mpi

What is the best MPI implementation

I have to implement MPI system in a cluster. If anyone here has any experience with MPI (MPICH/OpenMPI), I'd like to know which is better and how the performance can be boosted on a cluster of x86_64 boxes. ...

MPI for multicore ?

With the recent buzz on multicore programming is anyone exploring the possibilities of using MPI ? ...

Why is MPI considered harder than shared memory and Erlang considered easier, when they are both message-passing?

There's a lot of interest these days in Erlang as a language for writing parallel programs on multicore. I've heard people argue that Erlang's message-passing model is easier to program than the dominant shared-memory models such as threads. Conversely, in the high-performance computing community the dominant parallel programming model...

How do I debug an MPI program?

I have an MPI program which compiles and runs, but I would like to step through it to make sure nothing bizarre is happening. Ideally, I would like a simple way to attach GDB to any particular process, but I'm not really sure whether that's possible or how to do it. An alternative would be having each process write debug output to a sepa...

OpenMPI: All nodes run as node 0

I have a c++ program that is using the openMPI library to pass messages between different processors. It is a parallel program that uses a genetic algorithm to get a good solution for the traveling salesperson problem. I am trying to set up the MPI environment on my two dual processor computers at my house so that I can run it. When...

F# + MPI + MONO : Clustered Computing

Is it possible for F# and MPI to run off of Mono on a linux computational cluster? Anyone able to attest to it's performance/reliability? ...

Java openmpi

Is there a current Java openmpi implementation. I have programmed in MPI a bit, and I enjoy programming in Java. I have seen this implementation in java, but it seems dated. Is there a more up to date java implementation that is being kept up? ...

mpirun on os X

Is there a way to run a local mpi job locally on os X leopard(10.5.6) with more than 62 processes. When I run the job with 62 processes, it dies $mpirun -np 62 a.out mpirun noticed that job rank 0 with PID 0 on node Macintosh-001D4F4BC6BC.private exited on signal 15 (Terminated). 60 additional processes aborted (not shown) and when...

MPI: Locking the stdout -- 1 process at a time?

Hello. I want to print out the content of integer array of each processes. Problem is, it's all cluttered because of race condition. What is the simplest solution? I don't want to debug. I want to show the contents because I'm doing sorting algorithm. So it's useful to show before and after sort. I added this in lock.c: #include <std...

Using Boost MPI for sending files?

Can I use the Boost MPI to send files to other computers? My worry is that it is optimized for very small messages and not larger (I need to send 700 MB or more in one go). The reason is that I will probably use mpi for other parts of the program anyway so I thought it would be a pretty clean solution to not mix and match. Has it been ...

MPI matrix multification compile err: undeclared

I coded a mpi matrix multification program, which use scanf("%d", &size), designate matrix size, then I defined int matrix[size*size], but when I complied it, it reported that matrix is undeclared. Please tell me why, or what my problem is! According Ed's suggestion, I changed the matrix definition to if(myid == 0) block, but got the sa...

MPI matrix multification compile err: undeclared with code

I coded a mpi matrix multification program, which use scanf("%d", &size), designate matrix size, then I defined int matrix[size*size], but when I complied it, it reported that matrix is undeclared. Please tell me why, or what my problem is! According Ed's suggestion, I changed the matrix definition to if(myid == 0) block, but got the sa...

C++: How is it possible that reading data can affect memory?

I've been going deeper into C++ recently and my bugs seem to get complex. I have a vector of objects, each object contains a vector of floats. I decided I needed to create a further flat array containing all the float values of all objects in one. It's a little more complex than that but the gist of the problem is that as I loop throu...

Performances evaluation with Message Passing

Hi, I have to build a distributed application, using MPI. One of the decision that I have to take is how to map instances of classes into process (and then into machines), in order to take maximum advantages from a distributed environement. My question is: there is a model that let me choose the better mapping? I mean, some arrangement...

MPI4Py Scatter sendbuf Argument Type?

I'm having trouble with the Scatter function in the MPI4Py Python module. My assumption is that I should be able to pass it a single list for the sendbuffer. However, I'm getting a consistent error message when I do that, or indeed add the other two arguments, recvbuf and root: File "code/step3.py", line 682, in subbox_grid i = m...

C: How long can a double be when printed through printf()

I need to specify the exact length of a string to be printed from a double value, but I don't want to restrict the output any more than is necessary. What is the maximum length that a 6-digit precision double will have when formatted by printf()? Specifically, what value should I give to X in printf("%X.6lg",doubleValue); to ensure tha...

Multicore - how to merge local groups of data found on each core?

I have a large set of scalar values distributed over a 3D mesh (one value per vertex.) My goal is to show: all points in the mesh where the value is greater than a threshold. AND group the points that are connected (to simplify the display.) So my basic solution was: Find the points that pass the threshold test For each point th...

How is MPI I/O Implemented?

Long-Winded Background I'm working on parallelising some code for cardiac electrophysiology simulations. Since users can specify their own simulations using an in-built scripting language, I have no way of knowing how to manage the trade-off of communication vs. computation. To combat this, I'm making a sort-of runtime profiler, which w...

MPI using C++

Hi, I have a program, that is been implemented in C++, now I want to add MPI support. The point is exist a MPI bind for C++, with namespace MPI and everything. In my case I have a specific object that is suitable to be the parallelized process into the cluster. Question, does anyone already did something like this ? Can give some advic...

gui for mpi program

Hi, I have a problem about a simple mpi program.This program have some 3D points and these points are moving during the program. I created an simple code by implemented c++ and then I tried to add an simple gui. I used gnuplot library and I have a problem. When I call the gui function the gui is created and it is disappeared at the same ...