Develop

.github/release_steps.md

@@ -110,7 +110,7 @@ git clone -b release --depth 10 https://github.com/lammps/lammps.git lammps-rele
 cmake -S lammps-release/cmake -B build-release -G Ninja -D CMAKE_INSTALL_PREFIX=$PWD/lammps-static -D CMAKE_TOOLCHAIN_FILE=/usr/musl/share/cmake/linux-musl.cmake -C lammps-release/cmake/presets/most.cmake -C lammps-release/cmake/presets/kokkos-openmp.cmake -D DOWNLOAD_POTENTIALS=OFF -D BUILD_MPI=OFF -D BUILD_TESTING=OFF -D CMAKE_BUILD_TYPE=Release -D PKG_ATC=ON -D PKG_AWPMD=ON -D PKG_MANIFOLD=ON -D PKG_MESONT=ON -D PKG_MGPT=ON -D PKG_ML-PACE=ON -D PKG_ML-RANN=ON -D PKG_MOLFILE=ON -D PKG_PTM=ON -D PKG_QTB=ON -D PKG_SMTBQ=ON
 cmake --build build-release --target all
 cmake --build build-release --target install
-/usr/musl/bin/x86_64-linux-musl-strip lammps-static/bin/*
+/usr/musl/bin/x86_64-linux-musl-strip -g lammps-static/bin/*
 tar -czvvf ../lammps-linux-x86_64-4Feb2025.tar.gz lammps-static
 exit # fedora 41 container
 cd ..

.github/workflows/check-cpp23.yml

@@ -55,8 +55,8 @@ jobs:
       uses: actions/cache@v4
       with:
         path: ${{ env.CCACHE_DIR }}
-        key: linux-cpp23-ccache-${{ github.sha }}
-        restore-keys: linux-cpp23-ccache-
+        key: linux-cpp23-ccache-${{ matrix.idx }}-${{ github.sha }}
+        restore-keys: linux-cpp23-ccache-${{ matrix.idx }}
 
     - name: Building LAMMPS via CMake
       shell: bash

bench/log.15Jul25.chain.fixed.g++.1

@@ -0,0 +1,95 @@
+LAMMPS (12 Jun 2025 - Development - patch_12Jun2025-808-g67067cbc80)
+  using 1 OpenMP thread(s) per MPI task
+# FENE beadspring benchmark
+
+units           lj
+atom_style      bond
+special_bonds   fene
+
+read_data       data.chain
+Reading data file ...
+  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
+  1 by 1 by 1 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+  scanning bonds ...
+  1 = max bonds/atom
+  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
+  1 by 1 by 1 MPI processor grid
+  reading bonds ...
+  31680 bonds
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0        1        1       
+  special bond factors coul:  0        1        1       
+     2 = max # of 1-2 neighbors
+     2 = max # of special neighbors
+  special bonds CPU = 0.002 seconds
+  read_data CPU = 0.098 seconds
+
+neighbor        0.4 bin
+neigh_modify    every 1 delay 1
+
+bond_style      fene
+bond_coeff      1 30.0 1.5 1.0 1.0
+
+pair_style      lj/cut 1.12
+pair_modify     shift yes
+pair_coeff      1 1 1.0 1.0 1.12
+
+fix             1 all nve
+fix             2 all langevin 1.0 1.0 10.0 904297
+
+thermo          100
+timestep        0.012
+
+run             100
+Generated 0 of 0 mixed pair_coeff terms from geometric mixing rule
+WARNING: Communication cutoff 1.52 is shorter than a bond length based estimate of 1.855. This may lead to errors. (src/comm.cpp:743)
+Neighbor list info ...
+  update: every = 1 steps, delay = 1 steps, check = yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.52
+  ghost atom cutoff = 1.52
+  binsize = 0.76, bins = 45 45 45
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair lj/cut, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/3d
+      bin: standard
+WARNING: Communication cutoff 1.52 is shorter than a bond length based estimate of 1.855. This may lead to errors. (src/comm.cpp:743)
+Per MPI rank memory allocation (min/avg/max) = 13.2 | 13.2 | 13.2 Mbytes
+   Step          Temp          E_pair         E_mol          TotEng         Press     
+         0   0.97029772     0.44484087     20.494523      22.394765      4.6721833    
+       100   0.9729966      0.4361122      20.507698      22.40326       4.6548819    
+Loop time of 0.531 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 195254.376 tau/day, 188.324 timesteps/s, 6.026 Matom-step/s
+99.6% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.092788   | 0.092788   | 0.092788   |   0.0 | 17.47
+Bond    | 0.021754   | 0.021754   | 0.021754   |   0.0 |  4.10
+Neigh   | 0.27771    | 0.27771    | 0.27771    |   0.0 | 52.30
+Comm    | 0.0088421  | 0.0088421  | 0.0088421  |   0.0 |  1.67
+Output  | 9.1455e-05 | 9.1455e-05 | 9.1455e-05 |   0.0 |  0.02
+Modify  | 0.12461    | 0.12461    | 0.12461    |   0.0 | 23.47
+Other   |            | 0.005205   |            |       |  0.98
+
+Nlocal:          32000 ave       32000 max       32000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:           9493 ave        9493 max        9493 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:         155873 ave      155873 max      155873 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 155873
+Ave neighs/atom = 4.8710312
+Ave special neighs/atom = 1.98
+Neighbor list builds = 25
+Dangerous builds = 0
+Total wall time: 0:00:00

bench/log.15Jul25.chain.fixed.g++.4

@@ -0,0 +1,95 @@
+LAMMPS (12 Jun 2025 - Development - patch_12Jun2025-808-g67067cbc80)
+  using 1 OpenMP thread(s) per MPI task
+# FENE beadspring benchmark
+
+units           lj
+atom_style      bond
+special_bonds   fene
+
+read_data       data.chain
+Reading data file ...
+  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
+  1 by 2 by 2 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+  scanning bonds ...
+  1 = max bonds/atom
+  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
+  1 by 2 by 2 MPI processor grid
+  reading bonds ...
+  31680 bonds
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0        1        1       
+  special bond factors coul:  0        1        1       
+     2 = max # of 1-2 neighbors
+     2 = max # of special neighbors
+  special bonds CPU = 0.001 seconds
+  read_data CPU = 0.081 seconds
+
+neighbor        0.4 bin
+neigh_modify    every 1 delay 1
+
+bond_style      fene
+bond_coeff      1 30.0 1.5 1.0 1.0
+
+pair_style      lj/cut 1.12
+pair_modify     shift yes
+pair_coeff      1 1 1.0 1.0 1.12
+
+fix             1 all nve
+fix             2 all langevin 1.0 1.0 10.0 904297
+
+thermo          100
+timestep        0.012
+
+run             100
+Generated 0 of 0 mixed pair_coeff terms from geometric mixing rule
+WARNING: Communication cutoff 1.52 is shorter than a bond length based estimate of 1.855. This may lead to errors. (src/comm.cpp:743)
+Neighbor list info ...
+  update: every = 1 steps, delay = 1 steps, check = yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.52
+  ghost atom cutoff = 1.52
+  binsize = 0.76, bins = 45 45 45
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair lj/cut, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/3d
+      bin: standard
+WARNING: Communication cutoff 1.52 is shorter than a bond length based estimate of 1.855. This may lead to errors. (src/comm.cpp:743)
+Per MPI rank memory allocation (min/avg/max) = 4.779 | 4.78 | 4.78 Mbytes
+   Step          Temp          E_pair         E_mol          TotEng         Press     
+         0   0.97029772     0.44484087     20.494523      22.394765      4.6721833    
+       100   0.97145835     0.43803883     20.502691      22.397872      4.626988     
+Loop time of 0.141838 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 730973.705 tau/day, 705.029 timesteps/s, 22.561 Matom-step/s
+99.6% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.023828   | 0.023917   | 0.024042   |   0.1 | 16.86
+Bond    | 0.0054718  | 0.0055341  | 0.0056027  |   0.1 |  3.90
+Neigh   | 0.072672   | 0.07269    | 0.072704   |   0.0 | 51.25
+Comm    | 0.0057901  | 0.00599    | 0.006123   |   0.2 |  4.22
+Output  | 3.2532e-05 | 4.1552e-05 | 5.0617e-05 |   0.0 |  0.03
+Modify  | 0.031418   | 0.031534   | 0.031657   |   0.0 | 22.23
+Other   |            | 0.002133   |            |       |  1.50
+
+Nlocal:           8000 ave        8030 max        7974 min
+Histogram: 1 0 0 1 0 1 0 0 0 1
+Nghost:           4177 ave        4191 max        4160 min
+Histogram: 1 0 0 0 1 0 0 1 0 1
+Neighs:        38995.8 ave       39169 max       38852 min
+Histogram: 1 0 0 1 1 0 0 0 0 1
+
+Total # of neighbors = 155983
+Ave neighs/atom = 4.8744688
+Ave special neighs/atom = 1.98
+Neighbor list builds = 25
+Dangerous builds = 0
+Total wall time: 0:00:00

bench/log.15Jul25.chain.scaled.g++.4

@@ -0,0 +1,95 @@
+LAMMPS (12 Jun 2025 - Development - patch_12Jun2025-784-g8c564460e6-modified)
+  using 1 OpenMP thread(s) per MPI task
+# FENE beadspring benchmark
+
+units           lj
+atom_style      bond
+special_bonds   fene
+
+read_data       data.chain
+Reading data file ...
+  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
+  1 by 2 by 2 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+  scanning bonds ...
+  1 = max bonds/atom
+  orthogonal box = (-16.796 -16.796 -16.796) to (16.796 16.796 16.796)
+  1 by 2 by 2 MPI processor grid
+  reading bonds ...
+  31680 bonds
+Finding 1-2 1-3 1-4 neighbors ...
+  special bond factors lj:    0        1        1       
+  special bond factors coul:  0        1        1       
+     2 = max # of 1-2 neighbors
+     2 = max # of special neighbors
+  special bonds CPU = 0.001 seconds
+  read_data CPU = 0.085 seconds
+
+neighbor        0.4 bin
+neigh_modify    every 1 delay 1
+
+bond_style      fene
+bond_coeff      1 30.0 1.5 1.0 1.0
+
+pair_style      lj/cut 1.12
+pair_modify     shift yes
+pair_coeff      1 1 1.0 1.0 1.12
+
+fix             1 all nve
+fix             2 all langevin 1.0 1.0 10.0 904297
+
+thermo          100
+timestep        0.012
+
+run             100
+Generated 0 of 0 mixed pair_coeff terms from geometric mixing rule
+WARNING: Communication cutoff 1.52 is shorter than a bond length based estimate of 1.855. This may lead to errors. (src/comm.cpp:743)
+Neighbor list info ...
+  update: every = 1 steps, delay = 1 steps, check = yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.52
+  ghost atom cutoff = 1.52
+  binsize = 0.76, bins = 45 45 45
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair lj/cut, perpetual
+      attributes: half, newton on
+      pair build: half/bin/newton
+      stencil: half/bin/3d
+      bin: standard
+WARNING: Communication cutoff 1.52 is shorter than a bond length based estimate of 1.855. This may lead to errors. (src/comm.cpp:743)
+Per MPI rank memory allocation (min/avg/max) = 4.779 | 4.78 | 4.78 Mbytes
+   Step          Temp          E_pair         E_mol          TotEng         Press     
+         0   0.97029772     0.44484087     20.494523      22.394765      4.6721833    
+       100   0.97145835     0.43803883     20.502691      22.397872      4.626988     
+Loop time of 0.14297 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 725185.191 tau/day, 699.446 timesteps/s, 22.382 Matom-step/s
+99.5% CPU use with 4 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.023853   | 0.023965   | 0.02413    |   0.1 | 16.76
+Bond    | 0.0054567  | 0.0055557  | 0.0056918  |   0.1 |  3.89
+Neigh   | 0.073792   | 0.073802   | 0.073811   |   0.0 | 51.62
+Comm    | 0.0055967  | 0.0059012  | 0.0060867  |   0.3 |  4.13
+Output  | 3.2282e-05 | 3.7126e-05 | 4.2381e-05 |   0.0 |  0.03
+Modify  | 0.031379   | 0.03148    | 0.031647   |   0.1 | 22.02
+Other   |            | 0.002229   |            |       |  1.56
+
+Nlocal:           8000 ave        8030 max        7974 min
+Histogram: 1 0 0 1 0 1 0 0 0 1
+Nghost:           4177 ave        4191 max        4160 min
+Histogram: 1 0 0 0 1 0 0 1 0 1
+Neighs:        38995.8 ave       39169 max       38852 min
+Histogram: 1 0 0 1 1 0 0 0 0 1
+
+Total # of neighbors = 155983
+Ave neighs/atom = 4.8744688
+Ave special neighs/atom = 1.98
+Neighbor list builds = 25
+Dangerous builds = 0
+Total wall time: 0:00:00

bench/log.15Jul25.chute.fixed.g++.1

@@ -0,0 +1,89 @@
+LAMMPS (12 Jun 2025 - Development - patch_12Jun2025-808-g67067cbc80)
+  using 1 OpenMP thread(s) per MPI task
+# LAMMPS benchmark of granular flow
+# chute flow of 32000 atoms with frozen base at 26 degrees
+
+units           lj
+atom_style      sphere
+boundary        p p fs
+newton          off
+comm_modify     vel yes
+
+read_data       data.chute
+Reading data file ...
+  orthogonal box = (0 0 0) to (40 20 37.2886)
+  1 by 1 by 1 MPI processor grid
+  reading atoms ...
+  32000 atoms
+  reading velocities ...
+  32000 velocities
+  read_data CPU = 0.102 seconds
+
+pair_style      gran/hooke/history 200000.0 NULL 50.0 NULL 0.5 0
+pair_coeff      * *
+
+neighbor        0.1 bin
+neigh_modify    every 1 delay 0
+
+timestep        0.0001
+
+group           bottom type 2
+912 atoms in group bottom
+group           active subtract all bottom
+31088 atoms in group active
+neigh_modify    exclude group bottom bottom
+
+fix             1 all gravity 1.0 chute 26.0
+fix             2 bottom freeze
+fix             3 active nve/sphere
+
+compute         1 all erotate/sphere
+thermo_style    custom step atoms ke c_1 vol
+thermo_modify   norm no
+thermo          100
+
+run             100
+Generated 0 of 1 mixed pair_coeff terms from geometric mixing rule
+Neighbor list info ...
+  update: every = 1 steps, delay = 0 steps, check = yes
+  max neighbors/atom: 2000, page size: 100000
+  master list distance cutoff = 1.1
+  ghost atom cutoff = 1.1
+  binsize = 0.55, bins = 73 37 68
+  1 neighbor lists, perpetual/occasional/extra = 1 0 0
+  (1) pair gran/hooke/history, perpetual
+      attributes: half, newton off, size, history
+      pair build: half/size/bin/atomonly/newtoff
+      stencil: full/bin/3d
+      bin: standard
+Per MPI rank memory allocation (min/avg/max) = 23.37 | 23.37 | 23.37 Mbytes
+   Step        Atoms        KinEng          c_1           Volume    
+         0       32000   784139.13      1601.1263      29833.783    
+       100       32000   784292.08      1571.0968      29834.707    
+Loop time of 0.155391 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 5560.184 tau/day, 643.540 timesteps/s, 20.593 Matom-step/s
+99.6% CPU use with 1 MPI tasks x 1 OpenMP threads
+
+MPI task timing breakdown:
+Section |  min time  |  avg time  |  max time  |%varavg| %total
+---------------------------------------------------------------
+Pair    | 0.099082   | 0.099082   | 0.099082   |   0.0 | 63.76
+Neigh   | 0.013743   | 0.013743   | 0.013743   |   0.0 |  8.84
+Comm    | 0.0042572  | 0.0042572  | 0.0042572  |   0.0 |  2.74
+Output  | 0.00017358 | 0.00017358 | 0.00017358 |   0.0 |  0.11
+Modify  | 0.033446   | 0.033446   | 0.033446   |   0.0 | 21.52
+Other   |            | 0.00469    |            |       |  3.02
+
+Nlocal:          32000 ave       32000 max       32000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost:           5463 ave        5463 max        5463 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs:         115133 ave      115133 max      115133 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 115133
+Ave neighs/atom = 3.5979062
+Neighbor list builds = 2
+Dangerous builds = 0
+Total wall time: 0:00:00