# Precompiler options
CPP_OPTIONS= -DHOST=\"LinuxIFC\"\
-DMPI -DMPI_BLOCK=8000 -Duse_collective \
-DscaLAPACK \
-DCACHE_SIZE=4000 \
-Davoidalloc \
-Dvasp6 \
-Duse_bse_te \
-Dtbdyn \
-Dfock_dblbuf
CPP = fpp -f_com=no -free -w0 $*$(FUFFIX) $*$(SUFFIX) $(CPP_OPTIONS)
FC = mpiifort
FCL = mpiifort -mkl=sequential
FREE = -free -names lowercase
FFLAGS = -assume byterecl -w -xHOST
OFLAG = -O2
OFLAG_IN = $(OFLAG)
DEBUG = -O0
MKL_PATH = $(MKLROOT)/lib/intel64
BLAS =
LAPACK =
BLACS = -lmkl_blacs_intelmpi_lp64
SCALAPACK = $(MKL_PATH)/libmkl_scalapack_lp64.a $(BLACS)
OBJECTS = fftmpiw.o fftmpi_map.o fft3dlib.o fftw3d.o
INCS =-I$(MKLROOT)/include/fftw
LLIBS = $(SCALAPACK) $(LAPACK) $(BLAS)
OBJECTS_O1 += fftw3d.o fftmpi.o fftmpiw.o
OBJECTS_O2 += fft3dlib.o
# For what used to be vasp.5.lib
CPP_LIB = $(CPP)
FC_LIB = $(FC)
CC_LIB = icc
CFLAGS_LIB = -O
FFLAGS_LIB = -O1
FREE_LIB = $(FREE)
OBJECTS_LIB= linpack_double.o getshmem.o
# For the parser library
CXX_PARS = icpc
LLIBS += -lstdc++
# Normally no need to change this
SRCDIR = ../../src
BINDIR = ../../bin
#================================================
# GPU Stuff
CPP_GPU = -DCUDA_GPU -DRPROMU_CPROJ_OVERLAP -DUSE_PINNED_MEMORY -DCUFFT_MIN=28 -UscaLAPACK -Ufock_dblbuf
OBJECTS_GPU= fftmpiw.o fftmpi_map.o fft3dlib.o fftw3d_gpu.o fftmpiw_gpu.o
CC = icc
CXX = icpc
CFLAGS = -fPIC -DADD_ -Wall -qopenmp -DMAGMA_WITH_MKL -DMAGMA_SETAFFINITY -DGPUSHMEM=300 -DHAVE_CUBLAS
# Minimal requirement is CUDA >= 10.X. For "sm_80" you need CUDA >= 11.X.
CUDA_ROOT ?= /usr/local/cuda/
NVCC := $(CUDA_ROOT)/bin/nvcc -ccbin=icc -allow-unsupported-compiler
CUDA_LIB := -L$(CUDA_ROOT)/lib64 -lnvToolsExt -lcudart -lcuda -lcufft -lcublas
GENCODE_ARCH := -gencode=arch=compute_60,code=\"sm_60,compute_60\" \
-gencode=arch=compute_70,code=\"sm_70,compute_70\" \
-gencode=arch=compute_80,code=\"sm_80,compute_80\"
## For all legacy Intel MPI versions (before 2021)
#MPI_INC = $(I_MPI_ROOT)/intel64/include/
# Or when you are using the Intel oneAPI compiler suite
MPI_INC = $(I_MPI_ROOT)/include/
