Load Balance Checker for MPP LS-DYNA

A simple ‘C’ program is included to extract the processor based timing information from D3HSP file and output load balance summary. Future versions of MPP-LS-DYNA may include more information such as the summary shown below.

Usage: load_balance_checker d3hsp_file_name {threshold_factor}

Download

Source Preview

/*
 Load Balance Diagnosis for MPP LS-DYNA
 Author: Suri Bala, Livermore Software
 Copyright: Livermore Software
 Credits: Brian Wainscott, Jason Wang
 Contact: suri@lstc.com
 Usage: exe_name d3hsp_file_name {threshold_factor}
 Description: Performs a load balance check for all processors
 Compilation: cc source_file_name.c -o exe_file_name
*/
#include
#include
#include

#define LINE_WIDTH 128

int main(int argc, char *argv[]) {

 FILE *d3hsp = NULL;
 char buffer[LINE_WIDTH];
 int i, num_threads=0, host_count=0;
 float *hosts, ratio, sum =0, average_timing=1, min_timing=1e20, max_timing=-1e20;;
 float threshold_factor = 0.2, max_threshold=0, min_threshold=0;


 // if no d3hsp file is specified, exit out
 if( argc == 1 ) {
    printf("Usage: %s d3hsp_file n", argv[0]);
    exit(-1);
 }

 // open the d3hsp file
 d3hsp = fopen(argv[1], "r");
 if( !d3hsp ) {
   printf("Could not open file %sn", argv[1]);
   exit(-2);
 }

 //if threshold is specified accept it
 if( argc==3) {
   sprintf(argv[2], "%10.4f", threshold_factor);
 }

 // start reading the lines from d3hsp file
 while( !feof(d3hsp) ) {
     fgets(buffer, LINE_WIDTH, d3hsp);
     // get the num of threads
     if( strncmp(buffer+1,"Parallel", 8) == 0 )  {
         sscanf(buffer+25,"%d", &num_threads);
         hosts = (float *) malloc(num_threads*sizeof(float));
     }
     // store the host based timing
     if( buffer[25] == '#' ) {
         sscanf(buffer+65," %e ", &hosts[host_count]);
         if( hosts[host_count] > max_timing) max_timing = hosts[host_count];
         if( hosts[host_count] < min_timing) min_timing = hosts[host_count];
         sum += hosts[host_count];
         ++host_count;
     }
 }

 average_timing = sum/num_threads;
 max_threshold = (float)1.0+threshold_factor;
 min_threshold = (float)1.0-threshold_factor;

 fprintf(stdout, "n  Load Balance Summary nn");
 fprintf(stdout, "     Processor Number            Ratio           Status            Remarksn");
 fprintf(stdout, " --------------------------------------------------------------------------------------------n");
 for(i=0; i<host_count; i++)="" {="" ratio="hosts[i]/average_timing;" fprintf(stdout,="" "="" %10d="" %2.2f",="" i,="" ratio);="" if(=""> max_threshold) fprintf(stdout,"%20s%10s%20s","Overloaded"," "," Better decomposition is needed");
     if( ratio < min_threshold ) fprintf(stdout,"%20s%10s%20s","Underloaded"," "," Better decomposition is needed");
     fprintf(stdout,"n");
 }
 fprintf(stdout, " --------------------------------------------------------------------------------------------n");
 fprintf(stdout, "     Total number of threads: %10dn", num_threads);
 fprintf(stdout, "     Timing n");
 fprintf(stdout, "     Average CPU (seconds)  : %10.4fn", average_timing);
 fprintf(stdout, "     Maximum CPU (seconds)  : %10.4fn", max_timing);
 fprintf(stdout, "     Minimum CPU (seconds)  : %10.4fn", min_timing);
 fprintf(stdout, "     Thresholds n");
 fprintf(stdout, "     Maximum threshold used : %10.4fn", max_threshold);
 fprintf(stdout, "     Minimum threshold used : %10.4fn", min_threshold);
 fprintf(stdout, "nn");

 fclose(d3hsp);
 exit(0);

}


</host_count;>

Sample Output

  Load Balance Summary

     Processor Number            Ratio           Status            Remarks
 --------------------------------------------------------------------------------------------
              0                  0.81
              1                  0.86
              2                  0.87
              3                  1.00
              4                  1.36          Overloaded           Better decomposition is needed
              5                  1.02
              6                  1.11
              7                  1.34          Overloaded           Better decomposition is needed
              8                  1.14
              9                  0.89
             10                  0.82
             11                  0.78         Underloaded           Better decomposition is needed
 --------------------------------------------------------------------------------------------
     Total number of threads:         12
     Timing
     Average CPU (seconds)  : 31791.2500
     Maximum CPU (seconds)  : 43180.0000
     Minimum CPU (seconds)  : 24829.0000
     Thresholds
     Maximum threshold used :     1.2000
     Minimum threshold used :     0.8000