CC = gcc CXX = g++ CPP = FC = mpifort LD = mpifort NVCC = nvcc GPUVER = $(_gpuver) AR = ar -r DFLAGS = -D__FFTW3 \ -D__LIBINT \ -D__parallel -D__ELPA -D__COSMA -D__SCALAPACK \ -D__LIBXSMM \ -D__LIBXC \ -D__SPGLIB \ -D__DBCSR_ACC -D__PW_CUDA -D__GRID_CUDA INCS = -I/usr/include \ -I/usr/include/elpa_openmp-$(_elpaver)/elpa \ -I/usr/include/elpa_openmp-$(_elpaver)/modules \ -I/opt/cuda/include OPTFLAGS = -O3 -march=native -fopenmp CFLAGS = $(DFLAGS) $(INCS) $(OPTFLAGS) CXXFLAGS = $(DFLAGS) $(INCS) $(OPTFLAGS) -std=c++11 CPPFLAGS = FCFLAGS = $(DFLAGS) $(INCS) $(OPTFLAGS) \ -ffree-form -ffree-line-length-none \ -fallow-argument-mismatch NVFLAGS = $(DFLAGS) -O3 -Xcompiler="-fopenmp" \ -gencode arch=compute_35,code=sm_35 \ -gencode arch=compute_37,code=sm_37 \ -gencode arch=compute_50,code=sm_50 \ -gencode arch=compute_52,code=sm_52 \ -gencode arch=compute_60,code=sm_60 \ -gencode arch=compute_61,code=sm_61 \ -gencode arch=compute_70,code=sm_70 \ -gencode arch=compute_75,code=sm_75 \ -gencode arch=compute_80,code=sm_80 \ -gencode arch=compute_86,code=sm_86 \ -Wno-deprecated-gpu-targets LDFLAGS = $(FCFLAGS) LIBS = -L/opt/cuda/lib64 -lcudart -lcuda \ -lcublas -lcufft -lrt -lnvrtc \ -lxsmmf -lxsmm -lelpa_openmp \ -lcosma_prefixed_pxgemm -lcosma -lcosta -lTiled-MM \ -lscalapack -lblas -llapack \ -lfftw3 -lfftw3_threads \ /usr/lib/libint2.a \ -lxcf03 -lxc \ -lsymspg \ -lstdc++ -lpthread -lm -ldl -lz