Hi all,
We’ve recently added some high performance workstations to our office so I’ve been trying to compile Lammps with CUDA on Ubuntu 13.10 OS. I’ve been able to compile a normal lammps install with no additional packages, however similar to http://lammps.sandia.gov/threads/msg31386.html I cannot compile with CUDA.
I’ve installed the CUDA library, and pointed to it in all the cuda files, however when compiling I get the following error:
mpic++ -g -O3 -L…/…/lib/cuda -L…/…/lib/gpu -L…/…/lib/colvars -L/usr/local/cuda/lib -L/usr/local/cuda/lib64 -lcufft -L/usr/local/cuda/lib64 angle_charmm.o angle_class2.o angle_cosine.o angle_cosine_delta.o angle_cosine_periodic.o angle_cosine_shift.o angle_cosine_shift_exp.o angle_cosine_squared.o angle.o angle_dipole.o angle_fourier.o angle_fourier_simple.o angle_harmonic.o angle_hybrid.o angle_quartic.o angle_table.o atom.o atom_map.o atom_vec_angle.o atom_vec_angle_cuda.o atom_vec_atomic.o atom_vec_atomic_cuda.o atom_vec_body.o atom_vec_bond.o atom_vec_charge.o atom_vec_charge_cuda.o atom_vec.o atom_vec_ellipsoid.o atom_vec_full.o atom_vec_full_cuda.o atom_vec_hybrid.o atom_vec_line.o atom_vec_molecular.o atom_vec_sphere.o atom_vec_template.o atom_vec_tri.o balance.o body.o bond_class2.o bond.o bond_fene.o bond_fene_expand.o bond_harmonic.o bond_harmonic_shift.o bond_harmonic_shift_cut.o bond_hybrid.o bond_morse.o bond_nonlinear.o bond_quartic.o bond_table.o change_box.o citeme.o colvarproxy_lammps.o comm_brick.o comm.o comm_cuda.o comm_tiled.o compute_ackland_atom.o compute_angle_local.o compute_atom_molecule.o compute_basal_atom.o compute_bond_local.o compute_centro_atom.o compute_cluster_atom.o compute_cna_atom.o compute_com.o compute_com_molecule.o compute_contact_atom.o compute_coord_atom.o compute.o compute_dihedral_local.o compute_displace_atom.o compute_erotate_rigid.o compute_erotate_sphere_atom.o compute_erotate_sphere.o compute_event_displace.o compute_group_group.o compute_gyration.o compute_gyration_molecule.o compute_heat_flux.o compute_improper_local.o compute_inertia_molecule.o compute_ke_atom.o compute_ke.o compute_ke_rigid.o compute_msd.o compute_msd_molecule.o compute_msd_nongauss.o compute_pair.o compute_pair_local.o compute_pe_atom.o compute_pe.o compute_pe_cuda.o compute_pressure.o compute_pressure_cuda.o compute_property_atom.o compute_property_local.o compute_property_molecule.o compute_rdf.o compute_reduce.o compute_reduce_region.o compute_slice.o compute_stress_atom.o compute_temp_com.o compute_temp.o compute_temp_cuda.o compute_temp_deform.o compute_temp_partial.o compute_temp_partial_cuda.o compute_temp_profile.o compute_temp_ramp.o compute_temp_region.o compute_temp_rotate.o compute_temp_sphere.o compute_ti.o compute_vacf.o create_atoms.o create_box.o cuda.o cuda_neigh_list.o delete_atoms.o delete_bonds.o dihedral_charmm.o dihedral_class2.o dihedral_cosine_shift_exp.o dihedral.o dihedral_fourier.o dihedral_harmonic.o dihedral_helix.o dihedral_hybrid.o dihedral_multi_harmonic.o dihedral_nharmonic.o dihedral_opls.o dihedral_quadratic.o dihedral_table.o displace_atoms.o domain.o domain_cuda.o dump_atom.o dump_cfg.o dump.o dump_custom.o dump_dcd.o dump_image.o dump_local.o dump_molfile.o dump_movie.o dump_xtc.o dump_xyz.o error.o ewald.o ewald_disp.o fft3d.o fft3d_cuda.o fft3d_wrap.o fft3d_wrap_cuda.o finish.o fix_adapt.o fix_addforce.o fix_addforce_cuda.o fix_addtorque.o fix_ave_atom.o fix_ave_correlate.o fix_aveforce.o fix_aveforce_cuda.o fix_ave_histo.o fix_ave_spatial.o fix_ave_time.o fix_balance.o fix_box_relax.o fix_colvars.o fix.o fix_deform.o fix_deposit.o fix_drag.o fix_dt_reset.o fix_efield.o fix_enforce2d.o fix_enforce2d_cuda.o fix_evaporate.o fix_event.o fix_event_prd.o fix_event_tad.o fix_external.o fix_gld.o fix_gpu.o fix_gravity.o fix_gravity_cuda.o fix_group.o fix_heat.o fix_imd.o fix_indent.o fix_langevin.o fix_lineforce.o fix_minimize.o fix_momentum.o fix_move.o fix_neb.o fix_nh.o fix_nh_cuda.o fix_nh_sphere.o fix_nph.o fix_nph_sphere.o fix_npt.o fix_npt_cuda.o fix_npt_sphere.o fix_nve.o fix_nve_cuda.o fix_nve_limit.o fix_nve_noforce.o fix_nve_sphere.o fix_nvt.o fix_nvt_cuda.o fix_nvt_sllod.o fix_nvt_sphere.o fix_oneway.o fix_orient_fcc.o fix_planeforce.o fix_press_berendsen.o fix_print.o fix_property_atom.o fix_read_restart.o fix_recenter.o fix_respa.o fix_restrain.o fix_rigid.o fix_rigid_nh.o fix_rigid_nh_small.o fix_rigid_nph.o fix_rigid_nph_small.o fix_rigid_npt.o fix_rigid_npt_small.o fix_rigid_nve.o fix_rigid_nve_small.o fix_rigid_nvt.o fix_rigid_nvt_small.o fix_rigid_small.o fix_setforce.o fix_set_force_cuda.o fix_shake.o fix_shake_cuda.o fix_shear_history.o fix_smd.o fix_spring.o fix_spring_rg.o fix_spring_self.o fix_store.o fix_store_force.o fix_store_state.o fix_temp_berendsen.o fix_temp_berendsen_cuda.o fix_temp_csvr.o fix_temp_rescale.o fix_temp_rescale_cuda.o fix_temp_rescale_limit_cuda.o fix_thermal_conductivity.o fix_ti_rs.o fix_ti_spring.o fix_tmd.o fix_ttm.o fix_tune_kspace.o fix_vector.o fix_viscosity.o fix_viscous.o fix_viscous_cuda.o fix_wall.o fix_wall_harmonic.o fix_wall_lj1043.o fix_wall_lj126.o fix_wall_lj93.o fix_wall_reflect.o fix_wall_region.o force.o gridcomm.o group.o group_ndx.o image.o improper_class2.o improper_cossq.o improper.o improper_cvff.o improper_fourier.o improper_harmonic.o improper_hybrid.o improper_ring.o improper_umbrella.o input.o integrate.o irregular.o kspace.o lammps.o lattice.o library.o main.o math_extra.o memory.o min_cg.o min.o min_fire.o min_hftn.o minimize.o min_linesearch.o min_quickmin.o min_sd.o modify.o modify_cuda.o molecule.o molfile_interface.o msm_cg.o msm.o neb.o neigh_bond.o neighbor.o neighbor_cuda.o neigh_derive.o neigh_full.o neigh_full_cuda.o neigh_gran.o neigh_half_bin.o neigh_half_multi.o neigh_half_nsq.o neigh_list.o neigh_request.o neigh_respa.o neigh_stencil.o output.o pair_beck.o pair_beck_gpu.o pair_born_coul_long.o pair_born_coul_long_cuda.o pair_born_coul_long_gpu.o pair_born_coul_msm.o pair_born_coul_wolf.o pair_born_coul_wolf_gpu.o pair_born.o pair_born_gpu.o pair_buck_coul_cut.o pair_buck_coul_cut_cuda.o pair_buck_coul_cut_gpu.o pair_buck_coul_long.o pair_buck_coul_long_cuda.o pair_buck_coul_long_gpu.o pair_buck_coul_msm.o pair_buck.o pair_buck_cuda.o pair_buck_gpu.o pair_buck_long_coul_long.o pair_coul_cut.o pair_coul_cut_gpu.o pair_coul_debye.o pair_coul_debye_gpu.o pair_coul_diel.o pair_coul_dsf.o pair_coul_dsf_gpu.o pair_coul_long.o pair_coul_long_gpu.o pair_coul_msm.o pair_coul_wolf.o pair.o pair_dpd.o pair_dpd_gpu.o pair_dpd_tstat.o pair_dpd_tstat_gpu.o pair_edip.o pair_gauss.o pair_gauss_cut.o pair_gauss_gpu.o pair_hbond_dreiding_lj.o pair_hbond_dreiding_morse.o pair_hybrid.o pair_hybrid_overlay.o pair_list.o pair_lj96_cut.o pair_lj96_cut_cuda.o pair_lj96_cut_gpu.o pair_lj_charmm_coul_charmm.o pair_lj_charmm_coul_charmm_cuda.o pair_lj_charmm_coul_charmm_implicit.o pair_lj_charmm_coul_charmm_implicit_cuda.o pair_lj_charmm_coul_long.o pair_lj_charmm_coul_long_cuda.o pair_lj_charmm_coul_long_gpu.o pair_lj_charmm_coul_msm.o pair_lj_class2_coul_cut.o pair_lj_class2_coul_cut_cuda.o pair_lj_class2_coul_long.o pair_lj_class2_coul_long_cuda.o pair_lj_class2_coul_long_gpu.o pair_lj_class2.o pair_lj_class2_cuda.o pair_lj_class2_gpu.o pair_lj_cubic.o pair_lj_cut_coul_cut.o pair_lj_cut_coul_cut_cuda.o pair_lj_cut_coul_cut_gpu.o pair_lj_cut_coul_debye.o pair_lj_cut_coul_debye_cuda.o pair_lj_cut_coul_debye_gpu.o pair_lj_cut_coul_dsf.o pair_lj_cut_coul_dsf_gpu.o pair_lj_cut_coul_long.o pair_lj_cut_coul_long_cuda.o pair_lj_cut_coul_long_gpu.o pair_lj_cut_coul_msm.o pair_lj_cut_coul_msm_gpu.o pair_lj_cut.o pair_lj_cut_cuda.o pair_lj_cut_experimental_cuda.o pair_lj_cut_gpu.o pair_lj_cut_tip4p_cut.o pair_lj_cut_tip4p_long.o pair_lj_expand.o pair_lj_expand_cuda.o pair_lj_expand_gpu.o pair_lj_gromacs_coul_gromacs.o pair_lj_gromacs_coul_gromacs_cuda.o pair_lj_gromacs.o pair_lj_gromacs_cuda.o pair_lj_gromacs_gpu.o pair_lj_long_coul_long.o pair_lj_long_tip4p_long.o pair_lj_sf.o pair_lj_sf_dipole_sf.o pair_lj_sf_dipole_sf_gpu.o pair_lj_smooth.o pair_lj_smooth_cuda.o pair_lj_smooth_linear.o pair_meam_spline.o pair_meam_sw_spline.o pair_mie_cut.o pair_mie_cut_gpu.o pair_morse.o pair_morse_cuda.o pair_morse_gpu.o pair_nm_cut_coul_cut.o pair_nm_cut_coul_long.o pair_nm_cut.o pair_soft.o pair_soft_gpu.o pair_table.o pair_table_gpu.o pair_tersoff_table.o pair_tip4p_cut.o pair_tip4p_long.o pair_yukawa.o pair_yukawa_gpu.o pair_zbl.o pppm_cg.o pppm.o pppm_cuda.o pppm_disp.o pppm_disp_tip4p.o pppm_gpu.o pppm_old.o pppm_stagger.o pppm_tip4p.o prd.o procmap.o random_mars.o random_park.o rcb.o read_data.o read_dump.o reader.o reader_molfile.o reader_native.o reader_xyz.o read_restart.o region_block.o region_cone.o region.o region_cylinder.o region_intersect.o region_plane.o region_prism.o region_sphere.o region_union.o remap.o remap_wrap.o replicate.o rerun.o respa.o run.o set.o special.o tad.o temper.o thermo.o timer.o universe.o update.o variable.o velocity.o verlet.o verlet_cuda.o verlet_split.o write_data.o write_dump.o write_restart.o xdr_compat.o -llammpscuda -lgpu -lcolvars -lfftw3 -ljpeg -lpng -lcuda -lcudart -lcudart -lcuda -ldl -o …/lmp_ubuntu
fft3d_cuda.o: In function fft_3d_cuda(FFT_DATA*, FFT_DATA*, int, fft_plan_3d*)': /home/kam/lammps-5Sep14/src/Obj_ubuntu/../fft3d_cuda.cpp:132: undefined reference to cufftExecC2C’
/home/kam/lammps-5Sep14/src/Obj_ubuntu/…/fft3d_cuda.cpp:128: undefined reference to cufftExecC2C' fft3d_cuda.o: In function fft_3d_create_plan_cuda(ompi_communicator_t*, int, int, int, int, int, int, int, int, int, int, int, int, int, int, int, int, int, int*, bool)’:
/home/kam/lammps-5Sep14/src/Obj_ubuntu/…/fft3d_cuda.cpp:439: undefined reference to cufftPlan3d' fft3d_cuda.o: In function fft_3d_destroy_plan_cuda(fft_plan_3d*)’:
/home/kam/lammps-5Sep14/src/Obj_ubuntu/…/fft3d_cuda.cpp:479: undefined reference to cufftDestroy' fft3d_cuda.o: In function fft_1d_only_cuda(FFT_DATA*, int, int, fft_plan_3d*)’:
/home/kam/lammps-5Sep14/src/Obj_ubuntu/…/fft3d_cuda.cpp:593: undefined reference to cufftExecC2C' collect2: error: ld returned 1 exit status make[1]: *** [../lmp_ubuntu] Error 1 make[1]: Leaving directory /home/kam/lammps-5Sep14/src/Obj_ubuntu’
make: *** [ubuntu] Error 2
Just wondering if anyone has been able to overcome this issue or has suggestions on how to overcome.