Compiling NAMD-2.11 with Intel 2013-SP1 and iMPI 4.1.3 and FFTW-2.1.5

Step 1: Prepare for Environment Setup

source /usr/local/intel_2013sp1/composerxe/mkl/bin/mklvars.sh intel64
source /usr/local/intel_2013sp1/composerxe/bin/compilervars.sh intel64
source /usr/local/intel_2013sp1/impi/4.1.3.048/intel64/bin/mpivars.sh intel64
source /usr/local/intel_2013sp1/composerxe/tbb/bin/tbbvars.sh intel64
source /usr/local/intel_2013sp1/itac/8.1.4.045/intel64/bin/itacvars.sh

export CC=icc
export CXX=icpc
export F77=ifort
export F90=ifort

Step 2: Building FFTW-2.1.5 with Intel

$ wget http://www.fftw.org/fftw-2.1.5.tar.gz
$ tar -zxvf fftw-2.1.5.tar.gz
$ cd fftw-2.1.5
$ ./configure F77=ifort CC=icc CFLAGS=-O3 FFLAGS=-O3 --enable-threads --enable-float --enable-type-prefix --prefix=/usr/local/fftw-2.1.5_intel-4.1.3
$ make -j 16
$ make install

Step 3: Building CHARM-6.7.0

$ tar -zxvf NAMD_2.11_Source.tar.gz
$ export $NAMD_SRC=$PWD/NAMD_2.11_Source
$ cd $NAMD_SRC
$ tar -xvf charm-6.7.0.tar
$ MPICXX=mpiicpc CXX=icpc ./build charm++  mpi-linux-x86_64 mpicxx ifort --with-production --no-shared -O3 -DCMK_OPTIMIZE=1
$ cd $NAMD_SRC

Step 4: Building TCL-8.5.9

$ wget http://www.ks.uiuc.edu/Research/namd/libraries/tcl8.5.9-linux-x86_64.tar.gz
$ wget http://www.ks.uiuc.edu/Research/namd/libraries/tcl8.5.9-linux-x86_64-threaded.tar.gz
$ tar xzf tcl8.5.9-linux-x86_64.tar.gz
$ tar xzf tcl8.5.9-linux-x86_64-threaded.tar.gz
$ mv tcl8.5.9-linux-x86_64 tcl-8.5.9
$ mv tcl8.5.9-linux-x86_64-threaded tcl-8.5.9-threaded

Step 5: Setup the CHARMBASE in $NAMD_SRC for Make.charm

# Set CHARMBASE to the top level charm directory.
# The config script will override this setting if there is a directory
# called charm-6.7.0 or charm in the NAMD base directory.
CHARMBASE = /home/user1/NAMD/NAMD_2.11_Source/charm-6.7.0

Step 6: Setup the FFTW architecture files in $NAMD_SRC/arch

$ vim $NAMD_SRC/arch/Linux-x86_64.fftw

FFTDIR=/usr/local/fftw-2.1.5_intel-14.0.2
FFTINCL=-I$(FFTDIR)/include
FFTLIB=-L$(FFTDIR)/lib -lsrfftw -lsfftw
FFTFLAGS=-DNAMD_FFTW
FFT=$(FFTINCL) $(FFTFLAGS)

Step 7: Setup the TCL architecture files in $NAMD_SRC/arch

 $ vim $NAMD_SRC/arch/Linux-x86_64.tcl

TCLDIR=/usr/local/tcl8.5.9-threaded
TCLINCL=-I$(TCLDIR)/include
TCLLIB=-L$(TCLDIR)/lib -ltcl8.5 -ldl -lpthread
TCLFLAGS=-DNAMD_TCL
TCL=$(TCLINCL) $(TCLFLAGS)

Step 8: Setup the $NAMD_SRC/Linux-x86_64-ics-2013.arch

$ vim Linux-x86_64-ics-2013.arch

NAMD_ARCH = Linux-x86_64
CHARMARCH = mpi-linux-x86_64-ifort-mpicxx
FLOATOPTS = -O2
CXX = icpc -std=c++11
CXXOPTS = -static-intel -O2 $(FLOATOPTS)
CXXNOALIASOPTS = -O3 -fno-alias $(FLOATOPTS)
CC = icc
COPTS = -static-intel -O2 $(FLOATOPTS)

Step 9: Compile the Code.

$ ./config Linux-x86_64-ics-2013 --charm-base ./charm-6.7.0 --charm-arch mpi-linux-x86_64-ifort-mpicxx
$ cd Linux-x86_64-ics-2013
$ make -j 16

You should see the namd2 executable

 Step 10: MPIRUN

$ mpirun -np 32 -machinefile $MACHINEFILE namd2  something.conf > job$LSB_JOBID.log

References:

1. How to install NAMD 2.9 with Intel Cluster Studio 2013 on Intel Sandy Bridge architecture and IB support
2. Compiling NAMD
3. Namd-old

Installing NAMD 2.9 with Intel Cluster Studio 2013 with IB support

There is a very good article of Installing NAMD 2.9 with Intel Cluster Studio 2013 with IB support. You may want to take a look at

How to install NAMD 2.9 with Intel Cluster Studio 2013 on Intel Sandy Bridge architecture and IB support

List of mkl_solver* libraries are deprecated libraries since version 10.2 Update 2

Taken from mkl_solver* libraries are deprecated libraries since version 10.2 Update 2

Since version 10.2 update 2 of Intel® MKL,
all components of Direct Solver (Pardiso and DSS), Trust-Region (TR) Solver, Iterative Sparse Solver (ISS) and GNU Multiple Precision (GMP) were moved to standard MKL libraries.
So now solver ( e.g: mkl_solver.lib and mkl_solver_sequential.lib for IA32 ) libraries are
empty (for backward compatibility).
The list of deprecated libraries are the following:

Intel® MKL for Linux:

lib/32/libmkl_solver.a
lib/32/libmkl_solver_sequential.a
lib/em64t/libmkl_solver_ilp64.a
lib/em64t/libmkl_solver_ilp64_sequential.a
lib/em64t/libmkl_solver_lp64.a
lib/em64t/libmkl_solver_lp64_sequential.a
lib/ia64/libmkl_solver_ilp64.a
lib/ia64/libmkl_solver_ilp64_sequential.a
lib/ia64/libmkl_solver_lp64.a
lib/ia64/libmkl_solver_lp64_sequential.a

Therefore, the updated linking line will look like:


Linking on Intel®64:
static linking:
ifort pardiso.f -L$MKLPATH -I$MKLINCLUDE \
-Wl,--start-group \
$MKLPATH/libmkl_intel_lp64.a $MKLPATH/libmkl_intel_thread.a $MKLPATH/libmkl_core.a \
-Wl,--end-group -liomp5 -lpthread
dynamic linking:
ifort pardiso.f -L$MKLPATH -I$MKLINCLUDE \
-lmkl_intel_lp64 -lmkl_intel_thread -lmkl_core -liomp5 -lpthread
where:
In these examples,
MKLPATH=$MKLROOT/lib/em64t
MKLINCLUDE=$MKLROOT/include.

Compiling CPMD-3.17.1 with Intel-13.0.1.117 and OpenMPI-1.8.3

I’m assuming you have compiled OpenMPI with Intel Compiler. If you are not sure, you can look at Blog Entry
Compiling OpenMPI 1.6.5 with Intel 12.1.5 on CentOS 6
To get the source code from CPMD, please go to http://www.cpmd.org/

Step 1: From the CPMD Directory

cd ~/CPMD-3.13.2/SOURCE
./mkconfig.sh IFORT-AMD64-MPI > Makefile

Step 2: I’m using CentOS 6 internal Blas, lapack and atlas. Make sure your configure the one below.

#--------------- Default Configuration for IFORT-AMD64-MPI ---------------
SRC  = .
DEST = .
BIN  = .
FFLAGS = -pc64  -tpp6 -O2 -unroll
#LFLAGS =  -L. -latlas_x86_64
LFLAGS =  -L/usr/lib64/atlas -llapack -lblas
CFLAGS = -O2 -Wall -m64
CPP = /lib/cpp -P -C -traditional
CPPFLAGS = -D__Linux -D__PGI -DFFT_DEFAULT -DPOINTER8 -DLINUX_IFC \
-DPARALLEL
NOOPT_FLAG =
CC = mpicc
FC = mpif77 -c
LD = mpif77 -i-static
AR = ar
#----------------------------------------------------------------------------

Step 3: Compile CPMD

# make

If the compilation succeed, it should generate a cpmd.x executable.

Step 4: Pathing
Make sure your $PATH reflect the path of the executable cpmd.x. It is also important to ensure that you check that the libraries are properly linked to the executable

# ldd cpmd.x

Step 5: Test your executable. You have to go to CPMD Consortium to download the cpmd-test.tar.gz for testing.

I/O Direction for Bash

This is a good article on I/O Redirection. I have always been interest to redirect stderr to stdout. So here is it 2>&1

 2>&1
      # Redirects stderr to stdout.
      # Error messages get sent to same place as standard output.
        >>filename 2>&1
            bad_command >>filename 2>&1
            # Appends both stdout and stderr to the file "filename" ...
        2>&1 | [command(s)]
            bad_command 2>&1 | awk '{print $5}'   # found
            # Sends stderr through a pipe.
            # |& was added to Bash 4 as an abbreviation for 2>&1 |.