Makefile.include.nvhpc acc: Difference between revisions
No edit summary |
No edit summary |
||
Line 8: | Line 8: | ||
-Davoidalloc \ | -Davoidalloc \ | ||
-Dvasp6 \ | -Dvasp6 \ | ||
-Dtbdyn \ | -Dtbdyn \ | ||
-Dqd_emulate \ | -Dqd_emulate \ | ||
-Dfock_dblbuf \ | -Dfock_dblbuf \ | ||
- | -DACC_OFFLOAD \ | ||
-DNVCUDA \ | |||
-DUSENCCL | -DUSENCCL | ||
Line 30: | Line 30: | ||
DEBUG = -Mfree -O0 -traceback | DEBUG = -Mfree -O0 -traceback | ||
LLIBS = -cudalib=cublas,cusolver,cufft,nccl -cuda | LLIBS = -cudalib=cublas,cusolver,cufft,nccl -cuda | ||
Line 98: | Line 96: | ||
# Use cusolvermp (optional) | # Use cusolvermp (optional) | ||
# supported as of NVHPC-SDK 24.1 (and needs CUDA-11.8) | # supported as of NVHPC-SDK 24.1 (and needs CUDA-11.8) | ||
#CPP_OPTIONS+= -DCUSOLVERMP | #CPP_OPTIONS+= -DCUSOLVERMP -DCUBLASMP | ||
#LLIBS += -cudalib=cusolvermp | #LLIBS += -cudalib=cusolvermp,cublasmp -lnvhpcwrapcal | ||
# HDF5-support (optional but strongly recommended) | # HDF5-support (optional but strongly recommended, and mandatory for some features) | ||
#CPP_OPTIONS+= -DVASP_HDF5 | #CPP_OPTIONS+= -DVASP_HDF5 | ||
#HDF5_ROOT ?= /path/to/your/hdf5/installation | #HDF5_ROOT ?= /path/to/your/hdf5/installation | ||
Line 113: | Line 109: | ||
#WANNIER90_ROOT ?= /path/to/your/wannier90/installation | #WANNIER90_ROOT ?= /path/to/your/wannier90/installation | ||
#LLIBS += -L$(WANNIER90_ROOT)/lib -lwannier | #LLIBS += -L$(WANNIER90_ROOT)/lib -lwannier | ||
# For machine learning library vaspml (experimental) | |||
#CPP_OPTIONS += -Dlibvaspml | |||
#CPP_OPTIONS += -DVASPML_USE_CBLAS | |||
#CPP_OPTIONS += -DVASPML_DEBUG_LEVEL=3 | |||
#CXX_ML = mpic++ | |||
#CXXFLAGS_ML = -O3 -std=c++17 -Wall -Wextra | |||
#INCLUDE_ML = | |||
</pre> | </pre> | ||
---- | ---- |
Latest revision as of 13:48, 18 December 2024
# Default precompiler options CPP_OPTIONS = -DHOST=\"LinuxNV\" \ -DMPI -DMPI_INPLACE -DMPI_BLOCK=8000 -Duse_collective \ -DscaLAPACK \ -DCACHE_SIZE=4000 \ -Davoidalloc \ -Dvasp6 \ -Dtbdyn \ -Dqd_emulate \ -Dfock_dblbuf \ -DACC_OFFLOAD \ -DNVCUDA \ -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=cc60,cc70,cc80,cuda11.8 FC = mpif90 -acc -gpu=cc60,cc70,cc80,cuda11.8 FCL = mpif90 -acc -gpu=cc60,cc70,cc80,cuda11.8 -c++libs FREE = -Mfree FFLAGS = -Mbackslash -Mlarge_arrays OFLAG = -fast DEBUG = -Mfree -O0 -traceback 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 ## ## 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 host 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 # BLAS (mandatory) BLAS = -lblas # LAPACK (mandatory) LAPACK = -llapack # scaLAPACK (mandatory) SCALAPACK = -Mscalapack LLIBS += $(SCALAPACK) $(LAPACK) $(BLAS) # FFTW (mandatory) FFTW_ROOT ?= /path/to/your/fftw/installation LLIBS += -L$(FFTW_ROOT)/lib -lfftw3 INCS += -I$(FFTW_ROOT)/include # Use cusolvermp (optional) # supported as of NVHPC-SDK 24.1 (and needs CUDA-11.8) #CPP_OPTIONS+= -DCUSOLVERMP -DCUBLASMP #LLIBS += -cudalib=cusolvermp,cublasmp -lnvhpcwrapcal # HDF5-support (optional but strongly recommended, and mandatory for some features) #CPP_OPTIONS+= -DVASP_HDF5 #HDF5_ROOT ?= /path/to/your/hdf5/installation #LLIBS += -L$(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 # For machine learning library vaspml (experimental) #CPP_OPTIONS += -Dlibvaspml #CPP_OPTIONS += -DVASPML_USE_CBLAS #CPP_OPTIONS += -DVASPML_DEBUG_LEVEL=3 #CXX_ML = mpic++ #CXXFLAGS_ML = -O3 -std=c++17 -Wall -Wextra #INCLUDE_ML =