diff --git a/doc/src/run_style.txt b/doc/src/run_style.txt index ba836a07dd..3240344a45 100644 --- a/doc/src/run_style.txt +++ b/doc/src/run_style.txt @@ -138,13 +138,19 @@ iterations of level 1 for a single iteration of level 2, N2 is the iterations of level 2 per iteration of level 3, etc. N-1 looping parameters must be specified. -The "timestep"_timestep.html command sets the timestep for the -outermost rRESPA level. Thus if the example command above for a -4-level rRESPA had an outer timestep of 4.0 fmsec, the inner timestep -would be 8x smaller or 0.5 fmsec. All other LAMMPS commands that -specify number of timesteps (e.g. "neigh_modify"_neigh_modify.html -parameters, "dump"_dump.html every N timesteps, etc) refer to the -outermost timesteps. +Thus with a 4-level respa setting of "2 2 2" for the 3 loop factors, +you could choose to have bond interactions computed 8x per large +timestep, angle interactions computed 4x, pair interactions computed +2x, and long-range interactions once per large timestep. + +The "timestep"_timestep.html command sets the large timestep for the +outermost rRESPA level. Thus if the 3 loop factors are "2 2 2" for +4-level rRESPA, and the outer timestep is set to 4.0 fmsec, then the +inner timestep would be 8x smaller or 0.5 fmsec. All other LAMMPS +commands that specify number of timesteps (e.g. "thermo"_thermo.html +for thermo output every N steps, "neigh_modify +delay/every"_neigh_modify.html parameters, "dump"_dump.html every N +steps, etc) refer to the outermost timesteps. The rRESPA keywords enable you to specify at what level of the hierarchy various forces will be computed. If not specified, the @@ -238,12 +244,24 @@ roughly a 1.5 fold speedup over the {verlet} style with SHAKE and a For non-biomolecular simulations, the {respa} style can be advantageous if there is a clear separation of time scales - fast and -slow modes in the simulation. Even a LJ system can benefit from -rRESPA if the interactions are divided by the inner, middle and outer -keywords. A 2-fold or more speedup can be obtained while maintaining -good energy conservation. In real units, for a pure LJ fluid at -liquid density, with a sigma of 3.0 angstroms, and epsilon of 0.1 -Kcal/mol, the following settings seem to work well: +slow modes in the simulation. For example, a system of slowly-moving +charged polymer chains could be setup as follows: + +timestep 4.0 +run_style respa 2 8 :pre + +This is two-level rRESPA with an 8x difference between the short and +long timesteps. The bonds, angles, dihedrals will be computed every +0.5 fs (assuming real units), while the pair and kspace interactions +will be computed once every 4 fs. These are the default settings for +each kind of interaction, so no additional keywords are necessary. + +Even a LJ system can benefit from rRESPA if the interactions are +divided by the inner, middle and outer keywords. A 2-fold or more +speedup can be obtained while maintaining good energy conservation. +In real units, for a pure LJ fluid at liquid density, with a sigma of +3.0 angstroms, and epsilon of 0.1 Kcal/mol, the following settings +seem to work well: timestep 36.0 run_style respa 3 3 4 inner 1 3.0 4.0 middle 2 6.0 7.0 outer 3 :pre @@ -271,9 +289,9 @@ more instructions on how to use the accelerated styles effectively. [Restrictions:] The {verlet/split} style can only be used if LAMMPS was built with the -REPLICA package. Correspondingly the {respa/omp} style is available only -if the USER-OMP package was included. See the "Making LAMMPS"_Section_start.html#start_3 -section for more info on packages. +REPLICA package. Correspondingly the {respa/omp} style is available +only if the USER-OMP package was included. See the "Making +LAMMPS"_Section_start.html#start_3 section for more info on packages. Whenever using rRESPA, the user should experiment with trade-offs in speed and accuracy for their system, and verify that they are @@ -287,6 +305,17 @@ conserving energy to adequate precision. run_style verlet :pre +For run_style respa, the default assignment of interactions +to rRESPA levels is as follows: + +bond forces = level 1 (innermost loop) +angle forces = same level as bond forces +dihedral forces = same level as angle forces +improper forces = same level as dihedral forces +pair forces = leven N (outermost level) +kspace forces = same level as pair forces +inner, middle, outer forces = no default :ul + :line :link(Tuckerman3) diff --git a/src/MAKE/MACHINES/Makefile.theta b/src/MAKE/MACHINES/Makefile.theta new file mode 100644 index 0000000000..cad5a03b42 --- /dev/null +++ b/src/MAKE/MACHINES/Makefile.theta @@ -0,0 +1,133 @@ +# knl = Flags for Knights Landing Xeon Phi Processor,Intel Compiler/MPI,MKL FFT +# module load perftools-base perftools +# make theta -j 8 +# pat_build -g mpi -u ./lmp_theta + +SHELL = /bin/sh + +# --------------------------------------------------------------------- +# compiler/linker settings +# specify flags and libraries needed for your compiler + +CC = CC -mkl +#OPTFLAGS = -O0 +OPTFLAGS = -xMIC-AVX512 -O3 -fp-model fast=2 -no-prec-div -qoverride-limits +CCFLAGS = -g -qopenmp -DLAMMPS_MEMALIGN=64 -qno-offload \ + -fno-alias -ansi-alias -restrict $(OPTFLAGS) +#CCFLAGS += -DLMP_INTEL_NO_TBB +#CCFLAGS += -DLAMMPS_BIGBIG +#CCFLAGS += -D_USE_PAPI +#CCFLAGS += -D_USE_CRAYPAT_API +SHFLAGS = -fPIC +DEPFLAGS = -M + +LINK = $(CC) +LINKFLAGS = -g -qopenmp $(OPTFLAGS) +LINKFLAGS += -dynamic +LIB = +#LIB += -L${TBBROOT}/lib/intel64/gcc4.7 -ltbbmalloc +LIB += -ltbbmalloc +#LIB += /soft/debuggers/forge-7.0-2017-02-16/lib/64/libdmallocthcxx.a -zmuldefs +SIZE = size + +ARCHIVE = ar +ARFLAGS = -rc +SHLIBFLAGS = -shared + +# --------------------------------------------------------------------- +# LAMMPS-specific settings, all OPTIONAL +# specify settings for LAMMPS features you will use +# if you change any -D setting, do full re-compile after "make clean" + +# LAMMPS ifdef settings +# see possible settings in Section 2.2 (step 4) of manual + +LMP_INC = -DLAMMPS_GZIP #-DLAMMPS_JPEG + +# MPI library +# see discussion in Section 2.2 (step 5) of manual +# MPI wrapper compiler/linker can provide this info +# can point to dummy MPI library in src/STUBS as in Makefile.serial +# use -D MPICH and OMPI settings in INC to avoid C++ lib conflicts +# INC = path for mpi.h, MPI compiler settings +# PATH = path for MPI library +# LIB = name of MPI library + +MPI_INC = -DMPICH_SKIP_MPICXX -DOMPI_SKIP_MPICXX=1 +MPI_PATH = +MPI_LIB = + +# FFT library +# see discussion in Section 2.2 (step 6) of manaul +# can be left blank to use provided KISS FFT library +# INC = -DFFT setting, e.g. -DFFT_FFTW, FFT compiler settings +# PATH = path for FFT library +# LIB = name of FFT library + +FFT_INC = -DFFT_MKL -DFFT_SINGLE +FFT_PATH = +FFT_LIB = -L$(MKLROOT)/lib/intel64/ -Wl,--start-group -lmkl_intel_ilp64 \ + -lmkl_intel_thread -lmkl_core -Wl,--end-group + +# JPEG and/or PNG library +# see discussion in Section 2.2 (step 7) of manual +# only needed if -DLAMMPS_JPEG or -DLAMMPS_PNG listed with LMP_INC +# INC = path(s) for jpeglib.h and/or png.h +# PATH = path(s) for JPEG library and/or PNG library +# LIB = name(s) of JPEG library and/or PNG library + +JPG_INC = +JPG_PATH = +JPG_LIB = + +# --------------------------------------------------------------------- +# build rules and dependencies +# do not edit this section + +include Makefile.package.settings +include Makefile.package + +EXTRA_INC = $(LMP_INC) $(PKG_INC) $(MPI_INC) $(FFT_INC) $(JPG_INC) $(PKG_SYSINC) +EXTRA_PATH = $(PKG_PATH) $(MPI_PATH) $(FFT_PATH) $(JPG_PATH) $(PKG_SYSPATH) +EXTRA_LIB = $(PKG_LIB) $(MPI_LIB) $(FFT_LIB) $(JPG_LIB) $(PKG_SYSLIB) + +# Path to src files + +vpath %.cpp .. +vpath %.h .. + +# Link target + +$(EXE): $(OBJ) + $(LINK) $(LINKFLAGS) $(EXTRA_PATH) $(OBJ) $(EXTRA_LIB) $(LIB) -o $(EXE) + $(SIZE) $(EXE) + +# Library targets + +lib: $(OBJ) + $(ARCHIVE) $(ARFLAGS) $(EXE) $(OBJ) + +shlib: $(OBJ) + $(CC) $(CCFLAGS) $(SHFLAGS) $(SHLIBFLAGS) $(EXTRA_PATH) -o $(EXE) \ + $(OBJ) $(EXTRA_LIB) $(LIB) + +# Compilation rules + +%.o:%.cpp + $(CC) $(CCFLAGS) $(SHFLAGS) $(EXTRA_INC) -c $< + +%.d:%.cpp + $(CC) $(CCFLAGS) $(EXTRA_INC) $(DEPFLAGS) $< > $@ + +%.o:%.cu + $(CC) $(CCFLAGS) $(SHFLAGS) $(EXTRA_INC) -c $< + +# Individual dependencies + +depend : fastdep.exe $(SRC) + @./fastdep.exe $(EXTRA_INC) -- $^ > .depend || exit 1 + +fastdep.exe: ../DEPEND/fastdep.c + icc -O -o $@ $< + +sinclude .depend