# Default precompiler options
CPP_OPTIONS = -DHOST=\"LinuxNV\" \
              -DMPI -DMPI_BLOCK=8000 -Duse_collective \
              -DscaLAPACK \
              -DCACHE_SIZE=4000 \
              -Davoidalloc \
              -Dvasp6 \
              -Duse_bse_te \
              -Dtbdyn \
              -Dqd_emulate \
              -Dfock_dblbuf \
              -D_OPENMP \
              -D_OPENACC \
              -DUSENCCL -DUSENCCLP2P -Duse_shmem -Dshmem_bcast_buffer -Dshmem_rproj

CPP         = nvfortran -Mpreprocess -Mfree -Mextend -E $(CPP_OPTIONS) $*$(FUFFIX)  > $*$(SUFFIX)

# N.B.: you might need to change the cuda-version here
#       to one that comes with your NVIDIA-HPC SDK
FC          = mpif90 -acc -gpu=@cudaCapabilities@ -mp
FCL         = mpif90 -acc -gpu=@cudaCapabilities@ -mp -c++libs

FREE        = -Mfree

FFLAGS      = -Mbackslash -Mlarge_arrays

OFLAG       = -fast

DEBUG       = -Mfree -O0 -traceback

OBJECTS     = fftmpiw.o fftmpi_map.o fftw3d.o fft3dlib.o

LLIBS       = -cudalib=cublas,cusolver,cufft,nccl -cuda

# Redefine the standard list of O1 and O2 objects
SOURCE_O1  := pade_fit.o
SOURCE_O2  := pead.o

# For what used to be vasp.5.lib
CPP_LIB     = $(CPP)
FC_LIB      = nvfortran
CC_LIB      = nvc -w
CFLAGS_LIB  = -O
FFLAGS_LIB  = -O1 -Mfixed
FREE_LIB    = $(FREE)

OBJECTS_LIB = linpack_double.o getshmem.o

# For the parser library
CXX_PARS    = nvc++ --no_warnings

##
## Customize as of this point! Of course you may change the preceding
## part of this file as well if you like, but it should rarely be
## necessary ...
##
# When compiling on the target machine itself , change this to the
# relevant target when cross-compiling for another architecture
VASP_TARGET_CPU ?= -tp=@nvhpcArch@
FFLAGS     += $(VASP_TARGET_CPU)

# Specify your NV HPC-SDK installation (mandatory)
#... first try to set it automatically
NVROOT      =$(shell which nvfortran | awk -F /compilers/bin/nvfortran '{ print $$1 }')

# If the above fails, then NVROOT needs to be set manually
#NVHPC      ?= /opt/nvidia/hpc_sdk
#NVVERSION   = 21.11
#NVROOT      = $(NVHPC)/Linux_x86_64/$(NVVERSION)

## Improves performance when using NV HPC-SDK >=21.11 and CUDA >11.2
OFLAG_IN   = -fast -Mwarperf
SOURCE_IN  := nonlr.o

# Software emulation of quadruple precsion (mandatory)
QD         ?= $(NVROOT)/compilers/extras/qd
LLIBS      += -L$(QD)/lib -lqdmod -lqd
INCS       += -I$(QD)/include/qd

# Intel MKL for FFTW, BLAS, LAPACK, and scaLAPACK
MKLROOT    ?= /path/to/your/mkl/installation
LLIBS_MKL   = -Mmkl -L$(MKLROOT)/lib -lmkl_scalapack_lp64 -lmkl_blacs_openmpi_lp64
INCS       += -I$(MKLROOT)/include/fftw

# Use a separate scaLAPACK installation (optional but recommended in combination with OpenMPI)
# Comment out the two lines below if you want to use scaLAPACK from MKL instead
# SCALAPACK_ROOT ?= /path/to/your/scalapack/installation
# LLIBS_MKL   = -L$(SCALAPACK_ROOT)/lib -lscalapack -Mmkl

LLIBS      += $(LLIBS_MKL)

# HDF5-support (optional but strongly recommended)
CPP_OPTIONS+= -DVASP_HDF5
HDF5_ROOT  ?= /path/to/your/hdf5/installation
LLIBS      += -L$(HDF5_ROOT)/lib -lhdf5_fortran
INCS       += -I$(HDF5_ROOT)/include

# For the VASP-2-Wannier90 interface (optional)
CPP_OPTIONS    += -DVASP2WANNIER90
# WANNIER90_ROOT ?= /path/to/your/wannier90/installation
# LLIBS          += -L$(WANNIER90_ROOT)/lib -lwannier
LLIBS          += @wannier@

# For the fftlib library (hardly any benefit for the OpenACC GPU port, especially in combination with MKL's FFTs)
#CPP_OPTIONS+= -Dsysv
#FCL        += fftlib.o
#CXX_FFTLIB  = nvc++ -mp --no_warnings -std=c++11 -DFFTLIB_USE_MKL -DFFTLIB_THREADSAFE
#INCS_FFTLIB = -I./include -I$(MKLROOT)/include/fftw
#LIBS       += fftlib
#LLIBS      += -ldl