Opened 8 years ago

Last modified 22 months ago

#919 new bug

Allgatherv performance

Reported by: balaji Owned by: huiweilu
Priority: major Milestone: mpich-3.3
Component: mpich Keywords:
Cc:

Description (last modified by balaji)

One of the users reported a performance problem for Allgatherv for non-power-of-2 number of processes on large systems. On reading through the code, it looks like our algorithms rely on the "total message size" gathered, rather than the message size contributed by each process. So, for large-scale systems, even small message sizes go through an O(P) algorithm.

We should take another look at the irregular collectives to improve these cases.

Change History (11)

comment:1 Changed 7 years ago by balaji

  • Milestone changed from mpich2-1.3 to mpich2-1.3.1

comment:2 Changed 7 years ago by balaji

  • Milestone changed from mpich2-1.3.2 to mpich2-1.3.3

comment:3 Changed 7 years ago by balaji

  • Milestone changed from mpich2-1.3.3 to mpich2-1.3.4

comment:4 Changed 7 years ago by balaji

  • Milestone changed from mpich2-1.3.4 to mpich2-1.4.1

Milestone mpich2-1.3.4 deleted

comment:5 Changed 5 years ago by balaji

  • Milestone changed from mpich2-1.5 to mpich2-1.5.1

comment:6 Changed 5 years ago by balaji

  • Milestone changed from mpich2-1.5.1 to mpich-3.0

Milestone mpich2-1.5.1 deleted

comment:7 Changed 5 years ago by balaji

  • Milestone changed from mpich-3.0 to mpich-3.0.1

comment:8 Changed 4 years ago by balaji

  • Description modified (diff)
  • Milestone changed from mpich-3.1 to mpich-3.1.1

comment:9 Changed 4 years ago by balaji

  • Owner changed from balaji to huiweilu

comment:10 Changed 3 years ago by balaji

  • Milestone changed from mpich-3.1.4 to mpich-3.2

Milestone mpich-3.1.4 deleted

comment:11 Changed 22 months ago by balaji

  • Milestone changed from mpich-3.2.1 to mpich-3.3

Milestone mpich-3.2.1 deleted

Note: See TracTickets for help on using tickets.