Re: [OMPI users] Using OSU benchmarks for checking network

t; > > Do you get similar results when you repeat the test? Another job > > could > > > have interfered with your run. > > > Benson > > > On 2/7/22 3:56 PM, Bertini, Denis Dr. via users wrote: > > >> Hi > > >> > > &

Re: [OMPI users] Using OSU benchmarks for checking Infiniband network

Hi I do not have so much experience with MVAPICH. Since we work with singularity container, i can create a container and install this version to compare. Cheers, Denis From: users on behalf of Joseph Schuchart via users Sent: Tuesday, February 8, 2022 4:0

Re: [OMPI users] Using OSU benchmarks for checking Infiniband network

Hi Denis, Sorry if I missed it in your previous messages but could you also try running a different MPI implementation (MVAPICH) to see whether Open MPI is at fault or the system is somehow to blame for it? Thanks Joseph On 2/8/22 03:06, Bertini, Denis Dr. via users wrote: Hi Thanks for a

Re: [OMPI users] Using OSU benchmarks for checking Infiniband network

Sorry it is float and size output by the benchmark is in bytes: https://github.com/ROCm-Developer-Tools/OSU_Microbenchmarks/blob/master/mpi/collective/osu_allreduce.c Data cache is 32 Kb per core: https://www.cpu-world.com/CPUs/Zen/AMD-EPYC%207571.html One send array of 16Kb and one receive array

Re: [OMPI users] Using OSU benchmarks for checking Infiniband network

Hi Thanks a lot for all the infos ! Very interesting thanks ! We use basically AMP EPYC processor >> vendor_id : AuthenticAMD cpu family : 23 model : 1 model name : AMD EPYC 7551 32-Core Processor stepping : 2 microcode : 0x8001250 cpu MHz : 2000.000 cache size : 512 KB physical id : 1 siblin

Re: [OMPI users] Using OSU benchmarks for checking Infiniband network

On 2/8/22 11:06 AM, Bertini, Denis Dr. via users wrote: Hi Thanks for all these informations ! But i have to confess that in this multi-tuning-parameter space, i got somehow lost. Furthermore it is somtimes mixing between user-space and kernel-space. I have only possibility to act on the us

[OMPI users] Issues with MPI_Win_Create on Debian 11

Hi all, There are several bug reports on 4.1.x describing MPI_Win_create failing for various architectures.  I too am seeing the same for 4.1.0-10 which is packaged for Debian 11, just on a standard workstation where at least vader,tcp,self, and sm are identified (not sure which are being used

Re: [OMPI users] Using OSU benchmarks for checking Infiniband network

Hi Thanks for all these informations ! But i have to confess that in this multi-tuning-parameter space, i got somehow lost. Furthermore it is somtimes mixing between user-space and kernel-space. I have only possibility to act on the user space. 1) So i have on the system max locked memory: