Makefile.include.nvhpc ompi mkl omp acc - Revision history

Wolloch at 08:19, 23 March 2026

2026-03-23T08:19:45Z

← Older revision		Revision as of 08:19, 23 March 2026
Line 23:		Line 23:
	# to the hardware you are targeting		# to the hardware you are targeting
	GPU ?= -gpu=cc60,cc70,cc80,cc89,cuda12.6		GPU ?= -gpu=cc60,cc70,cc80,cc89,cuda12.6

			# For Blackwell (cc100 and above):
			# - the CUDA version needs to be 13.0 or higher.
			# - cc100 (or higher) may not be combined with lower compute capabilities.
			# Uncomment the line below
			#GPU = -gpu=cc100,cuda13.1

	CC = mpicc -mp -acc $(GPU)		CC = mpicc -mp -acc $(GPU)
Line 124:		Line 130:
	#LLIBS += -ldl		#LLIBS += -ldl

	# For machine learning library ~~vaspml~~ (experimental)		# For machine learning library VASPml (experimental)
	#CPP_OPTIONS += -Dlibvaspml		#CPP_OPTIONS += -Dlibvaspml
	#CPP_OPTIONS += -~~DVASPML_USE_CBLAS~~		#CPP_OPTIONS += -DVASPML_USE_MKL
	~~#CPP_OPTIONS += -DVASPML_DEBUG_LEVEL=3~~		#CXX_ML = mpic++ -mp
	#CXX_ML = mpic++ -mp		#CXXFLAGS_ML = -O3 -std=c++17 -Wall -Wextra
	#CXXFLAGS_ML = -O3 -std=c++17 -Wall -Wextra		#INCLUDE_ML =
	#INCLUDE_ML =		## This may be required for the C++17 filesystem library if the underlying
			## system compiler is older than GNU 9.1. For newer versions this can be removed.
			#LLIBS += -lstdc++fs

	# Add -gpu=tripcount:host to compiler commands for NV HPC-SDK > 25.1		# Add -gpu=tripcount:host to compiler commands for NV HPC-SDK > 25.1

Hampel at 13:16, 10 June 2025

2025-06-10T13:16:15Z

← Older revision		Revision as of 13:16, 10 June 2025
Line 19:		Line 19:

	# N.B.: you might need to change the cuda-version here		# N.B.: you might need to change the cuda-version here
	# to one that comes with your NVIDIA-HPC SDK		# to one that comes with your NVIDIA-HPC SDK, and
	CC = ~~mpicc -acc~~ -gpu=cc60,cc70,cc80,~~cuda11~~.8 -mp		# the compute capabilities to the ones applicable
	FC = mpif90 -acc ~~-gpu=cc60,cc70,cc80,cuda11.8 -mp~~		# to the hardware you are targeting
	FCL = mpif90 -acc ~~-gpu=cc60,cc70,cc80,cuda11.8 -mp~~ -c++libs		GPU ?= -gpu=cc60,cc70,cc80,cc89,cuda12.6

			CC = mpicc -mp -acc $(GPU)
			FC = mpif90 -mp -acc $(GPU)
			FCL = mpif90 -mp -acc $(GPU) -c++libs

	FREE = -Mfree		FREE = -Mfree
Line 81:		Line 85:
	# Intel MKL for FFTW, BLAS, LAPACK, and scaLAPACK		# Intel MKL for FFTW, BLAS, LAPACK, and scaLAPACK
	MKLROOT ?= /path/to/your/mkl/installation		MKLROOT ?= /path/to/your/mkl/installation
	#MKLLIBS = -Mmkl		MKLLIBS = -Mmkl
	MKLLIBS = -lmkl_intel_lp64 -lmkl_pgi_thread -lmkl_core -pgf90libs -mp -lpthread -lm -ldl		#MKLLIBS = -lmkl_intel_lp64 -lmkl_pgi_thread -lmkl_core -pgf90libs -mp -lpthread -lm -ldl

	# If you want to use scaLAPACK from MKL		# If you want to use scaLAPACK from MKL
Line 127:		Line 131:
	#CXXFLAGS_ML = -O3 -std=c++17 -Wall -Wextra		#CXXFLAGS_ML = -O3 -std=c++17 -Wall -Wextra
	#INCLUDE_ML =		#INCLUDE_ML =

			# Add -gpu=tripcount:host to compiler commands for NV HPC-SDK > 25.1
			NVFORTRAN_VERSION := $(shell nvfortran --version \| sed -n '2s/^nvfortran $[0-9.]$./\1/p')
			define greater_or_equal
			$(shell printf '%s\n%s\n' '$(1)' '$(2)' \| sort -V \| head -n1 \| grep -q '$(2)' && echo true \|\| echo false)
			endef
			ifeq ($(call greater_or_equal,$(NVFORTRAN_VERSION),25.1),true)
			CC += -gpu=tripcount:host
			FC += -gpu=tripcount:host
			endif
	</pre>		</pre>
	----		----

Csheldon at 13:49, 18 December 2024

2024-12-18T13:49:50Z

← Older revision		Revision as of 13:49, 18 December 2024
Line 8:		Line 8:
	-Davoidalloc \		-Davoidalloc \
	-Dvasp6 \		-Dvasp6 \
	~~-Duse_bse_te \~~
	-Dtbdyn \		-Dtbdyn \
	-Dqd_emulate \		-Dqd_emulate \
	-Dfock_dblbuf \		-Dfock_dblbuf \
	-D_OPENMP \		-D_OPENMP \
	-~~D_OPENACC~~ \		-DACC_OFFLOAD \
			-DNVCUDA \
	-DUSENCCL		-DUSENCCL

Line 20:		Line 20:
	# N.B.: you might need to change the cuda-version here		# N.B.: you might need to change the cuda-version here
	# to one that comes with your NVIDIA-HPC SDK		# to one that comes with your NVIDIA-HPC SDK
	CC = mpicc -acc -gpu=cc60,cc70,cc80,cuda11.8 -mp		CC = mpicc -acc -gpu=cc60,cc70,cc80,cuda11.8 -mp
	FC = mpif90 -acc -gpu=cc60,cc70,cc80,cuda11.8 -mp		FC = mpif90 -acc -gpu=cc60,cc70,cc80,cuda11.8 -mp
	FCL = mpif90 -acc -gpu=cc60,cc70,cc80,cuda11.8 -mp -c++libs		FCL = mpif90 -acc -gpu=cc60,cc70,cc80,cuda11.8 -mp -c++libs

Line 31:		Line 31:

	DEBUG = -Mfree -O0 -traceback		DEBUG = -Mfree -O0 -traceback

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

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

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

Line 83:		Line 81:
	# Intel MKL for FFTW, BLAS, LAPACK, and scaLAPACK		# Intel MKL for FFTW, BLAS, LAPACK, and scaLAPACK
	MKLROOT ?= /path/to/your/mkl/installation		MKLROOT ?= /path/to/your/mkl/installation
	LLIBS_MKL = ~~-Mmkl~~ -L$(MKLROOT)/lib~~/intel64~~ -lmkl_scalapack_lp64 -lmkl_blacs_openmpi_lp64		#MKLLIBS = -Mmkl
	~~INCS += -I~~$(~~MKLROOT~~)~~/include/fftw~~		MKLLIBS = -lmkl_intel_lp64 -lmkl_pgi_thread -lmkl_core -pgf90libs -mp -lpthread -lm -ldl

			# If you want to use scaLAPACK from MKL
			LLIBS_MKL = -L$(MKLROOT)/lib -lmkl_scalapack_lp64 -lmkl_blacs_openmpi_lp64 $(MKLLIBS)

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

	LLIBS += $(LLIBS_MKL)		LLIBS += $(LLIBS_MKL)

			INCS += -I$(MKLROOT)/include/fftw

	# 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
	~~#CFLAGS_LIB +=~~ -~~cudalib=cusolvermp~~
	~~#OBJECTS_LIB+= cal_mpi.o~~

	# 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 118:		Line 119:
	#LIBS += fftlib		#LIBS += fftlib
	#LLIBS += -ldl		#LLIBS += -ldl

			# For machine learning library vaspml (experimental)
			#CPP_OPTIONS += -Dlibvaspml
			#CPP_OPTIONS += -DVASPML_USE_CBLAS
			#CPP_OPTIONS += -DVASPML_DEBUG_LEVEL=3
			#CXX_ML = mpic++ -mp
			#CXXFLAGS_ML = -O3 -std=c++17 -Wall -Wextra
			#INCLUDE_ML =
	</pre>		</pre>
	----		----

Huebsch at 15:13, 6 February 2024

2024-02-06T15:13:48Z

← Older revision		Revision as of 15:13, 6 February 2024
Line 3:		Line 3:
	# Default precompiler options		# Default precompiler options
	CPP_OPTIONS = -DHOST=\"LinuxNV\" \		CPP_OPTIONS = -DHOST=\"LinuxNV\" \
	-DMPI -DMPI_BLOCK=8000 -Duse_collective \		-DMPI -DMPI_INPLACE -DMPI_BLOCK=8000 -Duse_collective \
	-DscaLAPACK \		-DscaLAPACK \
	-DCACHE_SIZE=4000 \		-DCACHE_SIZE=4000 \
Line 14:		Line 14:
	-D_OPENMP \		-D_OPENMP \
	-D_OPENACC \		-D_OPENACC \
	-DUSENCCL ~~-DUSENCCLP2P~~		-DUSENCCL

	CPP = nvfortran -Mpreprocess -Mfree -Mextend -E $(CPP_OPTIONS) $$(FUFFIX) > $$(SUFFIX)		CPP = nvfortran -Mpreprocess -Mfree -Mextend -E $(CPP_OPTIONS) $$(FUFFIX) > $$(SUFFIX)
Line 20:		Line 20:
	# N.B.: you might need to change the cuda-version here		# N.B.: you might need to change the cuda-version here
	# to one that comes with your NVIDIA-HPC SDK		# to one that comes with your NVIDIA-HPC SDK
	FC = mpif90 -acc -gpu=cc60,cc70,cc80,cuda11.0 -mp		CC = mpicc -acc -gpu=cc60,cc70,cc80,cuda11.8 -mp
	FCL = mpif90 -acc -gpu=cc60,cc70,cc80,cuda11.0 -mp -c++libs		FC = mpif90 -acc -gpu=cc60,cc70,cc80,cuda11.8 -mp
			FCL = mpif90 -acc -gpu=cc60,cc70,cc80,cuda11.8 -mp -c++libs

	FREE = -Mfree		FREE = -Mfree
Line 36:		Line 37:

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

	# For what used to be vasp.5.lib		# For what used to be vasp.5.lib
	CPP_LIB = $(CPP)		CPP_LIB = $(CPP)
	FC_LIB = ~~nvfortran~~		FC_LIB = $(FC)
	CC_LIB = ~~nvc -w~~		CC_LIB = $(CC)
	CFLAGS_LIB = -O		CFLAGS_LIB = -O -w
	FFLAGS_LIB = -O1 -Mfixed		FFLAGS_LIB = -O1 -Mfixed
	FREE_LIB = $(FREE)		FREE_LIB = $(FREE)
Line 57:		Line 58:
	## necessary ...		## 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)		# Specify your NV HPC-SDK installation (mandatory)
Line 66:		Line 71:
	#NVVERSION = 21.11		#NVVERSION = 21.11
	#NVROOT = $(NVHPC)/Linux_x86_64/$(NVVERSION)		#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)		# Software emulation of quadruple precsion (mandatory)
Line 72:		Line 81:
	INCS += -I$(QD)/include/qd		INCS += -I$(QD)/include/qd

	# Intel MKL (FFTW, BLAS, LAPACK, and scaLAPACK)		# Intel MKL for FFTW, BLAS, LAPACK, and scaLAPACK
	MKLROOT ?= /path/to/your/mkl/installation		MKLROOT ?= /path/to/your/mkl/installation
	~~LLIBS +~~= -Mmkl -L${MKLROOT}/lib/intel64 -lmkl_scalapack_lp64 -lmkl_blacs_openmpi_lp64		LLIBS_MKL = -Mmkl -L$(MKLROOT)/lib/intel64 -lmkl_scalapack_lp64 -lmkl_blacs_openmpi_lp64
	INCS += -I$(MKLROOT)/include/fftw		INCS += -I$(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)

			# Use cusolvermp (optional)
			# supported as of NVHPC-SDK 24.1 (and needs CUDA-11.8)
			#CPP_OPTIONS+= -DCUSOLVERMP
			#LLIBS += -cudalib=cusolvermp
			#CFLAGS_LIB += -cudalib=cusolvermp
			#OBJECTS_LIB+= cal_mpi.o

	# HDF5-support (optional but strongly recommended)		# HDF5-support (optional but strongly recommended)
Line 88:		Line 111:
	#LLIBS += -L$(WANNIER90_ROOT)/lib -lwannier		#LLIBS += -L$(WANNIER90_ROOT)/lib -lwannier

	# For the fftlib library (~~experimental~~)		# For the fftlib library (hardly any benefit for the OpenACC GPU port, especially in combination with MKL's FFTs)
	#CPP_OPTIONS+= -Dsysv		#CPP_OPTIONS+= -Dsysv
	#FCL += fftlib.o		#FCL += fftlib.o
Line 97:		Line 120:
	</pre>		</pre>
	----		----
			[[makefile.include]]

	[[Category:VASP]]		[[Category:VASP]]
	[[Category:Installation]]		[[Category:Installation]]

Ftran at 08:33, 20 October 2023

2023-10-20T08:33:40Z

← Older revision		Revision as of 08:33, 20 October 2023
Line 97:		Line 97:
	</pre>		</pre>
	----		----
	~~[[The_VASP_Manual\|Contents]]~~

	[[Category:VASP]]		[[Category:VASP]]
	[[Category:Installation]]		[[Category:Installation]]

Huebsch at 09:58, 20 January 2022

2022-01-20T09:58:52Z

← Older revision		Revision as of 09:58, 20 January 2022
Line 96:		Line 96:
	#LLIBS += -ldl		#LLIBS += -ldl
	</pre>		</pre>
			----
			[[The_VASP_Manual\|Contents]]

			[[Category:VASP]]
			[[Category:Installation]]

Huebsch: Created page with "{{DISPLAYTITLE:makefile.include.nvhpc_ompi_mkl_omp_acc}}

 # Default precompiler options CPP_OPTIONS = -DHOST=\"LinuxNV\" \               -DMPI -DMPI_BLOCK=8000 -Duse_coll..."

2022-01-19T07:58:14Z

Created page with "{{DISPLAYTITLE:makefile.include.nvhpc_ompi_mkl_omp_acc}} <pre> # Default precompiler options CPP_OPTIONS = -DHOST=\"LinuxNV\" \ -DMPI -DMPI_BLOCK=8000 -Duse_coll..."

New page

{{DISPLAYTITLE:makefile.include.nvhpc_ompi_mkl_omp_acc}}
<pre>
# 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

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=cc60,cc70,cc80,cuda11.0 -mp
FCL = mpif90 -acc -gpu=cc60,cc70,cc80,cuda11.0 -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

# 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 ...
##

# 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)

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

# Intel MKL (FFTW, BLAS, LAPACK, and scaLAPACK)
MKLROOT ?= /path/to/your/mkl/installation
LLIBS += -Mmkl -L${MKLROOT}/lib/intel64 -lmkl_scalapack_lp64 -lmkl_blacs_openmpi_lp64
INCS += -I$(MKLROOT)/include/fftw

# 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

# For the fftlib library (experimental)
#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
</pre>