VASP: Add uenv tests for GH200

checks/apps/vasp/src/makefile.include.gh200

@@ -0,0 +1,122 @@
+# 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_OPENMP \
+              -D_OPENACC \
+              -DUSENCCL -DUSENCCLP2P
+
+CPP         = nvfortran -Mpreprocess -Mfree -Mextend -E $(CPP_OPTIONS) $*$(FUFFIX)  > $*$(SUFFIX)
+
+CUDA_VERSION = $(shell nvcc -V | grep -E -o -m 1 "[0-9][0-9]\.[0-9]," | rev | cut -c 2- | rev)
+
+CC          = mpicc -acc -gpu=cc90,cuda${CUDA_VERSION} -mp
+FC          = mpif90 -acc -gpu=cc90,cuda${CUDA_VERSION} -mp
+FCL         = mpif90 -acc -gpu=cc90,cuda${CUDA_VERSION} -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 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
+#
+# NOTE: Using "-tp neoverse-v2" causes some tests to fail. On GH200 architecture, "-tp host"
+# is recommended.
+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 -Wl,-rpath,$(QD)/lib
+INCS       += -I$(QD)/include/qd
+
+# BLAS (mandatory)
+BLAS        = -lnvpl_blas_lp64_gomp -lnvpl_blas_core
+
+# LAPACK (mandatory)
+LAPACK      = -lnvpl_lapack_lp64_gomp -lnvpl_lapack_core
+
+# scaLAPACK (mandatory)
+SCALAPACK   = -lscalapack
+
+LLIBS      += $(SCALAPACK) $(LAPACK) $(BLAS) -Wl,-rpath,/user-environment/env/develop/lib -Wl,-rpath,/user-environment/env/develop/lib64 -Wl,--disable-new-dtags
+
+# FFTW (mandatory)
+FFTW_ROOT  ?= /user-environment/env/develop
+LLIBS      += -L$(FFTW_ROOT)/lib -lfftw3 -lfftw3_omp
+INCS       += -I$(FFTW_ROOT)/include
+
+# Use cusolvermp (optional)
+# supported as of NVHPC-SDK 24.1 (and needs CUDA-11.8)
+#CPP_OPTIONS+= -DCUSOLVERMP -DCUBLASMP
+#LLIBS      += -cudalib=cusolvermp,cublasmp -lnvhpcwrapcal
+
+# HDF5-support (optional but strongly recommended)
+CPP_OPTIONS+= -DVASP_HDF5
+HDF5_ROOT  ?= /user-environment/env/develop
+LLIBS      += -L$(HDF5_ROOT)/lib -lhdf5_fortran
+INCS       += -I$(HDF5_ROOT)/include
+
+# For the VASP-2-Wannier90 interface (optional)
+CPP_OPTIONS    += -DVASP2WANNIER90
+WANNIER90_ROOT ?= /user-environment/env/develop
+LLIBS          += -L$(WANNIER90_ROOT)/lib -lwannier
+
+# For the fftlib library (recommended)
+#CPP_OPTIONS+= -Dsysv
+#FCL        += fftlib.o
+#CXX_FFTLIB  = nvc++ -mp --no_warnings -std=c++11 -DFFTLIB_THREADSAFE
+#INCS_FFTLIB = -I./include -I$(FFTW_ROOT)/include
+#LIBS       += fftlib
+#LLIBS      += -ldl