Gilles Gouaillardet

Results 87 comments of Gilles Gouaillardet

I was able to reproduce the issue on a RHEL7 box with external PMIx `4.2.3`. On archlinux, I can reproduce the bug if I use a manually recompiled PMIX `4.2.3`,...

@rhc54 could you please shed some light? the locality (e.g. the `pmix.loc` key) is set by `ess/pmi`: ``` kv = OBJ_NEW(opal_value_t); kv->key = strdup(OPAL_PMIX_LOCALITY); kv->type = OPAL_UINT16; OPAL_OUTPUT_VERBOSE((1, orte_ess_base_framework.framework_output, "%s...

@rhc54 thanks! I did a quick try but i messed up somewhere ... anyway, I did a differential debugging, and found something that looks suspicious to me: - `4.2.2`: `PMIX_INFO_CREATE()`...

@rhc54 I think I see what is going on ... we should use `PMIX_INFO_LOAD(...)` in `pmix3x_value_load(...)` instead of doing some `memcpy()`. I did the following hack in `PMIx_Get(...)` from `ext3x_client.c`...

FWIW I am unable to reproduce the issue on a RHEL8 system with `Intel(R) Fortran Compiler for applications running on Intel(R) 64, Version 2023.2.0 Build 20230622` ``` $ ../../src/ompi-v5.0.x/configure --prefix=$HOME/local/ompi-v5.0.x-isan...

I still do not get why `libxml2.so` gets pulled. Can you please run `mpirun -np 1 ldd ./just_init.exe` in order to make sure the right Open MPI library gets pulled?...

Thanks, yes `libxml2.so` is detected at `configure` time, but as you can see in the `ldd` output, `libhwloc.so` does not depend on it. I guess it gets pulled indirectly by...

From your `hwloc``config.log` ``` configure:27839: checking for rocm_smi/rocm_smi.h configure:27839: gcc -c -g -O2 -I/opt/rocm/rocm_smi/include/ conftest.c >&5 configure:27839: $? = 0 configure:27839: result: yes configure:27847: checking for rsmi_init in -lrocm_smi64 configure:27870:...

On second thought, it seems the real issue is `ROCm` is indeed detected and flagged as usable **but** it cannot be used because its API is incompatible with `hwloc 2.7.1`....

@bgoglin In this environment, ROCm is detected but cannot be used (that sound like an incompatible API) Is this something you are aware of? Has it been fixed in the...