Project

General

Profile

Bug #1168

Test that number of PEs running actually matches expectations (often an issue on MPI builds)

Added by Phil Miller almost 3 years ago. Updated almost 3 years ago.

Status:
Merged
Priority:
High
Assignee:
Category:
Build & Test Automation
Target version:
Start date:
08/18/2016
Due date:
% Done:

0%


Description

On mpi-win64 from autobuild:

../../../bin/testrun  ./migrateHello +p2 10000 65536  

Running on 2 processors:  ./migrateHello 10000 65536
charmrun> mpirun -np 2  ./migrateHello 10000 65536
Charm++> Running on MPI version: 2.0
Charm++> level of thread support used: MPI_THREAD_SINGLE (desired: MPI_THREAD_SINGLE)
Charm++> Running in non-SMP mode: numPes 1
Converse/Charm++ Commit ID: 3cb576a
[0] isomalloc.c> Disabling isomalloc because mmap() does not work
CharmLB> Load balancer assumes all CPUs are same.
Charm++> Running on 1 unique compute nodes (8-way SMP).
Charm++> cpu topology info is gathered in 0.000 seconds.
Running MigrateHello on 1 processors for 10000 iterations 
 migration cost total : 0.000000 sec single migration cost: 0.000000 us
[Partition 0][Node 0] End of program
Charm++> Running on MPI version: 2.0
Charm++> level of thread support used: MPI_THREAD_SINGLE (desired: MPI_THREAD_SINGLE)
Charm++> Running in non-SMP mode: numPes 1
Converse/Charm++ Commit ID: 3cb576a
[0] isomalloc.c> Disabling isomalloc because mmap() does not work
CharmLB> Load balancer assumes all CPUs are same.
Charm++> Running on 1 unique compute nodes (8-way SMP).
Charm++> cpu topology info is gathered in 0.000 seconds.
Running MigrateHello on 1 processors for 10000 iterations 
 migration cost total : 0.000000 sec single migration cost: 0.000000 us
[Partition 0][Node 0] End of program

Note that execution is two instances of 1 PE, not one job with 2 PEs.

Add a test that takes the expected number of PEs as a command-line argument, and asserts that it it matches CkNumPes()

History

#1 Updated by Phil Miller almost 3 years ago

  • Tracker changed from Support to Bug
  • Status changed from New to Implemented

#2 Updated by Phil Miller almost 3 years ago

  • Subject changed from Test that number PEs running actually matches expectations (often an issue on MPI builds) to Test that number of PEs running actually matches expectations (often an issue on MPI builds)
  • Status changed from Implemented to Merged
  • translation missing: en.field_closed_date set to 2016-08-23 18:11:31.674511

#3 Updated by Phil Miller almost 3 years ago

  • Target version changed from 6.8.0 to 6.8.0-beta1

Also available in: Atom PDF