diff --git a/bench/log.15Feb16.chain.fixed.icc.1 b/bench/log.15Feb16.chain.fixed.icc.1
new file mode 100644
index 0000000000000000000000000000000000000000..553241bf228f9d75fecf4648baa018251f9fd808
--- /dev/null
+++ b/bench/log.15Feb16.chain.fixed.icc.1
@@ -0,0 +1,78 @@
+LAMMPS (15 Feb 2016)
+# FENE beadspring benchmark
+
+units lj
+atom_style bond
+special_bonds fene
+
+read_data data.chain
+ 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
+ reading bonds ...
+ 31680 bonds
+ 2 = max # of 1-2 neighbors
+ 2 = max # of special neighbors
+
+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
+Neighbor list info ...
+ 1 neighbor list requests
+ 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
+Memory usage per processor = 11.5189 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 0.978585 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 105948.895 tau/day, 102.188 timesteps/s
+100.0% CPU use with 1 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 0.19562 | 0.19562 | 0.19562 | 0.0 | 19.99
+Bond | 0.087475 | 0.087475 | 0.087475 | 0.0 | 8.94
+Neigh | 0.44861 | 0.44861 | 0.44861 | 0.0 | 45.84
+Comm | 0.032932 | 0.032932 | 0.032932 | 0.0 | 3.37
+Output | 0.00010395 | 0.00010395 | 0.00010395 | 0.0 | 0.01
+Modify | 0.19413 | 0.19413 | 0.19413 | 0.0 | 19.84
+Other | | 0.01972 | | | 2.02
+
+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 = 4.87103
+Ave special neighs/atom = 1.98
+Neighbor list builds = 25
+Dangerous builds = 0
+Total wall time: 0:00:01
diff --git a/bench/log.15Feb16.chain.fixed.icc.4 b/bench/log.15Feb16.chain.fixed.icc.4
new file mode 100644
index 0000000000000000000000000000000000000000..1ff445b27a153b43e0fb97a7f8cb6f6c1721a4e8
--- /dev/null
+++ b/bench/log.15Feb16.chain.fixed.icc.4
@@ -0,0 +1,78 @@
+LAMMPS (15 Feb 2016)
+# FENE beadspring benchmark
+
+units lj
+atom_style bond
+special_bonds fene
+
+read_data data.chain
+ 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
+ reading bonds ...
+ 31680 bonds
+ 2 = max # of 1-2 neighbors
+ 2 = max # of special neighbors
+
+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
+Neighbor list info ...
+ 1 neighbor list requests
+ 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
+Memory usage per processor = 3.91518 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 0.271187 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 382319.453 tau/day, 368.749 timesteps/s
+99.6% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 0.048621 | 0.050076 | 0.051229 | 0.4 | 18.47
+Bond | 0.022254 | 0.022942 | 0.023567 | 0.3 | 8.46
+Neigh | 0.11873 | 0.11881 | 0.11887 | 0.0 | 43.81
+Comm | 0.019066 | 0.021357 | 0.024297 | 1.3 | 7.88
+Output | 5.0068e-05 | 5.5015e-05 | 6.1035e-05 | 0.1 | 0.02
+Modify | 0.048737 | 0.050198 | 0.051231 | 0.4 | 18.51
+Other | | 0.007751 | | | 2.86
+
+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 = 4.87447
+Ave special neighs/atom = 1.98
+Neighbor list builds = 25
+Dangerous builds = 0
+Total wall time: 0:00:00
diff --git a/bench/log.15Feb16.chain.scaled.icc.4 b/bench/log.15Feb16.chain.scaled.icc.4
new file mode 100644
index 0000000000000000000000000000000000000000..df541d404ce816d8b225ada75ff62ed542fbcd05
--- /dev/null
+++ b/bench/log.15Feb16.chain.scaled.icc.4
@@ -0,0 +1,94 @@
+LAMMPS (15 Feb 2016)
+# FENE beadspring benchmark
+
+variable x index 1
+variable y index 1
+variable z index 1
+
+units lj
+atom_style bond
+atom_modify map hash
+special_bonds fene
+
+read_data data.chain
+ 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
+ reading bonds ...
+ 31680 bonds
+ 2 = max # of 1-2 neighbors
+ 2 = max # of special neighbors
+
+replicate $x $y $z
+replicate 2 $y $z
+replicate 2 2 $z
+replicate 2 2 1
+ orthogonal box = (-16.796 -16.796 -16.796) to (50.388 50.388 16.796)
+ 2 by 2 by 1 MPI processor grid
+ 128000 atoms
+ 126720 bonds
+ 2 = max # of 1-2 neighbors
+ 2 = max # of special neighbors
+
+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
+Neighbor list info ...
+ 1 neighbor list requests
+ 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 = 89 89 45
+Memory usage per processor = 12.8735 Mbytes
+Step Temp E_pair E_mol TotEng Press
+ 0 0.97027498 0.44484087 20.494523 22.394765 4.6721833
+ 100 0.97682955 0.44239968 20.500229 22.407862 4.6527025
+Loop time of 1.20889 on 4 procs for 100 steps with 128000 atoms
+
+Performance: 85764.410 tau/day, 82.720 timesteps/s
+99.8% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 0.21738 | 0.23306 | 0.23926 | 1.9 | 19.28
+Bond | 0.094536 | 0.10196 | 0.10534 | 1.4 | 8.43
+Neigh | 0.52311 | 0.52392 | 0.52519 | 0.1 | 43.34
+Comm | 0.090161 | 0.10022 | 0.12557 | 4.7 | 8.29
+Output | 0.00012207 | 0.00017327 | 0.00019598 | 0.2 | 0.01
+Modify | 0.19662 | 0.20262 | 0.20672 | 0.8 | 16.76
+Other | | 0.04694 | | | 3.88
+
+Nlocal: 32000 ave 32015 max 31983 min
+Histogram: 1 0 1 0 0 0 0 0 1 1
+Nghost: 9492 ave 9522 max 9432 min
+Histogram: 1 0 0 0 0 0 1 0 0 2
+Neighs: 155837 ave 156079 max 155506 min
+Histogram: 1 0 0 0 0 1 0 0 1 1
+
+Total # of neighbors = 623349
+Ave neighs/atom = 4.86991
+Ave special neighs/atom = 1.98
+Neighbor list builds = 25
+Dangerous builds = 0
+Total wall time: 0:00:01
diff --git a/bench/log.15Feb16.chute.fixed.icc.1 b/bench/log.15Feb16.chute.fixed.icc.1
new file mode 100644
index 0000000000000000000000000000000000000000..e256524152f4c7c02f6781c566c75f3f8e226a52
--- /dev/null
+++ b/bench/log.15Feb16.chute.fixed.icc.1
@@ -0,0 +1,80 @@
+LAMMPS (15 Feb 2016)
+# 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
+ 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
+
+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
+Neighbor list info ...
+ 2 neighbor list requests
+ 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
+Memory usage per processor = 15.567 Mbytes
+Step Atoms KinEng 1 Volume
+ 0 32000 784139.13 1601.1263 29833.783
+ 100 32000 784292.08 1571.0968 29834.707
+Loop time of 0.550482 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 1569.534 tau/day, 181.659 timesteps/s
+100.1% CPU use with 1 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 0.33849 | 0.33849 | 0.33849 | 0.0 | 61.49
+Neigh | 0.040353 | 0.040353 | 0.040353 | 0.0 | 7.33
+Comm | 0.018023 | 0.018023 | 0.018023 | 0.0 | 3.27
+Output | 0.00020385 | 0.00020385 | 0.00020385 | 0.0 | 0.04
+Modify | 0.13155 | 0.13155 | 0.13155 | 0.0 | 23.90
+Other | | 0.02186 | | | 3.97
+
+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 = 3.59791
+Neighbor list builds = 2
+Dangerous builds = 0
+Total wall time: 0:00:00
diff --git a/bench/log.15Feb16.chute.fixed.icc.4 b/bench/log.15Feb16.chute.fixed.icc.4
new file mode 100644
index 0000000000000000000000000000000000000000..8252408833fc32372a068751c7c440fc230a214f
--- /dev/null
+++ b/bench/log.15Feb16.chute.fixed.icc.4
@@ -0,0 +1,80 @@
+LAMMPS (15 Feb 2016)
+# 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
+ orthogonal box = (0 0 0) to (40 20 37.2886)
+ 2 by 1 by 2 MPI processor grid
+ reading atoms ...
+ 32000 atoms
+ reading velocities ...
+ 32000 velocities
+
+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
+Neighbor list info ...
+ 2 neighbor list requests
+ 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
+Memory usage per processor = 6.81783 Mbytes
+Step Atoms KinEng 1 Volume
+ 0 32000 784139.13 1601.1263 29833.783
+ 100 32000 784292.08 1571.0968 29834.707
+Loop time of 0.13141 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 6574.833 tau/day, 760.976 timesteps/s
+99.3% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 0.062505 | 0.067 | 0.07152 | 1.5 | 50.99
+Neigh | 0.010041 | 0.0101 | 0.010178 | 0.1 | 7.69
+Comm | 0.012347 | 0.012895 | 0.013444 | 0.5 | 9.81
+Output | 6.3896e-05 | 0.00010294 | 0.00014091 | 0.3 | 0.08
+Modify | 0.031802 | 0.032348 | 0.032897 | 0.3 | 24.62
+Other | | 0.008965 | | | 6.82
+
+Nlocal: 8000 ave 8008 max 7992 min
+Histogram: 2 0 0 0 0 0 0 0 0 2
+Nghost: 2439 ave 2450 max 2428 min
+Histogram: 2 0 0 0 0 0 0 0 0 2
+Neighs: 29500.5 ave 30488 max 28513 min
+Histogram: 2 0 0 0 0 0 0 0 0 2
+
+Total # of neighbors = 118002
+Ave neighs/atom = 3.68756
+Neighbor list builds = 2
+Dangerous builds = 0
+Total wall time: 0:00:00
diff --git a/bench/log.15Feb16.chute.scaled.icc.4 b/bench/log.15Feb16.chute.scaled.icc.4
new file mode 100644
index 0000000000000000000000000000000000000000..0b9807a4477f1c14f94680d0c740434dc90542f0
--- /dev/null
+++ b/bench/log.15Feb16.chute.scaled.icc.4
@@ -0,0 +1,90 @@
+LAMMPS (15 Feb 2016)
+# LAMMPS benchmark of granular flow
+# chute flow of 32000 atoms with frozen base at 26 degrees
+
+variable x index 1
+variable y index 1
+
+units lj
+atom_style sphere
+boundary p p fs
+newton off
+comm_modify vel yes
+
+read_data data.chute
+ orthogonal box = (0 0 0) to (40 20 37.2886)
+ 2 by 1 by 2 MPI processor grid
+ reading atoms ...
+ 32000 atoms
+ reading velocities ...
+ 32000 velocities
+
+replicate $x $y 1
+replicate 2 $y 1
+replicate 2 2 1
+ orthogonal box = (0 0 0) to (80 40 37.2922)
+ 2 by 2 by 1 MPI processor grid
+ 128000 atoms
+
+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
+3648 atoms in group bottom
+group active subtract all bottom
+124352 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
+Neighbor list info ...
+ 2 neighbor list requests
+ 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 = 146 73 68
+Memory usage per processor = 15.7007 Mbytes
+Step Atoms KinEng 1 Volume
+ 0 128000 3136556.5 6404.5051 119335.13
+ 100 128000 3137168.3 6284.3873 119338.83
+Loop time of 0.906913 on 4 procs for 100 steps with 128000 atoms
+
+Performance: 952.683 tau/day, 110.264 timesteps/s
+99.7% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 0.51454 | 0.53094 | 0.55381 | 2.0 | 58.54
+Neigh | 0.042597 | 0.043726 | 0.045801 | 0.6 | 4.82
+Comm | 0.063027 | 0.064657 | 0.067367 | 0.7 | 7.13
+Output | 0.00024891 | 0.00059718 | 0.00086498 | 1.0 | 0.07
+Modify | 0.16508 | 0.17656 | 0.1925 | 2.6 | 19.47
+Other | | 0.09043 | | | 9.97
+
+Nlocal: 32000 ave 32000 max 32000 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+Nghost: 5463 ave 5463 max 5463 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+Neighs: 115133 ave 115133 max 115133 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 460532
+Ave neighs/atom = 3.59791
+Neighbor list builds = 2
+Dangerous builds = 0
+Total wall time: 0:00:01
diff --git a/bench/log.15Feb16.eam.fixed.icc.1 b/bench/log.15Feb16.eam.fixed.icc.1
new file mode 100644
index 0000000000000000000000000000000000000000..0408d2c8d71defc739ae1268cf5611ec80e1f092
--- /dev/null
+++ b/bench/log.15Feb16.eam.fixed.icc.1
@@ -0,0 +1,83 @@
+LAMMPS (15 Feb 2016)
+# bulk Cu lattice
+
+variable x index 1
+variable y index 1
+variable z index 1
+
+variable xx equal 20*$x
+variable xx equal 20*1
+variable yy equal 20*$y
+variable yy equal 20*1
+variable zz equal 20*$z
+variable zz equal 20*1
+
+units metal
+atom_style atomic
+
+lattice fcc 3.615
+Lattice spacing in x,y,z = 3.615 3.615 3.615
+region box block 0 ${xx} 0 ${yy} 0 ${zz}
+region box block 0 20 0 ${yy} 0 ${zz}
+region box block 0 20 0 20 0 ${zz}
+region box block 0 20 0 20 0 20
+create_box 1 box
+Created orthogonal box = (0 0 0) to (72.3 72.3 72.3)
+ 1 by 1 by 1 MPI processor grid
+create_atoms 1 box
+Created 32000 atoms
+
+pair_style eam
+pair_coeff 1 1 Cu_u3.eam
+Reading potential file Cu_u3.eam with DATE: 2007-06-11
+
+velocity all create 1600.0 376847 loop geom
+
+neighbor 1.0 bin
+neigh_modify every 1 delay 5 check yes
+
+fix 1 all nve
+
+timestep 0.005
+thermo 50
+
+run 100
+Neighbor list info ...
+ 1 neighbor list requests
+ update every 1 steps, delay 5 steps, check yes
+ max neighbors/atom: 2000, page size: 100000
+ master list distance cutoff = 5.95
+ ghost atom cutoff = 5.95
+ binsize = 2.975 -> bins = 25 25 25
+Memory usage per processor = 10.2238 Mbytes
+Step Temp E_pair E_mol TotEng Press
+ 0 1600 -113280 0 -106662.09 18703.573
+ 50 781.69049 -109873.35 0 -106640.13 52273.088
+ 100 801.832 -109957.3 0 -106640.77 51322.821
+Loop time of 5.90097 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 7.321 ns/day, 3.278 hours/ns, 16.946 timesteps/s
+99.9% CPU use with 1 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 5.2121 | 5.2121 | 5.2121 | 0.0 | 88.33
+Neigh | 0.58212 | 0.58212 | 0.58212 | 0.0 | 9.86
+Comm | 0.030392 | 0.030392 | 0.030392 | 0.0 | 0.52
+Output | 0.00023389 | 0.00023389 | 0.00023389 | 0.0 | 0.00
+Modify | 0.060871 | 0.060871 | 0.060871 | 0.0 | 1.03
+Other | | 0.01527 | | | 0.26
+
+Nlocal: 32000 ave 32000 max 32000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost: 19909 ave 19909 max 19909 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs: 1.20778e+06 ave 1.20778e+06 max 1.20778e+06 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 1207784
+Ave neighs/atom = 37.7433
+Neighbor list builds = 13
+Dangerous builds = 0
+Total wall time: 0:00:06
diff --git a/bench/log.15Feb16.eam.fixed.icc.4 b/bench/log.15Feb16.eam.fixed.icc.4
new file mode 100644
index 0000000000000000000000000000000000000000..6a7c47a58b3fc4cf0076387b89bc685ac6138e66
--- /dev/null
+++ b/bench/log.15Feb16.eam.fixed.icc.4
@@ -0,0 +1,83 @@
+LAMMPS (15 Feb 2016)
+# bulk Cu lattice
+
+variable x index 1
+variable y index 1
+variable z index 1
+
+variable xx equal 20*$x
+variable xx equal 20*1
+variable yy equal 20*$y
+variable yy equal 20*1
+variable zz equal 20*$z
+variable zz equal 20*1
+
+units metal
+atom_style atomic
+
+lattice fcc 3.615
+Lattice spacing in x,y,z = 3.615 3.615 3.615
+region box block 0 ${xx} 0 ${yy} 0 ${zz}
+region box block 0 20 0 ${yy} 0 ${zz}
+region box block 0 20 0 20 0 ${zz}
+region box block 0 20 0 20 0 20
+create_box 1 box
+Created orthogonal box = (0 0 0) to (72.3 72.3 72.3)
+ 1 by 2 by 2 MPI processor grid
+create_atoms 1 box
+Created 32000 atoms
+
+pair_style eam
+pair_coeff 1 1 Cu_u3.eam
+Reading potential file Cu_u3.eam with DATE: 2007-06-11
+
+velocity all create 1600.0 376847 loop geom
+
+neighbor 1.0 bin
+neigh_modify every 1 delay 5 check yes
+
+fix 1 all nve
+
+timestep 0.005
+thermo 50
+
+run 100
+Neighbor list info ...
+ 1 neighbor list requests
+ update every 1 steps, delay 5 steps, check yes
+ max neighbors/atom: 2000, page size: 100000
+ master list distance cutoff = 5.95
+ ghost atom cutoff = 5.95
+ binsize = 2.975 -> bins = 25 25 25
+Memory usage per processor = 5.09629 Mbytes
+Step Temp E_pair E_mol TotEng Press
+ 0 1600 -113280 0 -106662.09 18703.573
+ 50 781.69049 -109873.35 0 -106640.13 52273.088
+ 100 801.832 -109957.3 0 -106640.77 51322.821
+Loop time of 1.58019 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 27.338 ns/day, 0.878 hours/ns, 63.284 timesteps/s
+99.8% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 1.3617 | 1.366 | 1.3723 | 0.4 | 86.45
+Neigh | 0.15123 | 0.15232 | 0.15374 | 0.2 | 9.64
+Comm | 0.033429 | 0.041275 | 0.047066 | 2.7 | 2.61
+Output | 0.00011301 | 0.0001573 | 0.000211 | 0.3 | 0.01
+Modify | 0.014694 | 0.015085 | 0.015421 | 0.2 | 0.95
+Other | | 0.005342 | | | 0.34
+
+Nlocal: 8000 ave 8008 max 7993 min
+Histogram: 2 0 0 0 0 0 0 0 1 1
+Nghost: 9130.25 ave 9138 max 9122 min
+Histogram: 2 0 0 0 0 0 0 0 0 2
+Neighs: 301946 ave 302392 max 301360 min
+Histogram: 1 0 0 0 1 0 0 0 1 1
+
+Total # of neighbors = 1207784
+Ave neighs/atom = 37.7433
+Neighbor list builds = 13
+Dangerous builds = 0
+Total wall time: 0:00:01
diff --git a/bench/log.15Feb16.eam.scaled.icc.4 b/bench/log.15Feb16.eam.scaled.icc.4
new file mode 100644
index 0000000000000000000000000000000000000000..2c1cd3273ee6c31c6e621fd36ee78c5de635ac18
--- /dev/null
+++ b/bench/log.15Feb16.eam.scaled.icc.4
@@ -0,0 +1,83 @@
+LAMMPS (15 Feb 2016)
+# bulk Cu lattice
+
+variable x index 1
+variable y index 1
+variable z index 1
+
+variable xx equal 20*$x
+variable xx equal 20*2
+variable yy equal 20*$y
+variable yy equal 20*2
+variable zz equal 20*$z
+variable zz equal 20*1
+
+units metal
+atom_style atomic
+
+lattice fcc 3.615
+Lattice spacing in x,y,z = 3.615 3.615 3.615
+region box block 0 ${xx} 0 ${yy} 0 ${zz}
+region box block 0 40 0 ${yy} 0 ${zz}
+region box block 0 40 0 40 0 ${zz}
+region box block 0 40 0 40 0 20
+create_box 1 box
+Created orthogonal box = (0 0 0) to (144.6 144.6 72.3)
+ 2 by 2 by 1 MPI processor grid
+create_atoms 1 box
+Created 128000 atoms
+
+pair_style eam
+pair_coeff 1 1 Cu_u3.eam
+Reading potential file Cu_u3.eam with DATE: 2007-06-11
+
+velocity all create 1600.0 376847 loop geom
+
+neighbor 1.0 bin
+neigh_modify every 1 delay 5 check yes
+
+fix 1 all nve
+
+timestep 0.005
+thermo 50
+
+run 100
+Neighbor list info ...
+ 1 neighbor list requests
+ update every 1 steps, delay 5 steps, check yes
+ max neighbors/atom: 2000, page size: 100000
+ master list distance cutoff = 5.95
+ ghost atom cutoff = 5.95
+ binsize = 2.975 -> bins = 49 49 25
+Memory usage per processor = 10.1402 Mbytes
+Step Temp E_pair E_mol TotEng Press
+ 0 1600 -453120 0 -426647.73 18704.012
+ 50 779.50001 -439457.02 0 -426560.06 52355.276
+ 100 797.97828 -439764.76 0 -426562.07 51474.74
+Loop time of 6.46849 on 4 procs for 100 steps with 128000 atoms
+
+Performance: 6.679 ns/day, 3.594 hours/ns, 15.460 timesteps/s
+99.9% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 5.581 | 5.5997 | 5.6265 | 0.8 | 86.57
+Neigh | 0.65287 | 0.658 | 0.66374 | 0.5 | 10.17
+Comm | 0.075706 | 0.11015 | 0.13655 | 7.2 | 1.70
+Output | 0.00026488 | 0.00028312 | 0.00029302 | 0.1 | 0.00
+Modify | 0.069607 | 0.072407 | 0.074555 | 0.7 | 1.12
+Other | | 0.02794 | | | 0.43
+
+Nlocal: 32000 ave 32092 max 31914 min
+Histogram: 1 0 0 1 0 1 0 0 0 1
+Nghost: 19910 ave 19997 max 19818 min
+Histogram: 1 0 0 0 1 0 1 0 0 1
+Neighs: 1.20728e+06 ave 1.21142e+06 max 1.2036e+06 min
+Histogram: 1 0 0 1 1 0 0 0 0 1
+
+Total # of neighbors = 4829126
+Ave neighs/atom = 37.7275
+Neighbor list builds = 14
+Dangerous builds = 0
+Total wall time: 0:00:06
diff --git a/bench/log.15Feb16.lj.fixed.icc.1 b/bench/log.15Feb16.lj.fixed.icc.1
new file mode 100644
index 0000000000000000000000000000000000000000..e889fba2258b57b6d2a0140434c178c8156aa6f9
--- /dev/null
+++ b/bench/log.15Feb16.lj.fixed.icc.1
@@ -0,0 +1,79 @@
+LAMMPS (15 Feb 2016)
+# 3d Lennard-Jones melt
+
+variable x index 1
+variable y index 1
+variable z index 1
+
+variable xx equal 20*$x
+variable xx equal 20*1
+variable yy equal 20*$y
+variable yy equal 20*1
+variable zz equal 20*$z
+variable zz equal 20*1
+
+units lj
+atom_style atomic
+
+lattice fcc 0.8442
+Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
+region box block 0 ${xx} 0 ${yy} 0 ${zz}
+region box block 0 20 0 ${yy} 0 ${zz}
+region box block 0 20 0 20 0 ${zz}
+region box block 0 20 0 20 0 20
+create_box 1 box
+Created orthogonal box = (0 0 0) to (33.5919 33.5919 33.5919)
+ 1 by 1 by 1 MPI processor grid
+create_atoms 1 box
+Created 32000 atoms
+mass 1 1.0
+
+velocity all create 1.44 87287 loop geom
+
+pair_style lj/cut 2.5
+pair_coeff 1 1 1.0 1.0 2.5
+
+neighbor 0.3 bin
+neigh_modify delay 0 every 20 check no
+
+fix 1 all nve
+
+run 100
+Neighbor list info ...
+ 1 neighbor list requests
+ update every 20 steps, delay 0 steps, check no
+ max neighbors/atom: 2000, page size: 100000
+ master list distance cutoff = 2.8
+ ghost atom cutoff = 2.8
+ binsize = 1.4 -> bins = 24 24 24
+Memory usage per processor = 8.21387 Mbytes
+Step Temp E_pair E_mol TotEng Press
+ 0 1.44 -6.7733681 0 -4.6134356 -5.0197073
+ 100 0.7574531 -5.7585055 0 -4.6223613 0.20726105
+Loop time of 2.26309 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 19088.920 tau/day, 44.187 timesteps/s
+99.9% CPU use with 1 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 1.9341 | 1.9341 | 1.9341 | 0.0 | 85.46
+Neigh | 0.2442 | 0.2442 | 0.2442 | 0.0 | 10.79
+Comm | 0.024158 | 0.024158 | 0.024158 | 0.0 | 1.07
+Output | 0.00011611 | 0.00011611 | 0.00011611 | 0.0 | 0.01
+Modify | 0.053222 | 0.053222 | 0.053222 | 0.0 | 2.35
+Other | | 0.007258 | | | 0.32
+
+Nlocal: 32000 ave 32000 max 32000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost: 19657 ave 19657 max 19657 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs: 1.20283e+06 ave 1.20283e+06 max 1.20283e+06 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 1202833
+Ave neighs/atom = 37.5885
+Neighbor list builds = 5
+Dangerous builds not checked
+Total wall time: 0:00:02
diff --git a/bench/log.15Feb16.lj.fixed.icc.4 b/bench/log.15Feb16.lj.fixed.icc.4
new file mode 100644
index 0000000000000000000000000000000000000000..53cdcdbee6f3186ee7a86a75e12ea01c839b9c76
--- /dev/null
+++ b/bench/log.15Feb16.lj.fixed.icc.4
@@ -0,0 +1,79 @@
+LAMMPS (15 Feb 2016)
+# 3d Lennard-Jones melt
+
+variable x index 1
+variable y index 1
+variable z index 1
+
+variable xx equal 20*$x
+variable xx equal 20*1
+variable yy equal 20*$y
+variable yy equal 20*1
+variable zz equal 20*$z
+variable zz equal 20*1
+
+units lj
+atom_style atomic
+
+lattice fcc 0.8442
+Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
+region box block 0 ${xx} 0 ${yy} 0 ${zz}
+region box block 0 20 0 ${yy} 0 ${zz}
+region box block 0 20 0 20 0 ${zz}
+region box block 0 20 0 20 0 20
+create_box 1 box
+Created orthogonal box = (0 0 0) to (33.5919 33.5919 33.5919)
+ 1 by 2 by 2 MPI processor grid
+create_atoms 1 box
+Created 32000 atoms
+mass 1 1.0
+
+velocity all create 1.44 87287 loop geom
+
+pair_style lj/cut 2.5
+pair_coeff 1 1 1.0 1.0 2.5
+
+neighbor 0.3 bin
+neigh_modify delay 0 every 20 check no
+
+fix 1 all nve
+
+run 100
+Neighbor list info ...
+ 1 neighbor list requests
+ update every 20 steps, delay 0 steps, check no
+ max neighbors/atom: 2000, page size: 100000
+ master list distance cutoff = 2.8
+ ghost atom cutoff = 2.8
+ binsize = 1.4 -> bins = 24 24 24
+Memory usage per processor = 4.09506 Mbytes
+Step Temp E_pair E_mol TotEng Press
+ 0 1.44 -6.7733681 0 -4.6134356 -5.0197073
+ 100 0.7574531 -5.7585055 0 -4.6223613 0.20726105
+Loop time of 0.640733 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 67422.779 tau/day, 156.071 timesteps/s
+99.7% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 0.49487 | 0.51733 | 0.5322 | 1.9 | 80.74
+Neigh | 0.061131 | 0.063685 | 0.065433 | 0.6 | 9.94
+Comm | 0.02457 | 0.042349 | 0.069598 | 8.1 | 6.61
+Output | 5.9843e-05 | 6.3181e-05 | 6.6996e-05 | 0.0 | 0.01
+Modify | 0.012961 | 0.013863 | 0.014491 | 0.5 | 2.16
+Other | | 0.003448 | | | 0.54
+
+Nlocal: 8000 ave 8037 max 7964 min
+Histogram: 2 0 0 0 0 0 0 0 1 1
+Nghost: 9007.5 ave 9050 max 8968 min
+Histogram: 1 1 0 0 0 0 0 1 0 1
+Neighs: 300708 ave 305113 max 297203 min
+Histogram: 1 0 0 1 1 0 0 0 0 1
+
+Total # of neighbors = 1202833
+Ave neighs/atom = 37.5885
+Neighbor list builds = 5
+Dangerous builds not checked
+Total wall time: 0:00:00
diff --git a/bench/log.15Feb16.lj.scaled.icc.4 b/bench/log.15Feb16.lj.scaled.icc.4
new file mode 100644
index 0000000000000000000000000000000000000000..7676040c5481c5e29de40da4b781524591231ebe
--- /dev/null
+++ b/bench/log.15Feb16.lj.scaled.icc.4
@@ -0,0 +1,79 @@
+LAMMPS (15 Feb 2016)
+# 3d Lennard-Jones melt
+
+variable x index 1
+variable y index 1
+variable z index 1
+
+variable xx equal 20*$x
+variable xx equal 20*2
+variable yy equal 20*$y
+variable yy equal 20*2
+variable zz equal 20*$z
+variable zz equal 20*1
+
+units lj
+atom_style atomic
+
+lattice fcc 0.8442
+Lattice spacing in x,y,z = 1.6796 1.6796 1.6796
+region box block 0 ${xx} 0 ${yy} 0 ${zz}
+region box block 0 40 0 ${yy} 0 ${zz}
+region box block 0 40 0 40 0 ${zz}
+region box block 0 40 0 40 0 20
+create_box 1 box
+Created orthogonal box = (0 0 0) to (67.1838 67.1838 33.5919)
+ 2 by 2 by 1 MPI processor grid
+create_atoms 1 box
+Created 128000 atoms
+mass 1 1.0
+
+velocity all create 1.44 87287 loop geom
+
+pair_style lj/cut 2.5
+pair_coeff 1 1 1.0 1.0 2.5
+
+neighbor 0.3 bin
+neigh_modify delay 0 every 20 check no
+
+fix 1 all nve
+
+run 100
+Neighbor list info ...
+ 1 neighbor list requests
+ update every 20 steps, delay 0 steps, check no
+ max neighbors/atom: 2000, page size: 100000
+ master list distance cutoff = 2.8
+ ghost atom cutoff = 2.8
+ binsize = 1.4 -> bins = 48 48 24
+Memory usage per processor = 8.13678 Mbytes
+Step Temp E_pair E_mol TotEng Press
+ 0 1.44 -6.7733681 0 -4.6133849 -5.0196788
+ 100 0.75841891 -5.759957 0 -4.6223375 0.20008866
+Loop time of 2.57914 on 4 procs for 100 steps with 128000 atoms
+
+Performance: 16749.768 tau/day, 38.773 timesteps/s
+99.8% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 2.042 | 2.1092 | 2.1668 | 3.1 | 81.78
+Neigh | 0.23982 | 0.24551 | 0.25233 | 1.0 | 9.52
+Comm | 0.067088 | 0.13887 | 0.22681 | 15.7 | 5.38
+Output | 0.00013185 | 0.00021666 | 0.00027108 | 0.4 | 0.01
+Modify | 0.060348 | 0.071269 | 0.077063 | 2.5 | 2.76
+Other | | 0.01403 | | | 0.54
+
+Nlocal: 32000 ave 32060 max 31939 min
+Histogram: 1 0 1 0 0 0 0 1 0 1
+Nghost: 19630.8 ave 19681 max 19562 min
+Histogram: 1 0 0 0 1 0 0 0 1 1
+Neighs: 1.20195e+06 ave 1.20354e+06 max 1.19931e+06 min
+Histogram: 1 0 0 0 0 0 0 2 0 1
+
+Total # of neighbors = 4807797
+Ave neighs/atom = 37.5609
+Neighbor list builds = 5
+Dangerous builds not checked
+Total wall time: 0:00:02
diff --git a/bench/log.15Feb16.rhodo.fixed.icc.1 b/bench/log.15Feb16.rhodo.fixed.icc.1
new file mode 100644
index 0000000000000000000000000000000000000000..994c69e585f04edd5d3fb36bb19005b6491c22af
--- /dev/null
+++ b/bench/log.15Feb16.rhodo.fixed.icc.1
@@ -0,0 +1,121 @@
+LAMMPS (15 Feb 2016)
+# Rhodopsin model
+
+units real
+neigh_modify delay 5 every 1
+
+atom_style full
+bond_style harmonic
+angle_style charmm
+dihedral_style charmm
+improper_style harmonic
+pair_style lj/charmm/coul/long 8.0 10.0
+pair_modify mix arithmetic
+kspace_style pppm 1e-4
+
+read_data data.rhodo
+ orthogonal box = (-27.5 -38.5 -36.3646) to (27.5 38.5 36.3615)
+ 1 by 1 by 1 MPI processor grid
+ reading atoms ...
+ 32000 atoms
+ reading velocities ...
+ 32000 velocities
+ scanning bonds ...
+ 4 = max bonds/atom
+ scanning angles ...
+ 8 = max angles/atom
+ scanning dihedrals ...
+ 18 = max dihedrals/atom
+ scanning impropers ...
+ 2 = max impropers/atom
+ reading bonds ...
+ 27723 bonds
+ reading angles ...
+ 40467 angles
+ reading dihedrals ...
+ 56829 dihedrals
+ reading impropers ...
+ 1034 impropers
+ 4 = max # of 1-2 neighbors
+ 12 = max # of 1-3 neighbors
+ 24 = max # of 1-4 neighbors
+ 26 = max # of special neighbors
+
+fix 1 all shake 0.0001 5 0 m 1.0 a 232
+ 1617 = # of size 2 clusters
+ 3633 = # of size 3 clusters
+ 747 = # of size 4 clusters
+ 4233 = # of frozen angles
+fix 2 all npt temp 300.0 300.0 100.0 z 0.0 0.0 1000.0 mtk no pchain 0 tchain 1
+
+special_bonds charmm
+
+thermo 50
+thermo_style multi
+timestep 2.0
+
+run 100
+PPPM initialization ...
+ G vector (1/distance) = 0.248835
+ grid = 25 32 32
+ stencil order = 5
+ estimated absolute RMS force accuracy = 0.0355478
+ estimated relative force accuracy = 0.000107051
+ using double precision FFTs
+ 3d grid and FFT values/proc = 41070 25600
+Neighbor list info ...
+ 1 neighbor list requests
+ update every 1 steps, delay 5 steps, check yes
+ max neighbors/atom: 2000, page size: 100000
+ master list distance cutoff = 12
+ ghost atom cutoff = 12
+ binsize = 6 -> bins = 10 13 13
+Memory usage per processor = 91.7487 Mbytes
+---------------- Step 0 ----- CPU = 0.0000 (sec) ----------------
+TotEng = -25356.2064 KinEng = 21444.8313 Temp = 299.0397
+PotEng = -46801.0377 E_bond = 2537.9940 E_angle = 10921.3742
+E_dihed = 5211.7865 E_impro = 213.5116 E_vdwl = -2307.8634
+E_coul = 207025.8927 E_long = -270403.7333 Press = -142.6035
+Volume = 307995.0335
+---------------- Step 50 ----- CPU = 17.6362 (sec) ----------------
+TotEng = -25330.0828 KinEng = 21501.0029 Temp = 299.8230
+PotEng = -46831.0857 E_bond = 2471.7004 E_angle = 10836.4975
+E_dihed = 5239.6299 E_impro = 227.1218 E_vdwl = -1993.2754
+E_coul = 206797.6331 E_long = -270410.3930 Press = 237.6701
+Volume = 308031.5639
+---------------- Step 100 ----- CPU = 35.9089 (sec) ----------------
+TotEng = -25290.7593 KinEng = 21592.0117 Temp = 301.0920
+PotEng = -46882.7709 E_bond = 2567.9807 E_angle = 10781.9408
+E_dihed = 5198.7432 E_impro = 216.7834 E_vdwl = -1902.4783
+E_coul = 206659.2326 E_long = -270404.9733 Press = 6.9960
+Volume = 308133.9888
+Loop time of 35.9089 on 1 procs for 100 steps with 32000 atoms
+
+Performance: 0.481 ns/day, 49.874 hours/ns, 2.785 timesteps/s
+99.9% CPU use with 1 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 25.731 | 25.731 | 25.731 | 0.0 | 71.66
+Bond | 1.2771 | 1.2771 | 1.2771 | 0.0 | 3.56
+Kspace | 3.2094 | 3.2094 | 3.2094 | 0.0 | 8.94
+Neigh | 4.4538 | 4.4538 | 4.4538 | 0.0 | 12.40
+Comm | 0.068507 | 0.068507 | 0.068507 | 0.0 | 0.19
+Output | 0.00025916 | 0.00025916 | 0.00025916 | 0.0 | 0.00
+Modify | 1.1417 | 1.1417 | 1.1417 | 0.0 | 3.18
+Other | | 0.027 | | | 0.08
+
+Nlocal: 32000 ave 32000 max 32000 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Nghost: 47958 ave 47958 max 47958 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+Neighs: 1.20281e+07 ave 1.20281e+07 max 1.20281e+07 min
+Histogram: 1 0 0 0 0 0 0 0 0 0
+
+Total # of neighbors = 12028107
+Ave neighs/atom = 375.878
+Ave special neighs/atom = 7.43187
+Neighbor list builds = 11
+Dangerous builds = 0
+Total wall time: 0:00:37
diff --git a/bench/log.15Feb16.rhodo.fixed.icc.4 b/bench/log.15Feb16.rhodo.fixed.icc.4
new file mode 100644
index 0000000000000000000000000000000000000000..dfa5b065f917dd08a3f19d1cb2f188eae64e2fa7
--- /dev/null
+++ b/bench/log.15Feb16.rhodo.fixed.icc.4
@@ -0,0 +1,121 @@
+LAMMPS (15 Feb 2016)
+# Rhodopsin model
+
+units real
+neigh_modify delay 5 every 1
+
+atom_style full
+bond_style harmonic
+angle_style charmm
+dihedral_style charmm
+improper_style harmonic
+pair_style lj/charmm/coul/long 8.0 10.0
+pair_modify mix arithmetic
+kspace_style pppm 1e-4
+
+read_data data.rhodo
+ orthogonal box = (-27.5 -38.5 -36.3646) to (27.5 38.5 36.3615)
+ 1 by 2 by 2 MPI processor grid
+ reading atoms ...
+ 32000 atoms
+ reading velocities ...
+ 32000 velocities
+ scanning bonds ...
+ 4 = max bonds/atom
+ scanning angles ...
+ 8 = max angles/atom
+ scanning dihedrals ...
+ 18 = max dihedrals/atom
+ scanning impropers ...
+ 2 = max impropers/atom
+ reading bonds ...
+ 27723 bonds
+ reading angles ...
+ 40467 angles
+ reading dihedrals ...
+ 56829 dihedrals
+ reading impropers ...
+ 1034 impropers
+ 4 = max # of 1-2 neighbors
+ 12 = max # of 1-3 neighbors
+ 24 = max # of 1-4 neighbors
+ 26 = max # of special neighbors
+
+fix 1 all shake 0.0001 5 0 m 1.0 a 232
+ 1617 = # of size 2 clusters
+ 3633 = # of size 3 clusters
+ 747 = # of size 4 clusters
+ 4233 = # of frozen angles
+fix 2 all npt temp 300.0 300.0 100.0 z 0.0 0.0 1000.0 mtk no pchain 0 tchain 1
+
+special_bonds charmm
+
+thermo 50
+thermo_style multi
+timestep 2.0
+
+run 100
+PPPM initialization ...
+ G vector (1/distance) = 0.248835
+ grid = 25 32 32
+ stencil order = 5
+ estimated absolute RMS force accuracy = 0.0355478
+ estimated relative force accuracy = 0.000107051
+ using double precision FFTs
+ 3d grid and FFT values/proc = 13230 6400
+Neighbor list info ...
+ 1 neighbor list requests
+ update every 1 steps, delay 5 steps, check yes
+ max neighbors/atom: 2000, page size: 100000
+ master list distance cutoff = 12
+ ghost atom cutoff = 12
+ binsize = 6 -> bins = 10 13 13
+Memory usage per processor = 36.629 Mbytes
+---------------- Step 0 ----- CPU = 0.0000 (sec) ----------------
+TotEng = -25356.2064 KinEng = 21444.8313 Temp = 299.0397
+PotEng = -46801.0377 E_bond = 2537.9940 E_angle = 10921.3742
+E_dihed = 5211.7865 E_impro = 213.5116 E_vdwl = -2307.8634
+E_coul = 207025.8927 E_long = -270403.7333 Press = -142.6035
+Volume = 307995.0335
+---------------- Step 50 ----- CPU = 4.7461 (sec) ----------------
+TotEng = -25330.0828 KinEng = 21501.0029 Temp = 299.8230
+PotEng = -46831.0857 E_bond = 2471.7004 E_angle = 10836.4975
+E_dihed = 5239.6299 E_impro = 227.1218 E_vdwl = -1993.2754
+E_coul = 206797.6331 E_long = -270410.3930 Press = 237.6701
+Volume = 308031.5639
+---------------- Step 100 ----- CPU = 9.6332 (sec) ----------------
+TotEng = -25290.7591 KinEng = 21592.0117 Temp = 301.0920
+PotEng = -46882.7708 E_bond = 2567.9807 E_angle = 10781.9408
+E_dihed = 5198.7432 E_impro = 216.7834 E_vdwl = -1902.4783
+E_coul = 206659.2327 E_long = -270404.9733 Press = 6.9960
+Volume = 308133.9888
+Loop time of 9.63322 on 4 procs for 100 steps with 32000 atoms
+
+Performance: 1.794 ns/day, 13.379 hours/ns, 10.381 timesteps/s
+99.9% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 6.4364 | 6.5993 | 6.7208 | 4.7 | 68.51
+Bond | 0.30755 | 0.32435 | 0.35704 | 3.4 | 3.37
+Kspace | 0.92248 | 1.0782 | 1.2597 | 13.0 | 11.19
+Neigh | 1.1669 | 1.1672 | 1.1675 | 0.0 | 12.12
+Comm | 0.094674 | 0.098065 | 0.10543 | 1.4 | 1.02
+Output | 0.00015521 | 0.00016224 | 0.00018215 | 0.1 | 0.00
+Modify | 0.32982 | 0.34654 | 0.35365 | 1.6 | 3.60
+Other | | 0.01943 | | | 0.20
+
+Nlocal: 8000 ave 8143 max 7933 min
+Histogram: 1 2 0 0 0 0 0 0 0 1
+Nghost: 22733.5 ave 22769 max 22693 min
+Histogram: 1 0 0 0 0 2 0 0 0 1
+Neighs: 3.00703e+06 ave 3.0975e+06 max 2.96493e+06 min
+Histogram: 1 2 0 0 0 0 0 0 0 1
+
+Total # of neighbors = 12028107
+Ave neighs/atom = 375.878
+Ave special neighs/atom = 7.43187
+Neighbor list builds = 11
+Dangerous builds = 0
+Total wall time: 0:00:10
diff --git a/bench/log.15Feb16.rhodo.scaled.icc.4 b/bench/log.15Feb16.rhodo.scaled.icc.4
new file mode 100644
index 0000000000000000000000000000000000000000..73cdb163b00853f4bdaf18666a3b0f2dd7ed0936
--- /dev/null
+++ b/bench/log.15Feb16.rhodo.scaled.icc.4
@@ -0,0 +1,142 @@
+LAMMPS (15 Feb 2016)
+# Rhodopsin model
+
+variable x index 1
+variable y index 1
+variable z index 1
+
+units real
+neigh_modify delay 5 every 1
+
+atom_style full
+atom_modify map hash
+bond_style harmonic
+angle_style charmm
+dihedral_style charmm
+improper_style harmonic
+pair_style lj/charmm/coul/long 8.0 10.0
+pair_modify mix arithmetic
+kspace_style pppm 1e-4
+
+read_data data.rhodo
+ orthogonal box = (-27.5 -38.5 -36.3646) to (27.5 38.5 36.3615)
+ 1 by 2 by 2 MPI processor grid
+ reading atoms ...
+ 32000 atoms
+ reading velocities ...
+ 32000 velocities
+ scanning bonds ...
+ 4 = max bonds/atom
+ scanning angles ...
+ 8 = max angles/atom
+ scanning dihedrals ...
+ 18 = max dihedrals/atom
+ scanning impropers ...
+ 2 = max impropers/atom
+ reading bonds ...
+ 27723 bonds
+ reading angles ...
+ 40467 angles
+ reading dihedrals ...
+ 56829 dihedrals
+ reading impropers ...
+ 1034 impropers
+ 4 = max # of 1-2 neighbors
+ 12 = max # of 1-3 neighbors
+ 24 = max # of 1-4 neighbors
+ 26 = max # of special neighbors
+
+replicate $x $y $z
+replicate 2 $y $z
+replicate 2 2 $z
+replicate 2 2 1
+ orthogonal box = (-27.5 -38.5 -36.3646) to (82.5 115.5 36.3615)
+ 2 by 2 by 1 MPI processor grid
+ 128000 atoms
+ 110892 bonds
+ 161868 angles
+ 227316 dihedrals
+ 4136 impropers
+ 4 = max # of 1-2 neighbors
+ 12 = max # of 1-3 neighbors
+ 24 = max # of 1-4 neighbors
+ 26 = max # of special neighbors
+
+fix 1 all shake 0.0001 5 0 m 1.0 a 232
+ 6468 = # of size 2 clusters
+ 14532 = # of size 3 clusters
+ 2988 = # of size 4 clusters
+ 16932 = # of frozen angles
+fix 2 all npt temp 300.0 300.0 100.0 z 0.0 0.0 1000.0 mtk no pchain 0 tchain 1
+
+special_bonds charmm
+
+thermo 50
+thermo_style multi
+timestep 2.0
+
+run 100
+PPPM initialization ...
+ G vector (1/distance) = 0.248593
+ grid = 48 60 36
+ stencil order = 5
+ estimated absolute RMS force accuracy = 0.0359793
+ estimated relative force accuracy = 0.00010835
+ using double precision FFTs
+ 3d grid and FFT values/proc = 41615 25920
+Neighbor list info ...
+ 1 neighbor list requests
+ update every 1 steps, delay 5 steps, check yes
+ max neighbors/atom: 2000, page size: 100000
+ master list distance cutoff = 12
+ ghost atom cutoff = 12
+ binsize = 6 -> bins = 19 26 13
+Memory usage per processor = 95.5339 Mbytes
+---------------- Step 0 ----- CPU = 0.0000 (sec) ----------------
+TotEng = -101425.4887 KinEng = 85779.3251 Temp = 299.0304
+PotEng = -187204.8138 E_bond = 10151.9760 E_angle = 43685.4968
+E_dihed = 20847.1460 E_impro = 854.0463 E_vdwl = -9231.4537
+E_coul = 827053.5824 E_long = -1080565.6077 Press = -142.3092
+Volume = 1231980.1340
+---------------- Step 50 ----- CPU = 18.7806 (sec) ----------------
+TotEng = -101320.2677 KinEng = 86003.4837 Temp = 299.8118
+PotEng = -187323.7514 E_bond = 9887.1072 E_angle = 43346.7922
+E_dihed = 20958.7032 E_impro = 908.4715 E_vdwl = -7973.4457
+E_coul = 826141.3831 E_long = -1080592.7629 Press = 238.0161
+Volume = 1232126.1855
+---------------- Step 100 ----- CPU = 38.3684 (sec) ----------------
+TotEng = -101158.1849 KinEng = 86355.6149 Temp = 301.0393
+PotEng = -187513.7998 E_bond = 10272.0693 E_angle = 43128.6454
+E_dihed = 20793.9759 E_impro = 867.0826 E_vdwl = -7586.7186
+E_coul = 825583.7122 E_long = -1080572.5667 Press = 15.2151
+Volume = 1232535.8423
+Loop time of 38.3684 on 4 procs for 100 steps with 128000 atoms
+
+Performance: 0.450 ns/day, 53.289 hours/ns, 2.606 timesteps/s
+99.9% CPU use with 4 MPI tasks x no OpenMP threads
+
+MPI task timing breakdown:
+Section | min time | avg time | max time |%varavg| %total
+---------------------------------------------------------------
+Pair | 26.205 | 26.538 | 26.911 | 5.0 | 69.17
+Bond | 1.298 | 1.3125 | 1.3277 | 1.0 | 3.42
+Kspace | 3.7099 | 4.0992 | 4.4422 | 13.3 | 10.68
+Neigh | 4.6137 | 4.6144 | 4.615 | 0.0 | 12.03
+Comm | 0.21398 | 0.21992 | 0.22886 | 1.2 | 0.57
+Output | 0.00030518 | 0.00031543 | 0.00033307 | 0.1 | 0.00
+Modify | 1.5066 | 1.5232 | 1.5388 | 1.0 | 3.97
+Other | | 0.06051 | | | 0.16
+
+Nlocal: 32000 ave 32000 max 32000 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+Nghost: 47957 ave 47957 max 47957 min
+Histogram: 4 0 0 0 0 0 0 0 0 0
+Neighs: 1.20281e+07 ave 1.20572e+07 max 1.1999e+07 min
+Histogram: 2 0 0 0 0 0 0 0 0 2
+
+Total # of neighbors = 48112472
+Ave neighs/atom = 375.879
+Ave special neighs/atom = 7.43187
+Neighbor list builds = 11
+Dangerous builds = 0
+Total wall time: 0:00:39