diff --git a/bench/FERMI/README b/bench/FERMI/README
index 03aeaf8ef9..5244aa8916 100644
--- a/bench/FERMI/README
+++ b/bench/FERMI/README
@@ -1,7 +1,9 @@
-These are input scripts used to run GPU versions of several of the
-benchmarks in the top-level bench directory.  The results of running
-these scripts on different machines are shown on the GPU section of
-the Benchmark page of the LAMMPS WWW site (lammps.sandia.gov/bench).
+These are input scripts used to run versions of several of the
+benchmarks in the top-level bench directory using the GPU and
+USER-CUDA accelerator packages.  The results of running these scripts
+on two different machines (a desktop with 2 Tesla GPUs and the ORNL
+Titan supercomputer) are shown on the "GPU (Fermi)" section of the
+Benchmark page of the LAMMPS WWW site: lammps.sandia.gov/bench.
 
 Examples are shown below of how to run these scripts.  This assumes
 you have built 3 executables with both the GPU and USER-CUDA packages
@@ -59,3 +61,8 @@ many MPI tasks per compute node the problem will run on, and the "g"
 setting determines how many GPUs per compute node the problem will run
 on, i.e. 1 or 2 in this case.  For the USER-CUDA package, the number
 of MPI tasks and GPUs (both per compute node) must be equal.
+
+------------------------------------------------------------------------
+
+If the script has "titan" in its name, it was run on the Titan supercomputer
+at ORNL.
diff --git a/bench/FERMI/in.eam.titan b/bench/FERMI/in.eam.titan
new file mode 100644
index 0000000000..871e5df4d0
--- /dev/null
+++ b/bench/FERMI/in.eam.titan
@@ -0,0 +1,37 @@
+# bulk Cu lattice
+
+newton          off
+package         gpu force/neigh 0 0 1
+processors      * * * grid numa
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+variable	xx equal 20*$x
+variable	yy equal 20*$y
+variable	zz equal 20*$z
+
+units		metal
+atom_style	atomic
+
+lattice		fcc 3.615
+region		box block 0 ${xx} 0 ${yy} 0 ${zz}
+create_box	1 box
+create_atoms	1 box
+
+pair_style	eam/gpu
+pair_coeff	1 1 Cu_u3.eam
+
+velocity	all create 1600.0 376847 loop geom
+
+neighbor	1.0 bin
+neigh_modify    every 1 delay 5 check yes
+
+fix		1 all nve
+
+timestep	0.005
+thermo		50
+
+run             15
+run		100
diff --git a/bench/FERMI/in.lj.titan b/bench/FERMI/in.lj.titan
new file mode 100644
index 0000000000..2b2e8b11e5
--- /dev/null
+++ b/bench/FERMI/in.lj.titan
@@ -0,0 +1,35 @@
+# 3d Lennard-Jones melt
+
+newton          off
+package         gpu force/neigh 0 0 1
+processors      * * * grid numa
+
+variable	x index 1
+variable	y index 1
+variable	z index 1
+
+variable	xx equal 20*$x
+variable	yy equal 20*$y
+variable	zz equal 20*$z
+
+units		lj
+atom_style	atomic
+
+lattice		fcc 0.8442
+region		box block 0 ${xx} 0 ${yy} 0 ${zz}
+create_box	1 box
+create_atoms	1 box
+mass		1 1.0
+
+velocity	all create 1.44 87287 loop geom
+
+pair_style	lj/cut/gpu 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             15
+run		100
diff --git a/bench/FERMI/in.rhodo.scaled.titan b/bench/FERMI/in.rhodo.scaled.titan
new file mode 100644
index 0000000000..00ee7eaefb
--- /dev/null
+++ b/bench/FERMI/in.rhodo.scaled.titan
@@ -0,0 +1,39 @@
+# Rhodopsin model
+
+newton          off
+package         gpu force/neigh 0 0 1
+processors      * * * grid numa
+
+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/gpu 8.0 ${cutoff}
+pair_modify     mix arithmetic 
+kspace_style    pppm/gpu 1e-4 
+
+read_data       data.rhodo
+
+replicate	$x $y $z
+
+fix             1 all shake 0.0001 5 0 m 1.0 a 232
+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             15
+run		100
diff --git a/bench/FERMI/in.rhodo.split.titan b/bench/FERMI/in.rhodo.split.titan
new file mode 100644
index 0000000000..83c6ef4eaa
--- /dev/null
+++ b/bench/FERMI/in.rhodo.split.titan
@@ -0,0 +1,42 @@
+# Rhodopsin model
+
+newton          off
+package         gpu force/neigh 0 0 1
+partition	yes 1 processors * * * grid twolevel ${grid} * * * &
+		part 1 2 multiple
+partition	yes 2 processors * * * part 1 2 multiple
+
+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/gpu 8.0 ${cutoff}
+pair_modify     mix arithmetic 
+kspace_style    pppm/gpu 1e-4 
+
+read_data       data.rhodo
+
+replicate	$x $y $z
+
+fix             1 all shake 0.0001 5 0 m 1.0 a 232
+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_style       verlet/split
+run             15
+run		100