Databases
StackOverflow2013
Postsdbo
POMPI_Scatter Segfaulting
 

Note that there are some explanatory texts on larger screens.

plurals
  1. POMPI_Scatter Segfaulting
    primarykey
    data
    text
    <p>I'm working on a parallel sort program to learn MPI, and I've been having problems with MPI_Scatter. Every time I attempt to run, I get the following:</p> <pre><code>reading input Scattering input _pmii_daemon(SIGCHLD): [NID 00012] PE 0 exit signal Segmentation fault [NID 00012] 2011-03-28 10:12:56 Apid 23655: initiated application termination </code></pre> <p>A basic look at other questions didn't really answer why I'm having troubles - The arrays are contiguous, so I shouldn't have problems with non-contiguous memory access, and I'm passing the correct pointers in the correct order. Does anyone have any ideas?</p> <p>Source code is below - It's specified for a specific number because I don't want to deal with variable input and rank size just yet.</p> <pre><code>#include &lt;mpi.h&gt; #include &lt;iostream&gt; using std::endl; using std::cout; #include &lt;fstream&gt; using std::ifstream; using std::ofstream; #include &lt;algorithm&gt; using std::sort; #define SIZEOF_INPUT 10000000 #define NUMTHREADS 100 #define SIZEOF_SUBARRAY SIZEOF_INPUT/NUMTHREADS int main(int argc, char** argv){ MPI_Init(&amp;argc, &amp;argv); int input[SIZEOF_INPUT]; int tempbuf[SIZEOF_SUBARRAY]; int myRank; MPI_Comm_rank(MPI_COMM_WORLD, &amp;myRank); /* Read input from file */ if(myRank == 0){ cout &lt;&lt; "reading input" &lt;&lt; endl; ifstream in(argv[1]); for(int i = 0; i &lt; SIZEOF_INPUT; ++i) in &gt;&gt; input[i]; cout &lt;&lt; "Scattering input" &lt;&lt; endl; } // Scatter, Sort, and Gather again MPI_Scatter(input,SIZEOF_INPUT,MPI_INT,tempbuf,SIZEOF_SUBARRAY,MPI_INT,0,MPI_COMM_WORLD); cout &lt;&lt; "Rank " &lt;&lt; myRank &lt;&lt; "Sorting" &lt;&lt; endl; sort(tempbuf,tempbuf+SIZEOF_SUBARRAY); MPI_Gather(tempbuf,SIZEOF_SUBARRAY,MPI_INT,input,SIZEOF_INPUT,MPI_INT,0,MPI_COMM_WORLD); if(myRank == 0){ cout &lt;&lt; "Sorting final output" &lt;&lt; endl; // I'm doing a multi-queue merge here using tricky pointer games //list of iterators representing things in the queue int* iterators[NUMTHREADS]; //The ends of those iterators int* ends[NUMTHREADS]; //Set up iterators and ends for(int i = 0; i &lt; NUMTHREADS; ++i){ iterators[i] = input + (i*SIZEOF_SUBARRAY); ends[i] = iterators[i] + SIZEOF_SUBARRAY; } ofstream out(argv[2]); int ULTRA_MAX = SIZEOF_INPUT + 1; int* ULTRA_MAX_POINTER = &amp;ULTRA_MAX; while(true){ int** curr_min = &amp;ULTRA_MAX_POINTER; for(int i = 0 ; i &lt; NUMTHREADS; ++i) if(iterators[i] &lt; ends[i] &amp;&amp; *iterators[i] &lt; **curr_min) curr_min = &amp;iterators[i]; if(curr_min == &amp;ULTRA_MAX_POINTER) break; out &lt;&lt; **curr_min &lt;&lt; endl; ++(*curr_min); } } MPI_Finalize(); } </code></pre> <p>Any help would be much appreciated. Regards, Zach</p>
    singulars
    1. PO
      singulars
      1. PTAnswer
    1. This table or related slice is empty.
    1. PTQuestion
    1. This table or related slice is empty.
    1. USZach H
    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
    2. PO
      singulars
      1. PTAnswer
    1. VO
      singulars
      1. POMPI_Scatter Segfaulting
      1. USZach H
      1. VTFavorite
    1. COKinda obvious, but are you sure you spawn the same number of processes that you use in the code?
      singulars
      1. POMPI_Scatter Segfaulting
      1. USsuszterpatt
    2. CO@suszterpatt Yes, I do. Good thought though
      singulars
      1. POMPI_Scatter Segfaulting
      1. USZach H
 

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