Closed mfdeakin-sandia closed 6 years ago
Performance comparison with a single rank on a node of white, with ne=4
, qsize=35
, ndays=2
HommeTime_stats.master.1
prim_main_loop 1 1 1.000000e+00 4.949342e+00 4.949 ( 0 0) 4.949 ( 0 0)
tl-ae U3-5stage_timestep 1 1 2.880000e+02 7.224100e-01 0.722 ( 0 0) 0.722 ( 0 0)
tl-ae advance_hypervis_dp 1 1 2.880000e+02 6.836495e-01 0.684 ( 0 0) 0.684 ( 0 0)
tl-s prim_advec_tracers_remap 1 1 2.880000e+02 2.901469e+00 2.901 ( 0 0) 2.901 ( 0 0)
tl-at prim_advec_tracers_remap_RK2 1 1 2.880000e+02 2.901349e+00 2.901 ( 0 0) 2.901 ( 0 0)
tl-sc vertical_remap 1 1 9.600000e+01 5.705938e-01 0.571 ( 0 0) 0.571 ( 0 0)
Remap Thickness Functor 1 1 9.600000e+01 9.619474e-03 0.010 ( 0 0) 0.010 ( 0 0)
Remap Scale States Functor 1 1 9.600000e+01 4.398346e-03 0.004 ( 0 0) 0.004 ( 0 0)
Remap Compute Grids Functor 1 1 9.600000e+01 1.410937e-02 0.014 ( 0 0) 0.014 ( 0 0)
Remap Compute Remap Functor 1 1 9.600000e+01 5.330272e-01 0.533 ( 0 0) 0.533 ( 0 0)
Remap Rescale States Functor 1 1 9.600000e+01 4.520655e-03 0.005 ( 0 0) 0.005 ( 0 0)
HommeTime_stats.master.2
prim_main_loop 1 1 1.000000e+00 4.957392e+00 4.957 ( 0 0) 4.957 ( 0 0)
tl-ae U3-5stage_timestep 1 1 2.880000e+02 7.213140e-01 0.721 ( 0 0) 0.721 ( 0 0)
tl-ae advance_hypervis_dp 1 1 2.880000e+02 6.830001e-01 0.683 ( 0 0) 0.683 ( 0 0)
tl-s prim_advec_tracers_remap 1 1 2.880000e+02 2.897520e+00 2.898 ( 0 0) 2.898 ( 0 0)
tl-at prim_advec_tracers_remap_RK2 1 1 2.880000e+02 2.897403e+00 2.897 ( 0 0) 2.897 ( 0 0)
tl-sc vertical_remap 1 1 9.600000e+01 5.708969e-01 0.571 ( 0 0) 0.571 ( 0 0)
Remap Thickness Functor 1 1 9.600000e+01 9.878635e-03 0.010 ( 0 0) 0.010 ( 0 0)
Remap Scale States Functor 1 1 9.600000e+01 4.478455e-03 0.004 ( 0 0) 0.004 ( 0 0)
Remap Compute Grids Functor 1 1 9.600000e+01 1.411796e-02 0.014 ( 0 0) 0.014 ( 0 0)
Remap Compute Remap Functor 1 1 9.600000e+01 5.328875e-01 0.533 ( 0 0) 0.533 ( 0 0)
Remap Rescale States Functor 1 1 9.600000e+01 4.540205e-03 0.005 ( 0 0) 0.005 ( 0 0)
HommeTime_stats.master.3
prim_main_loop 1 1 1.000000e+00 4.945650e+00 4.946 ( 0 0) 4.946 ( 0 0)
tl-ae U3-5stage_timestep 1 1 2.880000e+02 7.183356e-01 0.718 ( 0 0) 0.718 ( 0 0)
tl-ae advance_hypervis_dp 1 1 2.880000e+02 6.815047e-01 0.682 ( 0 0) 0.682 ( 0 0)
tl-s prim_advec_tracers_remap 1 1 2.880000e+02 2.892132e+00 2.892 ( 0 0) 2.892 ( 0 0)
tl-at prim_advec_tracers_remap_RK2 1 1 2.880000e+02 2.892018e+00 2.892 ( 0 0) 2.892 ( 0 0)
tl-sc vertical_remap 1 1 9.600000e+01 5.696325e-01 0.570 ( 0 0) 0.570 ( 0 0)
Remap Thickness Functor 1 1 9.600000e+01 9.657621e-03 0.010 ( 0 0) 0.010 ( 0 0)
Remap Scale States Functor 1 1 9.600000e+01 4.410028e-03 0.004 ( 0 0) 0.004 ( 0 0)
Remap Compute Grids Functor 1 1 9.600000e+01 1.410007e-02 0.014 ( 0 0) 0.014 ( 0 0)
Remap Compute Remap Functor 1 1 9.600000e+01 5.319192e-01 0.532 ( 0 0) 0.532 ( 0 0)
Remap Rescale States Functor 1 1 9.600000e+01 4.602909e-03 0.005 ( 0 0) 0.005 ( 0 0)
HommeTime_stats.master.4
prim_main_loop 1 1 1.000000e+00 4.956190e+00 4.956 ( 0 0) 4.956 ( 0 0)
tl-ae U3-5stage_timestep 1 1 2.880000e+02 7.198551e-01 0.720 ( 0 0) 0.720 ( 0 0)
tl-ae advance_hypervis_dp 1 1 2.880000e+02 6.862381e-01 0.686 ( 0 0) 0.686 ( 0 0)
tl-s prim_advec_tracers_remap 1 1 2.880000e+02 2.896113e+00 2.896 ( 0 0) 2.896 ( 0 0)
tl-at prim_advec_tracers_remap_RK2 1 1 2.880000e+02 2.896000e+00 2.896 ( 0 0) 2.896 ( 0 0)
tl-sc vertical_remap 1 1 9.600000e+01 5.697227e-01 0.570 ( 0 0) 0.570 ( 0 0)
Remap Thickness Functor 1 1 9.600000e+01 9.668589e-03 0.010 ( 0 0) 0.010 ( 0 0)
Remap Scale States Functor 1 1 9.600000e+01 4.442692e-03 0.004 ( 0 0) 0.004 ( 0 0)
Remap Compute Grids Functor 1 1 9.600000e+01 1.413298e-02 0.014 ( 0 0) 0.014 ( 0 0)
Remap Compute Remap Functor 1 1 9.600000e+01 5.320165e-01 0.532 ( 0 0) 0.532 ( 0 0)
Remap Rescale States Functor 1 1 9.600000e+01 4.548311e-03 0.005 ( 0 0) 0.005 ( 0 0)
HommeTime_stats.rm_ppm_single.1
prim_main_loop 1 1 1.000000e+00 4.737081e+00 4.737 ( 0 0) 4.737 ( 0 0)
tl-ae U3-5stage_timestep 1 1 2.880000e+02 7.194693e-01 0.719 ( 0 0) 0.719 ( 0 0)
tl-ae advance_hypervis_dp 1 1 2.880000e+02 6.832917e-01 0.683 ( 0 0) 0.683 ( 0 0)
tl-s prim_advec_tracers_remap 1 1 2.880000e+02 2.940022e+00 2.940 ( 0 0) 2.940 ( 0 0)
tl-at prim_advec_tracers_remap_RK2 1 1 2.880000e+02 2.939922e+00 2.940 ( 0 0) 2.940 ( 0 0)
tl-sc vertical_remap 1 1 9.600000e+01 3.095670e-01 0.310 ( 0 0) 0.310 ( 0 0)
Remap Thickness Functor 1 1 9.600000e+01 9.611845e-03 0.010 ( 0 0) 0.010 ( 0 0)
Remap Scale States Functor 1 1 9.600000e+01 4.430056e-03 0.004 ( 0 0) 0.004 ( 0 0)
Remap Compute Grids Functor 1 1 9.600000e+01 1.406622e-02 0.014 ( 0 0) 0.014 ( 0 0)
Remap Compute Remap Functor 1 1 9.600000e+01 2.718105e-01 0.272 ( 0 0) 0.272 ( 0 0)
Remap Rescale States Functor 1 1 9.600000e+01 4.611969e-03 0.005 ( 0 0) 0.005 ( 0 0)
HommeTime_stats.rm_ppm_single.2
prim_main_loop 1 1 1.000000e+00 4.686712e+00 4.687 ( 0 0) 4.687 ( 0 0)
tl-ae U3-5stage_timestep 1 1 2.880000e+02 7.189929e-01 0.719 ( 0 0) 0.719 ( 0 0)
tl-ae advance_hypervis_dp 1 1 2.880000e+02 6.813204e-01 0.681 ( 0 0) 0.681 ( 0 0)
tl-s prim_advec_tracers_remap 1 1 2.880000e+02 2.893331e+00 2.893 ( 0 0) 2.893 ( 0 0)
tl-at prim_advec_tracers_remap_RK2 1 1 2.880000e+02 2.893208e+00 2.893 ( 0 0) 2.893 ( 0 0)
tl-sc vertical_remap 1 1 9.600000e+01 3.088970e-01 0.309 ( 0 0) 0.309 ( 0 0)
Remap Thickness Functor 1 1 9.600000e+01 9.595871e-03 0.010 ( 0 0) 0.010 ( 0 0)
Remap Scale States Functor 1 1 9.600000e+01 4.397154e-03 0.004 ( 0 0) 0.004 ( 0 0)
Remap Compute Grids Functor 1 1 9.600000e+01 1.407027e-02 0.014 ( 0 0) 0.014 ( 0 0)
Remap Compute Remap Functor 1 1 9.600000e+01 2.713315e-01 0.271 ( 0 0) 0.271 ( 0 0)
Remap Rescale States Functor 1 1 9.600000e+01 4.594088e-03 0.005 ( 0 0) 0.005 ( 0 0)
HommeTime_stats.rm_ppm_single.3
prim_main_loop 1 1 1.000000e+00 4.706897e+00 4.707 ( 0 0) 4.707 ( 0 0)
tl-ae U3-5stage_timestep 1 1 2.880000e+02 7.231956e-01 0.723 ( 0 0) 0.723 ( 0 0)
tl-ae advance_hypervis_dp 1 1 2.880000e+02 6.896915e-01 0.690 ( 0 0) 0.690 ( 0 0)
tl-s prim_advec_tracers_remap 1 1 2.880000e+02 2.899728e+00 2.900 ( 0 0) 2.900 ( 0 0)
tl-at prim_advec_tracers_remap_RK2 1 1 2.880000e+02 2.899582e+00 2.900 ( 0 0) 2.900 ( 0 0)
tl-sc vertical_remap 1 1 9.600000e+01 3.095093e-01 0.310 ( 0 0) 0.310 ( 0 0)
Remap Thickness Functor 1 1 9.600000e+01 9.728432e-03 0.010 ( 0 0) 0.010 ( 0 0)
Remap Scale States Functor 1 1 9.600000e+01 4.549026e-03 0.005 ( 0 0) 0.005 ( 0 0)
Remap Compute Grids Functor 1 1 9.600000e+01 1.419091e-02 0.014 ( 0 0) 0.014 ( 0 0)
Remap Compute Remap Functor 1 1 9.600000e+01 2.713857e-01 0.271 ( 0 0) 0.271 ( 0 0)
Remap Rescale States Functor 1 1 9.600000e+01 4.646063e-03 0.005 ( 0 0) 0.005 ( 0 0)
HommeTime_stats.rm_ppm_single.4
prim_main_loop 1 1 1.000000e+00 4.689117e+00 4.689 ( 0 0) 4.689 ( 0 0)
tl-ae U3-5stage_timestep 1 1 2.880000e+02 7.191291e-01 0.719 ( 0 0) 0.719 ( 0 0)
tl-ae advance_hypervis_dp 1 1 2.880000e+02 6.840129e-01 0.684 ( 0 0) 0.684 ( 0 0)
tl-s prim_advec_tracers_remap 1 1 2.880000e+02 2.892758e+00 2.893 ( 0 0) 2.893 ( 0 0)
tl-at prim_advec_tracers_remap_RK2 1 1 2.880000e+02 2.892622e+00 2.893 ( 0 0) 2.893 ( 0 0)
tl-sc vertical_remap 1 1 9.600000e+01 3.088999e-01 0.309 ( 0 0) 0.309 ( 0 0)
Remap Thickness Functor 1 1 9.600000e+01 9.649992e-03 0.010 ( 0 0) 0.010 ( 0 0)
Remap Scale States Functor 1 1 9.600000e+01 4.474640e-03 0.004 ( 0 0) 0.004 ( 0 0)
Remap Compute Grids Functor 1 1 9.600000e+01 1.408386e-02 0.014 ( 0 0) 0.014 ( 0 0)
Remap Compute Remap Functor 1 1 9.600000e+01 2.711520e-01 0.271 ( 0 0) 0.271 ( 0 0)
Remap Rescale States Functor 1 1 9.600000e+01 4.555941e-03 0.005 ( 0 0) 0.005 ( 0 0)
master and rm_ppm_single runs were interleaved
This passes nightly tests on ride and bowman, and dev tests on shepard. I will test on skybridge tomorrow.
This appears to have a slight (unexpected, so verifying) performance benefit (3% overall) on bowman with ne=8
, qsize=35
, ndays=4
:
HommeTime_stats.master.1
prim_main_loop 64 64 6.400000e+01 2.195759e+03 34.310 ( 8 0) 34.307 ( 28 0)
tl-ae U3-5stage_timestep 64 64 3.686400e+04 2.621676e+02 4.862 ( 30 0) 3.424 ( 8 0)
tl-ae advance_hypervis_dp 64 64 3.686400e+04 2.177693e+02 3.444 ( 58 0) 3.384 ( 48 0)
tl-s prim_advec_tracers_remap 64 64 3.686400e+04 1.469102e+03 23.638 ( 8 0) 22.145 ( 30 0)
tl-at prim_advec_tracers_remap_RK2 64 64 3.686400e+04 1.468886e+03 23.635 ( 8 0) 22.141 ( 30 0)
tl-sc vertical_remap 64 64 1.228800e+04 2.171702e+02 3.463 ( 44 0) 3.359 ( 56 0)
Remap Thickness Functor 64 64 1.228800e+04 1.489665e+00 0.024 ( 6 0) 0.022 ( 61 0)
Remap Scale States Functor 64 64 1.228800e+04 7.867690e-01 0.013 ( 39 0) 0.011 ( 2 0)
Remap Compute Grids Functor 64 64 1.228800e+04 8.527969e+00 0.137 ( 52 0) 0.129 ( 8 0)
Remap Compute Remap Functor 64 64 1.228800e+04 2.041988e+02 3.258 ( 44 0) 3.160 ( 56 0)
Remap Rescale States Functor 64 64 1.228800e+04 1.122507e+00 0.019 ( 7 0) 0.017 ( 29 0)
HommeTime_stats.master.2
prim_main_loop 64 64 6.400000e+01 2.201904e+03 34.407 ( 58 0) 34.403 ( 28 0)
tl-ae U3-5stage_timestep 64 64 3.686400e+04 2.656623e+02 4.923 ( 30 0) 3.424 ( 8 0)
tl-ae advance_hypervis_dp 64 64 3.686400e+04 2.187265e+02 3.460 ( 62 0) 3.395 ( 35 0)
tl-s prim_advec_tracers_remap 64 64 3.686400e+04 1.470934e+03 23.711 ( 8 0) 22.155 ( 30 0)
tl-at prim_advec_tracers_remap_RK2 64 64 3.686400e+04 1.470712e+03 23.707 ( 8 0) 22.151 ( 30 0)
tl-sc vertical_remap 64 64 1.228800e+04 2.170143e+02 3.460 ( 51 0) 3.355 ( 38 0)
Remap Thickness Functor 64 64 1.228800e+04 1.491414e+00 0.025 ( 54 0) 0.022 ( 8 0)
Remap Scale States Functor 64 64 1.228800e+04 7.885790e-01 0.014 ( 6 0) 0.011 ( 10 0)
Remap Compute Grids Functor 64 64 1.228800e+04 8.514999e+00 0.138 ( 52 0) 0.129 ( 8 0)
Remap Compute Remap Functor 64 64 1.228800e+04 2.040784e+02 3.254 ( 51 0) 3.156 ( 38 0)
Remap Rescale States Functor 64 64 1.228800e+04 1.125978e+00 0.019 ( 13 0) 0.017 ( 30 0)
HommeTime_stats.master.3
prim_main_loop 64 64 6.400000e+01 2.201295e+03 34.397 ( 58 0) 34.393 ( 27 0)
tl-ae U3-5stage_timestep 64 64 3.686400e+04 2.664574e+02 4.975 ( 30 0) 3.407 ( 8 0)
tl-ae advance_hypervis_dp 64 64 3.686400e+04 2.186488e+02 3.506 ( 58 0) 3.383 ( 48 0)
tl-s prim_advec_tracers_remap 64 64 3.686400e+04 1.469571e+03 23.748 ( 8 0) 22.089 ( 30 0)
tl-at prim_advec_tracers_remap_RK2 64 64 3.686400e+04 1.469350e+03 23.745 ( 8 0) 22.086 ( 30 0)
tl-sc vertical_remap 64 64 1.228800e+04 2.170606e+02 3.456 ( 44 0) 3.356 ( 14 0)
Remap Thickness Functor 64 64 1.228800e+04 1.488806e+00 0.024 ( 4 0) 0.022 ( 2 0)
Remap Scale States Functor 64 64 1.228800e+04 7.852150e-01 0.014 ( 43 0) 0.011 ( 8 0)
Remap Compute Grids Functor 64 64 1.228800e+04 8.519231e+00 0.138 ( 52 0) 0.128 ( 8 0)
Remap Compute Remap Functor 64 64 1.228800e+04 2.041068e+02 3.254 ( 44 0) 3.155 ( 14 0)
Remap Rescale States Functor 64 64 1.228800e+04 1.122532e+00 0.019 ( 7 0) 0.017 ( 30 0)
HommeTime_stats.master.4
prim_main_loop 64 64 6.400000e+01 2.196942e+03 34.329 ( 36 0) 34.325 ( 27 0)
tl-ae U3-5stage_timestep 64 64 3.686400e+04 2.633150e+02 4.844 ( 30 0) 3.454 ( 8 0)
tl-ae advance_hypervis_dp 64 64 3.686400e+04 2.181744e+02 3.453 ( 58 0) 3.384 ( 15 0)
tl-s prim_advec_tracers_remap 64 64 3.686400e+04 1.468719e+03 23.616 ( 8 0) 22.168 ( 30 0)
tl-at prim_advec_tracers_remap_RK2 64 64 3.686400e+04 1.468503e+03 23.613 ( 8 0) 22.165 ( 30 0)
tl-sc vertical_remap 64 64 1.228800e+04 2.171793e+02 3.466 ( 51 0) 3.358 ( 61 0)
Remap Thickness Functor 64 64 1.228800e+04 1.487122e+00 0.024 ( 4 0) 0.022 ( 8 0)
Remap Scale States Functor 64 64 1.228800e+04 7.837300e-01 0.014 ( 39 0) 0.011 ( 5 0)
Remap Compute Grids Functor 64 64 1.228800e+04 8.524191e+00 0.138 ( 52 0) 0.130 ( 8 0)
Remap Compute Remap Functor 64 64 1.228800e+04 2.042216e+02 3.261 ( 51 0) 3.162 ( 61 0)
Remap Rescale States Functor 64 64 1.228800e+04 1.124913e+00 0.019 ( 8 0) 0.017 ( 52 0)
HommeTime_stats.rm_ppm_single.1
prim_main_loop 64 64 6.400000e+01 2.120706e+03 33.138 ( 33 0) 33.133 ( 27 0)
tl-ae U3-5stage_timestep 64 64 3.686400e+04 2.632431e+02 4.926 ( 30 0) 3.436 ( 8 0)
tl-ae advance_hypervis_dp 64 64 3.686400e+04 2.174456e+02 3.449 ( 58 0) 3.376 ( 27 0)
tl-s prim_advec_tracers_remap 64 64 3.686400e+04 1.466160e+03 23.590 ( 8 0) 22.092 ( 30 0)
tl-at prim_advec_tracers_remap_RK2 64 64 3.686400e+04 1.465944e+03 23.586 ( 8 0) 22.088 ( 30 0)
tl-sc vertical_remap 64 64 1.228800e+04 1.443126e+02 2.285 ( 43 0) 2.240 ( 61 0)
Remap Thickness Functor 64 64 1.228800e+04 1.506256e+00 0.025 ( 4 0) 0.022 ( 2 0)
Remap Scale States Functor 64 64 1.228800e+04 7.825590e-01 0.014 ( 43 0) 0.011 ( 58 0)
Remap Compute Grids Functor 64 64 1.228800e+04 8.520673e+00 0.137 ( 52 0) 0.129 ( 55 0)
Remap Compute Remap Functor 64 64 1.228800e+04 1.313548e+02 2.077 ( 43 0) 2.042 ( 16 0)
Remap Rescale States Functor 64 64 1.228800e+04 1.124931e+00 0.019 ( 7 0) 0.017 ( 51 0)
HommeTime_stats.rm_ppm_single.2
prim_main_loop 64 64 6.400000e+01 2.123196e+03 33.177 ( 36 0) 33.172 ( 25 0)
tl-ae U3-5stage_timestep 64 64 3.686400e+04 2.642343e+02 4.921 ( 30 0) 3.452 ( 8 0)
tl-ae advance_hypervis_dp 64 64 3.686400e+04 2.180476e+02 3.449 ( 58 0) 3.387 ( 15 0)
tl-s prim_advec_tracers_remap 64 64 3.686400e+04 1.466882e+03 23.605 ( 8 0) 22.111 ( 30 0)
tl-at prim_advec_tracers_remap_RK2 64 64 3.686400e+04 1.466664e+03 23.602 ( 8 0) 22.108 ( 30 0)
tl-sc vertical_remap 64 64 1.228800e+04 1.444895e+02 2.280 ( 52 0) 2.240 ( 38 0)
Remap Thickness Functor 64 64 1.228800e+04 1.507111e+00 0.025 ( 54 0) 0.022 ( 61 0)
Remap Scale States Functor 64 64 1.228800e+04 7.838370e-01 0.014 ( 52 0) 0.011 ( 5 0)
Remap Compute Grids Functor 64 64 1.228800e+04 8.533307e+00 0.138 ( 52 0) 0.130 ( 2 0)
Remap Compute Remap Functor 64 64 1.228800e+04 1.315150e+02 2.073 ( 48 0) 2.039 ( 38 0)
Remap Rescale States Functor 64 64 1.228800e+04 1.123631e+00 0.019 ( 36 0) 0.017 ( 46 0)
HommeTime_stats.rm_ppm_single.3
prim_main_loop 64 64 6.400000e+01 2.120112e+03 33.129 ( 19 0) 33.124 ( 27 0)
tl-ae U3-5stage_timestep 64 64 3.686400e+04 2.637084e+02 4.932 ( 30 0) 3.442 ( 8 0)
tl-ae advance_hypervis_dp 64 64 3.686400e+04 2.174151e+02 3.428 ( 58 0) 3.374 ( 28 0)
tl-s prim_advec_tracers_remap 64 64 3.686400e+04 1.465150e+03 23.580 ( 8 0) 22.075 ( 30 0)
tl-at prim_advec_tracers_remap_RK2 64 64 3.686400e+04 1.464936e+03 23.576 ( 8 0) 22.072 ( 30 0)
tl-sc vertical_remap 64 64 1.228800e+04 1.442805e+02 2.276 ( 52 0) 2.239 ( 20 0)
Remap Thickness Functor 64 64 1.228800e+04 1.508901e+00 0.025 ( 4 0) 0.022 ( 8 0)
Remap Scale States Functor 64 64 1.228800e+04 7.863550e-01 0.014 ( 43 0) 0.011 ( 55 0)
Remap Compute Grids Functor 64 64 1.228800e+04 8.531173e+00 0.137 ( 52 0) 0.130 ( 58 0)
Remap Compute Remap Functor 64 64 1.228800e+04 1.312947e+02 2.069 ( 52 0) 2.037 ( 20 0)
Remap Rescale States Functor 64 64 1.228800e+04 1.123969e+00 0.019 ( 7 0) 0.016 ( 48 0)
HommeTime_stats.rm_ppm_single.4
prim_main_loop 64 64 6.400000e+01 2.126971e+03 33.236 ( 36 0) 33.232 ( 29 0)
tl-ae U3-5stage_timestep 64 64 3.686400e+04 2.676657e+02 5.039 ( 30 0) 3.430 ( 8 0)
tl-ae advance_hypervis_dp 64 64 3.686400e+04 2.173446e+02 3.477 ( 58 0) 3.365 ( 15 0)
tl-s prim_advec_tracers_remap 64 64 3.686400e+04 1.468184e+03 23.719 ( 8 0) 22.075 ( 30 0)
tl-at prim_advec_tracers_remap_RK2 64 64 3.686400e+04 1.467969e+03 23.716 ( 8 0) 22.071 ( 30 0)
tl-sc vertical_remap 64 64 1.228800e+04 1.442429e+02 2.274 ( 52 0) 2.238 ( 14 0)
Remap Thickness Functor 64 64 1.228800e+04 1.507726e+00 0.025 ( 4 0) 0.022 ( 8 0)
Remap Scale States Functor 64 64 1.228800e+04 7.840750e-01 0.014 ( 39 0) 0.011 ( 8 0)
Remap Compute Grids Functor 64 64 1.228800e+04 8.534283e+00 0.137 ( 39 0) 0.130 ( 8 0)
Remap Compute Remap Functor 64 64 1.228800e+04 1.312830e+02 2.067 ( 43 0) 2.037 ( 31 0)
Remap Rescale States Functor 64 64 1.228800e+04 1.121617e+00 0.019 ( 1 0) 0.016 ( 28 0)
Shepard comparison appears neutral/potentially slightly worse with ne=4
, qsize=35
, ndays=4
:
HommeTime_stats.master.1
prim_main_loop 32 32 3.200000e+01 8.737607e+02 27.305 ( 0 0) 27.305 ( 11 0)
tl-ae U3-5stage_timestep 32 32 1.843200e+04 6.871333e+01 4.293 ( 21 0) 1.035 ( 6 0)
tl-ae advance_hypervis_dp 32 32 1.843200e+04 2.994486e+01 0.946 ( 30 0) 0.925 ( 7 0)
tl-s prim_advec_tracers_remap 32 32 1.843200e+04 7.291517e+02 23.862 ( 6 0) 20.678 ( 21 0)
tl-at prim_advec_tracers_remap_RK2 32 32 1.843200e+04 7.291117e+02 23.861 ( 6 0) 20.677 ( 21 0)
tl-sc vertical_remap 32 32 6.144000e+03 3.562811e+01 1.168 ( 15 0) 1.084 ( 23 0)
Remap Thickness Functor 32 32 6.144000e+03 4.397166e-01 0.021 ( 15 0) 0.010 ( 18 0)
Remap Scale States Functor 32 32 6.144000e+03 2.246063e-01 0.014 ( 15 0) 0.003 ( 23 0)
Remap Compute Grids Functor 32 32 6.144000e+03 2.102585e+00 0.102 ( 15 0) 0.047 ( 23 0)
Remap Compute Remap Functor 32 32 6.144000e+03 3.253628e+01 1.037 ( 22 0) 1.008 ( 10 0)
Remap Rescale States Functor 32 32 6.144000e+03 2.228884e-01 0.008 ( 0 0) 0.007 ( 25 0)
HommeTime_stats.master.2
prim_main_loop 32 32 3.200000e+01 8.726374e+02 27.270 ( 0 0) 27.270 ( 25 0)
tl-ae U3-5stage_timestep 32 32 1.843200e+04 6.849703e+01 4.310 ( 21 0) 1.048 ( 6 0)
tl-ae advance_hypervis_dp 32 32 1.843200e+04 3.013889e+01 0.952 ( 30 0) 0.932 ( 5 0)
tl-s prim_advec_tracers_remap 32 32 1.843200e+04 7.278940e+02 23.806 ( 6 0) 20.617 ( 21 0)
tl-at prim_advec_tracers_remap_RK2 32 32 1.843200e+04 7.278509e+02 23.805 ( 6 0) 20.616 ( 21 0)
tl-sc vertical_remap 32 32 6.144000e+03 3.563842e+01 1.169 ( 14 0) 1.079 ( 28 0)
Remap Thickness Functor 32 32 6.144000e+03 4.452025e-01 0.021 ( 11 0) 0.010 ( 23 0)
Remap Scale States Functor 32 32 6.144000e+03 2.268802e-01 0.014 ( 11 0) 0.003 ( 23 0)
Remap Compute Grids Functor 32 32 6.144000e+03 2.108664e+00 0.099 ( 11 0) 0.047 ( 23 0)
Remap Compute Remap Functor 32 32 6.144000e+03 3.252897e+01 1.032 ( 22 0) 1.005 ( 9 0)
Remap Rescale States Functor 32 32 6.144000e+03 2.232977e-01 0.008 ( 1 0) 0.007 ( 27 0)
HommeTime_stats.master.3
prim_main_loop 32 32 3.200000e+01 8.722681e+02 27.259 ( 0 0) 27.258 ( 11 0)
tl-ae U3-5stage_timestep 32 32 1.843200e+04 6.955696e+01 4.316 ( 21 0) 1.049 ( 6 0)
tl-ae advance_hypervis_dp 32 32 1.843200e+04 3.057956e+01 0.967 ( 30 0) 0.946 ( 5 0)
tl-s prim_advec_tracers_remap 32 32 1.843200e+04 7.261445e+02 23.791 ( 6 0) 20.582 ( 21 0)
tl-at prim_advec_tracers_remap_RK2 32 32 1.843200e+04 7.261050e+02 23.790 ( 6 0) 20.581 ( 21 0)
tl-sc vertical_remap 32 32 6.144000e+03 3.562392e+01 1.176 ( 12 0) 1.083 ( 27 0)
Remap Thickness Functor 32 32 6.144000e+03 4.389247e-01 0.020 ( 15 0) 0.010 ( 23 0)
Remap Scale States Functor 32 32 6.144000e+03 2.232599e-01 0.014 ( 15 0) 0.003 ( 18 0)
Remap Compute Grids Functor 32 32 6.144000e+03 2.091088e+00 0.101 ( 11 0) 0.047 ( 23 0)
Remap Compute Remap Functor 32 32 6.144000e+03 3.254489e+01 1.036 ( 12 0) 1.006 ( 27 0)
Remap Rescale States Functor 32 32 6.144000e+03 2.234919e-01 0.008 ( 6 0) 0.007 ( 10 0)
HommeTime_stats.master.4
prim_main_loop 32 32 3.200000e+01 8.729287e+02 27.279 ( 0 0) 27.279 ( 25 0)
tl-ae U3-5stage_timestep 32 32 1.843200e+04 6.836315e+01 4.295 ( 21 0) 1.041 ( 6 0)
tl-ae advance_hypervis_dp 32 32 1.843200e+04 3.010457e+01 0.954 ( 30 0) 0.930 ( 8 0)
tl-s prim_advec_tracers_remap 32 32 1.843200e+04 7.283976e+02 23.822 ( 6 0) 20.639 ( 21 0)
tl-at prim_advec_tracers_remap_RK2 32 32 1.843200e+04 7.283582e+02 23.821 ( 6 0) 20.638 ( 21 0)
tl-sc vertical_remap 32 32 6.144000e+03 3.559987e+01 1.173 ( 11 0) 1.082 ( 28 0)
Remap Thickness Functor 32 32 6.144000e+03 4.412566e-01 0.021 ( 11 0) 0.010 ( 23 0)
Remap Scale States Functor 32 32 6.144000e+03 2.226421e-01 0.014 ( 11 0) 0.003 ( 23 0)
Remap Compute Grids Functor 32 32 6.144000e+03 2.085484e+00 0.101 ( 11 0) 0.047 ( 23 0)
Remap Compute Remap Functor 32 32 6.144000e+03 3.252386e+01 1.028 ( 22 0) 1.006 ( 4 0)
Remap Rescale States Functor 32 32 6.144000e+03 2.241230e-01 0.008 ( 0 0) 0.007 ( 27 0)
HommeTime_stats.rm_ppm_single.1
prim_main_loop 32 32 3.200000e+01 8.755246e+02 27.360 ( 0 0) 27.360 ( 13 0)
tl-ae U3-5stage_timestep 32 32 1.843200e+04 6.853247e+01 4.271 ( 21 0) 1.033 ( 6 0)
tl-ae advance_hypervis_dp 32 32 1.843200e+04 3.008810e+01 0.950 ( 30 0) 0.931 ( 5 0)
tl-s prim_advec_tracers_remap 32 32 1.843200e+04 7.309029e+02 23.923 ( 6 0) 20.745 ( 21 0)
tl-at prim_advec_tracers_remap_RK2 32 32 1.843200e+04 7.308613e+02 23.922 ( 6 0) 20.745 ( 21 0)
tl-sc vertical_remap 32 32 6.144000e+03 3.566047e+01 1.176 ( 15 0) 1.075 ( 18 0)
Remap Thickness Functor 32 32 6.144000e+03 4.376241e-01 0.021 ( 15 0) 0.010 ( 18 0)
Remap Scale States Functor 32 32 6.144000e+03 2.238449e-01 0.014 ( 15 0) 0.003 ( 18 0)
Remap Compute Grids Functor 32 32 6.144000e+03 2.093430e+00 0.101 ( 11 0) 0.047 ( 18 0)
Remap Compute Remap Functor 32 32 6.144000e+03 3.258055e+01 1.036 ( 22 0) 1.006 ( 18 0)
Remap Rescale States Functor 32 32 6.144000e+03 2.230985e-01 0.008 ( 0 0) 0.007 ( 10 0)
HommeTime_stats.rm_ppm_single.2
prim_main_loop 32 32 3.200000e+01 8.769835e+02 27.406 ( 0 0) 27.406 ( 25 0)
tl-ae U3-5stage_timestep 32 32 1.843200e+04 6.871850e+01 4.311 ( 21 0) 1.033 ( 6 0)
tl-ae advance_hypervis_dp 32 32 1.843200e+04 3.019336e+01 0.963 ( 30 0) 0.929 ( 8 0)
tl-s prim_advec_tracers_remap 32 32 1.843200e+04 7.319451e+02 23.958 ( 6 0) 20.748 ( 21 0)
tl-at prim_advec_tracers_remap_RK2 32 32 1.843200e+04 7.319057e+02 23.957 ( 6 0) 20.747 ( 21 0)
tl-sc vertical_remap 32 32 6.144000e+03 3.568692e+01 1.161 ( 15 0) 1.084 ( 28 0)
Remap Thickness Functor 32 32 6.144000e+03 4.410455e-01 0.019 ( 15 0) 0.011 ( 26 0)
Remap Scale States Functor 32 32 6.144000e+03 2.264747e-01 0.013 ( 14 0) 0.003 ( 23 0)
Remap Compute Grids Functor 32 32 6.144000e+03 2.097900e+00 0.098 ( 14 0) 0.047 ( 23 0)
Remap Compute Remap Functor 32 32 6.144000e+03 3.259723e+01 1.029 ( 31 0) 1.011 ( 28 0)
Remap Rescale States Functor 32 32 6.144000e+03 2.233663e-01 0.008 ( 1 0) 0.007 ( 27 0)
HommeTime_stats.rm_ppm_single.3
prim_main_loop 32 32 3.200000e+01 8.739455e+02 27.311 ( 0 0) 27.311 ( 7 0)
tl-ae U3-5stage_timestep 32 32 1.843200e+04 6.881764e+01 4.300 ( 21 0) 1.022 ( 6 0)
tl-ae advance_hypervis_dp 32 32 1.843200e+04 3.011805e+01 0.955 ( 30 0) 0.929 ( 6 0)
tl-s prim_advec_tracers_remap 32 32 1.843200e+04 7.289426e+02 23.884 ( 6 0) 20.663 ( 21 0)
tl-at prim_advec_tracers_remap_RK2 32 32 1.843200e+04 7.289034e+02 23.883 ( 6 0) 20.662 ( 21 0)
tl-sc vertical_remap 32 32 6.144000e+03 3.570675e+01 1.177 ( 15 0) 1.084 ( 28 0)
Remap Thickness Functor 32 32 6.144000e+03 4.385276e-01 0.022 ( 15 0) 0.010 ( 18 0)
Remap Scale States Functor 32 32 6.144000e+03 2.238488e-01 0.015 ( 15 0) 0.003 ( 26 0)
Remap Compute Grids Functor 32 32 6.144000e+03 2.103088e+00 0.107 ( 15 0) 0.046 ( 26 0)
Remap Compute Remap Functor 32 32 6.144000e+03 3.261683e+01 1.034 ( 21 0) 1.010 ( 29 0)
Remap Rescale States Functor 32 32 6.144000e+03 2.238711e-01 0.008 ( 6 0) 0.007 ( 14 0)
HommeTime_stats.rm_ppm_single.4
prim_main_loop 32 32 3.200000e+01 8.759420e+02 27.373 ( 0 0) 27.373 ( 2 0)
tl-ae U3-5stage_timestep 32 32 1.843200e+04 6.888372e+01 4.297 ( 21 0) 1.075 ( 6 0)
tl-ae advance_hypervis_dp 32 32 1.843200e+04 3.098512e+01 0.983 ( 30 0) 0.957 ( 12 0)
tl-s prim_advec_tracers_remap 32 32 1.843200e+04 7.300060e+02 23.861 ( 6 0) 20.703 ( 20 0)
tl-at prim_advec_tracers_remap_RK2 32 32 1.843200e+04 7.299649e+02 23.860 ( 6 0) 20.702 ( 20 0)
tl-sc vertical_remap 32 32 6.144000e+03 3.570281e+01 1.178 ( 15 0) 1.083 ( 17 0)
Remap Thickness Functor 32 32 6.144000e+03 4.407698e-01 0.020 ( 15 0) 0.010 ( 23 0)
Remap Scale States Functor 32 32 6.144000e+03 2.256609e-01 0.014 ( 15 0) 0.003 ( 23 0)
Remap Compute Grids Functor 32 32 6.144000e+03 2.110836e+00 0.100 ( 15 0) 0.047 ( 23 0)
Remap Compute Remap Functor 32 32 6.144000e+03 3.260146e+01 1.046 ( 25 0) 1.006 ( 6 0)
Remap Rescale States Functor 32 32 6.144000e+03 2.231150e-01 0.008 ( 1 0) 0.007 ( 27 0)
This appears to work on White now