ith OpenMPI
Let me try to reproduce this. This should not have anything to do with GPU
Direct RDMA. However, to eliminate it, you could run with:
--mca btl_openib_want_cuda_gdr 0.
Rolf
From: users [mailto:users-boun...@open-mpi.org] On Behalf Of Aulwes, Rob
Sent: Wednesday, February 11, 2015 2:17 PM
To:
Hi,
I built OpenMPI 1.8.3 using PGI 14.7 and enabled CUDA support for CUDA 6.0. I
have a Fortran test code that tests GPUDirect and have included it here. When
I run it across 2 nodes using 4 MPI procs, sometimes it fails with incorrect
results. Specifically, sometimes rank 1 does not
Hi,
I'm trying to allocate and bind memory on the same NUMA domain as the calling
thread. The code I use is as follows.
/* retrieve the single PU where the current thread actually runs within
this process binding */
int err = hwloc_get_last_cpu_location(topo, set,
Hi,
A call to hwloc_topology_load is failing, but all that is returned is –1. Are
there error reporting routines that can be called to get more details about the
error? The doc for hwloc_topology_load only says that –1 is returned on error,
but doesn't give any hints about what could cause
to better show how to use bitmaps, cpu
and memory binding etc.
https://github.com/open-mpi/hwloc/tree/master/doc/examples
If you see anything missing, don't hesitate to ask.
Brice
Le 19/08/2014 19:10, Aulwes, Rob a écrit :
ok, in the meantime, is there a way to manually 'replicate'? Tha
specific sets of cores) so you still need to check the return value :)
I will better document all this, and what happens in case of failure with and
without the STRICT flag. And I'll see if I add a good example somewhere.
Brice
Le 19/08/2014 19:00, Aulwes, Rob a écrit :
nope, no error. is the
oc();
/* iterate over remaining bits and alloc/bind there */
hwloc_bitmap_foreach_begin(i, totalset) {
hwloc_bitmap_only(newset, i);
p = hwloc_alloc_membind_nodeset(, newset, ...);
}
hwloc_bitmap_free(totalset);
hwloc_bitmap_free(bindset);
hwloc_bitmap_free(newset);
Brice
Le 19/08/
ly.
I'll look at clarifying the doc and/or returning an error and/or adding a way
to find out.
Brice
Le 19/08/2014 19:00, Aulwes, Rob a écrit :
nope, no error. is there a way to find out what policies are supported? I
would like to try 'replicate'.
From: Brice Goglin <brice.gog...@inria.
t an error if you request it.
Brice
Le 19/08/2014 18:48, Aulwes, Rob a écrit :
Hi Brice,
I've tried:
p = hwloc_alloc_membind_policy(_topo, cnt * sizeof (T),
mem_nodeset, HWLOC_MEMBIND_NEXTTOUCH, 0);
and
p = hwloc_alloc_me
Hi,
I'm trying to write a custom C++ allocator that wraps hwloc calls. I've tried
using various hwloc_alloc* functions to set the memory bindings, but when I
call hwloc_get_area_membind_nodeset to verify, I don't get the same policy I
passed to alloc. Are there example codes that show how to
10 matches
Mail list logo
