- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
The structure of my code is,
//part1
if(i>1){
Compute1;
}
//part2
if(i<m)
{
Compute2;
MPI_Allgatherv(); //Replaced by MPI_Iallgatherv();
}
//part3
if(i>0)
{
Compute3;
MPI_Allreduce();
}
part4
if(i<m){
Compute4;
}
Collective operations in part 2 is the bottleneck of this program.
I replaced "MPI_Allgatherv()" by the NBC "MPI_Iallgatherv()" in order to hide the collective communication by part3 and part4. But part3 and part4 take much longer than before. What do you think is the cause of this problem?
Thanks!
Link Copied
0 Replies

Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page