Open MPI User's Mailing List Archives

Subject: Re: [OMPI users] Processor/core selection/affinity for large shared memory systems
From: V. Ram (v_r_959_at_[hidden])
Date: 2008-12-05 13:07:20

• Next message: Nick Wright: "Re: [OMPI users] Issue with Profiling Fortran code"
• Previous message: Brian W. Barrett: "Re: [OMPI users] Issue with Profiling Fortran code"
• Maybe in reply to: V. Ram: "[OMPI users] Processor/core selection/affinity for large shared memory systems"
• Next in thread: Lenny Verkhovsky: "Re: [OMPI users] Processor/core selection/affinity for large shared memory systems"
• Reply: Lenny Verkhovsky: "Re: [OMPI users] Processor/core selection/affinity for large shared memory systems"

Terry Frankcombe wrote:

> Isn't it up to the OS scheduler what gets run where?

I was under the impression that the processor affinity API was designed
to let the OS (at least Linux) know how a given task preferred to be
bound in terms of the system topology.

-- 
  V. Ram
  v_r_959_at_[hidden]
-- 
http://www.fastmail.fm - Accessible with your email software
                          or over the web

• Next message: Nick Wright: "Re: [OMPI users] Issue with Profiling Fortran code"
• Previous message: Brian W. Barrett: "Re: [OMPI users] Issue with Profiling Fortran code"
• Maybe in reply to: V. Ram: "[OMPI users] Processor/core selection/affinity for large shared memory systems"
• Next in thread: Lenny Verkhovsky: "Re: [OMPI users] Processor/core selection/affinity for large shared memory systems"
• Reply: Lenny Verkhovsky: "Re: [OMPI users] Processor/core selection/affinity for large shared memory systems"