[hwloc-devel] Create success (hwloc git 1.11.3-4-gb1a3a18)

Creating nightly hwloc snapshot git tarball was a success. Snapshot: hwloc 1.11.3-4-gb1a3a18 Start time: Mon May 2 21:03:20 EDT 2016 End time: Mon May 2 21:05:00 EDT 2016 Your friendly daemon, Cyrador

[hwloc-devel] Create success (hwloc git dev-1141-g246c702)

Creating nightly hwloc snapshot git tarball was a success. Snapshot: hwloc dev-1141-g246c702 Start time: Mon May 2 21:01:02 EDT 2016 End time: Mon May 2 21:02:59 EDT 2016 Your friendly daemon, Cyrador

Re: [OMPI devel] [2.0.0rc2] xlc build failure (pmix)

Fix setup here: https://github.com/open-mpi/ompi-release/pull/1129 > On May 2, 2016, at 5:13 PM, Paul Hargrove wrote: > > AFTER fixing the inline asm problem detailed in >

[OMPI devel] [2.0.0rc2] xlc build failure (pmix)

AFTER fixing the inline asm problem detailed in https://www.open-mpi.org/community/lists/devel/2016/05/18886.php, I still cannot build with xlc. The issue arises in the pmix code and originates from a disagreement between pmix_hash_table.h and pmix_hash_table.c. The header declares 8 functions

[OMPI devel] [2.0.0rc2] xlc build failure (inline asm)

It appears that xlc's support for gcc-style inline asm does not allow an empty clobbers list. The failure I see is libtool: compile: xlc -DHAVE_CONFIG_H -I. -I/home/hargrove/SCRATCH/OMPI/openmpi-2.0.0rc2-linux-ppc64-xlc-12.1/openmpi-2.0.0rc2/opal/asm -I../../opal/include -I../../ompi/include

Re: [OMPI devel] [2.0.0rc2] Illegal instruction on Pentium III

Should be fixed by https://github.com/open-mpi/ompi/pull/1618 Thanks for catching this. -Nathan On Mon, May 02, 2016 at 02:30:19PM -0700, Paul Hargrove wrote: >I have an Pentium III Linux system which fails "make check" with: >make[3]: Entering directory > >

Re: [OMPI devel] [2.0.0rc2] openib btl build failure

Fixed by https://github.com/open-mpi/ompi/pull/1619 Thanks for catching this. -Nathan On Mon, May 02, 2016 at 01:57:07PM -0700, Paul Hargrove wrote: >I have an x86-64/Linux system with a fairly standard install of Scientific >Linux 6.3 (a RHEL clone like CentOS). >However, it

Re: [OMPI devel] [2.0.0rc2] Linux/MIPS64 failures

Looks like patcher/linux needs some work on 32-bit systems. I will try to get this fixed in the next day or two. -Nathan On Mon, May 02, 2016 at 03:36:35PM -0700, Paul Hargrove wrote: >New since the last time I did testing, I now have access to Linux MIPS64 >(Cavium Octeon II) systems.

Re: [OMPI devel] [2.0.0rc2] build failure with ppc64 and "gcc -m32" (hwloc)

FWIW, this problem does not occur with Open MPI 1.10.2 on the same system and configured identically. -Paul On Mon, May 2, 2016 at 12:53 PM, Paul Hargrove wrote: > I have a linux/ppc64 host running Fedora 20. > I have configured the 2.0.0rc2 tarball with > > --prefix=[]

[OMPI devel] [2.0.0rc2] "make check" failure on ARMv6

Running on a Raspberry Pi w/ Debian Jessie. A "make check" fails with a SEGV in the dl_open test. The output is pretty much the same as my previous 2 reports for other architectures: make[4]: Entering directory '/home/phargrov/OMPI/openmpi-2.0.0rc2-linux-arm-rpi/BLD/ompi/debuggers' PASS:

[OMPI devel] [2.0.0rc2] ppc SEGVs

Running in several different PPC platforms I see "make check" fail as follows: make[4]: Entering directory `/home/phargrov/OMPI/openmpi-2.0.0rc2-linux-ppc32-gcc/BLD/ompi/debuggers' PASS: predefined_gap_test PASS: predefined_pad_test

Re: [OMPI devel] [2.0.0rc2] Illegal instruction on Pentium III

Thanks Paul, I will see what I can do to fix this one. -Nathan On Mon, May 02, 2016 at 02:30:19PM -0700, Paul Hargrove wrote: >I have an Pentium III Linux system which fails "make check" with: >make[3]: Entering directory > >

[OMPI devel] [2.0.0rc2] Illegal instruction on Pentium III

I have an Pentium III Linux system which fails "make check" with: make[3]: Entering directory `/home/phargrov/OMPI/openmpi-2.0.0rc2-linux-x86-OpenSuSE-10.2/BLD/ompi/debuggers' make[4]: Entering directory `/home/phargrov/OMPI/openmpi-2.0.0rc2-linux-x86-OpenSuSE-10.2/BLD/ompi/debuggers' PASS:

[OMPI devel] [2.0.0rc2] run failure on OpenBSD5-i386

With OpenBSD-5.9 on x86 (but *not* amd64) when I try to run an application built with Open MPI 2.0.0rc2, I get a SEGV before any output: $ mpirun -mca btl sm,self -np 2 examples /ring_c' -- mpirun noticed that process rank 1

[OMPI devel] [2.0.0rc2] openib btl build failure

I have an x86-64/Linux system with a fairly standard install of Scientific Linux 6.3 (a RHEL clone like CentOS). However, it appears from the error messages (at the bottom of this email) that the OFED install differs in some way from OMPI's expectations. It appears the OFED was not installed via

[OMPI devel] [2.0.0rc2] build failure on Linux w/ studio 12.x and -m32

The 2.0.0rc2 tarball fails to compile on Linux/x86-64 with the Sun/Oracle Studio compilers when using "-m32". I have reproduced with the 12.2 and 12.4 compiler releases (I have others, but only tested those 2). The error appears to be the same one I previously reported multiple times. The latest

[OMPI devel] [2.0.0rc2] build failure on Solaris-11.2 (alloca undefined)

It appears that 2.0.0rc2 contains the same sort of alloca()-related error I reported against 1.10.2rc1 in https://www.open-mpi.org/community/lists/devel/2015/12/18440.php This time the problem is in osc_rdma_peer.c, which *does* attempt the appropriate conditional include of alloca.h, but

[OMPI devel] [2.0.0rc2] netbsd-7 build failure

Both i386 and amd64 systems running NetBSD-7 fail with: libtool: compile: gcc -std=gnu99 -DHAVE_CONFIG_H -I. -I/home/phargrov/OMPI/openmpi-2.0.0rc2-netbsd7-amd64/openmpi-2.0.0rc2/opal/mca/memory/patcher -I../../../../opal/include -I../../../../ompi/include -I../../../../oshmem/include

Re: [OMPI devel] [2.0.0rc2] build failure on RHEL AS4

Nathan just fixed: https://github.com/open-mpi/ompi/pull/1615 > On May 2, 2016, at 3:45 PM, Paul Hargrove wrote: > > I have a fairly old x86-64 system running RHEL AS4. > The build is failing (as shown at the bottom of this message), with > MREMAP_FIXED undeclared. > There

[OMPI devel] [2.0.0rc2] build failure on IA64/Linux

I have an IA64 system running SLES11. I have configured with only --prefix= and --enable-debug I have no particular reason to think this failure is specific to SLES11. However, the error is coming from code within "#if defined(__ia64__)". The build failure: libtool: compile: gcc -std=gnu99

[OMPI devel] [2.0.0rc2] build failure with ppc64 and "gcc -m32" (hwloc)

I have a linux/ppc64 host running Fedora 20. I have configured the 2.0.0rc2 tarball with --prefix=[] --enable-debug \ CFLAGS=-m32 --with-wrapper-cflags=-m32 \ CXXFLAGS=-m32 --with-wrapper-cxxflags=-m32 \ FCFLAGS=-m32 --with-wrapper-fcflags=-m32 --disable-mpi-fortran [yes, I know the fortran

[OMPI devel] [2.0.0rc2] build failure on RHEL AS4

I have a fairly old x86-64 system running RHEL AS4. The build is failing (as shown at the bottom of this message), with MREMAP_FIXED undeclared. There *is* a definition in the system headers, but in linux/mmap.h rather than sys/mmap.h $ grep -rw MREMAP_FIXED /usr/include/

[OMPI devel] 1.8/1.10 --> 2.0.0 migration guide

Geoff: can you put this on the agenda for tomorrow? https://github.com/open-mpi/ompi/wiki/User-Migration-Guide:-1.8.x-and-v1.10.x-to-v2.0.0 Thanks. -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/

Re: [OMPI devel] Open MPI v2.0.0rc2

On 04/28/2016 05:01 PM, Jeff Squyres (jsquyres) wrote: > At long last, here's the next v2.0.0 release candidate: 2.0.0rc2: > > https://www.open-mpi.org/software/ompi/v2.x/ > > We didn't keep a good list of all the things that have changed since rc1 -- > but it's many things. Here's a link