.701) +5.2σ | 0.676 ± 0.00048 (0.072) -0.7σ | 0.678 ± 0.00112 (0.084) -0.4σ | o.f. | OK |
| mf_setup | 0.315 ± 0.00110 (8.277) | 0.290 ± 0.00041 (0.112) -4.9σ | 0.291 ± 0.00074 (0.079) +0.2σ | 0.291 ± 0.00133 (0.048) +0.2σ | o.f. | OK |
| mf_kokkos_vmult | 15.900 ± 0.05662 (312.905) | 13.868 ± 0.18850 (1011.860) -10.3σ | 10.291 ± 0.02493 (1.753) -18.8σ | 10.387 ± 0.08377 (1.003) -16.9σ | OK | IMP |
| mf_kokkos_setup | 0.837 ± 0.00786 (382.481) | 0.642 ± 0.01013 (372.884) -14.2σ | 0.616 ± 0.00088 (1.393) -2.2σ | 0.617 ± 0.00103 (0.244) -2.2σ | OK | OK |
clang-16/timing-matrix_free_kokkos
--------------------------------
Long-term plots: [minimum over 1000](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-matrix_free_kokkos.png), and [minimum over lifetime](https://dealii.org/performance_tests/graphs//whistler-gentoo-clang-16/timing-matrix_free_kokkos.full_history.png)
| measurement | μ_1k ±σ (r𝛘²) | μ_100 ±σ (r𝛘²) Δ | μ_20 ±σ (r𝛘²) Δ | μ_4 ±σ (r𝛘²) Δ | Stability | Status |
| :- | :-: | :-: | :-: | :-: | :-: | :-: |
| mf_vmult | 0.839 ± 0.00189 (1.974) | 0.699 ± 0.00238 (0.206) -23.9σ | 0.696 ± 0.00534 (0.247) -0.5σ | 0.702 ± 0.01060 (0.161) +0.3σ | o.f. | OK |
| mf_setup | 0.347 ± 0.00154 (0.989) | 0.312 ± 0.00170 (0.089) -6.4σ | 0.324 ± 0.00260 (0.064) +2.1σ | 0.323 ± 0.00452 (0.040) +1.5σ | o.f. | OK |
| mf_kokkos_vmult | 17.903 ± 0.10340 (972.288) | 14.779 ± 0.07907 (74.925) -24.0σ | 12.979 ± 0.03864 (1.683) -20.4σ | 12.982 ± 0.04849 (0.336) -19.3σ | OK | IMP |
| mf_kokkos_setup | 1.356 ± 0.00472 (576.089) | 1.225 ± 0.02334 (3519.240) -5.4σ | 0.614 ± 0.00134 (0.268) -25.6σ | 0.611 ± 0.00182 (0.173) -25.6σ | o.f. | IMP |
Notes
-----
- μ_1k,μ_100,μ_20,μ_4: weighted mean values of the last 1000 / 100 / 20 / 4 computed averages
- σ: estimate of the "asymptotic standard error" of the weighted mean value as computed by gnuplot. Note that, (a) gnuplot tends to compute an overly optimistic estimate, (b) the weighted mean value and asymptotic standard error do not factor in systematic effects present in performance tests. We nevertheless use this value as a baseline but with rather large thresholds for the triggers.
- r𝛘²: reduced chi-square value of the weighted mean value. A value much larger than 1 indicates "underfitting", a value much smaller than 1 indicates "overfitting". The status of the measurement is reported in the "stability" column based on the reduced chi-square value of the A20 average.
- Δ: The μ_20 and μ_4 weighted mean values are compared to μ_100, and the μ_100 mean value is compared to 1000.
- When normalizing the deviations Δ with σ, a noise floor of σ_sys = 5ms is added.
- Status: status triggers are set at a deviation between μ_20 and μ_100 of 3σ asymptotic standard error for a "consensus regression", or "improvement" and 4σ for a "minority regression". The "deviation" trigger compares μ_4 with μ_100 with a threshold of 3σ.
[end automated performance testsuite report]