Hi,
@Gilles Awesome. --bind-to hwthread does the trick. I thought binding
and mapping would not be read if using --rankfile.
@Jeff I am running on a shared cluster. Some apps do use HT for
achieving better performance. Nothing we could do with BIOS settings.
Regards
On 08/09/2023 17:53, Jeff
@Gilles @Jeff Sorry, I think I replied too quickly. This is what I see
if using --bind-to hwthread
This is not what I was after. I only want to use thread 0 of a core ie
(cores 0-7), so "cores 192-199" should not have any activity. If I do
--bind-to core, the activity jumps from "core 0" to
Isn't this a case for --map-by core --bind-to hwthread? Because you want to map each
process by core but bind the the first hwthread.From the looks of it your process is
both binding and mapping by hwthread now. -NathanOn Sep 11, 2023, at 10:20 AM, Luis
Cebamanos via users wrote:@Gilles @Jeff
HIi Nathan,
Isn't this a case for --map-by core --bind-to hwthread? Because you
want to map each process by core but bind the the first hwthread.
It is, but indicating a rankfile I can map to certain core numbers. I
cannot use both --map-by and --rankfile:
Conflicting directives for mapping p
What is the syntax of the mpirun command running an application built with
OpenMPI 4.1.4 to place the first N MPI processes with a density of n PEs per a
Cascade Lake node (n/2 per socket, each node has 48 cores) and the next M
(N+1, N+2, ..., N+M) MPI processes after that with a density of m M
