用NVIDIA HPC-SDK和FFTW 安装GPU版VASP

fftw下载网址：FFTW Download Page

wget http://www.fftw.org/fftw-3.3.10.tar.gz
tar -xvzf fftw-3.3.10.tar.gz
cd fftw-3.3.10.tar.gz
source ~/intel/oneapi/setvars.sh
./configure --prefix /home/wliu/Applications/fftw
make
make install

NVIDIA HPC-SDK安装：参见Ubuntu安装GPU版VASP6.4.3（含NVIDIA显卡驱动安装更新）-CSDN博客

makefile.include文件内容 

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

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
CC          = mpicc  -acc -gpu=cc89,cc90,cuda12.2
FC          = mpif90 -acc -gpu=cc89,cc90,cuda12.2
FCL         = mpif90 -acc -gpu=cc89,cc90,cuda12.2 -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 minimax_dependence.o
SOURCE_O2  := pead.o

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

OBJECTS_LIB = linpack_double.o

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

# When compiling on the target machine itself , change this to the
# relevant target when cross-compiling for another architecture
VASP_TARGET_CPU ?= -tp znver4
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 }')

## 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

# BLAS (mandatory)
BLAS        = -lblas

# LAPACK (mandatory)
LAPACK      = -llapack

# scaLAPACK (mandatory)
SCALAPACK   = -Mscalapack

LLIBS      += $(SCALAPACK) $(LAPACK) $(BLAS)

# FFTW (mandatory)
FFTW_ROOT  ?= /home/wliu/Applications/fftw
LLIBS      += -L$(FFTW_ROOT)/lib -lfftw3
INCS       += -I$(FFTW_ROOT)/include

# 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

编译 

make std DEPS=1 -j 20

个人测试结果，发现HPC-SDK+MKL编译出的VASP比HPC-SDK+FFTW编译出的VASP计算速度快。