diff -ruN as-is/vasp.5.2/makefile.open64 open64/vasp.5.2/makefile.open64
--- as-is/vasp.5.2/makefile.open64	1969-12-31 16:00:00.000000000 -0800
+++ open64/vasp.5.2/makefile.open64	2013-01-15 11:27:42.000000000 -0800
@@ -0,0 +1,253 @@
+.SUFFIXES: .inc .f .f90 .F
+#-----------------------------------------------------------------------
+# Makefile for AMD systems with the Open64 compiler and ACML library
+#
+# The makefile was created by Martin Hilgeman <martin_hilgeman@dell.com>
+#-----------------------------------------------------------------------
+
+# all CPP processed fortran files have the extension .f 
+SUFFIX=.f90
+
+#-----------------------------------------------------------------------
+# START CUSTOMIZATION HERE 
+#-----------------------------------------------------------------------
+
+#-----------------------------------------------------------------------
+# whereis CPP ?? (I need CPP, can't use gcc with proper options)
+# the following works almost on all systems
+# possible cpp is located in a different directory
+#-----------------------------------------------------------------------
+
+CPP_ =  ./preprocess <$*.F | /usr/bin/cpp -P -C -traditional >$*$(SUFFIX)
+
+#-----------------------------------------------------------------------
+# f90 compiler
+#-----------------------------------------------------------------------
+
+# simple version, use mpif77 wrapper
+# this works only if mpif77 has been compiled using the exactly
+# same fortran compiler
+FC=mpif90
+FCL=$(FC)
+
+#-----------------------------------------------------------------------
+# general fortran flags  (there must a trailing blank on this line)
+#-----------------------------------------------------------------------
+VSC=
+
+FFLAGS = -fno-second-underscore -freeform -ftpp -woff1278,1279,1615 -r8 
+
+#-----------------------------------------------------------------------
+# optimization
+# for some files a lower optimization level is explicitly selected
+# at the bottom
+#-----------------------------------------------------------------------
+
+OFLAG = -O3 -OPT:Olimit=0 -march=bdver1 -mavx -mfma4
+
+OFLAG_HIGH  = $(OFLAG)
+OFLAG_MED   = -O2 -march=bdver1 -mavx -mfma4
+OFLAG_LOW   = -O1 -march=bdver1
+OFLAG_NOOPT = -O0 -march=bdver1
+OBJ_HIGH = 
+OBJ_NOOPT = 
+DEBUG  = -g
+INLINE = $(OFLAG)
+
+#-----------------------------------------------------------------------
+# the following lines specify the position of BLAS  and LAPACK,
+# PBLAS and scaLAPACK
+#-----------------------------------------------------------------------
+
+# Use AMD ACML library for BLAS and LAPACK
+ACML_PATH=/home/martinh/opt/acml/5.2.0/open64_64_fma4
+BLAS=-L$(ACML_PATH)/lib -lacml -lfortran -Wl,-rpath,$(ACML_PATH)/lib
+
+LAPACK =
+
+# location of BLACS and SCALAPACK
+# optional only required if SCA is defined below
+#BLACSdir      = $(VSC)/BLACS/BLACS/LIB
+#BLACS=$(BLACSdir)/blacsF77init_MPI-LINUX-OPENMPI-0.a $(BLACSdir)/blacs_MPI-LINUX-OPENMPI-0.a $(BLACSdir)/blacsF77init_MPI-LINUX-OPENMPI-0.a
+
+## For openmpi
+#BLACS=-lmkl_blacs_openmpi_lp64
+BLACS=
+
+## For mpich
+#BLACS=-lmkl_blacs_lp64
+
+## Just a test for qlogic
+#BLACS=-lmkl_blacs_intelmpi_lp64
+
+SCA_=
+
+# BLACS and SCALAPACK libraries if available
+# if SCA is defined SCALAPACK will be used
+
+#SCA=/home/martinh/opt/scalapack/mvapich2/2.0.2/lib/libscalapack.a
+SCA=/home/martinh/opt/scalapack/openmpi-1.5.5/2.0.2/lib/libscalapack.a
+
+LINK=
+#-----------------------------------------------------------------------
+# END CUSTOMIZATION
+#-----------------------------------------------------------------------
+
+#-----------------------------------------------------------------------
+# options for CPP in parallel version (see also above):
+# NGZhalf               charge density   reduced in Z direction
+# wNGZhalf              gamma point only reduced in Z direction
+# scaLAPACK             use scaLAPACK (usually slower on 100 Mbit Net)
+#-----------------------------------------------------------------------
+ifdef SCA
+CPP    = $(CPP_) -DMPI  -DHOST=\"AMD\ Open64\" \
+     -Dkind8 -DNGZhalf -DCACHE_SIZE=4000 -Davoidalloc \
+     -DscaLAPACK -Duse_collective -Davoidalloc
+else
+CPP    = $(CPP_) -DMPI  -DHOST=\"AMD Open64\" \
+     -Dkind8 -DNGZhalf -DCACHE_SIZE=4000 -Davoidalloc \
+     -Duse_collective -Davoidalloc
+endif
+
+#-----------------------------------------------------------------------
+# libraries for vasp
+#-----------------------------------------------------------------------
+ifdef SCA
+LIB     = -L../vasp.5.lib.open64 -ldmy  \
+      ../vasp.5.lib.open64/linpack_double.o   \
+       $(SCA) $(LAPACK) $(BLAS)  
+else
+LIB     = -L../vasp.5.lib.open64 -ldmy  \
+      ../vasp.5.lib.open64/linpack_double.o   \
+      $(LAPACK)  $(BLAS) 
+endif
+
+# FFT: fftmpi.o with fft3dlib of Juergen Furthmueller
+# must be used for this benchmark
+FFT3D     = fftmpi.o fftmpi_map.o fft3dfurth.o fft3dlib.o
+#rv,sgi FFT3D   = fftmpi.o fftmpi_map.o fft3dlib.o 
+#FFT3D   =  fftmpi.o fftmpi_map.o  fft3dfurth.o fft3dlib.o
+#FFT3D   = fftmpi.o fftmpi_map.o  fftw3d.o  fft3dlib.o   ./libfftw3.a
+#FFT3D   = fftmpi.o fftmpi_map.o  fftw3d.o  fft3dlib.o   ./libfftw3xf_intel.a
+#FFT3D   = fftmpi.o fftmpi_map.o  fftw3d.o  fft3dlib.o  /opt/intel/Compiler/11.0/083/mkl/lib/em64t/libfftw3xf_intel.a
+# FFT3D   = fftmpi.o fftmpi_map.o fftw3d.o fft3dlib.o $(VSC)/FFTW_Intel/lib/em64t/libfftw3xf_intel.a
+
+#-----------------------------------------------------------------------
+# general rules and compile lines
+#-----------------------------------------------------------------------
+OBJ_HIGH   =
+OBJ_MED    = relativistic.o LDApU.o paw_base.o
+OBJ_LOW    = fftmpiw.o fftmpi.o fftw3d.o wave_high.o broyden.o
+OBJ_NOOPT  = nmr.o
+
+BASIC=   symmetry.o symlib.o   lattlib.o  random.o
+
+SOURCE=  base.o     mpi.o      smart_allocate.o      xml.o  \
+         constant.o jacobi.o   main_mpi.o  scala.o   \
+         asa.o      lattice.o  poscar.o   ini.o       xclib.o     xclib_grad.o \
+         radial.o   pseudo.o   mgrid.o    gridq.o     ebs.o  \
+         mkpoints.o wave.o     wave_mpi.o  wave_high.o  \
+         $(BASIC)   nonl.o     nonlr.o    nonl_high.o dfast.o    choleski2.o \
+         mix.o      hamil.o    xcgrad.o   xcspin.o    potex1.o   potex2.o  \
+         constrmag.o cl_shift.o relativistic.o LDApU.o \
+         paw_base.o metagga.o  egrad.o    pawsym.o   pawfock.o  pawlhf.o   rhfatm.o  paw.o   \
+         mkpoints_full.o       charge.o   dipol.o    pot.o  \
+         dos.o      elf.o      tet.o      tetweight.o hamil_rot.o \
+         steep.o    chain.o    dyna.o     sphpro.o    us.o  core_rel.o \
+         aedens.o   wavpre.o   wavpre_noio.o broyden.o \
+         dynbr.o    rmm-diis.o reader.o   writer.o   tutor.o xml_writer.o \
+         brent.o    stufak.o   fileio.o   opergrid.o stepver.o  \
+         chgloc.o   fast_aug.o fock.o     mkpoints_change.o sym_grad.o \
+         mymath.o   internals.o dimer_heyden.o dvvtrajectory.o vdwforcefield.o \
+         hamil_high.o nmr.o    force.o \
+         pead.o     mlwf.o     subrot.o   subrot_scf.o pwlhf.o  gw_model.o optreal.o   davidson.o \
+         electron.o rot.o  electron_all.o shm.o    pardens.o  paircorrection.o \
+         optics.o   constr_cell_relax.o   stm.o    finite_diff.o elpol.o    \
+         hamil_lr.o rmm-diis_lr.o  subrot_cluster.o subrot_lr.o \
+         lr_helper.o hamil_lrf.o   elinear_response.o ilinear_response.o \
+         linear_optics.o linear_response.o   \
+         setlocalpp.o  wannier.o electron_OEP.o electron_lhf.o twoelectron4o.o \
+         ratpol.o screened_2e.o wave_cacher.o chi_base.o wpot.o local_field.o \
+         ump2.o bse.o acfdt.o chi.o sydmat.o
+ 
+INC=
+
+vasp: $(SOURCE) $(FFT3D) $(INC) main.o 
+	rm -f vasp
+	$(FCL) -o vasp main.o $(SOURCE) $(FFT3D) $(LIB) $(LINK)
+vasp_: $(SOURCE) $(FFT3D) $(INC) main.o 
+	rm -f vasp_
+	$(FCL) -o vasp_ main.o  $(SOURCE)   $(FFT3D) $(LIB) $(LINK)
+makeparam: $(SOURCE) $(FFT3D) makeparam.o main.F $(INC)
+	$(FCL) -o makeparam  $(LINK) makeparam.o $(SOURCE) $(FFT3D) $(LIB)
+zgemmtest: zgemmtest.o base.o random.o $(INC)
+	$(FCL) -o zgemmtest $(LINK) zgemmtest.o random.o base.o $(LIB)
+dgemmtest: dgemmtest.o base.o random.o $(INC)
+	$(FCL) -o dgemmtest $(LINK) dgemmtest.o random.o base.o $(LIB) 
+ffttest: base.o smart_allocate.o mpi.o mgrid.o random.o ffttest.o $(FFT3D) $(INC)
+	$(FCL) -o ffttest $(LINK) ffttest.o mpi.o mgrid.o random.o smart_allocate.o base.o $(FFT3D) $(LIB)
+kpoints: $(SOURCE) $(FFT3D) makekpoints.o main.F $(INC)
+	$(FCL) -o kpoints $(LINK) makekpoints.o $(SOURCE) $(FFT3D) $(LIB)
+
+clean:	
+	-rm -f *.mod *.f90 *.o *.L ; touch *.F
+
+main.o: main$(SUFFIX)
+	$(FC) $(FFLAGS)$(DEBUG)  $(INCS) -c main$(SUFFIX)
+xcgrad.o: xcgrad$(SUFFIX)
+	$(FC) $(FFLAGS) $(INLINE)  $(INCS) -c xcgrad$(SUFFIX)
+xcspin.o: xcspin$(SUFFIX)
+	$(FC) $(FFLAGS) $(INLINE)  $(INCS) -c xcspin$(SUFFIX)
+
+makeparam.o: makeparam$(SUFFIX)
+	$(FC) $(FFLAGS)$(DEBUG)  $(INCS) -c makeparam$(SUFFIX)
+
+makeparam$(SUFFIX): makeparam.F main.F 
+#
+# MIND: I do not have a full dependency list for the include
+# and MODULES: here are only the minimal basic dependencies
+# if one strucuture is changed then touch_dep must be called
+# with the corresponding name of the structure
+#
+base.o: base.inc base.F
+mgrid.o: mgrid.inc mgrid.F
+constant.o: constant.inc constant.F
+lattice.o: lattice.inc lattice.F
+setex.o: setexm.inc setex.F
+pseudo.o: pseudo.inc pseudo.F
+poscar.o: poscar.inc poscar.F
+mkpoints.o: mkpoints.inc mkpoints.F
+wave.o: wave.inc wave.F
+nonl.o: nonl.inc nonl.F
+nonlr.o: nonlr.inc nonlr.F
+
+fft3dlib_f77.o: fft3dlib_f77.F
+	$(CPP)
+	$(F77) $(FFLAGS_F77) -c $*$(SUFFIX)
+
+.F.o:
+	$(CPP)
+	$(FC) $(FFLAGS) $(OFLAG) $(INCS) -c $*$(SUFFIX)
+.F$(SUFFIX):
+	$(CPP)
+$(SUFFIX).o:
+	$(FC) $(FFLAGS) $(OFLAG) $(INCS) -c $*$(SUFFIX)
+
+# special rules
+#-----------------------------------------------------------------------
+
+# -tpp5|6|7 P, PII-PIII, PIV
+# -xW use SIMD (does not pay of on PII, since fft3d uses double prec)
+# all other options do no affect the code performance since -O1 is used
+$(OBJ_HIGH):
+	$(CPP)
+	$(FC) $(FFLAGS) $(OFLAG_HIGH) $(INCS) -c $*$(SUFFIX)
+$(OBJ_MED):
+	$(CPP)
+	$(FC) $(FFLAGS) $(OFLAG_MED) $(INCS) -c $*$(SUFFIX)
+$(OBJ_LOW):
+	$(CPP)
+	$(FC) $(FFLAGS) $(OFLAG_LOW) $(INCS) -c $*$(SUFFIX)
+$(OBJ_NOOPT):
+	$(CPP)
+	$(FC) $(FFLAGS) $(OFLAG_NOOPT) $(INCS) -c $*$(SUFFIX)