Hi David,
Open MPI will try to load libcuda during MPI_Init when you are using
either the openib BTL or the smcuda BTL (and CUDA support has been
compiled in).
It is looking in /usr/lib64 and in LD_LIBRARY_PATH as well I guess.
You should not need anything else than libcuda for the Open M
The issue is related to openCL, not NVML.
So the correct export would be "export enable_opencl=no" (you may want
to "export enable_nvml=no" as well).
On 09/21/2017 12:32 AM, Tim Jim wrote:
Hi,
I tried as you suggested: export nvml_enable=no, then reconfigured and
ran make all install again,
To solve the undefined references to cudaMalloc and cudaFree, you need
to link the CUDA runtime. So you should replace -lcuda by -lcudart.
For the OPENCL undefined references, I don't know where those are coming
from ... could it be that hwloc is compiling OpenCL support but not
adding -lOpenC
Hi Siegmar,
This has been fixed in the driver some time ago. Getting the latest
driver should solve your problem.
You can check the driver version with nvidia-smi, then go to
http://www.nvidia.com/Download/index.aspx to get the latest.
Sylvain
On 08/14/2017 12:46 AM, Siegmar Gross wrote:
Justin, can you try setting mpi_leave_pinned to 0 to disable
libptmalloc2 and confirm this is related to ptmalloc ?
Thanks,
Sylvain
On 06/19/2017 03:05 PM, Justin Luitjens wrote:
I have an application that works on other systems but on the current
system I’m running I’m seeing the following
message with
2.1.0 built against CUDA 8.0. We're using libcuda.so.375.39. Has
anyone had any luck suppressing these messages?
Thanks,
Ben
On 27 Mar 2017, at 7:13 pm, Roland Fehrenbacher <mailto:r...@q-leap.de>> wrote:
"SJ" == Sylvain Jeaugey <mailto:sjeau...@nvidia
I also saw IBM and ignored the email :-)
Thanks for reporting the issue, I passed it to the PGI team.
On 05/01/2017 11:49 AM, Prentice Bisbal wrote:
Jeff,
You probably were thrown off when I said I've only really seen this
problem when people didn't cross-compile correctly on the Blue Gene/P
again, until I find
the code responsible for that, I can't say for sure.
I'm sorry it's taking so long -- I'm on it though.
On 03/24/2017 01:56 PM, Roland Fehrenbacher wrote:
"SJ" == Sylvain Jeaugey writes:
Hi Sylvain,
SJ> Hi Roland, I can't find this m
If you installed CUDA libraries and includes in /usr, then it's not
surprising hwloc finds them even without defining CFLAGS.
I'm just saying I think you won't get the error message if Open MPI
finds CUDA but hwloc does not.
On 03/21/2017 11:05 AM, Roland Fehrenbacher wrote:
Hi Siegmar,
I think this "NVIDIA : ..." error message comes from the fact that you
add CUDA includes in the C*FLAGS. If you just use --with-cuda, Open MPI
will compile with CUDA support, but hwloc will not find CUDA and that
will be fine. However, setting CUDA in CFLAGS will make hwloc find CU
Hi Roland,
I can't find this message in the Open MPI source code. Could it be hwloc
? Some other library you are using ?
Sylvain
On 03/16/2017 04:23 AM, Roland Fehrenbacher wrote:
Hi,
OpenMPI 2.0.2 built with cuda support brings up lots of warnings like
NVIDIA: no NVIDIA devices found
whe
On 10/28/2016 10:33 AM, Craig tierney wrote:
Sylvain,
If I do not set --with-cuda, I get:
configure:9964: result: no
configure:10023: checking whether CU_POINTER_ATTRIBUTE_SYNC_MEMOPS is
declared
configure:10023: gcc -c -DNDEBUG conftest.c >&5
conftest.c:83:19: fatal error: /cuda.h: No such
I guess --with-cuda is disabling the default CUDA path which is
/usr/local/cuda. So you should either not set --with-cuda or set
--with-cuda $CUDA_HOME (no include).
Sylvain
On 10/27/2016 03:23 PM, Craig tierney wrote:
Hello,
I am trying to build OpenMPI 1.10.3 with CUDA but I am unable to b
As a workaround, you can also try adding -noswitcherror to PGCC flags.
On 07/11/2016 03:52 PM, Åke Sandgren wrote:
Looks like you are compiling with slurm support.
If so, you need to remove the "-pthread" from libslurm.la and libpmi.la
On 07/11/2016 02:54 PM, Michael Di Domenico wrote:
I'm tr
Hi Durga,
Sorry for the late reply and thanks for reporting that issue. As Rayson
mentioned, CUDA is intrinsically C++ and indeed uses the host C++
compiler. Hence linking MPI + CUDA code may need to use mpic++.
It happens to work with mpicc on various platforms where the libstdc++
is linked
a frustrating exercise. Thanks for the suggestion. I think I
can say 'case closed'
Spencer
------------
*From:* users on behalf of Sylvain
Jeaugey
*Sent:* Friday, January 22, 2016 11:34 AM
*To:* us...@open-mpi.or
Hi Spencer,
Could you be more specific about what fails ? Did the configure stop at
some point ? Or is it a compile error during the build ?
I'm not sure the errors you are seeing in config.log are actually the
real problem (I'm seeing the same error traces on a perfectly working
machine). N
17 matches
Mail list logo