working on the MHFEM section - added Hypre results (9d4cf490) · Commits · Jakub Klinkovský / Dissertation

data/mcwhdd/comptimes_cpu_2D.tex

+22 −10

Original line number	Diff line number	Diff line
		@@ -8,17 +8,26 @@
		% \usepackage{stackengine}
		% \usepackage[np]{numprint}

		\begin{tabular}{rN{5}{1} N{2}{1} N{1}{2} N{5}{1} N{2}{1} N{1}{2}}
		\begin{tabular}{rN{5}{1} N{2}{1} N{1}{2} N{5}{1} N{2}{1} N{1}{2} N{4}{1} N{2}{1} N{1}{2}}
		\toprule

		% header row 0
		& \multicolumn{6}{c}{TNL}
		& \multicolumn{3}{c}{Hypre}
		\\
		\cmidrule(lr){2-7}
		\cmidrule(l){8-10}

		% header row 1
		& \multicolumn{3}{c}{OpenMP}
		& \multicolumn{3}{c}{MPI}
		& \multicolumn{3}{c}{MPI}
		\\
		\cmidrule(lr){2-4}
		\cmidrule(l){5-7}
		\cmidrule(lr){5-7}
		\cmidrule(l){8-10}

		% header row 1
		% header row 2
		\multicolumn{1}{c}{Cores}
		& \multicolumn{1}{c}{$ CT $}
		& \multicolumn{1}{c}{$ Sp $}
		@@ -26,6 +35,9 @@
		& \multicolumn{1}{c}{$ CT $}
		& \multicolumn{1}{c}{$ Sp $}
		& \multicolumn{1}{c}{$ E\!f\!f $}
		& \multicolumn{1}{c}{$ CT $}
		& \multicolumn{1}{c}{$ Sp $}
		& \multicolumn{1}{c}{$ E\!f\!f $}
		\\

		\midrule
		@@ -34,37 +46,37 @@
		$ \np{1} $
		&

		10743.9 & 1.0 & 1.00 & 10800.2 & 1.0 & 1.00 \\
		10743.9 & 1.0 & 1.00 & 10800.2 & 1.0 & 1.00 & 3510.1 & 1.0 & 1.00 \\

		$ \np{2} $
		&

		6349.0 & 1.7 & 0.85 & 5693.5 & 1.9 & 0.95 \\
		6349.0 & 1.7 & 0.85 & 5693.5 & 1.9 & 0.95 & 2058.0 & 1.7 & 0.85 \\

		$ \np{4} $
		&

		3375.9 & 3.2 & 0.80 & 3143.0 & 3.4 & 0.86 \\
		3375.9 & 3.2 & 0.80 & 3143.0 & 3.4 & 0.86 & 1097.1 & 3.2 & 0.80 \\

		$ \np{6} $
		&

		2294.6 & 4.7 & 0.78 & 2506.0 & 4.3 & 0.72 \\
		2294.6 & 4.7 & 0.78 & 2506.0 & 4.3 & 0.72 & 750.5 & 4.7 & 0.78 \\

		$ \np{8} $
		&

		1818.1 & 5.9 & 0.74 & 1787.6 & 6.0 & 0.76 \\
		1818.1 & 5.9 & 0.74 & 1787.6 & 6.0 & 0.76 & 587.6 & 6.0 & 0.75 \\

		$ \np{12} $
		&

		1296.2 & 8.3 & 0.69 & 1096.8 & 9.8 & 0.82 \\
		1296.2 & 8.3 & 0.69 & 1096.8 & 9.8 & 0.82 & 424.8 & 8.3 & 0.69 \\

		$ \np{24} $
		&

		977.0 & 11.0 & 0.46 & 549.3 & 19.7 & 0.82 \\
		977.0 & 11.0 & 0.46 & 549.3 & 19.7 & 0.82 & 215.5 & 16.3 & 0.68 \\

		\bottomrule
		\end{tabular}

data/mcwhdd/comptimes_cpu_3D.tex

+39 −25

Original line number	Diff line number	Diff line
		@@ -8,19 +8,30 @@
		% \usepackage{stackengine}
		% \usepackage[np]{numprint}

		\begin{tabular}{rrrN{6}{1} N{2}{1} N{1}{2} N{6}{1} N{3}{1} N{1}{2}}
		\begin{tabular}{rrrN{6}{1} N{2}{1} N{1}{2} N{6}{1} N{3}{1} N{1}{2} N{5}{1} N{3}{1} N{1}{2}}
		\toprule

		% header row 0
		&
		&
		& \multicolumn{6}{c}{TNL}
		& \multicolumn{3}{c}{Hypre}
		\\
		\cmidrule(lr){4-9}
		\cmidrule(l){10-12}

		% header row 1
		&
		&
		& \multicolumn{3}{c}{OpenMP}
		& \multicolumn{3}{c}{MPI}
		& \multicolumn{3}{c}{MPI}
		\\
		\cmidrule(lr){4-6}
		\cmidrule(l){7-9}
		\cmidrule(lr){7-9}
		\cmidrule(l){10-12}

		% header row 1
		% header row 2
		\multicolumn{1}{c}{Cores}
		& \multicolumn{1}{c}{CPUs}
		& \multicolumn{1}{c}{Nodes}
		@@ -30,76 +41,79 @@
		& \multicolumn{1}{c}{$ CT $}
		& \multicolumn{1}{c}{$ Sp $}
		& \multicolumn{1}{c}{$ E\!f\!f $}
		& \multicolumn{1}{c}{$ CT $}
		& \multicolumn{1}{c}{$ Sp $}
		& \multicolumn{1}{c}{$ E\!f\!f $}
		\\

		\midrule


		$ \np{1} $ & & &
		188243.0 & 1.0 & 1.00 & 188706.0 & 1.0 & 1.00 \\
		188243.0 & 1.0 & 1.00 & 188706.0 & 1.0 & 1.00 & 37991.2 & 1.0 & 1.00 \\

		$ \np{2} $ & & &
		102074.0 & 1.8 & 0.92 & 93659.1 & 2.0 & 1.01 \\
		102074.0 & 1.8 & 0.92 & 93659.1 & 2.0 & 1.01 & 21170.2 & 1.8 & 0.90 \\

		$ \np{4} $ & & &
		55937.6 & 3.4 & 0.84 & 49553.0 & 3.8 & 0.95 \\
		55937.6 & 3.4 & 0.84 & 49553.0 & 3.8 & 0.95 & 11252.2 & 3.4 & 0.84 \\

		$ \np{6} $ & & &
		40796.4 & 4.6 & 0.77 & 35594.3 & 5.3 & 0.88 \\
		40796.4 & 4.6 & 0.77 & 35594.3 & 5.3 & 0.88 & 7798.1 & 4.9 & 0.81 \\

		$ \np{8} $ & & &
		32026.3 & 5.9 & 0.73 & 28958.6 & 6.5 & 0.81 \\
		32026.3 & 5.9 & 0.73 & 28958.6 & 6.5 & 0.81 & 6085.4 & 6.2 & 0.78 \\

		$ \np{12} $ & $ \np{1} $ & $ 1/2 $ &
		26369.7 & 7.1 & 0.59 & 23839.0 & 7.9 & 0.66 \\
		26369.7 & 7.1 & 0.59 & 23839.0 & 7.9 & 0.66 & 4708.8 & 8.1 & 0.67 \\

		$ \np{24} $ & $ \np{2} $ & $ \np{1} $ &
		15695.0 & 12.0 & 0.50 & 12184.2 & 15.5 & 0.65 \\
		15695.0 & 12.0 & 0.50 & 12184.2 & 15.5 & 0.65 & 2485.0 & 15.3 & 0.64 \\

		$ \np{48} $ & $ \np{4} $ & $ \np{2} $ &
		& & & 6171.4 & 30.6 & 0.64 \\
		& & & 6171.4 & 30.6 & 0.64 & 1249.1 & 30.4 & 0.63 \\

		$ \np{72} $ & $ \np{6} $ & $ \np{3} $ &
		& & & 4026.3 & 46.9 & 0.65 \\
		& & & 4026.3 & 46.9 & 0.65 & 880.2 & 43.2 & 0.60 \\

		$ \np{96} $ & $ \np{8} $ & $ \np{4} $ &
		& & & 3016.0 & 62.6 & 0.65 \\
		& & & 3016.0 & 62.6 & 0.65 & 592.3 & 64.1 & 0.67 \\

		$ \np{120} $ & $ \np{10} $ & $ \np{5} $ &
		& & & 2374.4 & 79.5 & 0.66 \\
		& & & 2374.4 & 79.5 & 0.66 & 471.2 & 80.6 & 0.67 \\

		$ \np{144} $ & $ \np{12} $ & $ \np{6} $ &
		& & & 1968.2 & 95.9 & 0.67 \\
		& & & 1968.2 & 95.9 & 0.67 & 415.8 & 91.4 & 0.63 \\

		$ \np{168} $ & $ \np{14} $ & $ \np{7} $ &
		& & & 1643.1 & 114.8 & 0.68 \\
		& & & 1643.1 & 114.8 & 0.68 & 372.2 & 102.1 & 0.61 \\

		$ \np{192} $ & $ \np{16} $ & $ \np{8} $ &
		& & & 1410.4 & 133.8 & 0.70 \\
		& & & 1410.4 & 133.8 & 0.70 & 310.7 & 122.3 & 0.64 \\

		$ \np{216} $ & $ \np{18} $ & $ \np{9} $ &
		& & & 1242.5 & 151.9 & 0.70 \\
		& & & 1242.5 & 151.9 & 0.70 & 277.5 & 136.9 & 0.63 \\

		$ \np{240} $ & $ \np{20} $ & $ \np{10} $ &
		& & & 1114.3 & 169.4 & 0.71 \\
		& & & 1114.3 & 169.4 & 0.71 & 240.3 & 158.1 & 0.66 \\

		$ \np{264} $ & $ \np{22} $ & $ \np{11} $ &
		& & & 1003.8 & 188.0 & 0.71 \\
		& & & 1003.8 & 188.0 & 0.71 & 251.5 & 151.0 & 0.57 \\

		$ \np{288} $ & $ \np{24} $ & $ \np{12} $ &
		& & & 924.2 & 204.2 & 0.71 \\
		& & & 924.2 & 204.2 & 0.71 & 223.9 & 169.7 & 0.59 \\

		$ \np{312} $ & $ \np{26} $ & $ \np{13} $ &
		& & & 860.5 & 219.3 & 0.70 \\
		& & & 860.5 & 219.3 & 0.70 & 202.9 & 187.2 & 0.60 \\

		$ \np{336} $ & $ \np{28} $ & $ \np{14} $ &
		& & & 807.3 & 233.8 & 0.70 \\
		& & & 807.3 & 233.8 & 0.70 & 201.9 & 188.2 & 0.56 \\

		$ \np{360} $ & $ \np{30} $ & $ \np{15} $ &
		& & & 761.6 & 247.8 & 0.69 \\
		& & & 761.6 & 247.8 & 0.69 & & & \\

		$ \np{384} $ & $ \np{32} $ & $ \np{16} $ &
		& & & 702.4 & 268.7 & 0.70 \\
		& & & 702.4 & 268.7 & 0.70 & & & \\

		\bottomrule
		\end{tabular}

data/mcwhdd/comptimes_gpu.tex

+24 −7

Original line number	Diff line number	Diff line
		@@ -8,18 +8,35 @@
		% \usepackage{stackengine}
		% \usepackage[np]{numprint}

		\begin{tabular}{rN{3}{1} N{1}{1} N{1}{2} N{4}{1} N{1}{1} N{1}{2}}
		\begin{tabular}{rN{3}{1} N{1}{1} N{1}{2} N{4}{1} N{1}{1} N{1}{2} N{3}{1} N{1}{1} N{1}{2} N{4}{1} N{1}{1} N{1}{2}}
		\toprule

		% header row 0
		& \multicolumn{6}{c}{TNL}
		& \multicolumn{6}{c}{Hypre}
		\\
		\cmidrule(lr){2-7}
		\cmidrule(l){8-13}

		% header row 1
		& \multicolumn{3}{c}{2D$^\triangle_5$}
		& \multicolumn{3}{c}{3D$^\triangle_5$}
		& \multicolumn{3}{c}{2D$^\triangle_5$}
		& \multicolumn{3}{c}{3D$^\triangle_5$}
		\\
		\cmidrule(lr){2-4}
		\cmidrule(l){5-7}
		\cmidrule(lr){5-7}
		\cmidrule(lr){8-10}
		\cmidrule(l){11-13}

		% header row 1
		% header row 2
		\multicolumn{1}{c}{GPUs}
		& \multicolumn{1}{c}{$ CT $}
		& \multicolumn{1}{c}{$ Sp $}
		& \multicolumn{1}{c}{$ E\!f\!f $}
		& \multicolumn{1}{c}{$ CT $}
		& \multicolumn{1}{c}{$ Sp $}
		& \multicolumn{1}{c}{$ E\!f\!f $}
		& \multicolumn{1}{c}{$ CT $}
		& \multicolumn{1}{c}{$ Sp $}
		& \multicolumn{1}{c}{$ E\!f\!f $}
		@@ -34,22 +51,22 @@
		$ \np{1} $
		&

		528.6 & 1.0 & 1.00 & 2654.8 & 1.0 & 1.00 \\
		528.6 & 1.0 & 1.00 & 2654.8 & 1.0 & 1.00 & 389.8 & 1.0 & 1.00 & 2014.5 & 1.0 & 1.00 \\

		$ \np{2} $
		&

		566.1 & 0.9 & 0.47 & 1415.4 & 1.9 & 0.94 \\
		566.1 & 0.9 & 0.47 & 1415.4 & 1.9 & 0.94 & 500.6 & 0.8 & 0.39 & 1233.1 & 1.6 & 0.82 \\

		$ \np{3} $
		&

		642.5 & 0.8 & 0.27 & 996.7 & 2.7 & 0.89 \\
		642.5 & 0.8 & 0.27 & 996.7 & 2.7 & 0.89 & 634.1 & 0.6 & 0.20 & 868.9 & 2.3 & 0.77 \\

		$ \np{4} $
		&

		709.7 & 0.7 & 0.19 & 793.3 & 3.3 & 0.84 \\
		709.7 & 0.7 & 0.19 & 793.3 & 3.3 & 0.84 & 726.8 & 0.5 & 0.13 & 704.2 & 2.9 & 0.72 \\

		\bottomrule
		\end{tabular}

data/mcwhdd/hypre_cpu/cube1m_1-BC-noML_mpi_np1/host-bicgstab+diagonal/log

0 → 100644

+55 −0

Original line number	Diff line number	Diff line
		+-------------------------------------------------------------------------------+
		\| \|
		\| NumDwarf solver \|
		\| \|
		+-------------------------------------------------------------------------------+
		\| MPI processes: 1 \|
		\| Device type: TNL::Devices::Host \|
		\| OMP enabled: no \|
		\| Real type: double \|
		\| Index type: int \|
		\| Mesh type:TNL::Meshes::Mesh<TNL::Meshes::DefaultConfig<TNL::Meshes::Topologies::Tetrahedron, 3, double, int, short>, TNL::Devices::Host> \|
		\| Sparse matrix:TNL::Matrices::SparseMatrix<double, TNL::Devices::Host, int, TNL::Matrices::GeneralMatrix, TNL::Algorithms::Segments::CSRLight, double, std::allocator<double>, std::allocator<int> > \|
		\| Mass lumping: disabled \|
		\| Material model: BrooksCorey \|
		\| Formulation: PwPn \|
		+-------------------------------------------------------------------------------+
		\| Host name: n16 \|
		\| System: Linux \|
		\| Release: 3.10.0-1127.13.1.el7.x86_64 \|
		\| Architecture: x86_64 \|
		\| TNL compiler: GNU G++ (10.2.0) \|
		\| CPU info \|
		\| Model name: Intel(R) Xeon(R) Gold 6136 CPU @ 3.00GHz \|
		\| Cores: 12 \|
		\| Threads per core: 2 \|
		\| Max clock rate (in MHz): 3001 \|
		\| Cache (L1d, L1i, L2, L3): 32, 32, 1024, 25344 \|
		+-------------------------------------------------------------------------------+
		\| Started at: Fri Jul 29 2022, 20:13:07 \|
		+-------------------------------------------------------------------------------+
		+-------------------------------------------------------------------------------+
		\| Finished at: Fri Jul 29 2022, 20:13:07 \|
		\| Total number of linear solver iterations: 351 \|
		\| Total number of time steps: 24 \|
		\| Number of time steps in which the preconditioner was updated: 2 \|
		\| Pre-iterate time: avg: 4.930318e-02 stddev: 0.000000e+00 min: 4.930318e-02 max: 4.930318e-02 \|
		\| nonlinear update time: avg: 1.725292e-02 stddev: 0.000000e+00 min: 1.725292e-02 max: 1.725292e-02 \|
		\| update_b time: avg: 1.540224e-02 stddev: 0.000000e+00 min: 1.540224e-02 max: 1.540224e-02 \|
		\| upwind update time: avg: 9.500597e-03 stddev: 0.000000e+00 min: 9.500597e-03 max: 9.500597e-03 \|
		\| upwind MPI synchronization time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| update_R time: avg: 3.426872e-03 stddev: 0.000000e+00 min: 3.426872e-03 max: 3.426872e-03 \|
		\| update_Q time: avg: 3.423305e-03 stddev: 0.000000e+00 min: 3.423305e-03 max: 3.423305e-03 \|
		\| model pre-iterate time: avg: 2.461200e-05 stddev: 0.000000e+00 min: 2.461200e-05 max: 2.461200e-05 \|
		\| Linear system assembler time: avg: 2.796267e-02 stddev: 0.000000e+00 min: 2.796267e-02 max: 2.796267e-02 \|
		\| Hypre matrix conversion time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| Hypre setup time: avg: 1.124451e-02 stddev: 0.000000e+00 min: 1.124451e-02 max: 1.124451e-02 \|
		\| Hypre solve time: avg: 4.931529e-01 stddev: 0.000000e+00 min: 4.931529e-01 max: 4.931529e-01 \|
		\| Post-iterate time: avg: 3.499364e-03 stddev: 0.000000e+00 min: 3.499364e-03 max: 3.499364e-03 \|
		\| Z_iF -> Z_iK update time: avg: 4.951700e-04 stddev: 0.000000e+00 min: 4.951700e-04 max: 4.951700e-04 \|
		\| velocities update time: avg: 2.862900e-03 stddev: 0.000000e+00 min: 2.862900e-03 max: 2.862900e-03 \|
		\| model post-iterate time: avg: 2.453500e-05 stddev: 0.000000e+00 min: 2.453500e-05 max: 2.453500e-05 \|
		\| Compute time: 0.585421 \|
		\| I/O time: 0.0168328 \|
		\| Total time: 0.620314 \|
		+-------------------------------------------------------------------------------+

data/mcwhdd/hypre_cpu/cube1m_1-BC-noML_mpi_np12/host-bicgstab+diagonal/log

0 → 100644

+62 −0

Original line number	Diff line number	Diff line
		+-------------------------------------------------------------------------------+
		\| \|
		\| NumDwarf solver \|
		\| \|
		+-------------------------------------------------------------------------------+
		\| MPI processes: 12 \|
		\| Device type: TNL::Devices::Host \|
		\| OMP enabled: no \|
		\| Real type: double \|
		\| Index type: int \|
		\| Mesh type:TNL::Meshes::Mesh<TNL::Meshes::DefaultConfig<TNL::Meshes::Topologies::Tetrahedron, 3, double, int, short>, TNL::Devices::Host> \|
		\| Sparse matrix:TNL::Matrices::SparseMatrix<double, TNL::Devices::Host, int, TNL::Matrices::GeneralMatrix, TNL::Algorithms::Segments::CSRLight, double, std::allocator<double>, std::allocator<int> > \|
		\| Mass lumping: disabled \|
		\| Material model: BrooksCorey \|
		\| Formulation: PwPn \|
		+-------------------------------------------------------------------------------+
		\| Host name: n11 \|
		\| System: Linux \|
		\| Release: 3.10.0-1127.13.1.el7.x86_64 \|
		\| Architecture: x86_64 \|
		\| TNL compiler: GNU G++ (10.2.0) \|
		\| CPU info \|
		\| Model name: Intel(R) Xeon(R) Gold 6136 CPU @ 3.00GHz \|
		\| Cores: 12 \|
		\| Threads per core: 2 \|
		\| Max clock rate (in MHz): 3001 \|
		\| Cache (L1d, L1i, L2, L3): 32, 32, 1024, 25344 \|
		+-------------------------------------------------------------------------------+
		\| Started at: Fri Jul 29 2022, 20:12:46 \|
		+-------------------------------------------------------------------------------+
		+-------------------------------------------------------------------------------+
		\| Finished at: Fri Jul 29 2022, 20:12:46 \|
		\| Total number of linear solver iterations: 355 \|
		\| Total number of time steps: 24 \|
		\| Number of time steps in which the preconditioner was updated: 2 \|
		\| Pre-iterate time: avg: 1.327222e-02 stddev: 3.870317e-03 min: 7.475905e-03 max: 1.959237e-02 \|
		\| nonlinear update time: avg: 2.094176e-03 stddev: 1.520214e-04 min: 1.926097e-03 max: 2.450871e-03 \|
		\| update_b time: avg: 2.100512e-03 stddev: 1.357080e-04 min: 1.829828e-03 max: 2.341923e-03 \|
		\| upwind update time: avg: 8.462911e-04 stddev: 4.918040e-05 min: 7.448410e-04 max: 9.340620e-04 \|
		\| upwind MPI synchronization time: avg: 7.158017e-03 stddev: 3.781009e-03 min: 1.206520e-03 max: 1.352675e-02 \|
		\| update_R time: avg: 4.121011e-04 stddev: 2.052028e-05 min: 3.794420e-04 max: 4.427780e-04 \|
		\| update_Q time: avg: 4.055774e-04 stddev: 2.112204e-05 min: 3.780560e-04 max: 4.429950e-04 \|
		\| model pre-iterate time: avg: 2.312175e-05 stddev: 5.434349e-07 min: 2.243800e-05 max: 2.406700e-05 \|
		\| Linear system assembler time: avg: 2.517975e-03 stddev: 1.950120e-04 min: 2.151005e-03 max: 2.802752e-03 \|
		\| Hypre matrix conversion time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| Hypre setup time: avg: 9.167852e-03 stddev: 1.133747e-04 min: 8.982092e-03 max: 9.403418e-03 \|
		\| Hypre solve time: avg: 1.377379e-01 stddev: 2.698516e-04 min: 1.372116e-01 max: 1.381316e-01 \|
		\| MPI synchronizations count: 0 \|
		\| MPI synchronization time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| async wait before start time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| async start time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| async wait time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| Post-iterate time: avg: 5.507078e-04 stddev: 2.262086e-05 min: 5.195300e-04 max: 5.978690e-04 \|
		\| Z_iF -> Z_iK update time: avg: 7.716208e-05 stddev: 3.189499e-06 min: 7.254800e-05 max: 8.368700e-05 \|
		\| velocities update time: avg: 3.520552e-04 stddev: 1.938576e-05 min: 3.264330e-04 max: 3.923350e-04 \|
		\| model post-iterate time: avg: 2.263892e-05 stddev: 3.215008e-07 min: 2.214800e-05 max: 2.341300e-05 \|
		\| MPI operations (included in the previous phases): \|
		\| MPI_Allreduce time: avg: 6.849431e-03 stddev: 4.053002e-03 min: 1.190520e-03 max: 1.576531e-02 \|
		\| Compute time: 0.162041 \|
		\| I/O time: 0.0654004 \|
		\| Total time: 0.268252 \|
		+-------------------------------------------------------------------------------+

Original line number	Diff line number	Diff line
		+-------------------------------------------------------------------------------+
		\| \|
		\| NumDwarf solver \|
		\| \|
		+-------------------------------------------------------------------------------+
		\| MPI processes: 1 \|
		\| Device type: TNL::Devices::Host \|
		\| OMP enabled: no \|
		\| Real type: double \|
		\| Index type: int \|
		\| Mesh type:TNL::Meshes::Mesh<TNL::Meshes::DefaultConfig<TNL::Meshes::Topologies::Tetrahedron, 3, double, int, short>, TNL::Devices::Host> \|
		\| Sparse matrix:TNL::Matrices::SparseMatrix<double, TNL::Devices::Host, int, TNL::Matrices::GeneralMatrix, TNL::Algorithms::Segments::CSRLight, double, std::allocator<double>, std::allocator<int> > \|
		\| Mass lumping: disabled \|
		\| Material model: BrooksCorey \|
		\| Formulation: PwPn \|
		+-------------------------------------------------------------------------------+
		\| Host name: n16 \|
		\| System: Linux \|
		\| Release: 3.10.0-1127.13.1.el7.x86_64 \|
		\| Architecture: x86_64 \|
		\| TNL compiler: GNU G++ (10.2.0) \|
		\| CPU info \|
		\| Model name: Intel(R) Xeon(R) Gold 6136 CPU @ 3.00GHz \|
		\| Cores: 12 \|
		\| Threads per core: 2 \|
		\| Max clock rate (in MHz): 3001 \|
		\| Cache (L1d, L1i, L2, L3): 32, 32, 1024, 25344 \|
		+-------------------------------------------------------------------------------+
		\| Started at: Fri Jul 29 2022, 20:13:07 \|
		+-------------------------------------------------------------------------------+
		+-------------------------------------------------------------------------------+
		\| Finished at: Fri Jul 29 2022, 20:13:07 \|
		\| Total number of linear solver iterations: 351 \|
		\| Total number of time steps: 24 \|
		\| Number of time steps in which the preconditioner was updated: 2 \|
		\| Pre-iterate time: avg: 4.930318e-02 stddev: 0.000000e+00 min: 4.930318e-02 max: 4.930318e-02 \|
		\| nonlinear update time: avg: 1.725292e-02 stddev: 0.000000e+00 min: 1.725292e-02 max: 1.725292e-02 \|
		\| update_b time: avg: 1.540224e-02 stddev: 0.000000e+00 min: 1.540224e-02 max: 1.540224e-02 \|
		\| upwind update time: avg: 9.500597e-03 stddev: 0.000000e+00 min: 9.500597e-03 max: 9.500597e-03 \|
		\| upwind MPI synchronization time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| update_R time: avg: 3.426872e-03 stddev: 0.000000e+00 min: 3.426872e-03 max: 3.426872e-03 \|
		\| update_Q time: avg: 3.423305e-03 stddev: 0.000000e+00 min: 3.423305e-03 max: 3.423305e-03 \|
		\| model pre-iterate time: avg: 2.461200e-05 stddev: 0.000000e+00 min: 2.461200e-05 max: 2.461200e-05 \|
		\| Linear system assembler time: avg: 2.796267e-02 stddev: 0.000000e+00 min: 2.796267e-02 max: 2.796267e-02 \|
		\| Hypre matrix conversion time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| Hypre setup time: avg: 1.124451e-02 stddev: 0.000000e+00 min: 1.124451e-02 max: 1.124451e-02 \|
		\| Hypre solve time: avg: 4.931529e-01 stddev: 0.000000e+00 min: 4.931529e-01 max: 4.931529e-01 \|
		\| Post-iterate time: avg: 3.499364e-03 stddev: 0.000000e+00 min: 3.499364e-03 max: 3.499364e-03 \|
		\| Z_iF -> Z_iK update time: avg: 4.951700e-04 stddev: 0.000000e+00 min: 4.951700e-04 max: 4.951700e-04 \|
		\| velocities update time: avg: 2.862900e-03 stddev: 0.000000e+00 min: 2.862900e-03 max: 2.862900e-03 \|
		\| model post-iterate time: avg: 2.453500e-05 stddev: 0.000000e+00 min: 2.453500e-05 max: 2.453500e-05 \|
		\| Compute time: 0.585421 \|
		\| I/O time: 0.0168328 \|
		\| Total time: 0.620314 \|
		+-------------------------------------------------------------------------------+

Original line number	Diff line number	Diff line
		+-------------------------------------------------------------------------------+
		\| \|
		\| NumDwarf solver \|
		\| \|
		+-------------------------------------------------------------------------------+
		\| MPI processes: 12 \|
		\| Device type: TNL::Devices::Host \|
		\| OMP enabled: no \|
		\| Real type: double \|
		\| Index type: int \|
		\| Mesh type:TNL::Meshes::Mesh<TNL::Meshes::DefaultConfig<TNL::Meshes::Topologies::Tetrahedron, 3, double, int, short>, TNL::Devices::Host> \|
		\| Sparse matrix:TNL::Matrices::SparseMatrix<double, TNL::Devices::Host, int, TNL::Matrices::GeneralMatrix, TNL::Algorithms::Segments::CSRLight, double, std::allocator<double>, std::allocator<int> > \|
		\| Mass lumping: disabled \|
		\| Material model: BrooksCorey \|
		\| Formulation: PwPn \|
		+-------------------------------------------------------------------------------+
		\| Host name: n11 \|
		\| System: Linux \|
		\| Release: 3.10.0-1127.13.1.el7.x86_64 \|
		\| Architecture: x86_64 \|
		\| TNL compiler: GNU G++ (10.2.0) \|
		\| CPU info \|
		\| Model name: Intel(R) Xeon(R) Gold 6136 CPU @ 3.00GHz \|
		\| Cores: 12 \|
		\| Threads per core: 2 \|
		\| Max clock rate (in MHz): 3001 \|
		\| Cache (L1d, L1i, L2, L3): 32, 32, 1024, 25344 \|
		+-------------------------------------------------------------------------------+
		\| Started at: Fri Jul 29 2022, 20:12:46 \|
		+-------------------------------------------------------------------------------+
		+-------------------------------------------------------------------------------+
		\| Finished at: Fri Jul 29 2022, 20:12:46 \|
		\| Total number of linear solver iterations: 355 \|
		\| Total number of time steps: 24 \|
		\| Number of time steps in which the preconditioner was updated: 2 \|
		\| Pre-iterate time: avg: 1.327222e-02 stddev: 3.870317e-03 min: 7.475905e-03 max: 1.959237e-02 \|
		\| nonlinear update time: avg: 2.094176e-03 stddev: 1.520214e-04 min: 1.926097e-03 max: 2.450871e-03 \|
		\| update_b time: avg: 2.100512e-03 stddev: 1.357080e-04 min: 1.829828e-03 max: 2.341923e-03 \|
		\| upwind update time: avg: 8.462911e-04 stddev: 4.918040e-05 min: 7.448410e-04 max: 9.340620e-04 \|
		\| upwind MPI synchronization time: avg: 7.158017e-03 stddev: 3.781009e-03 min: 1.206520e-03 max: 1.352675e-02 \|
		\| update_R time: avg: 4.121011e-04 stddev: 2.052028e-05 min: 3.794420e-04 max: 4.427780e-04 \|
		\| update_Q time: avg: 4.055774e-04 stddev: 2.112204e-05 min: 3.780560e-04 max: 4.429950e-04 \|
		\| model pre-iterate time: avg: 2.312175e-05 stddev: 5.434349e-07 min: 2.243800e-05 max: 2.406700e-05 \|
		\| Linear system assembler time: avg: 2.517975e-03 stddev: 1.950120e-04 min: 2.151005e-03 max: 2.802752e-03 \|
		\| Hypre matrix conversion time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| Hypre setup time: avg: 9.167852e-03 stddev: 1.133747e-04 min: 8.982092e-03 max: 9.403418e-03 \|
		\| Hypre solve time: avg: 1.377379e-01 stddev: 2.698516e-04 min: 1.372116e-01 max: 1.381316e-01 \|
		\| MPI synchronizations count: 0 \|
		\| MPI synchronization time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| async wait before start time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| async start time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| async wait time: avg: 0.000000e+00 stddev: 0.000000e+00 min: 0.000000e+00 max: 0.000000e+00 \|
		\| Post-iterate time: avg: 5.507078e-04 stddev: 2.262086e-05 min: 5.195300e-04 max: 5.978690e-04 \|
		\| Z_iF -> Z_iK update time: avg: 7.716208e-05 stddev: 3.189499e-06 min: 7.254800e-05 max: 8.368700e-05 \|
		\| velocities update time: avg: 3.520552e-04 stddev: 1.938576e-05 min: 3.264330e-04 max: 3.923350e-04 \|
		\| model post-iterate time: avg: 2.263892e-05 stddev: 3.215008e-07 min: 2.214800e-05 max: 2.341300e-05 \|
		\| MPI operations (included in the previous phases): \|
		\| MPI_Allreduce time: avg: 6.849431e-03 stddev: 4.053002e-03 min: 1.190520e-03 max: 1.576531e-02 \|
		\| Compute time: 0.162041 \|
		\| I/O time: 0.0654004 \|
		\| Total time: 0.268252 \|
		+-------------------------------------------------------------------------------+