similar to: RScaLAPACK package with OpenMPI

All, We are researching approaches to parallel R with the end goal of running R in a distributed manner on a Linux cluster. We expect of course to do some work decomposing our problems to be task-parallel or data-parallel, but wouldn't mind getting an initial boost working with "embarrassingly parallel" code sections and one of the approaches below. Incidentally our environment

Dear R-Users, I have a model with a latent variable for a spatio-temporal process. I would like to use EM algorithm to estimate the parameters. Does anybody know how to implement the algorithm in R? Thank you very much in advance, Michela

Hi all, now I'm testing R in a "virtual cluster", made it with VirtualBox. This one has 3 nodes, running CentOS 5 and OpenMPI 1.2.8, and the principal node (called "server") exports the /home to other nodes. I have installed R and OpenMPI in /home, in fact, it seems work OK. Editing the openmpi-default-hostfile and run "mpirun -np 3 hostname" I can see the

After the 7.2 upgrade?boost-openmpi-1.53.0-25 was installed, along with?openmpi-1.10.0-10. ?The old openmpi was then replaced with?compat- openmpi16-1.6.4-10. ?All fine. Except boost-openmpi has a dependency on the old libmpi.so.1 and the new openmpi has libmpi.so.12: # ldd libboost_mpi-mt.so.1.53.0? linux-vdso.so.1 =>??(0x00007ffe8c182000) libboost_serialization-mt.so.1.53.0 =>

Just wondering if anyone can shed some light into an issue we are having with compat-openmpi after upgrading CentOS to version 6.5 Some of our cluster applications are dependent on an older version of OpenMPI, so we are using compat-openmpi. Up to CentOS 6.4 this was version 1.4.3: % /usr/lib64/compat-openmpi/bin/mpirun -V mpirun (Open MPI) 1.4.3 but after the upgrade to CentOS 6.5 it

Sorry to take so long to reply ... On Thu, 2015-12-17 at 11:53 -0500, Tony Schreiner wrote: > Did you load the compat-openmpi environment module? > > module load mpi/compat-openmpi16-x86_64 Yes, but you can't load both mpi/openmpi-x86_64 and?mpi/compat- openmpi16-x86_64 as they are labelled as conflicting. As I said, if you load just mpi/compat-openmpi16-x86_64 it can't find

I am trying to install the R package "Rmpi" which needs libmpi. I've installed openmpi and lam in Centos 5.2: [root at rab45-1 /]# rpm -qv openmpi openmpi-1.2.5-5.el5 openmpi-1.2.5-5.el5 [root at rab45-1 /]# rpm -qv lam lam-7.1.2-14.el5 lam-7.1.2-14.el5 But I get the following error message when trying to install Rmpi: /usr/bin/ld: skipping incompatible /usr/lib/lam/lib/libmpi.so

Hi list, It appears there is a problem with the OpenMPI I/O library on CentOS 6.2 & 6.3 (package openmpi-1.5.4-1.el6.x86_64). When I compile the attached program it ends up in the error path since MPI_File_open returns 16. The corresponding (unhelpful) message is: MPI_ERR_OTHER: known error not in list I couldn't find any pointers on the net and the same program works with OpenMPI

Greetings. I see a warning message while compiling OpenMPI and would appreciate it if you tell me what it means. This warning happens with any OpenMPI > 1.6.5. Even before starting a cluster, just "sessionInfo" triggers this warning. I'm pasting in the message from R-3.3.2 (this is MRO). Do the R parallel package cluster functions violate the warnings described here? >

I try to install RScaLAPACK on Ubuntu 6.10 and LAM 7.0.x Does anybody know a useful link top some how-to site about RScaLAPACK. Now I manage to get the package compiling, but the linker shows me lots of unsolved references: sudo R CMD INSTALL RScaLAPACK_0.5.1.tar.gz --configure-args="--with-mpi=/usr/lib/lam": * Installing *source* package 'RScaLAPACK' ... configure:

Dear knowledgeable experts :-), I am trying to get openmpi, Rmpi and SNOW running on a Myrinet/GM cluster. I'm not an IT expert, but I surely could use a working installation of Rmpi and SNOW. I try to load the Rmpi library and get the following: > library(Rmpi) [master:07230] mca: base: component_find: unable to open osc pt2pt: file not found (ignored)

I'm running R/snow on a small cluster with opensuse, openmpi, and openshh. I start up R with "mpirun -n 1 R --no-save". That works but it strikes me how easily I get kicked out of R whenever I run into syntax errors. Is there a way to avoid this, for instance, by starting up a regular R session and invoking/activating(?) openmpi within R, e.g. by passing on extra arguments to the

Dear R-Users, I'm using SSPIR package for a spatio-temporal application. Is it possible to modify the structure of the involved matrixes (Fmat, Gmat, Vmat,Wmat)? I want to create a model like this #y(t)=k*theta(t)+epsilon(t) #theta(t)=h*theta(t-1)+eta(t) #epsilon(t) N(0,V) V=sigma2*I #eta(t) N(0,W) W=sigma2_eta where the state variable theta has dimension 1(p=1) and at

Dear R Debian Users: I wrote a quick C program (eventually to become R code) and compiled it as: mpicc -o greet greet.c So far so good. Now when I run mpirun, this happens: erin at erin-laptop:~$ mpirun -np 2 greet ----------------------------------------------------------------------------- It seems that there is no lamd running on the host erin-laptop. This indicates that the LAM/MPI

We have spent some time setting up Sun Grid Engine and OpenMPI on a group of linux boxes. I have created a parallel environment and everything seems to be working. I have Rmpi 0.5.5-5 installed on all machines. I would like to start an interactive R session using, say, 8 processors and then start the Rmpi cluster. I haven't been able to find what needs to be done in order to accomplish

The OpenMPI package that ships with CentOS 5.1 does not seem to be compiled with torque support. It does, however, seem to be compiled with gridengine and slurm support. Would it be possible to get this changed?

Dear all, I usually run R on my laptop with Windows XP Professional. Now I really want to run R on a computer cluster (4 processors) with Suse Linux Enterprise ver. 10. But I am new with computer cluster. Should I modify my functions in order to use the greater performance and availability than that provided by my laptop? Is there any R manual on parallel computations on

Has anybody tried to use Rmpi with the OpenMPI library instead of LAM/MPI? LAM appears to be somewhat hardcoded in the Rmpi setup. Before I start to experiment with changing this, has anybody else tried Rmpi with non-LAM MPI implementations? Dirk -- Hell, there are no rules here - we're trying to accomplish something. -- Thomas A. Edison

Hello, We have R working with Rmpi/openmpi, but I'm a little worried. Specifically, (a) the -np flag doesn't seem to override the hostfile (it works fine with fortran hello world) and (b) I appear to have twice as many processes running as I think I should. Rmpi version 0.5.5 Openmpi version 1.1 Viglen HPC with (effectively) 9 blades and 8 nodes on each blade. myhosts file contains

I have Windows XP Professional Version 2002 and the R-Version 2.1.1. I want to do factor analysis with R. In Google Search I find the reference to the RScaLAPACK-Package, but my R-Version 2.1.1. told me that "RScaLAPACK is invalid package, bevor 2.0.0. installed" . Which package can I take for factor analysis? [[alternative HTML version deleted]]