ibv_get_device_list_compat() and not finding it, I finally realized
that it was a function in OMPI. So let's name it with a proper ompi_
prefix, not an ibv_ prefix.
This commit was SVN r26867.
1000. Refs trac:3154.
IB/iWarp vendors need to get together to figure out a real fix.
This commit was SVN r26777.
The following SVN revision numbers were found above:
r26730 --> open-mpi/ompi@5315c91baf
The following Trac tickets were found above:
Ticket 3154 --> https://svn.open-mpi.org/trac/ompi/ticket/3154
* If the MCA param btl_openib_cq_size is set to 0 (which is the
default), use the device CQ max size. Otherwise, use the MCA param
value (and never adjust it again).
* Remove the CQ size adjustment code. Since we default to max CQ
size, there really isn't much point in having it any more. I think
people setting an absolute CQ size is going to be rare, so let's
not do anything fancy with it.
* If the MCA param value is larger than what the device supports,
print a warning (only once per process) and default to using the
device max
* Add a BTL_VERBOSE displaying which CQ size we used
This commit was SVN r26730.
The following Trac tickets were found above:
Ticket 3152 --> https://svn.open-mpi.org/trac/ompi/ticket/3152
hook early in the setup, but ''not'' during the component register
function. And then properly unset it if was set.
This commit was SVN r26697.
The following Trac tickets were found above:
Ticket 3130 --> https://svn.open-mpi.org/trac/ompi/ticket/3130
helper file, even if we find that the system has <infiniband/verbs.h>.
The reason is because there are some inline functions in that verbs
helper file that invoke ibv_* functions. Some linkers (e.g., Solaris
Studio Compilers) will instantiate those static inline functions --
even if we don't use them -- and therefore we need to be able to
resolve the ibv_* symbols at link time.
But since -libverbs is only specified in places where we use other
ibv_* functions (e.g., the OpenFabrics-based BTLs), that means that
linking random executables can/will fail (e.g., orterun).
So instead, introduce a new #define: OPAL_HWLOC_WANT_VERBS_HELPER. If
this macro is set to 1 before including opal/mca/hwloc/hwloc.h, then
you'll also get the hwloc OpenFabrics verbs helper header file (*if*
hwloc found <infiniband/verbs.h> -- otherwise, it'll #error).
This commit was SVN r26417.
* Remove paffinity, maffinity, and carto frameworks -- they've been
wholly replaced by hwloc.
* Move ompi_mpi_init() affinity-setting/checking code down to ORTE.
* Update sm, smcuda, wv, and openib components to no longer use carto.
Instead, use hwloc data. There are still optimizations possible in
the sm/smcuda BTLs (i.e., making multiple mpools). Also, the old
carto-based code found out how many NUMA nodes were ''available''
-- not how many were used ''in this job''. The new hwloc-using
code computes the same value -- it was not updated to calculate how
many NUMA nodes are used ''by this job.''
* Note that I cannot compile the smcuda and wv BTLs -- I ''think''
they're right, but they need to be verified by their owners.
* The openib component now does a bunch of stuff to figure out where
"near" OpenFabrics devices are. '''THIS IS A CHANGE IN DEFAULT
BEHAVIOR!!''' and still needs to be verified by OpenFabrics vendors
(I do not have a NUMA machine with an OpenFabrics device that is a
non-uniform distance from multiple different NUMA nodes).
* Completely rewrite the OMPI_Affinity_str() routine from the
"affinity" mpiext extension. This extension now understands
hyperthreads; the output format of it has changed a bit to reflect
this new information.
* Bunches of minor changes around the code base to update names/types
from maffinity/paffinity-based names to hwloc-based names.
* Add some helper functions into the hwloc base, mainly having to do
with the fact that we have the hwloc data reporting ''all''
topology information, but sometimes you really only want the
(online | available) data.
This commit was SVN r26391.
Roll in the ORTE state machine. Remove last traces of opal_sos. Remove UTK epoch code.
Please see the various emails about the state machine change for details. I'll send something out later with more info on the new arch.
This commit was SVN r26242.
zeroes);
if so, use it for bit-operations like opal_cube_dim and opal_hibit.
Implement two versions of power-of-two.
In case of opal_next_poweroftwo, this reduces the average execution
time from 83 cycles to 4 cycles (Intel Nehalem, icc, -O2, inlining,
measured rdtsc, with loop over 2^27 values).
Numbers for other functions are similar (but of course heavily depend
on the usage, e.g. opal_hibit() with a start of 4 does not save
much). The bsr instruction on AMD Opteron is also not as fast.
- Replace various places where the next power-of-two is computed.
Tested on Intel Nehalem Cluster with openib, compilers GNU-4.6.1 and
Intel-12.0.4 using mpi_testsuite -t "Collective" with 128 processes.
This commit was SVN r25270.
