====vasp====
For use by authorized users only.
Local copy 5.4.4 (for Intel) is modified from distribution as follows:
installs$ diff -r VASP-REFERENCE/vasp.5.4.4/src VASP/5.4.4/vasp.5.4.4/build/std | grep -v "\.o$" | grep -v "\.f90$" | grep -v "\.mod$"
Only in VASP-REFERENCE/vasp.5.4.4/src: CUDA
Only in VASP-REFERENCE/vasp.5.4.4/src: fftlib
Only in VASP/5.4.4/vasp.5.4.4/build/std/lib: libdmy.a
Only in VASP/5.4.4/vasp.5.4.4/build/std/lib: makefile.include
diff -r VASP-REFERENCE/vasp.5.4.4/src/makefile VASP/5.4.4/vasp.5.4.4/build/std/makefile
18c18
< LLIB=-Llib -ldmy
---
> LLIB=lib/getshmem.o lib/linpack_double.o -Llib -ldmy
131c131
< #OBJCTS_f90=$(filter-out getshmem.o, $(OBJCTS))
---
> OBJCTS_f90=$(filter-out getshmem.o, $(OBJCTS))
Only in VASP/5.4.4/vasp.5.4.4/build/std: makefile.include
Only in VASP/5.4.4/vasp.5.4.4/build/std/parser: libparser.a
Only in VASP/5.4.4/vasp.5.4.4/build/std/parser: makefile.include
Only in VASP-REFERENCE/vasp.5.4.4/src: README
Only in VASP-REFERENCE/vasp.5.4.4/src: vasp.cfg
Only in VASP/5.4.4/vasp.5.4.4/build/std: vasp.O2.smkl
Only in VASP/5.4.4/vasp.5.4.4/build/std: vasp.O3.pmkl
Only in VASP/5.4.4/vasp.5.4.4/build/std: vasp.O3.smkl
installs$
''getshmem.o'' and ''linpack_double.o'' are made in build/lib, and modules and ''makefile.include'' are:
installs$ module load intel/19.0.5 mkl/19.0.5 impi/19.0.5
installs$ cat VASP/5.4.4/vasp.5.4.4/build/std/makefile.include
# Precompiler options
CPP_OPTIONS= -DHOST=\"LinuxIFC\"\
-DMPI -DMPI_BLOCK=8000 \
-Duse_collective \
-DscaLAPACK \
-DCACHE_SIZE=4000 \
-Davoidalloc \
-Duse_bse_te \
-Dtbdyn \
-Duse_shmem
CPP = fpp -f_com=no -free -w0 $*$(FUFFIX) $*$(SUFFIX) $(CPP_OPTIONS)
FC = mpiifort
FCL = mpiifort -mkl=sequential -lstdc++
FREE = -free -names lowercase
FFLAGS = -assume byterecl -w
OFLAG = -O2 -xHOST -qopenmp
OFLAG = -O3 -xsse3 -axsse4.2,AVX,COREAVX512 -qopenmp
OFLAG = -O2 -xsse3 -axsse4.2,AVX,COREAVX512 -qopenmp
OFLAG_IN = $(OFLAG)
DEBUG = -O0
MKL_PATH = $(MKLROOT)/lib/intel64
BLAS =
LAPACK =
BLACS = -lmkl_blacs_intelmpi_lp64
SCALAPACK = $(MKL_PATH)/libmkl_scalapack_lp64.a $(BLACS)
OBJECTS = fftmpiw.o fftmpi_map.o fft3dlib.o fftw3d.o
INCS =-I$(MKLROOT)/include/fftw
LLIBS = $(SCALAPACK) $(LAPACK) $(BLAS)
OBJECTS_O1 += fftw3d.o fftmpi.o fftmpiw.o
OBJECTS_O2 += fft3dlib.o
# For what used to be vasp.5.lib
CPP_LIB = $(CPP)
FC_LIB = $(FC)
CC_LIB = icc
CFLAGS_LIB = -O
FFLAGS_LIB = -O1
FREE_LIB = $(FREE)
OBJECTS_LIB= linpack_double.o getshmem.o
# For the parser library
CXX_PARS = icpc
LIBS += parser
LLIBS += -Lparser -lparser -lstdc++
# Normally no need to change this
SRCDIR = ../../src
BINDIR = ../../bin
#================================================
# GPU Stuff
#CPP_GPU = -DCUDA_GPU -DRPROMU_CPROJ_OVERLAP -DUSE_PINNED_MEMORY -DCUFFT_MIN=28 -UscaLAPACK
#OBJECTS_GPU = fftmpiw.o fftmpi_map.o fft3dlib.o fftw3d_gpu.o fftmpiw_gpu.o
#CC = icc
#CXX = icpc
#CFLAGS = -fPIC -DADD_ -Wall -openmp -DMAGMA_WITH_MKL -DMAGMA_SETAFFINITY -DGPUSHMEM=300 -DHAVE_CUBLAS
#CUDA_ROOT ?= /usr/local/cuda/
#NVCC := $(CUDA_ROOT)/bin/nvcc -ccbin=icc
#CUDA_LIB := -L$(CUDA_ROOT)/lib64 -lnvToolsExt -lcudart -lcuda -lcufft -lcublas
#GENCODE_ARCH := -gencode=arch=compute_30,code=\"sm_30,compute_30\" \
-gencode=arch=compute_35,code=\"sm_35,compute_35\" \
-gencode=arch=compute_60,code=\"sm_60,compute_60\"
MPI_INC = $(I_MPI_ROOT)/intel64/include/
installs$
Some run examples with an OpenMP, MKL sequential build:
module load intel/19.0.5 mkl/19.0.5 impi/19.0.5
mpirun -np 16 -genv OMP_NUM_THREADS=2 /scrfs/apps/vasp/vasp.5.4.4/build/std/vasp.O2.smkl
took 75 seconds on Trestles, 35 seconds on Razor 16-core (with OMP_NUM_THREADS=1)**, 27.3 seconds on Pinnacle.
vasp.o2.smkl took 26.1 seconds on Pinnacle.
**For performance MPI threads x OpenMP threads should not exceed physical cores.