Databases
StackOverflow2013
Postsdbo
POMPI Matrix Multiplication with scatter gather
 

Note that there are some explanatory texts on larger screens.

plurals
  1. POMPI Matrix Multiplication with scatter gather
    primarykey
    data
    text
    <p>I'm trying to do matrix multiplication using MPI in C and we have to do a version that sequential and one parallel version. My parallel version is not giving the correct answers and I'm not sure why. I think I'm not sending the right communications to the processes but I can't be sure. The professor just went over the different send/receive/gather etc messages, but didn't really get into much detail... I've seen a lot of different examples but none complete and none using scatter/gather. If anyone can take a look at my code and tell me if anything pops out at them I'd appreciate it. I'm pretty sure my problem is in the scatter/gather messages or the actual calculation of the c matrix.</p> <pre><code>#define N 512 #include &lt;stdio.h&gt; #include &lt;math.h&gt; #include &lt;sys/time.h&gt; #include &lt;stdlib.h&gt; #include &lt;stddef.h&gt; #include "mpi.h" print_results(char *prompt, float a[N][N]); int main(int argc, char *argv[]) { int i, j, k, rank, size, tag = 99, blksz, sum = 0; float a[N][N], b[N][N], c[N][N]; char *usage = "Usage: %s file\n"; FILE *fd; double elapsed_time, start_time, end_time; struct timeval tv1, tv2; MPI_Init(&amp;argc, &amp;argv); MPI_Comm_size(MPI_COMM_WORLD, &amp;size); MPI_Comm_rank(MPI_COMM_WORLD, &amp;rank); if (argc &lt; 2) { fprintf (stderr, usage, argv[0]); return -1; } if ((fd = fopen (argv[1], "r")) == NULL) { fprintf (stderr, "%s: Cannot open file %s for reading.\n", argv[0], argv[1]); fprintf (stderr, usage, argv[0]); return -1; } for (i = 0; i &lt; N; i++) for (j = 0; j &lt; N; j++) fscanf (fd, "%f", &amp;a[i][j]); for (i = 0; i &lt; N; i++) for (j = 0; j &lt; N; j++) fscanf (fd, "%f", &amp;b[i][j]); MPI_Barrier(MPI_COMM_WORLD); gettimeofday(&amp;tv1, NULL); MPI_Scatter(a, N*N/size, MPI_INT, a, N*N/size, MPI_INT, 0, MPI_COMM_WORLD); MPI_Bcast(b, N*N, MPI_INT, 0, MPI_COMM_WORLD); if (rank != 0) { for (i = 0; i &lt; N; i++) { for (j = 0; j &lt; N; j++) { for (k = 0; k &lt; N; k++) { sum = sum + a[i][k] * b[k][j]; } c[i][j] = sum; sum = 0; } } } MPI_Gather(c, N*N/size, MPI_INT, c, N*N/size, MPI_INT, 0, MPI_COMM_WORLD); MPI_Finalize(); gettimeofday(&amp;tv2, NULL); elapsed_time = (tv2.tv_sec - tv1.tv_sec) + ((tv2.tv_usec - tv1.tv_usec)/1000000.0); printf ("elapsed_time=\t%lf (seconds)\n", elapsed_time); print_results("C = ", c); } print_results(char *prompt, float a[N][N]) { int i, j; printf ("\n\n%s\n", prompt); for (i = 0; i &lt; N; i++) { for (j = 0; j &lt; N; j++) { printf(" %.2f", a[i][j]); } printf ("\n"); } printf ("\n\n"); } </code></pre> <p>updated part of code:</p> <pre><code>for (i=0;i&lt;size; i++) { if (rank == i) { for (i = rank*(N/size); i &lt; (rank*(N/size)+(N/size)); i++) { for (j = rank*(N/size); j &lt; (rank*(N/size)+(N/size)); j++) { for (k = rank*N; k &lt; rank*N+N; k++) { sum = sum + a[i][k] * b[k][j]; } c[i][j] = sum; sum = 0; } } } } </code></pre>
    singulars
    1. PO
      singulars
      1. PTAnswer
    1. This table or related slice is empty.
    1. PTQuestion
    1. USuser939287
    1. USuser939287
    plurals
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. PO
      singulars
      1. PTAnswer
    1. This table or related slice is empty.
    1. COOne thing that jumps out: the root should supply the magic value `MPI_IN_PLACE` for `recvbuf` in scatter and gather. Just supplying the same pointer for `sendbuf` and `recvbuf` technically violates the spec. Also, `MPI_Finalize` can take a long time. You should probably not be timing it.
      singulars
      1. POMPI Matrix Multiplication with scatter gather
      1. USGreg Inozemtsev
    2. COSorry, `MPI_IN_PLACE` should be supplied for `sendbuf` in `MPI_Gather`. Also, the root participates in scatter and gather, but then you exclude it from doing the computation. It should participate, just like the other ranks.
      singulars
      1. POMPI Matrix Multiplication with scatter gather
      1. USGreg Inozemtsev
    3. COBesides what Greg Inozemtsev and Francesco have already spotted, your computational kernel loops over the entire matrix `a` and not only over the part that resides in the memory of the current rank. The range of the `i` loop should be restricted accordingly. Also MPI provides the `MPI_Wtime()` timer function which has the same precision as `gettimeofday` if not even higher (as the MPI standard advises the implementors to use the highest resolution timer available).
      singulars
      1. POMPI Matrix Multiplication with scatter gather
      1. USHristo Iliev
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload