Par_file 16.9 KB
Newer Older
# Simulation input parameters

# forward or adjoint simulation
SIMULATION_TYPE                 = 1   # set to 1 for forward simulations, 2 for adjoint simulations for sources, and 3 for kernel simulations
NOISE_TOMOGRAPHY                = 0   # flag of noise tomography, three steps (1,2,3). If earthquake simulation, set it to 0.
SAVE_FORWARD                    = .false.   # save last frame of forward simulation or not

# number of chunks (1,2,3 or 6)
NCHUNKS                         = 6

# angular width of the first chunk (not used if full sphere with six chunks)
ANGULAR_WIDTH_XI_IN_DEGREES     = 90.d0   # angular size of a chunk

# number of elements at the surface along the two sides of the first chunk
# (must be multiple of 16 and 8 * multiple of NPROC below)
NEX_XI                          = 64
NEX_ETA                         = 64

# number of MPI processors along the two sides of the first chunk
NPROC_XI                        = 1
NPROC_ETA                       = 1

# Model

# 1D models with real structure:
# 1D_isotropic_prem, 1D_transversely_isotropic_prem, 1D_iasp91, 1D_1066a, 1D_ak135f_no_mud, 1D_ref, 1D_ref_iso, 1D_jp3d,1D_sea99
# 1D models with only one fictitious averaged crustal layer:
# 1D_isotropic_prem_onecrust, 1D_transversely_isotropic_prem_onecrust, 1D_iasp91_onecrust, 1D_1066a_onecrust, 1D_ak135f_no_mud_onecrust
# fully 3D models:
# transversely_isotropic_prem_plus_3D_crust_2.0, 3D_anisotropic, 3D_attenuation,
# s20rts, s40rts, s362ani, s362iso, s362wmani, s362ani_prem, s362ani_3DQ, s362iso_3DQ,
# s29ea, s29ea,sea99_jp3d1994,sea99,jp3d1994,heterogen,full_sh
# 3D models with 1D crust: append "_1Dcrust" the the 3D model name
#                          to take the 1D crustal model from the
#                          associated reference model rather than the default 3D crustal model
# e.g. s20rts_1Dcrust, s362ani_1Dcrust, etc.
MODEL                           = s362ani 

# parameters describing the Earth model
OCEANS                          = .true.
ELLIPTICITY                     = .true.
TOPOGRAPHY                      = .true.
GRAVITY                         = .true.
ROTATION                        = .true.
ATTENUATION                     = .true.

# absorbing boundary conditions for a regional simulation
ABSORBING_CONDITIONS            = .false.

# record length in minutes

# to undo attenuation for sensitivity kernel calculations or forward runs with SAVE_FORWARD
# use one (and only one) of the two flags below. UNDO_ATTENUATION is much better (it is exact)
# but requires a significant amount of disk space for temporary storage.
UNDO_ATTENUATION                = .false.
# How much memory (in GB) is installed on your machine per CPU core (only used for UNDO_ATTENUATION, can be ignored otherwise)
#         (or per GPU card or per INTEL MIC Phi board)
#   Beware, this value MUST be given per core, i.e. per MPI thread, i.e. per MPI rank, NOT per node.
#   This value is for instance:
#   -  4 GB on Tiger at Princeton
#   -  4 GB on TGCC Curie in Paris
#   -  4 GB on Titan at ORNL when using CPUs only (no GPUs); start your run with "aprun -n$NPROC -N8 -S4 -j1"
#   -  2 GB on the machine used by Christina Morency
#   -  2 GB on the TACC machine used by Min Chen
#   -  1.5 GB on the GPU cluster in Marseille
# When running on GPU machines, it is simpler to set PERCENT_OF_MEM_TO_USE_PER_CORE = 100.d0
# and then set MEMORY_INSTALLED_PER_CORE_IN_GB to the amount of memory that you estimate is free (rather than installed)
# on the host of the GPU card while running your GPU job.
# For GPU runs on Titan at ORNL, use PERCENT_OF_MEM_TO_USE_PER_CORE = 100.d0 and MEMORY_INSTALLED_PER_CORE_IN_GB = 25.d0
# and run your job with "aprun -n$NPROC -N1 -S1 -j1"
# (each host has 32 GB on Titan, each GPU has 6 GB, thus even if all the GPU arrays are duplicated on the host
#  this leaves 32 - 6 = 26 GB free on the host; leaving 1 GB for the Linux system, we can safely use 100% of 25 GB)
# What percentage of this total do you allow us to use for arrays to undo attenuation, keeping in mind that you
# need to leave some memory available for the GNU/Linux system to run
#   (a typical value is 85%; any value below is fine but the code will then save a lot of data to disk;
#    values above, say 90% or 92%, can be OK on some systems but can make the adjoint code run out of memory
#    on other systems, depending on how much memory per node the GNU/Linux system needs for itself; thus you can try
#    a higher value and if the adjoint crashes then try again with a lower value)

# three mass matrices instead of one are needed to handle rotation very accurately;
# otherwise rotation is handled slightly less accurately (but still reasonably well);
# set to .true. if you are interested in precise effects related to rotation;
# set to .false. if you are solving very large inverse problems at high frequency and also undoing attenuation exactly
# using the UNDO_ATTENUATION flag above, in which case saving as much memory as possible can be a good idea.
# You can also safely set it to .false. if you are not in a period range in which rotation matters, e.g. if you are targetting very short-period body waves.
# if in doubt, set to .true.
# Set it to .true. if you have ABSORBING_CONDITIONS above, because in that case the code will use the three mass matrices anyway
# and thus there is no additional cost.
# this flag is of course unused if ROTATION above is set to .false.


# this for LDDRK high-order time scheme instead of Newmark
USE_LDDRK                       = .false.

# the maximum CFL of LDDRK is significantly higher than that of the Newmark scheme,
# in a ratio that is theoretically 1.327 / 0.697 = 1.15 / 0.604 = 1.903 for a solid with Poisson's ratio = 0.25
# and for a fluid (see the manual of the 2D code, SPECFEM2D, Tables 4.1 and 4.2, and that ratio does not
# depend on whether we are in 2D or in 3D). However in practice a ratio of about 1.5 to 1.7 is often safer
# (for instance for models with a large range of Poisson's ratio values).
# Since the code computes the time step using the Newmark scheme, for LDDRK we will simply
# multiply that time step by this ratio when LDDRK is on and when flag INCREASE_CFL_FOR_LDDRK is true.
INCREASE_CFL_FOR_LDDRK          = .true.

# Visualization

# save AVS or OpenDX movies
#MOVIE_COARSE saves movie only at corners of elements (SURFACE OR VOLUME)
#MOVIE_COARSE does not work with create_movie_AVS_DX
MOVIE_SURFACE                   = .false.
MOVIE_VOLUME                    = .false.
MOVIE_COARSE                    = .false.
HDUR_MOVIE                      = 0.d0

# save movie in volume.  Will save element if center of element is in prescribed volume
# top/bottom: depth in KM, use MOVIE_TOP = -100 to make sure the surface is stored.
# west/east: longitude, degrees East [-180/180] top/bottom: latitute, degrees North [-90/90]
# start/stop: frames will be stored at MOVIE_START + i*NSTEP_BETWEEN_FRAMES, where i=(0,1,2..) and iNSTEP_BETWEEN_FRAMES <= MOVIE_STOP
# movie_volume_type: 1=strain, 2=time integral of strain, 3=\mu*time integral of strain
# type 4 saves the trace and deviatoric stress in the whole volume, 5=displacement, 6=velocity
MOVIE_VOLUME_TYPE               = 2
MOVIE_TOP_KM                    = -100.0
MOVIE_BOTTOM_KM                 = 1000.0
MOVIE_WEST_DEG                  = -90.0
MOVIE_EAST_DEG                  = 90.0
MOVIE_NORTH_DEG                 = 90.0
MOVIE_SOUTH_DEG                 = -90.0
MOVIE_START                     = 0
MOVIE_STOP                      = 40000

# save mesh files to check the mesh
SAVE_MESH_FILES                 = .false.

# restart files (number of runs can be 1 or higher, choose 1 for no restart files)
NUMBER_OF_RUNS                  = 1
NUMBER_OF_THIS_RUN              = 1

# path to store the local database files on each node
LOCAL_PATH                      = ./DATABASES_MPI
# temporary wavefield/kernel/movie files
LOCAL_TMP_PATH                  = ./DATABASES_MPI

# interval at which we output time step info and max of norm of displacement

# Sources & seismograms

# interval in time steps for temporary writing of seismograms

# use a (tilted) FORCESOLUTION force point source (or several) instead of a CMTSOLUTION moment-tensor source.
# # This can be useful e.g. for asteroid simulations
# # in which the source is a vertical force, normal force, tilted force, impact etc.
# # If this flag is turned on, the FORCESOLUTION file must be edited by giving:
# # - the corresponding time-shift parameter,
# # - the half duration parameter of the source,
# # - the coordinates of the source,
# # - the source time function of the source,
# # - the magnitude of the force source,
# # - the components of a (non necessarily unitary) direction vector for the force source in the E/N/Z_UP basis.
# # The direction vector is made unitary internally in the code and thus only its direction matters here;
# # its norm is ignored and the norm of the force used is the factor force source times the source time function.
USE_FORCE_POINT_SOURCE          = .false.

# option to save strain seismograms
# this option is useful for strain Green's tensor
# this feature is currently under development

# save seismograms also when running the adjoint runs for an inverse problem
# (usually they are unused and not very meaningful, leave this off in almost all cases)

# output format for the seismograms (one can use either or all of the three formats)
OUTPUT_SEISMOS_ASDF             = .false.

# rotate seismograms to Radial-Transverse-Z or use default North-East-Z reference frame
ROTATE_SEISMOGRAMS_RT           = .false.

# decide if master process writes all the seismograms or if all processes do it in parallel

# save all seismograms in one large combined file instead of one file per seismogram
# to avoid overloading shared non-local file systems such as LUSTRE or GPFS for instance

# flag to impose receivers at the surface or allow them to be buried
RECEIVERS_CAN_BE_BURIED         = .true.

# print source time function

#  Adjoint kernel outputs

# use ASDF format for reading the adjoint sources
READ_ADJSRC_ASDF                = .false.

# this parameter must be set to .true. to compute anisotropic kernels
# in crust and mantle (related to the 21 Cij in geographical coordinates)
# default is .false. to compute isotropic kernels (related to alpha and beta)
ANISOTROPIC_KL                  = .false.

# output only transverse isotropic kernels (alpha_v,alpha_h,beta_v,beta_h,eta,rho)
# rather than fully anisotropic kernels when ANISOTROPIC_KL above is set to .true.
# means to save radial anisotropic kernels, i.e., sensitivity kernels for beta_v, beta_h, etc.
SAVE_TRANSVERSE_KL_ONLY         = .false.

# output approximate Hessian in crust mantle region.
# means to save the preconditioning for gradients, they are cross correlations between forward and adjoint accelerations.
APPROXIMATE_HESS_KL             = .false.

# forces transverse isotropy for all mantle elements
# (default is to use transverse isotropy only between MOHO and 220)
# means we allow radial anisotropy between the bottom of the crust to the bottom of the transition zone, i.e., 660~km depth.
USE_FULL_TISO_MANTLE            = .false.

# output kernel mask to zero out source region
# to remove large values near the sources in the sensitivity kernels
SAVE_SOURCE_MASK                = .false.

# output kernels on a regular grid instead of on the GLL mesh points (a bit expensive)
SAVE_REGULAR_KL                 = .false.


# Dimitri Komatitsch, July 2014, CNRS Marseille, France:
# added the ability to run several calculations (several earthquakes)
# in an embarrassingly-parallel fashion from within the same run;
# this can be useful when using a very large supercomputer to compute
# many earthquakes in a catalog, in which case it can be better from
# a batch job submission point of view to start fewer and much larger jobs,
# each of them computing several earthquakes in parallel.
# To turn that option on, set parameter NUMBER_OF_SIMULTANEOUS_RUNS to a value greater than 1.
# To implement that, we create NUMBER_OF_SIMULTANEOUS_RUNS MPI sub-communicators,
# each of them being labeled "my_local_mpi_comm_world", and we use them
# in all the routines in "src/shared/parallel.f90", except in MPI_ABORT() because in that case
# we need to kill the entire run.
# When that option is on, of course the number of processor cores used to start
# the code in the batch system must be a multiple of NUMBER_OF_SIMULTANEOUS_RUNS,
# all the individual runs must use the same number of processor cores,
# which as usual is NPROC in the Par_file,
# and thus the total number of processor cores to request from the batch system
# All the runs to perform must be placed in directories called run0001, run0002, run0003 and so on
# (with exactly four digits).
# Imagine you have 10 independent calculations to do, each of them on 100 cores; you have three options:
# 1/ submit 10 jobs to the batch system
# 2/ submit a single job on 1000 cores to the batch, and in that script create a sub-array of jobs to start 10 jobs,
# each running on 100 cores (see e.g. )
# 3/ submit a single job on 1000 cores to the batch, start SPECFEM3D on 1000 cores, create 10 sub-communicators,
# cd into one of 10 subdirectories (called e.g. run0001, run0002,... run0010) depending on the sub-communicator
# your MPI rank belongs to, and run normally on 100 cores using that sub-communicator.
# The option below implements 3/.

# if we perform simultaneous runs in parallel, if only the source and receivers vary between these runs
# but not the mesh nor the model (velocity and density) then we can also read the mesh and model files
# from a single run in the beginning and broadcast them to all the others; for a large number of simultaneous
# runs for instance when solving inverse problems iteratively this can DRASTICALLY reduce I/Os to disk in the solver
# (by a factor equal to NUMBER_OF_SIMULTANEOUS_RUNS), and reducing I/Os is crucial in the case of huge runs.
# Thus, always set this option to .true. if the mesh and the model are the same for all simultaneous runs.
# In that case there is no need to duplicate the mesh and model file database (the content of the DATABASES_MPI
# directories) in each of the run0001, run0002,... directories, it is sufficient to have one in run0001
# and the code will broadcast it to the others)

# if one or a few of these simultaneous runs fail, kill all the runs or let the others finish using a fail-safe mechanism
# (in most cases, should be set to false)
USE_FAILSAFE_MECHANISM          = .false.


# set to true to use GPUs
GPU_MODE                        = .false.
# Only used if GPU_MODE = .true. :
GPU_RUNTIME                     = 1
# 2 (OpenCL), 1 (Cuda) ou 0 (Compile-time -- does not work if configured with --with-cuda *AND* --with-opencl)
GPU_PLATFORM                    = NVIDIA
GPU_DEVICE                      = Tesla

# set to true to use the ADIOS library for I/Os
ADIOS_ENABLED                   = .false.
ADIOS_FOR_MPI_ARRAYS            = .true.
ADIOS_FOR_ARRAYS_SOLVER         = .true.
ADIOS_FOR_AVS_DX                = .true.
ADIOS_FOR_KERNELS               = .true.
ADIOS_FOR_MODELS                = .true.