From b87d4d3093ad5269cde25bbfdeef02709987af99 Mon Sep 17 00:00:00 2001 From: Wolfgang Bangerth Date: Mon, 23 Mar 2020 17:23:34 -0600 Subject: [PATCH] Improve naming of a section. --- examples/step-67/doc/results.dox | 20 ++++++++++---------- examples/step-67/step-67.cc | 2 +- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/examples/step-67/doc/results.dox b/examples/step-67/doc/results.dox index 6b0c5aa7cc..2c31e0e9dd 100644 --- a/examples/step-67/doc/results.dox +++ b/examples/step-67/doc/results.dox @@ -30,7 +30,7 @@ Time: 10, dt: 0.0096, error rho: 7.231e-07, rho * u: 2.666e-07, energy: | compute errors | 11 | 0.008066s 13 | 0.00952s | 0.01041s 20 | | compute transport speed | 258 | 0.01012s 13 | 0.05392s | 0.08574s 25 | | output | 11 | 0.9597s 13 | 0.9613s | 0.9623s 6 | -| rk time step total | 1283 | 0.9827s 25 | 1.015s | 1.06s 13 | +| rk time stepping total | 1283 | 0.9827s 25 | 1.015s | 1.06s 13 | | rk_stage - integrals L_h | 6415 | 0.8803s 26 | 0.9198s | 0.9619s 14 | | rk_stage - inv mass + vec upd | 6415 | 0.05677s 15 | 0.06487s | 0.07597s 13 | +-------------------------------------------+------------------+------------+------------------+ @@ -81,7 +81,7 @@ $p=5$, and the same system of 40 cores of dual-socket Intel Xeon Gold 6230): | compute errors | 11 | 0.4239s 12 | 0.4318s | 0.4408s 9 | | compute transport speed | 2053 | 3.962s 12 | 6.727s | 10.12s 7 | | output | 11 | 30.35s 12 | 30.36s | 30.37s 9 | -| rk time step total | 10258 | 201.7s 7 | 205.1s | 207.8s 12 | +| rk time stepping total | 10258 | 201.7s 7 | 205.1s | 207.8s 12 | | rk_stage - integrals L_h | 51290 | 121.3s 6 | 126.6s | 136.3s 16 | | rk_stage - inv mass + vec upd | 51290 | 66.19s 16 | 77.52s | 81.84s 10 | +-------------------------------------------+------------------+------------+------------------+ @@ -125,7 +125,7 @@ in run time can be traced back to cache effects on the given hardware (with 40 MB of L2 cache and 55 MB of L3 cache): While not all of the relevant data fits into caches for 9.4 million DoFs (one vector takes 75 MB and we have three vectors plus some additional data in MatrixFree), there is capacity for almost -half of it nonetheless. Given that modern caches are more sophisticated than +half of one vector nonetheless. Given that modern caches are more sophisticated than the naive least-recently-used strategy (where we would have little re-use as the data is used in a streaming-like fashion), we can assume that a sizeable fraction of data can indeed be delivered from caches for the 9.4 million DoFs @@ -480,7 +480,7 @@ Time: 2, dt: 5.7e-05, norm rho: 0.01432, rho * u: 0.03969, energy: | compute errors | 41 | 0.01112s 35 | 0.0672s | 0.1337s 0 | | compute transport speed | 6914 | 5.422s 35 | 15.96s | 29.99s 1 | | output | 41 | 37.24s 35 | 37.3s | 37.37s 0 | -| rk time step total | 34564 | 205.4s 1 | 219.5s | 230.1s 35 | +| rk time stepping total | 34564 | 205.4s 1 | 219.5s | 230.1s 35 | | rk_stage - integrals L_h | 172820 | 153.6s 1 | 164.9s | 175.6s 27 | | rk_stage - inv mass + vec upd | 172820 | 47.13s 13 | 53.09s | 64.05s 33 | +-------------------------------------------+------------------+------------+------------------+ @@ -511,7 +511,7 @@ Number of degrees of freedom: 14,745,600 ( = 4 [vars] x 102,400 [cells] x 36 [do | compute errors | 41 | 0.04537s 32 | 0.173s | 0.3489s 0 | | compute transport speed | 13858 | 40.75s 32 | 85.99s | 149.8s 0 | | output | 41 | 153.8s 32 | 153.9s | 154.1s 0 | -| rk time step total | 69284 | 2386s 0 | 2450s | 2496s 32 | +| rk time stepping total | 69284 | 2386s 0 | 2450s | 2496s 32 | | rk_stage - integrals L_h | 346420 | 1365s 32 | 1574s | 1718s 19 | | rk_stage - inv mass + vec upd | 346420 | 722.5s 10 | 870.7s | 1125s 32 | +-------------------------------------------+------------------+------------+------------------+ @@ -525,7 +525,7 @@ fitting in caches. An interesting effect, typical of programs with a mix of local communication (integrals L_h) and global communication (computation of transport speed) with some load imbalance, can be observed by looking at the MPI rank that measure the minimal and maximal time of different phases, -respectively. Rank 0 reports the fastest throughput for the "rk time step +respectively. Rank 0 reports the fastest throughput for the "rk time stepping total" part. At the same time, it appears to be slowest for the "compute transport speed" part, more almost a factor of 2 slower than the average. Since the latter involves global communication, we can attribute the @@ -564,13 +564,13 @@ Time: 2, dt: 1.4e-05, norm rho: 0.01431, rho * u: 0.03969, energy: | compute errors | 41 | 0.1758s 30 | 0.672s | 1.376s 1 | | compute transport speed | 27748 | 321.3s 34 | 678.8s | 1202s 1 | | output | 41 | 616.3s 32 | 616.4s | 616.4s 34 | -| rk time step total | 138733 | 1.983e+04s 1 | 2.036e+04s | 2.072e+04s 34 | +| rk time stepping total | 138733 | 1.983e+04s 1 | 2.036e+04s | 2.072e+04s 34 | | rk_stage - integrals L_h | 693665 | 1.052e+04s 32 | 1.248e+04s | 1.387e+04s 19 | | rk_stage - inv mass + vec upd | 693665 | 6404s 10 | 7868s | 1.018e+04s 32 | +-------------------------------------------+------------------+------------+------------------+ @endcode -The "rk time stop total" part corresponds to a throughput of 2010 MDoFs/s. The +The "rk time stepping total" part corresponds to a throughput of 2010 MDoFs/s. The overall run time to perform 139k time steps is 20k seconds (5.7 hours) or 7 time steps per second. More throughput can be achieved by adding more cores to the computation. @@ -596,7 +596,7 @@ Time: 2, dt: 0.00011, norm rho: 0.0119, rho * u: 0.03142, energy: | compute errors | 41 | 0.6551s 34 | 3.216s | 7.281s 0 | | compute transport speed | 3546 | 160s 34 | 393.2s | 776.9s 0 | | output | 41 | 1350s 34 | 1353s | 1357s 0 | -| rk time step total | 17723 | 1.519e+04s 0 | 1.558e+04s | 1.582e+04s 34 | +| rk time stepping total | 17723 | 1.519e+04s 0 | 1.558e+04s | 1.582e+04s 34 | | rk_stage - integrals L_h | 88615 | 1.005e+04s 32 | 1.126e+04s | 1.23e+04s 11 | | rk_stage - inv mass + vec upd | 88615 | 3056s 11 | 4322s | 5759s 32 | +-------------------------------------------+------------------+------------+------------------+ @@ -643,7 +643,7 @@ Time: 2, dt: 5.6e-05, norm rho: 0.01189, rho * u: 0.03145, energy: | compute errors | 41 | 2.632s 178 | 7.221s | 16.56s 0 | | compute transport speed | 7072 | 714s 193 | 1553s | 3351s 0 | | output | 35350 | 8065s 176 | 8070s | 8079s 0 | -| rk time step total | 35350 | 4.25e+04s 0 | 4.43e+04s | 4.515e+04s 193 | +| rk time stepping total | 35350 | 4.25e+04s 0 | 4.43e+04s | 4.515e+04s 193 | | rk_stage - integrals L_h | 176750 | 2.936e+04s 134 | 3.222e+04s | 3.67e+04s 99 | | rk_stage - inv mass + vec upd | 176750 | 7004s 99 | 1.207e+04s | 1.55e+04s 132 | +-------------------------------------------+------------------+------------+------------------+ diff --git a/examples/step-67/step-67.cc b/examples/step-67/step-67.cc index 2169eebbd5..4f413b2c87 100644 --- a/examples/step-67/step-67.cc +++ b/examples/step-67/step-67.cc @@ -2128,7 +2128,7 @@ namespace Euler_DG euler_operator.compute_cell_transport_speed(solution), 3); { - TimerOutput::Scope t(timer, "rk time step total"); + TimerOutput::Scope t(timer, "rk time stepping total"); integrator.perform_time_step(euler_operator, time, time_step, -- 2.39.5