Re: [hwloc-devel] Build system issues

2009-09-08 Thread Samuel Thibault
Jeff Squyres, le Tue 08 Sep 2009 17:30:59 -0400, a écrit : > What version of help2man do you guys have? 1.36.4 > On my OS X Leopard MBP, I have v1.36 (brought in via darwin ports). > It does not recognize the "--version-string" option. Indeed, it does > not appear to support an option that

Re: [hwloc-devel] What's left for v0.9.1?

2009-09-14 Thread Samuel Thibault
Brice Goglin, le Mon 14 Sep 2009 15:17:40 +0200, a écrit : > And Samuel will likely find some breakage on non-Linux OS :) Ah, indeed, I need to re-test it all on all ports. Samuel

Re: [hwloc-devel] What's left for v0.9.1?

2009-09-14 Thread Samuel Thibault
Jeff Squyres, le Mon 14 Sep 2009 10:30:08 -0400, a écrit : > On Sep 14, 2009, at 10:03 AM, Brice Goglin wrote: > > >> Does "make check" work properly? I.e., will it return pass/fail on > >> all the different platforms? > > > >It's supposed to be fully automake-compliant so I think so. > > Ok --

Re: [hwloc-devel] hwloc web site

2009-09-15 Thread Samuel Thibault
Hello, BTW, thanks for your work on the website/trac/etc. integration, I hardly have any time atm to do things like this :) Jeff Squyres, le Fri 11 Sep 2009 09:41:03 -0400, a écrit : > I did a bunch of integration work for the hwloc web site -- could you > guys review this before it goes live?

Re: [hwloc-devel] hwloc web site

2009-09-15 Thread Samuel Thibault
Jeff Squyres, le Tue 15 Sep 2009 20:07:22 -0400, a écrit : > On Sep 15, 2009, at 7:14 PM, Samuel Thibault wrote: > > >> I did a bunch of integration work for the hwloc web site -- could > >you > >> guys review this before it goes live? This is my development copy:

Re: [hwloc-devel] last API possible changes

2009-09-20 Thread Samuel Thibault
Brice Goglin, le Thu 17 Sep 2009 09:50:57 +0200, a écrit : > * Do we actually need hwloc_get_type_order() or would > hwloc_compare_types() be enough? I can't find any example where some > type "orders" is not used for direct comparison. And the latter is probably clearer, indeed. > * I think the

Re: [hwloc-devel] last API possible changes

2009-09-21 Thread Samuel Thibault
Jeff Squyres, le Mon 21 Sep 2009 08:22:06 -0400, a écrit : > FWIW, is there a reason we're not using AC_C_RESTRICT in > configure.ac? This allows you to use "restrict" in C code everywhere; > it'll be #defined to something acceptable by the compiler if > "restrict" itself is not. Our

Re: [hwloc-devel] last API possible changes

2009-09-21 Thread Samuel Thibault
Jeff Squyres, le Mon 21 Sep 2009 08:51:35 -0400, a écrit : > On Sep 21, 2009, at 8:44 AM, Samuel Thibault wrote: > > >> FWIW, is there a reason we're not using AC_C_RESTRICT in > >> configure.ac? This allows you to use "restrict" in C code > >everywh

Re: [hwloc-devel] last API possible changes

2009-09-21 Thread Samuel Thibault
Jeff Squyres, le Mon 21 Sep 2009 10:04:21 -0400, a écrit : > On Sep 21, 2009, at 9:40 AM, Samuel Thibault wrote: > >> So it should be ok to use AC_C_RESTRICT then, right? > > > >But then we can't expose restrict in installed headers since we don't > >know _

Re: [hwloc-devel] last API possible changes

2009-09-21 Thread Samuel Thibault
Jeff Squyres, le Mon 21 Sep 2009 12:31:41 -0400, a écrit : > On Sep 21, 2009, at 10:42 AM, Samuel Thibault wrote: > >It's part of the language starting from C99 only. An application could > >enable non-C99 mode where it becomes undefined, you can never know. > >

Re: [hwloc-devel] last API possible changes

2009-09-21 Thread Samuel Thibault
Samuel Thibault, le Mon 21 Sep 2009 19:33:11 +0200, a écrit : > Jeff Squyres, le Mon 21 Sep 2009 12:31:41 -0400, a écrit : > > On Sep 21, 2009, at 10:42 AM, Samuel Thibault wrote: > > >It's part of the language starting from C99 only. An application could > > >enable no

Re: [hwloc-devel] Cache size/sharing errors on 8x4 Opteron system

2009-09-22 Thread Samuel Thibault
Samuel Thibault, le Tue 22 Sep 2009 16:44:11 +0200, a écrit : > I'm afraid the bug is most probably in the kernel, BTW, I know that on x86 at least glibc and libgomp use the cpuid instruction themselves to discover the cpu topology. Such backend could be written to compensate for kernel b

Re: [hwloc-devel] restricted topology (& topology changes)

2009-09-27 Thread Samuel Thibault
Fawzi Mohamed, le Sun 27 Sep 2009 14:09:59 +0200, a écrit : > the topology load returns the topology of the whole system (I think), Nope, else it's a bug :) > but shouldn't it return the restricted topology (or have a method that > returns the restricted topology). It should already be the

Re: [hwloc-devel] structure assumptions, duplication

2009-09-29 Thread Samuel Thibault
Fawzi Mohamed, le Tue 29 Sep 2009 17:39:17 +0200, a écrit : > so that in the future one could avoid storing it at least in the > deepest levels where it is easy and relatively cheap to generate (and > where one would have the largest savings). Even the deepest levels would have a L1 cache level

Re: [hwloc-devel] dynamic cpuset_t?

2009-09-29 Thread Samuel Thibault
Fawzi Mohamed, le Tue 29 Sep 2009 20:39:02 +0200, a écrit : > It comes down to what you want to have, if you think you might want to > go the sparse full granularity way then indeed alloc/copy/free should > be added Yes, that's my point: do we really want it? Samuel

Re: [hwloc-devel] structure assumptions, duplication

2009-09-30 Thread Samuel Thibault
Fawzi Mohamed, le Wed 30 Sep 2009 10:10:47 +0200, a écrit : > If you look at the example described in the document that I had linked > > http://opensolaris.org/os/community/performance/mpo_overview.pdf > > you see the that for a ring topology some level (that you always get adding > the Ah,

Re: [hwloc-devel] release status

2009-10-02 Thread Samuel Thibault
Jeff Squyres, le Fri 02 Oct 2009 13:53:48 -0400, a écrit : > On Oct 2, 2009, at 1:39 PM, Samuel Thibault wrote: > > >I also think inlining doesn't bring much performance compared to the > >cost of parsing a cpuset. > > > >> You'll get warnings from the li

Re: [hwloc-devel] dynamic cpuset_t?

2009-10-07 Thread Samuel Thibault
Jeff Squyres, le Wed 07 Oct 2009 12:28:00 -0400, a écrit : > On Oct 7, 2009, at 12:20 PM, Brice Goglin wrote: > > >> One comment, I see that you have a > >> hwloc_cpuset_copy (which I would have called duplicate) > >> but copy in the sense of assignment is not really possible (i.e. > >>

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1119

2009-10-08 Thread Samuel Thibault
Jeff Squyres, le Thu 08 Oct 2009 07:55:08 -0400, a écrit : > Another random doxy comment -- would you guys mind if I change the > default to output PDF for US letter rather than a4wide? Oh, I actually hadn't noticed the field and assumed that doxygen would just take the local papersize. > US

Re: [hwloc-devel] MPICH2 question

2009-10-21 Thread Samuel Thibault
Jeff Squyres, le Wed 21 Oct 2009 12:46:38 -0400, a écrit : > I'd be surprised if there's a system out there that doesn't have some > flavor of egrep that satisfies AC_PROG_EGREP (especially if Libtool > uses it heavily). Do we know if this is the case, or is this a > hypothetical that a

Re: [hwloc-devel] MPICH2 question

2009-10-21 Thread Samuel Thibault
Jeff Squyres, le Wed 21 Oct 2009 12:50:55 -0400, a écrit : > configuring/building hwloc with icc results in a *lot* > of warnings; I didn't test functionality). Mmm, I have already successfully tested with icc9. The kind of warnings I've seen were not worth fixing to my mind: unused

Re: [hwloc-devel] 0.9.1rc2 failures

2009-10-22 Thread Samuel Thibault
Pavan Balaji, le Wed 21 Oct 2009 20:31:17 -0500, a écrit : > With suncc (sunstudio 12): > == > "topology-linux.c", line 782: syntax error before or at: ... Ah, you are using suncc on linux, I wouldn't have expected such combination.

Re: [hwloc-devel] [hwloc] #21: Allow lookup of specific PIDs

2009-10-22 Thread Samuel Thibault
Hello, Ashley Pittman, le Thu 22 Oct 2009 15:15:24 +0100, a écrit : > I've added the code to padb to run this against jobs, you can now do > "padb -a --lstopo -c" to see information about hosts where your jobs are > running. > > http://code.google.com/p/padb/source/detail?r=297 Just to fix

Re: [hwloc-devel] hwloc compile warnings patch

2009-10-23 Thread Samuel Thibault
Hello, These should now be fixed in the v0.9 branch. Thanks, Samuel

Re: [hwloc-devel] 0.9.1rc2 failures

2009-10-23 Thread Samuel Thibault
Hello, Thanks for the logs. Pavan Balaji, le Thu 22 Oct 2009 09:57:30 -0500, a écrit : > topology.c(74): remark #869: parameter "objs" was never referenced > topology.c(452): remark #981: operands are evaluated in unspecified order Such remarks are ok. (Google says 981 is really pedantism) >

Re: [hwloc-devel] Priority of env vars vs. application options

2009-10-27 Thread Samuel Thibault
Brice Goglin, le Wed 28 Oct 2009 00:04:48 +0100, a écrit : > So I am not sure which order is the best. Maybe provide the two possibilities, i.e. two series of en vars, one that comes before the application configuration and the other that comes after? Samuel

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1255

2009-10-29 Thread Samuel Thibault
sthib...@osl.iu.edu, le Thu 29 Oct 2009 07:33:39 -0400, a écrit : > + * \note Depending on OSes and implementations, strict binding > + * may not be possible (implementation reason) or not allowed > + * (administrative reasons), and the function will fail in that case. I'm just wondering: maybe

Re: [hwloc-devel] 0.9.1rc3 has been released

2009-10-29 Thread Samuel Thibault
Jeff Squyres, le Thu 29 Oct 2009 09:54:35 -0400, a écrit : > Brice/Samuel -- do you have any verbiage written up for a release > announcement email / Freshmeat record, perchance? Adapted from the 0.9 libtopology release: it was mostly the top of README :) “ hwloc 0.9.1 has been released today.

Re: [hwloc-devel] 0.9.1rc3 has been released

2009-10-29 Thread Samuel Thibault
Jeff Squyres, le Thu 29 Oct 2009 11:14:10 -0400, a écrit : > I tweaked this a bit -- how's this: Looks great, maybe the documentation (from which the original version was extracted) could get some of these tweaks? Samuel

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1261

2009-10-29 Thread Samuel Thibault
jsquy...@osl.iu.edu, le Thu 29 Oct 2009 13:55:17 -0400, a écrit : > Updates to frontmatter of the doxy docs. Seems great, please push! Samuel

Re: [hwloc-devel] hwloc-0.9.1rc3 fails with pgcc

2009-10-30 Thread Samuel Thibault
Chris Samuel, le Fri 30 Oct 2009 16:50:25 +1100, a écrit : > PGC-S-0043-Redefinition of symbol, nbobjs (topology.c: 77) Arf. I'll commit something to circumvent it. Samuel

Re: [hwloc-devel] === CREATE FAILURE (trunk) ===

2009-11-03 Thread Samuel Thibault
MPI Team, le Tue 03 Nov 2009 21:01:23 -0500, a écrit : > ERROR: Command returned a non-zero exist status (trunk): >./autogen.sh Ah, sorry, it is. Mmmm how is it running > autoreconf: running: aclocal --force -I config while autoreconf was passed -I m4? I've just tried from a fresh

Re: [hwloc-devel] Pgcc issues fixed?

2009-11-04 Thread Samuel Thibault
Chris Samuel, le Wed 04 Nov 2009 16:04:40 +1100, a écrit : > I'm still seeing a heap with the Intel compilers. Yes, these are mostly pedantism warnings which we do not need to fix for this release (would need tagging parameters as unused etc.) Samuel

Re: [hwloc-devel] Pgcc issues fixed?

2009-11-04 Thread Samuel Thibault
Brice Goglin, le Wed 04 Nov 2009 22:03:11 +0100, a écrit : > I think pgcc building fine was the last possible problem, so I assume > everything is ok now. Same for me. Samuel

Re: [hwloc-devel] Pgcc issues fixed?

2009-11-09 Thread Samuel Thibault
Jeff Squyres, le Thu 05 Nov 2009 07:58:58 -0500, a écrit : > This problem may go away if we adapt PLPA's approach to sched_[set| > get]affinity. What I dislike in that approach is that it means we'd have to closely follow future changes in the kernel ABI, while the API is not supposed to change

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1330

2009-11-11 Thread Samuel Thibault
Jeff Squyres, le Wed 11 Nov 2009 05:54:00 -0800, a écrit : > How about HWLOC_UNSUPPORTED_SYS? I don't think it's a good idea to make it a compile-time thing rather than a runtime-time thing: if we expose to the application the fact that the OS on which the application is building is not

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1333

2009-11-11 Thread Samuel Thibault
bgog...@osl.iu.edu, le Wed 11 Nov 2009 11:33:31 -0500, a écrit : > + /* FIXME: should be SET_THREAD_CPUBIND given with a pid */ > + if (flags & HWLOC_SUPPORT_SET_PROC_CPUBIND) > +*api_type = HWLOC_PLPA_PROBE_OK; > + else > +*api_type = HWLOC_PLPA_PROBE_NOT_SUPPORTED; > + return 0; > +}

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1333

2009-11-11 Thread Samuel Thibault
bgog...@osl.iu.edu, le Wed 11 Nov 2009 11:33:31 -0500, a écrit : > +/** \brief Bind thread given by \p pid to CPU set \p cpuset. > + * > + * \note This function now manipulates hwloc cpusets. > + */ > +static __inline int > +hwloc_plpa_sched_setaffinity(hwloc_topology_t topology, hwloc_pid_t pid,

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1333

2009-11-11 Thread Samuel Thibault
Brice Goglin, le Thu 12 Nov 2009 00:31:48 +0100, a écrit : > The problem is that our hwloc/Linux does not implement > set_proc_cpubind() so far. But it can implement one that assumes that the target process is singlethreaded, i.e. in hwloc_set_proc_cpubind distinguish between

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1333

2009-11-11 Thread Samuel Thibault
Another way to go is in hwloc_plpa_sched_setaffinity put in #ifdef HWLOC_LINUX_SYS some code that calls the internal hwloc_linux_set_tid_cpubind (with a strong comment that nobody else should call it), so that - existing linux plpa users can have the same behavior, but we can document here that

Re: [hwloc-devel] Pgcc issues fixed?

2009-11-11 Thread Samuel Thibault
Jeff Squyres, le Mon 09 Nov 2009 08:05:47 -0500, a écrit : > Fair enough. What about if we have an AC check for > pthread_setaffinity_np and use that if it exists, and if it doesn't > use the PLPA way? Err, remember that pthread_setaffinity_np alone doesn't permit to bind another process,

Re: [hwloc-devel] towards PLPA-like API in 1.0

2009-11-11 Thread Samuel Thibault
Brice Goglin, le Thu 05 Nov 2009 17:22:15 +0100, a écrit : > + int hwloc_plpa_sched_getaffinity(pid_t pid, hwloc_cpuset_t cpuset); > > It's just a hwloc_get_cpubind(), but we don't have it since it would not > be supported on all OS. But I think we should add it anyway. Being discussed in

Re: [hwloc-devel] towards PLPA-like API in 1.0

2009-11-11 Thread Samuel Thibault
Brice Goglin, le Mon 09 Nov 2009 15:18:11 +0100, a écrit : > I don't think we need SET_CPUBIND since (from what I understand) it > would be equivalent to SET_PROC_CPUBIND | SET_THREAD_CPUBIND. Being able to set oneself's cpuset is not the same as being able to set the cpuset of other processes or

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1333

2009-11-12 Thread Samuel Thibault
Jeff Squyres, le Thu 12 Nov 2009 08:28:32 -0800, a écrit : > One thing to not forget is that some (many?) applications don't care a > whit about portability to other OS's. You view feature X as a > portability horror; they view it as a feature. > > Hence, they may actually *want* to take

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1333

2009-11-12 Thread Samuel Thibault
Jeff Squyres, le Thu 12 Nov 2009 08:31:50 -0800, a écrit : > On Nov 11, 2009, at 4:22 PM, Samuel Thibault wrote: > >- non-linux plpa users are restricted to what really is portable. > > > > PLPA = Linux only. :-) I know, but there's usually no reason why they shouldn't now

Re: [hwloc-devel] Pgcc issues fixed?

2009-11-12 Thread Samuel Thibault
Jeff Squyres, le Thu 12 Nov 2009 08:34:24 -0800, a écrit : > On Nov 11, 2009, at 4:57 PM, Samuel Thibault wrote: > >Maybe what we can do is using PLPA's functions if __GLIBC__ is <= > >2 and __GLIBC_MINOR__ is < the first version which is known to be > >correct or i

Re: [hwloc-devel] Pgcc issues fixed?

2009-11-12 Thread Samuel Thibault
Jeff Squyres, le Thu 12 Nov 2009 08:58:19 -0800, a écrit : > The *only* weird possibility would be if RH (or Suse) patched their > old glibcs to fix this problem but didn't update the minor number. Ok but in that case we'd just use the PLPA implementation that should work fine. On the long

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1333

2009-11-12 Thread Samuel Thibault
Jeff Squyres, le Thu 12 Nov 2009 09:08:45 -0800, a écrit : > Fair enough. I think we actually agree -- these emails are quite > confusing. :-) Ok :) > 1. Let's not mix thread and PIDs into a single argument like Linux does Ok, I've just done it :) but in the linux.h header only, for people

Re: [hwloc-devel] towards PLPA-like API in 1.0

2009-11-12 Thread Samuel Thibault
Brice Goglin, le Thu 12 Nov 2009 18:13:34 +0100, a écrit : > Jeff Squyres wrote: > >> * PLPA-like API is prefixed with hwloc_plpa_ and all functions get a new > >> hwloc_topology_t parameter. The problematic ones are: > >> > >> + int hwloc_plpa_sched_getaffinity(pid_t pid, hwloc_cpuset_t cpuset);

Re: [hwloc-devel] towards PLPA-like API in 1.0

2009-11-12 Thread Samuel Thibault
Jeff Squyres, le Thu 12 Nov 2009 10:05:32 -0800, a écrit : > apps that run on specific servers for specific purposes, where the > developers hard code in there "bind to cores 1-4" or "bind to sockets > 1,3" because they already know the setup and this app is not intended > to be portable.

Re: [hwloc-devel] hwloc at SC09

2009-11-12 Thread Samuel Thibault
Ashley Pittman, le Thu 12 Nov 2009 19:11:11 +, a écrit : > I just tried to run it on my arm but failed as I only have autoconf > 2.61, You can run ./configure && make dist on another machine to get an autoconfied tarball ready to unpack/conf/make. Samuel

[hwloc-devel] hwloc on ARM [Was: hwloc at SC09]

2009-11-13 Thread Samuel Thibault
Ashley Pittman, le Thu 12 Nov 2009 19:57:11 +, a écrit : > That didn't go so well actually, this is on a NSLU2 arm machine with > 32Mb of ram running debian etch so hardly your target market! I've just tried on my mips router with 13MB and it works fine there :) > hwloc_obj_snprintf

Re: [hwloc-devel] Crash with ignoring HWLOC_OBJ_NODE in 0.9.2

2009-11-19 Thread Samuel Thibault
Michael Raymond, le Thu 19 Nov 2009 14:33:49 -0600, a écrit : > --- hwloc-0.9.2/src/topology-linux.c 2009-11-03 16:40:31.0 -0600 > +++ hwloc-new//src/topology-linux.c 2009-11-19 14:20:43.630035434 -0600 > @@ -536,6 +536,10 @@ >struct dirent *dirent; >hwloc_obj_t node; > > + if

Re: [hwloc-devel] Crash with ignoring HWLOC_OBJ_NODE in 0.9.2

2009-11-20 Thread Samuel Thibault
Michael Raymond, le Fri 20 Nov 2009 08:18:53 -0600, a écrit : > It looks like I spoke too soon on the fix. That solves the problem > but it keeps the Miscs from being created and in some situations I'd > like to keep the Miscs but not the nodes. Oh? In which situation? Can't you just ignore

Re: [hwloc-devel] Crash with ignoring HWLOC_OBJ_NODE in 0.9.2

2009-11-20 Thread Samuel Thibault
Samuel Thibault, le Fri 20 Nov 2009 15:54:43 +0100, a écrit : > Introduce several numagroup types? How many? That's not easy to > answer. Or maybe we can add an "ignore" configuration function that also takes a pair of depth parameters to ignore a range of depths for a give

Re: [hwloc-devel] Crash with ignoring HWLOC_OBJ_NODE in 0.9.2

2009-11-24 Thread Samuel Thibault
Hello, Michael Raymond, le Fri 20 Nov 2009 12:36:13 -0600, a écrit : > I wouldn't say no to the ability to flatten Misc / NUMA. As to the > current issue though, does my patch look acceptable? Thanks. The problem is that it doesn't solve Solaris :) subversion r1372 should however fix the

Re: [hwloc-devel] Crash with ignoring HWLOC_OBJ_NODE in 0.9.2

2009-11-24 Thread Samuel Thibault
Chris Samuel, le Sat 21 Nov 2009 16:55:12 +1100, a écrit : > - "Michael Raymond" wrote: > > > Our architecture has blades with two Nehalems on > > them, and the blades are connected together in a > > CC-NUMA fashion. > > I've heard on the grapevine that there will be

Re: [hwloc-devel] hwloc on ARM [Was: hwloc at SC09]

2009-11-24 Thread Samuel Thibault
Ashley Pittman, le Tue 24 Nov 2009 16:18:36 +, a écrit : > * Topology extraction from /proc/cpuinfo * > > 0 online processors found, with id max 0 That was it. > Removing empty objects except numa nodes and PCI devices > Segmentation fault Not so fine, then :) Could you post a backtrace

Re: [hwloc-devel] hwloc on ARM [Was: hwloc at SC09]

2009-11-24 Thread Samuel Thibault
Ashley Pittman, le Tue 24 Nov 2009 17:25:18 +, a écrit : > Just to be absolutely clear, head SVN works but the error is running > from a version from two weeks ago. Ah, ok. Samuel

Re: [hwloc-devel] hwloc on ARM [Was: hwloc at SC09]

2009-11-24 Thread Samuel Thibault
Ashley Pittman, le Tue 24 Nov 2009 17:25:18 +, a écrit : > Do you mean the attached file? Yes. It seems to work with the v0.9 branch so it's all good. > gather-topology.sh failed Yes, after building the .tar.gz it dumps what lstopo would see, thus the same failure. Thanks, Samuel

Re: [hwloc-devel] 0.9.3rc1 posted

2009-11-24 Thread Samuel Thibault
Hello, Jeff Squyres, le Tue 24 Nov 2009 13:14:02 -0500, a écrit : > A bunch of fixes have been applied to the 0.9 branch; v0.9.3rc1 has > been posted: > > http://www.open-mpi.org/software/hwloc/v0.9/ > > Please test it as much as you can so that we can get it out the door. On machines

Re: [hwloc-devel] 0.9.3rc1 posted

2009-11-24 Thread Samuel Thibault
Samuel Thibault, le Tue 24 Nov 2009 21:03:39 +0100, a écrit : > Jeff Squyres, le Tue 24 Nov 2009 13:14:02 -0500, a écrit : > > A bunch of fixes have been applied to the 0.9 branch; v0.9.3rc1 has > > been posted: > > > > http://www.open-mpi.org/software/hwloc

Re: [hwloc-devel] Crash with ignoring HWLOC_OBJ_NODE in 0.9.2

2009-11-30 Thread Samuel Thibault
Michael Raymond, le Mon 30 Nov 2009 09:23:02 -0600, a écrit : > At the moment I'm thinking SLES11 (and RHEL6) RPMs of 0.9.3 / TOT > installed in /opt[/sgi]/hwloc. I'd also add module support. What do you mean by "module support"? Samuel

Re: [hwloc-devel] Crash with ignoring HWLOC_OBJ_NODE in 0.9.2

2009-11-30 Thread Samuel Thibault
Michael Raymond, le Mon 30 Nov 2009 09:56:23 -0600, a écrit : > Software modules, eg on SuSE see the Modules RPM. The way that a lot > of software installations used to be managed was to throw them all under > /usr in the standard directories. Ah, ok, right. (module is so generic a name,

Re: [hwloc-devel] Disabling X component

2009-12-04 Thread Samuel Thibault
Ashley Pittman, le Fri 04 Dec 2009 11:06:12 +, a écrit : > The debian version of -.txt (lstopo 0.9.3rc1) leaves my terminal with > the colours inverted after I call it, I have to do a reset to get back > to black on grey background. Uh, odd. Which terminal are you using? Samuel

Re: [hwloc-devel] Disabling X component

2009-12-08 Thread Samuel Thibault
Hello, Ashley Pittman, le Fri 04 Dec 2009 12:08:11 +, a écrit : > On Fri, 2009-12-04 at 13:04 +0100, Samuel Thibault wrote: > > Ashley Pittman, le Fri 04 Dec 2009 11:06:12 +, a écrit : > > > The debian version of -.txt (lstopo 0.9.3rc1) leaves my terminal with > >

Re: [hwloc-devel] embedding m4 code

2009-12-09 Thread Samuel Thibault
Hello, Jeff Squyres, le Fri 04 Dec 2009 12:53:35 -0500, a écrit : > Could you guys try builds on the supported platforms to see if I broke > anything? I only have access to rhel4, rhel5, and osx. The code is in a > mercurial branch here: > > http://bitbucket.org/jsquyres/hwloc-embedded/

Re: [hwloc-devel] more embedded

2009-12-16 Thread Samuel Thibault
Jeff Squyres, le Tue 15 Dec 2009 21:13:55 -0500, a écrit : > Would it be desirable to have compiler visibility enabled in hwloc? Yes. I don't have an m4 fragment to check for visibility off-hand, that's why I hadn't done it yet and just relied on the hwloc_ prefix :) (which is still useful when

Re: [hwloc-devel] more embedded

2009-12-16 Thread Samuel Thibault
Samuel Thibault, le Wed 16 Dec 2009 15:06:15 +0100, a écrit : > Jeff Squyres, le Tue 15 Dec 2009 21:13:55 -0500, a écrit : > > Would it be desirable to have compiler visibility enabled in hwloc? > > Yes. I don't have an m4 fragment to check for visibility off-hand, BTW, do

Re: [hwloc-devel] more embedded

2009-12-16 Thread Samuel Thibault
Jeff Squyres, le Wed 16 Dec 2009 09:42:21 -0500, a écrit : > Yes -- we (OMPI) have m4 for checking for oodles of attributes. Ok, found it in config/ompi_check_attributes.m4. > Want me to bring them over and you and trim want you don't want? I'll pick up directly from openmpi. Samuel

Re: [hwloc-devel] more embedded

2009-12-16 Thread Samuel Thibault
Jeff Squyres, le Wed 16 Dec 2009 10:35:22 -0500, a écrit : > Actually, do you mind if I add it? No pb, you can as well just add the whole file indeed. Samuel

Re: [hwloc-devel] signed / unsigned

2009-12-17 Thread Samuel Thibault
Jeff Squyres, le Thu 17 Dec 2009 07:51:34 -0500, a écrit : > > > Re make check - I know it exists, but it was difficult to integrate the > > > embedded test in with the existing "check" target because the embedded > > > test > > > effectively needs a full hwloc tarball to compile against. > > >

Re: [hwloc-devel] "file name is too long" error during make dist with libpci branch

2010-01-06 Thread Samuel Thibault
Cédric Augonnet, le Wed 06 Jan 2010 21:20:48 +0100, a écrit : > tar: > hwloc-1.0a1r1568/doc/doxygen-doc/latex/structhwloc__obj__attr__u_1_1hwloc__bridge__attr__u_1_1hwloc__bridge__downstream__attr__u_1_1hwl68ed11ab93c48099bfcc01f3e8bca322.tex: > > file name is too long (cannot be split); not

Re: [hwloc-devel] #23: network topology support and v1.0 semantic fixes

2010-01-07 Thread Samuel Thibault
Hello, Happy new year btw :D Considering future network topology support, I believe we probably need to fix a couple of things before releasing 1.0. Just to sum up the a bunch of points that have been raised in the past months: - there should be a way to have the complete toplogy in just one

Re: [hwloc-devel] sometimes unused params

2010-01-08 Thread Samuel Thibault
Jeff Squyres, le Fri 08 Jan 2010 12:22:59 -0500, a écrit : > On Jan 8, 2010, at 12:22 PM, Samuel Thibault wrote: > > >> How do you guys want to handle params that are *sometimes* unused? > > > > I'd just mark them unused. > > Is it harmful to mark them

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1589

2010-01-09 Thread Samuel Thibault
jsquy...@osl.iu.edu, le Sat 09 Jan 2010 07:42:12 -0500, a écrit : > +lstopo \- Show the topology of the system (note that hwloc-bind(1) > +provides a detailed explanation of the hwloc system; it should be read > +before reading this man page). Mmm, couldn't that information (I guess you mean the

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1589

2010-01-09 Thread Samuel Thibault
Samuel Thibault, le Sat 09 Jan 2010 18:03:05 +0100, a écrit : > jsquy...@osl.iu.edu, le Sat 09 Jan 2010 07:42:12 -0500, a écrit : > > +lstopo \- Show the topology of the system (note that hwloc-bind(1) > > +provides a detailed explanation of the hwloc system; it should be read >

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1589

2010-01-11 Thread Samuel Thibault
Jeff Squyres, le Mon 11 Jan 2010 09:48:14 -0500, a écrit : > If we keep them separate, I think I'd be in favor of splitting much of the > top of hwloc-bind.1in off into hwloc.1in and having each of the tool man > pages refer to it. That was my plan. The idea is that while the PDF has general

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1589

2010-01-11 Thread Samuel Thibault
Jeff Squyres, le Mon 11 Jan 2010 10:12:45 -0500, a écrit : > > The idea is that while the PDF has general principles, the details of > > the vocabulary & such looks like a manpage and is useful to have in a > > manpage. Having it as a real manpages is convenient when using man tools > > that can

Re: [hwloc-devel] #23: network topology support andv1.0semanticfixes

2010-01-11 Thread Samuel Thibault
Jeff Squyres, le Mon 11 Jan 2010 15:20:45 -0500, a écrit : > > > I'm curious -- what's the definition of cat'ing 2 XML files together? > > > Does the 2nd become a subtree of the first? > > > > No, I mean putting both under a "misc" object for instance. > > Can you explain more; maybe provide

Re: [hwloc-devel] #23: network topology support andv1.0semanticfixes

2010-01-11 Thread Samuel Thibault
Jeff Squyres, le Mon 11 Jan 2010 15:54:55 -0500, a écrit : > cat a.xml b.xml > c.xml > > and then using c.xml directly (which I didn't see how that would work). > Instead, you're talking about manually stitching multiple XML files together > under a single , further enclosed under a single

Re: [hwloc-devel] "file name is too long" error during make distwith libpci branch

2010-01-11 Thread Samuel Thibault
Brice Goglin, le Mon 11 Jan 2010 23:50:43 +0100, a écrit : > Anyway, if we're going to drop latex files before building the tarball, > maybe we can drop manpages that are not in $(man3_MANS) too? Agree, we don't need to install them anyway, and it saves room too :) Samuel

Re: [hwloc-devel] memory size attributes

2010-01-19 Thread Samuel Thibault
Jeff Squyres, le Tue 19 Jan 2010 07:03:55 -0500, a écrit : > On Jan 17, 2010, at 6:31 AM, Brice Goglin wrote: > > > Right now we have total amount + number of hugepages + size of > > hugepages. I was only talking about modifying the way to store all this > > so as it'd be to easier to add

Re: [hwloc-devel] [hwloc-svn] svn:hwloc r1664

2010-01-25 Thread Samuel Thibault
Jeff Squyres, le Mon 25 Jan 2010 08:35:40 -0500, a écrit : > Ick! Yes :/ > Does this mean that some versions of doxy have this bug and some don't? Yes. Samuel

Re: [hwloc-devel] memory size attributes

2010-01-26 Thread Samuel Thibault
Brice Goglin, le Tue 26 Jan 2010 16:09:13 +0100, a écrit : > = 0 ? if some OS fail to give the size of normal pages or huge pages, we > might have count !=0 while size = 0 in some cases. In that case the size wouldn't be advertised at all. count == 0 is however plausible when you run out of big

Re: [hwloc-devel] processor restriction + lookup of pid for 1.0

2010-01-30 Thread Samuel Thibault
Brice Goglin, le Fri 29 Jan 2010 22:48:13 +0100, a écrit : > I am looking at the remaining tickets for v1.0. Assuming there are no > "critical" warning anymore, and assuming we have done enough for people > to combine network topologies (manually for now), only 2 ticket remains: > #12 support

Re: [hwloc-devel] processor restriction + lookup of pid for 1.0

2010-01-30 Thread Samuel Thibault
Brice Goglin, le Sat 30 Jan 2010 15:32:51 +0100, a écrit : > I still don't see much difference. In #12, you get_cpubind(pid=0) and > use the resulting cpuset to restrict our topology. In #21, you > get_cpubind(another pid) and apply the cpuset to restrict our topology > as well. No: the

Re: [hwloc-devel] P#0 -> P0 for logical numbers?

2010-01-30 Thread Samuel Thibault
With p/l prefixes: € lstopo -p - Machine(993MB) + Socketp0 + L2(2048KB) L1(32KB) + Corep0 + Pp0 L1(32KB) + Corep1 + Pp1 € lstopo - Machine(993MB) + Socketl0 + L2l0(2048KB) L1l0(32KB) + Corel0 + Pl0 L1l1(32KB) + Corel1 + Pl1 What I dislike is that this seems to bring odd words like

Re: [hwloc-devel] processor restriction + lookup of pid for 1.0

2010-01-30 Thread Samuel Thibault
Brice Goglin, le Sat 30 Jan 2010 15:47:26 +0100, a écrit : > Samuel Thibault wrote: > > Brice Goglin, le Sat 30 Jan 2010 15:32:51 +0100, a écrit : > > > >> I still don't see much difference. In #12, you get_cpubind(pid=0) and > >> use the resulting cpuset to r

Re: [hwloc-devel] processor restriction + lookup of pid for 1.0

2010-01-30 Thread Samuel Thibault
Samuel Thibault, le Sat 30 Jan 2010 15:55:00 +0100, a écrit : > #21 implicitly does: "what cpuset they're bound to" is just an example. > A configuration function hwloc_topology_set_pid(topology, pid) would > mean that the discovery has to be done from the view of the gi

Re: [hwloc-devel] processor restriction + lookup of pid for 1.0

2010-01-30 Thread Samuel Thibault
Samuel Thibault, le Sat 30 Jan 2010 15:55:00 +0100, a écrit : > > 1) hwloc_topology_from_cpu/membind(pid) (or cpuset as argument) => > > restrict topology to given cpu/membind > > 2) hwloc_topology_get_from_pid(pid) reads both cpu/membind and > > administrative restri

Re: [hwloc-devel] random api questions

2010-01-30 Thread Samuel Thibault
Brice Goglin, le Sat 30 Jan 2010 16:42:34 +0100, a écrit : > Do we want a #define HWLOC_API_VERSION to help people support both the > 0.9 and the 1.0 APIs at runtime ? At build time you mean? > What's the difference between obj->cpuset and the other obj->*cpuset ? > Some documentation is missing

Re: [hwloc-devel] random api questions

2010-01-30 Thread Samuel Thibault
Brice Goglin, le Sat 30 Jan 2010 17:05:29 +0100, a écrit : > >> What's the difference between obj->cpuset and the other obj->*cpuset ? > >> Some documentation is missing there, > >> > > > > Is the documentation on the right of the fields not sufficient? > > > > No at all... What about

Re: [hwloc-devel] random api questions

2010-01-30 Thread Samuel Thibault
Brice Goglin, le Sat 30 Jan 2010 17:40:29 +0100, a écrit : > Samuel Thibault wrote: > > Brice Goglin, le Sat 30 Jan 2010 17:34:32 +0100, a écrit : > > > >> But now that I understand all this, I wonder what application developers > >> will think about it. Most ap

Re: [hwloc-devel] random api questions

2010-01-30 Thread Samuel Thibault
Brice Goglin, le Sat 30 Jan 2010 18:17:31 +0100, a écrit : > Wait, does WHOLE_SYSTEM also toggle the ignoring of offline_cpus in > obj->cpuset? Yes, I believe it has always been that way. Samuel

Re: [hwloc-devel] [hwloc] #12: support user-defined processor restriction

2010-02-15 Thread Samuel Thibault
Brice Goglin, le Mon 15 Feb 2010 22:19:33 +0100, a écrit : > hwloc wrote: > > - Add a configuration flag to limit the discovery to the current binding > > of the process > > Do we still want this for 1.0? > > I think Ashley wanted the first item when he requested lstopo --pid > but I may be

Re: [hwloc-devel] [hwloc] #12: support user-defined processor restriction

2010-02-15 Thread Samuel Thibault
Samuel Thibault, le Mon 15 Feb 2010 22:29:55 +0100, a écrit : > Brice Goglin, le Mon 15 Feb 2010 22:19:33 +0100, a écrit : > > hwloc wrote: > > > - Add a configuration flag to limit the discovery to the current binding > > > of the process > > > Do we still

Re: [hwloc-devel] [hwloc] #12: support user-defined processor restriction

2010-02-15 Thread Samuel Thibault
Ashley Pittman, le Mon 15 Feb 2010 21:39:29 +, a écrit : > On 15 Feb 2010, at 21:29, Samuel Thibault wrote: > > > Brice Goglin, le Mon 15 Feb 2010 22:19:33 +0100, a écrit : > >> hwloc wrote: > >>> - Add a configuration flag to limit the discovery to the cur

Re: [hwloc-devel] [hwloc] #12: support user-defined processor restriction

2010-02-15 Thread Samuel Thibault
Ashley Pittman, le Mon 15 Feb 2010 21:52:29 +, a écrit : > On 15 Feb 2010, at 21:46, Samuel Thibault wrote: > >> I say the commit r1726 which closed #21 and am working on testing this > >> now, it certainly appears to be what I requested. > > > > May

Re: [hwloc-devel] 1.0-rc1

2010-02-26 Thread Samuel Thibault
Brice Goglin, le Fri 26 Feb 2010 15:32:08 +0100, a écrit : > * are there actually some important warnings to fix ? In my memory there isn't. What hasn't been finished yet and to my opinion needs to be for v1.0, is the prefix/suffix/whatever to easily distinguish between physical and logical

  1   2   3   4   5   >