On Mon, Oct 10, 2022 at 8:13 AM Rob Kudyba wrote:
> OK, let's walk back and don't use -DCMAKE_C_COMPILER=/path/to/mpicc
>>
> Will do
>
>
>> libompitrace.so.40.30.0 is not the OpenMP library; it is the tracing
>> library for OpenMPI, https://github.com/open-mpi/ompi/issues/10036
>>
> Does that
OK so I missed the OpenMP vs OpenMPI with incorrectly setting
-DOpenMP_libomp_LIBRARY="/path/to/openmpi-4.1.1_ucx_cuda_11.0.3_support/lib//libompitrace.so.40.30.0
So
I changed it to point to /cm/local/apps/gcc/10.2.0/lib/libgomp.so.1.0.0
-- Found PETSc 3.18.0
CMake Error at
>
> OK, let's walk back and don't use -DCMAKE_C_COMPILER=/path/to/mpicc
>
Will do
> libompitrace.so.40.30.0 is not the OpenMP library; it is the tracing
> library for OpenMPI, https://github.com/open-mpi/ompi/issues/10036
>
Does that mean I should remove this option in the cmake command?
> In
OK, let's walk back and don't use -DCMAKE_C_COMPILER=/path/to/mpicc
libompitrace.so.40.30.0 is not the OpenMP library; it is the tracing
library for OpenMPI, https://github.com/open-mpi/ompi/issues/10036
In your previous email, there was
/path/to/cmake/cmake-3.22.1-linux-x86_64/bin/cmake -E
I did have -DMPI_CXX_COMPILER set, so I added -DCMAKE_C_COMPILER and now
get these errors:
[ 25%] Linking CXX shared library librichdem.so
/lib/../lib64/crt1.o: In function `_start':
(.text+0x24): undefined reference to `main'
CMakeFiles/richdem.dir/src/random.cpp.o: In function
In the last link step to generate the executable
/cm/local/apps/gcc/10.2.0/bin/c++ -isystem -O3 -g -Wall -Wextra -pedantic
-Wshadow CMakeFiles/wtm.x.dir/src/WTM.cpp.o -o wtm.x
-Wl,-rpath,/path/to/WTM/build/common/richdem:/path/to/
gdal-3.3.0/lib:/path/to/openmpi-4.1.1_ucx_cuda_11.0.3_
>
> Perhaps we can back one step:
> Use your mpicc to build a "hello world" mpi test, then run it on a compute
> node (with GPU) to see if it works.
> If no, then your MPI environment has problems;
> If yes, then use it to build petsc (turn on petsc's gpu support,
> --with-cuda
True, but when users send reports back to us they will never have used the
VERBOSE=1 option, so it requires one more round trip of email to get this
additional information.
> On Oct 8, 2022, at 6:48 PM, Jed Brown wrote:
>
> Barry Smith writes:
>
>> I hate these kinds of make rules
Barry Smith writes:
>I hate these kinds of make rules that hide what the compiler is doing (in
> the name of having less output, I guess) it makes it difficult to figure out
> what is going wrong.
You can make VERBOSE=1 with CMake-generated makefiles.
Perhaps we can back one step:
Use your mpicc to build a "hello world" mpi test, then run it on a compute
node (with GPU) to see if it works.
If no, then your MPI environment has problems;
If yes, then use it to build petsc (turn on petsc's gpu support,
--with-cuda --with-cudac=nvcc), and then
I hate these kinds of make rules that hide what the compiler is doing (in
the name of having less output, I guess) it makes it difficult to figure out
what is going wrong.
Anyways, either some of the MPI libraries are missing from the link line or
they are in the wrong order and thus it
The error changes now and at an earlier place, 66% vs 70%:
make LDFLAGS="-Wl,--copy-dt-needed-entries"
Consolidate compiler generated dependencies of target fmt
[ 12%] Built target fmt
Consolidate compiler generated dependencies of target richdem
[ 37%] Built target richdem
Consolidate compiler
> Thanks for the quick reply. I added these options to make and make check
>> still produce the warnings so I used the command like this:
>> make PETSC_DIR=/path/to/petsc PETSC_ARCH=arch-linux-c-debug
>> MPIEXEC="mpiexec -mca orte_base_help_aggregate 0 --mca
>> opal_warn_on_missing_libcuda 0 -mca
On Fri, Oct 7, 2022 at 1:08 PM Rob Kudyba wrote:
> Thanks for the quick reply. I added these options to make and make check
> still produce the warnings so I used the command like this:
> make PETSC_DIR=/path/to/petsc PETSC_ARCH=arch-linux-c-debug
> MPIEXEC="mpiexec -mca
Thanks for the quick reply. I added these options to make and make check
still produce the warnings so I used the command like this:
make PETSC_DIR=/path/to/petsc PETSC_ARCH=arch-linux-c-debug
MPIEXEC="mpiexec -mca orte_base_help_aggregate 0 --mca
opal_warn_on_missing_libcuda 0 -mca pml ucx --mca
We are on RHEL 8, using modules that we can load/unload various version of
packages/libraries, and I have OpenMPI 4.1.1 with CUDA aware loaded along
with GDAL 3.3.0, GCC 10.2.0, and cmake 3.22.1
make PETSC_DIR=/path/to/petsc PETSC_ARCH=arch-linux-c-debug check
fails with the below errors,
Running
16 matches
Mail list logo