https://medjava.ro/ 2026-04-07T11:17:33+00:00 https://medjava.ro/ https://medjava.ro/lib/exe/fetch.php?media=wiki:dokuwiki.svg text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:broadcast&rev=1735842138&do=diff MPI Broadcast MPI program using MPI_Bcast for broadcasting a message from one process (typically the master process) to all other processes in the communicator. This example will demonstrate how a single value can be sent from one process to all others in a simple and efficient way using MPI's broadcast functionality. text/html 2024-02-21T15:20:35+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:clion-ide-mpi-config&rev=1708528835&do=diff Configure CLion to run an Open MPI project on Windows Install OpenMPI on Ubuntu After installing WSL2/Ubuntu, run: sudo apt-get install openmpi-bin openmpi-common libopenmpi-dev Configure CLion to use WSL2 Change build directory Set build directory to the root project folder: text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:comm-split&rev=1735842138&do=diff MPI Comm Split A number of processes N, divisible by 4, are divided into groups of 4. Within each group, processes will form a ring and send their rank to the next process in the ring. The program will use MPI_Comm_split to create these groups. Each process will then print its original rank and the size of the original group, as well as its new rank and the size of the new group. text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:hello-world&rev=1735842138&do=diff MPI Hello World #include <mpi.h> #include <stdio.h> int main(int argc, char** argv) { // Initialize the MPI environment MPI_Init(NULL, NULL); // Get the number of processes int world_size; MPI_Comm_size(MPI_COMM_WORLD, &world_size); // Get the rank of the process int world_rank; MPI_Comm_rank(MPI_COMM_WORLD, &world_rank); // Check if the current process is the master process if (world_rank == 0) { // Master process prints this message … text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:makefile&rev=1735842138&do=diff Makefile build: mpicc -o helloapp helloapp.c -pthread -Wall run: mpirun -np 8 --oversubscribe helloapp clean: rm -f helloapp -- text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:pipeline-polynomial&rev=1735842138&do=diff MPI Calculate Polynom Using Pipeline An MPI program in English to calculate a polynomial using a pipeline approach. In this example, we'll compute a polynomial of the form f(x) = ax^2 + bx + c, where a, b and c are coefficients and x is the variable. text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:pipeline-vector-sort&rev=1735842138&do=diff MPI Pipeline Vector Sort Let's implement a pipeline-based sorting algorithm using MPI. In this scenario, we have n + 1 MPI processes: 1 master and n workers. Each worker will eventually hold one number from the original unsorted array, and the array will be sorted in ascending order across the ranks of the workers. text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:pipeline&rev=1735842138&do=diff MPI Pipeline In a pipeline pattern, data is passed through a series of processes in stages, much like an assembly line in a factory. Each process in the pipeline performs some operation on the data and then passes it to the next process. Let's create a simple pipeline where each process receives a number, adds its rank to this number, and passes it to the next process in the pipeline. The first process starts with a number (say, 0), and the last process prints the final result. This example wi… text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:rank-sort-parallel&rev=1735842138&do=diff MPI Rank Sort in Parallel We will follow the specific steps of the rank-based sorting algorithm, parallelizing the calculation of ranks. Each process will compute the rank for a subset of the vector and contribute to determining the final position of elements in the sorted array. text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:reduce&rev=1735842138&do=diff MPI Reduce The MPI_Reduce function is used to perform a reduction operation (like sum, max, min, etc.) on values held by each process, gathering them into a single result at a designated root process. In this example, each process will generate a random number, and we'll use text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:ring-algorithm&rev=1735842138&do=diff MPI Ring Algorithm In this algorithm, processes form a logical ring. Each process sends a message to the next process in the ring (the last process sends the message back to the first process). This is a typical example used to demonstrate MPI communication patterns. text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:scan&rev=1735842138&do=diff MPI Scan MPI_Scan is similar to MPI_Reduce, but instead of gathering the reduced result at a single root process, it performs a parallel prefix reduction, providing each process with a partial result of the reduction operation up to that point in the sequence of processes. text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:scatter-gather&rev=1735842138&do=diff MPI Scatter and Gather MPI program that combines both MPI_Scatter and MPI_Gather. In this example, the master process (rank 0) will scatter an array to all processes. Each process will perform some operation on its received portion, and then MPI_Gather text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:scatter&rev=1735842138&do=diff MPI Scatter Using MPI_Scatter to distribute parts of an array from the master process to all processes in an MPI communicator. MPI_Scatter is used to divide an array into equal segments and distribute each segment to a different process. #include <mpi.h> #include <stdio.h> int main(int argc, char** argv) { // Initialize the MPI environment MPI_Init(&argc, &argv); // Get the rank of the process int world_rank; MPI_Comm_rank(MPI_COMM_WORLD, &world_rank); // Get the t… text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:send-receive&rev=1735842138&do=diff MPI Send and Receive MPI program using MPI_Send and MPI_Recv for communication between processes. This program will involve two processes: the master process (rank 0) will send a message to a worker process (rank 1), which will then receive the message and print it. text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:topology-validation-epidemic-algorithm&rev=1735842138&do=diff MPI Topology Validation Using Epidemic Algorithm Creating a full program implementation that includes all stages—leader election, topology validation through an epidemic algorithm, and constructing a topology matrix using a tree algorithm. Assumptions text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:wave-algorithm-leader-election-spanning-tree&rev=1735842138&do=diff MPI Wave algorithm with leader election and spanning tree construction Implementing a wave algorithm with leader election and spanning tree construction in MPI is a complex task that involves multiple phases: leader election using a heartbeat algorithm, constructing a text/html 2025-01-02T18:22:18+00:00 Anonymous (anonymous@undisclosed.example.com) https://medjava.ro/doku.php?id=c:mpi:wave-algorithm&rev=1735842138&do=diff MPI Wave Algorithm Implementing a wave algorithm in MPI involves creating a pattern where each process communicates with its neighbors in a specific sequence. This can be used to model wave-like propagation of information across the processes. In this example, let's consider a simple scenario where each process sends a message to its next neighbor, waits to receive a message from its previous neighbor, and then sends a confirmation back.