Re: [hwloc-users] hwloc 0.9.3 not showing opt275 caches correctly?

2010-01-23 Thread Samuel Thibault
Hello, Brock Palen, le Sat 23 Jan 2010 13:51:09 -0500, a écrit : > System(7870MB) > Node#0(3906MB) + Socket#0 > L2(1024KB) + L1(1024KB) + Core#0 + P#0 > L2(1024KB) + L1(1024KB) + Core#1 + P#1 > Node#1(4040MB) + Socket#1 > L2(1024KB) + L1(1024KB) + Core#0 + P#2 > L2(1024KB) +

Re: [hwloc-users] howloc with scalemp

2010-04-07 Thread Samuel Thibault
Brock Palen, le Wed 07 Apr 2010 15:52:19 -0400, a écrit : > has anyone done work with hwloc on scalemp systems? Not here, but I guess something could be done, yes. Samuel

Re: [hwloc-users] howloc with scalemp

2010-04-07 Thread Samuel Thibault
Brock Palen, le Wed 07 Apr 2010 16:46:53 -0400, a écrit : > I don't know why they are all labeled Misc0 Because it doesn't know what these actually are, just that there is some distance being involved :) Samuel

Re: [hwloc-users] howloc with scalemp

2010-04-07 Thread Samuel Thibault
Brock Palen, le Wed 07 Apr 2010 16:53:49 -0400, a écrit : > Sure: > [root@nyx0809 ~]# cat /sys/devices/system/node/node*/distance > 10 20 254 254 254 254 254 254 > 20 10 254 254 254 254 254 254 > 254 254 10 20 254 254 254 254 > 254 254 20 10 254 254 254 254 > 254 254 254 254 10 20 254 254 > 254

Re: [hwloc-users] hwloc RPM spec file

2010-04-26 Thread Samuel Thibault
Brice Goglin, le Mon 26 Apr 2010 17:21:35 +0200, a écrit : > Maybe adding the spec file to the SVN could be good too? Possibly, depending on the distribution usages about it. (In the Debian case for instance, we made it in an independant branch precisely because of distribution usages). Samuel

Re: [hwloc-users] hwloc RPM spec file

2010-04-26 Thread Samuel Thibault
Jirka Hladky, le Mon 26 Apr 2010 17:32:17 +0200, a écrit : > I'm using it on system without X11 being installed. > > I have created it as the starting point to pack hwloc into rpm. What the > opinion of others - should we add dependency on X11 and sacrify the > possibility to run hwloc on

Re: [hwloc-users] Problem: hwloc-1.0rc1 on AMD Barcelona processor

2010-04-29 Thread Samuel Thibault
Brice Goglin, le Thu 29 Apr 2010 07:35:12 +0200, a écrit : > In the vast majority of cases, hwloc does nothing but reading what the > kernel says anyway. Maybe we should explicit that in the documentation, advising users to first upgrade their BIOS and kernel before reporting seemingly strange

[hwloc-users] standalone lstopo.exe?

2010-04-29 Thread Samuel Thibault
Hello, Currently, we build the whole hwloc for windows as a .zip file. I was wondering: maybe it'd be cool to also build a standalone lstopo.exe file that windows admins could keep in the corner of their desktop? Samuel

Re: [hwloc-users] Wrong cache with hwloc 1.0 on windows

2010-05-24 Thread Samuel Thibault
Hello, Αλέξανδρος Παπαδογιαννάκης, le Tue 25 May 2010 02:58:57 +0300, a écrit : > As you can see hwloc 1.0 doesn't show my L3 and L2 cache while it > worked fine with hwloc 0.9.3. Are you able to rebuild a version yourself with debugging enabled to check the output? On windows 7, the difference

Re: [hwloc-users] Distances

2010-05-25 Thread Samuel Thibault
Wheeler, Kyle Bruce, le Tue 25 May 2010 13:02:35 -0600, a écrit : > I don't see anything in hwloc for determining "distance" between objects in > the hierarchy. Is there something I'm missing? Like memory binding, it's in the TODO list :) Samuel

Re: [hwloc-users] topology object

2010-05-25 Thread Samuel Thibault
Wheeler, Kyle Bruce, le Tue 25 May 2010 15:13:51 -0600, a écrit : > On May 25, 2010, at 2:56 PM, Brice Goglin wrote: > > > On 25/05/2010 22:55, Wheeler, Kyle Bruce wrote: > >> Is the hwloc_topology_t object thread-safe? > > > > No, see the thread-safery section in the doc. > > Ah. Hm. Good to

Re: [hwloc-users] Is OSX a supported platform ?

2010-06-06 Thread Samuel Thibault
Olivier Cessenat, le Sun 06 Jun 2010 15:52:12 +0200, a écrit : > Couldn't bind to cpuset 0x0002 > >> > Is hwloc supported on OSX 10.4 platform ? Yes. But Apple has always beeing refusing to provide binding functions, so hwloc returns ENOSYS for these. Samuel

Re: [hwloc-users] Is OSX a supported platform ?

2010-06-06 Thread Samuel Thibault
Olivier Cessenat, le Sun 06 Jun 2010 17:37:23 +0200, a écrit : > I would like to get the cache sizes and hierachy; > hwloc-ls returns > << > Machine + L1 #0 (0KB) > PU #0 (phys=0) > PU #1 (phys=1) > >> > which detects my dual core, but not the cache sizes, L2 and L1. This depends on what the

Re: [hwloc-users] Is OSX a supported platform ?

2010-06-06 Thread Samuel Thibault
Olivier Cessenat, le Sun 06 Jun 2010 18:41:26 +0200, a écrit : > Thank you for the other point; it's in case the sys admin installs with > --enable-debug, so that the codes that use the API do not get awfully > verbose. As its name suggests, --enable-debug was never intended for production builds

Re: [hwloc-users] Getting the cache hierarchy

2010-06-06 Thread Samuel Thibault
Olivier Cessenat, le Sun 06 Jun 2010 19:02:21 +0200, a écrit : > Le dimanche 06 juin 2010 à 18:39 +0200, Samuel Thibault a écrit : > > Olivier Cessenat, le Sun 06 Jun 2010 18:14:35 +0200, a écrit : > > > In file included from topology.c:17: > > > /opt/gfortran/irun/bin/.

Re: [hwloc-users] Getting the cache hierarchy

2010-06-06 Thread Samuel Thibault
Olivier Cessenat, le Sun 06 Jun 2010 21:22:50 +0200, a écrit : > My system is "normal" to me : Well, the fact that it goes fetching some header from /opt/gfortran tells me it's not completely "normal" :) > /opt/gfortran/irun/bin/../lib/gcc/i386-pc-linux-gnu/4.3.0/include-fixed/sys/stat.h:345: >

Re: [hwloc-users] Is OSX a supported platform ?

2010-06-06 Thread Samuel Thibault
Olivier Cessenat, le Sun 06 Jun 2010 21:24:40 +0200, a écrit : > svn checkout from where ? As announced on the website and in README: svn checkout http://svn.open-mpi.org/svn/hwloc/trunk Samuel

Re: [hwloc-users] Getting a graphics view for a non graphic system...

2010-06-06 Thread Samuel Thibault
Olivier Cessenat, le Sun 06 Jun 2010 21:30:18 +0200, a écrit : > I see that --xml can be used to read an XML file, but what should I do > to write a file ? lstopo file.xml Samuel

Re: [hwloc-users] Is OSX a supported platform ?

2010-06-06 Thread Samuel Thibault
Olivier Cessenat, le Sun 06 Jun 2010 22:10:22 +0200, a écrit : > Great, my newest system is with autoconf 2.61 Here you are: http://dept-info.labri.fr/~thibault/tmp/hwloc-1.1a1-1.tar.gz Samuel

Re: [hwloc-users] Is OSX a supported platform ?

2010-06-06 Thread Samuel Thibault
Olivier Cessenat, le Sun 06 Jun 2010 22:44:17 +0200, a écrit : > By the way, my x86_64 configure says: > << > checking for XML... no > >> > I see I have "libxml2-utils" installed... and the --xml mechanism works. You mean lstopo --xml somefile.xml does not say This installation of hwloc does not

Re: [hwloc-users] Is OSX a supported platform ?

2010-06-07 Thread Samuel Thibault
Wheeler, Kyle Bruce, le Mon 07 Jun 2010 13:00:48 -0600, a écrit : > True; but you can make each "cpu" a thread set ID. Ok, that's what I feared :) The problem is that you don't control _location_ at all, so yes, this really seems like lying too much :) Samuel

Re: [hwloc-users] Problem with hwloc_set_thread_cpubind() and pthread_barrier_wait() on new debianj

2010-06-16 Thread Samuel Thibault
Αλέξανδρος Παπαδογιαννάκης, le Wed 16 Jun 2010 15:52:04 +0300, a écrit : > hwloc_set_thread_cpubind() by itself works. I have it on a different test > program > and it binds the threads without a problem. The problem is when the thread is > waiting on a barrier. I understand. I'm just saying that

Re: [hwloc-users] Problem with hwloc_set_thread_cpubind() and pthread_barrier_wait() on new debianj

2010-06-16 Thread Samuel Thibault
Αλέξανδρος Παπαδογιαννάκης, le Wed 16 Jun 2010 16:11:12 +0300, a écrit : > There is no shed affinity call at all if the thread is on a barrier :/ Ok, so since hwloc_set_thread_cpubind returns 0, the issue can only be in glibc's pthread_setaffinity_np() (and I guess your are calling it on a thread

Re: [hwloc-users] Could not bind on Power6

2010-06-18 Thread Samuel Thibault
Hello, Alfredo Buttari, le Fri 18 Jun 2010 08:54:35 +0200, a écrit : > Couldn't bind to cpuset 0xc000,0x0 > --> Error 0 How odd. Could you retry with the latest trunk revision I've just commited, and also give us the output of make check? Samuel

Re: [hwloc-users] hwloc and rpath

2010-06-18 Thread Samuel Thibault
Hello, I agree that rpath should be avoided. However, hwloc itself doesn't add any. Jirka Hladky, le Fri 18 Jun 2010 22:09:56 +0200, a écrit : > = > hwloc.x86_64: E: binary-or-shlib-defines-rpath /usr/bin/hwloc-distrib > ['/usr/lib64'] So

Re: [hwloc-users] FW: Problem with hwloc_set_thread_cpubind() and pthread_barrier_wait() on new debianj

2010-06-20 Thread Samuel Thibault
Αλέξανδρος Παπαδογιαννάκης, le Sun 20 Jun 2010 17:31:09 +0300, a écrit : > Thanks a lot for your help. Seems like the problem is > only in 2.6.32 kernel, 2.6.33 and 2.6.34 ara working > fine. I used git bisect like you suggested and the > problem is on a commit: > > sched: Fix a race between

Re: [hwloc-users] quick question

2010-07-22 Thread Samuel Thibault
Hello, Rupert Brooks, le Thu 22 Jul 2010 09:20:34 -0400, a écrit : > So i apologize if this question has been asked many times before. Is > there a way using hwloc (or otherwise) that i can identify which core > of the machine a thread is currently using? Hwloc provides a function to get the

Re: [hwloc-users] hwloc 1.0.2 fails to compile on Cygwin

2010-09-18 Thread Samuel Thibault
jay...@mcs.anl.gov, le Fri 17 Sep 2010 14:42:19 -0600, a écrit : > /usr/lib/gcc/i686-pc-cygwin/4.3.4/../../../../include/w32api/winspool.h:255: > error: two or more data Uh, Xwindow headers #define Status to some type... hacked around in svn, thanks for the report. Samuel

Re: [hwloc-users] Compiling Hwloc-1.1 on Windows 7 x64 Edition

2010-12-09 Thread Samuel Thibault
Amna Aslam, le Thu 09 Dec 2010 17:54:32 +0100, a écrit : > I am unable to compile hwloc library on windows 7 x64 edition using CMake. Can > anyone please help me with compiling this library using CMake or let me know > what steps to follow. Mmm, why using cmake? I don't think autoconf/automake

Re: [hwloc-users] Compiling Hwloc-1.1 on Windows 7 x64 Editiono

2010-12-09 Thread Samuel Thibault
Hello, Amna Aslam, le Thu 09 Dec 2010 19:08:21 +0100, a écrit : > This is for the first time i am using mingw64, This is the first time for us too actually. > can you tell me the steps for compiling hwloc using this mingw64. The same as usual: ./configure && make > i am getting this error,

Re: [hwloc-users] some questions about hwloc

2011-01-28 Thread Samuel Thibault
guillaume Arnal, le Fri 28 Jan 2011 15:32:40 +0100, a écrit : > First: I'm looking for a way to find which core is using by the current > thread. > (maybe with hwloc_get_thread_cpubind ??) You mean where the current thread is actually executing, not where it is just allowed to execute? Hwloc

Re: [hwloc-users] some questions about hwloc

2011-01-28 Thread Samuel Thibault
Jim Burnes, le Fri 28 Jan 2011 17:51:00 +0100, a écrit : > While hwloc might not support it, should your local threading library > do it? (ie: pthread?) There's no standard about it. The problem is that the value can be expired right after you have gotten it, that's probably why nobody managed

Re: [hwloc-users] some questions about hwloc

2011-01-28 Thread Samuel Thibault
guillaume Arnal, le Fri 28 Jan 2011 17:42:31 +0100, a écrit : > Actually, i want to know where my current thread is executing. But is seens to > be impossible, jeez ... It's not impossible, it's just not implemented in hwloc (yet). Samuel

Re: [hwloc-users] Problem getting cpuset of MPI task

2011-02-09 Thread Samuel Thibault
Hendryk Bockelmann, le Wed 09 Feb 2011 16:57:43 +0100, a écrit : > Since I am new to hwloc there might be a misunderstanding from my side, > but I have a problem getting the cpuset of MPI tasks. >/* get native cpuset of this process */ >cpuset = hwloc_bitmap_alloc(); >

Re: [hwloc-users] hwloc-ps output - how to verify process binding on the core level?

2011-02-14 Thread Samuel Thibault
Brice Goglin, le Mon 14 Feb 2011 07:56:56 +0100, a écrit : > The operating system decides where each process runs (according to the > binding). It usually has no knowledge of MPI ranks. And I don't think it looks > at the PID numbers during the scheduling. It doesn't either, indeed. Samuel

Re: [hwloc-users] Fwd: [OMPI devel] problem with absent L3 on AMD CPU

2011-04-10 Thread Samuel Thibault
Jeff Squyres, le Sun 10 Apr 2011 13:06:58 +0200, a écrit : > > It seems that lstopo can get mightly confused with AMD Athlon II processor > > (family 10h) that doesn't have L3 cache. Indeed, thanks for the fix! OpenMPI might want to pick up r3418 from the 1.1 branch. Samuel

Re: [hwloc-users] Patch to disable GCC __builtin_ operations

2011-06-08 Thread Samuel Thibault
Josh Hursey, le Wed 08 Jun 2011 22:28:53 +0200, a écrit : > I hit a problem when installing hwloc statically on a machine with a > slightly different gcc support libraries and OSs on the head/compile > node versus the compute nodes. The builtin functions would cause hwloc > to segfault when run on

Re: [hwloc-users] Patch to disable GCC __builtin_ operations

2011-06-09 Thread Samuel Thibault
Josh Hursey, le Thu 09 Jun 2011 14:52:39 +0200, a écrit : > The odd thing about this environment is that the head node seems to > have a slightly different setup than the compute nodes (not sure why > exactly, but that's what it is). So hwloc is configured and runs > correctly on the head node,

Re: [hwloc-users] Patch to disable GCC __builtin_ operations

2011-06-09 Thread Samuel Thibault
Hello, Josh Hursey, le Thu 09 Jun 2011 17:03:29 +0200, a écrit : > Program terminated with signal 4, Illegal instruction. > #0 0x0041d8d9 in hwloc_weight_long () > 0x0041d8d9 : popcnt > 0xfff8(%rbp),%rax This is SSE4 indeed. You could

Re: [hwloc-users] hwloc 1.2 compilation problems

2011-06-11 Thread Samuel Thibault
Hello, c...@pbspro.com, le Thu 09 Jun 2011 23:33:08 +0200, a écrit : > I wonder whether anyone could speak about exactly what > versions of the supporting operating systems we should expect to > work, particularly specifics about compilation requirements and > instructions. Unfortunately

Re: [hwloc-users] hwloc 1.2 compilation problems

2011-06-20 Thread Samuel Thibault
Carl Smith, le Tue 21 Jun 2011 00:44:20 +0200, a écrit : > Seems like it's lstopo-text.c's assumption that /usr/include/term.h is > appropriate to include with ncurses support that's causing the > cross-pollution. Ah, ok. So what fails to link is /* cc test.c -o test -lncurses */ #include

Re: [hwloc-users] hwloc 1.2 compilation problems

2011-06-20 Thread Samuel Thibault
Carl Smith, le Tue 21 Jun 2011 02:07:09 +0200, a écrit : > > Ah, ok. So what fails to link is > > > > /* cc test.c -o test -lncurses */ > > #include > > #include > > int main(void) { > > } > > > > is that right? > > Yes, and > > > /* cc test.c -I/usr/include/ncurses -o test -lncurses

Re: [hwloc-users] hwloc 1.2 compilation problems

2011-07-03 Thread Samuel Thibault
Samuel Thibault, le Tue 21 Jun 2011 02:10:22 +0200, a écrit : > Carl Smith, le Tue 21 Jun 2011 02:07:09 +0200, a écrit : > > > Ah, ok. So what fails to link is > > > > > > /* cc test.c -o test -lncurses */ > > > #include > > > #include > >

Re: [hwloc-users] on using hwloc_get_area_membind_nodeset

2011-07-05 Thread Samuel Thibault
Alfredo Buttari, le Tue 05 Jul 2011 20:13:55 +0200, a écrit : > if I understand correctly this routine can tell on which NUMA node(s) > a specific memory area resides, is this correct? Yes. > Will this routine work on any memory area allocated with any > allocation routine other than those

Re: [hwloc-users] hwloc 1.2 compilation problems

2011-07-07 Thread Samuel Thibault
Carl Smith, le Thu 07 Jul 2011 22:46:07 +0200, a écrit : > checking ncurses.h usability... yes > checking ncurses.h presence... yes > checking for ncurses.h... yes > checking for term.h... yes > checking for library containing tparm... -lncurses > checking curses.h usability... no > checking

Re: [hwloc-users] hwloc 1.2 compilation problems

2011-07-07 Thread Samuel Thibault
Carl Smith, le Fri 08 Jul 2011 01:01:53 +0200, a écrit : > > Oops, I hadn't realized that AC_CHECK_HEADERS checks for all of them. > > I've rewritten it quite a bit, in an actually more straightforward way, > > could you test it? > > Sure - still no joy. It's still selecting ncurses. Ow,

Re: [hwloc-users] hwloc 1.2 compilation problems

2011-07-09 Thread Samuel Thibault
Carl Smith, le Fri 08 Jul 2011 03:51:07 +0200, a écrit : > > Alright, I give up trying to use autoconf high-end macros, here is > > another, low-level try. > > Alas, I think this one comes full circle: it's deciding on ncurses, > then failing the link step. Uh. That's not coherent:

Re: [hwloc-users] hwloc 1.2 compilation problems

2011-07-12 Thread Samuel Thibault
Carl Smith, le Tue 12 Jul 2011 02:46:27 +0200, a écrit : > > is it perhaps the presence of -L/usr/local/lib which makes the linking > > fail? I've commited something that might help. > > Perhaps. Your latest change does work on this AIX system. Thanks > for persisting. Great! I've

Re: [hwloc-users] regression in 1.2 onwards?

2011-07-14 Thread Samuel Thibault
Erkcan Özcan, le Thu 14 Jul 2011 08:50:54 +0200, a écrit : > I have been testing hwloc on my macbook (OSX 10.6.8, Core 2 Duo, 4MB L2 > Cache), and the 1.2 version of hwloc is unable to determine the cache sizes > at all. I had initially used 1.0.3, which was doing fine, and I also tested >

Re: [hwloc-users] regression in 1.2 onwards?

2011-07-14 Thread Samuel Thibault
Erkcan Özcan, le Thu 14 Jul 2011 10:18:53 +0200, a écrit : > Attached are the output of lstopo with the trunk version and the 1.1.2 > version, along with the output of sysctl hw. Oops, de-C99-ization missed a sizeof, could you test trunk again? Samuel

Re: [hwloc-users] Thread core affinity

2011-07-29 Thread Samuel Thibault
Hello, Gabriele Fatigati, le Fri 29 Jul 2011 12:43:47 +0200, a écrit : > I'm so confused. I see couples of cores with the same core id! ( Core#8 for > example)  How is it possible?  That's because they are on different sockets. These are physical IDs (not logical IDs), and are thus not garanteed

Re: [hwloc-users] Thread core affinity

2011-07-29 Thread Samuel Thibault
Gabriele Fatigati, le Fri 29 Jul 2011 13:24:17 +0200, a écrit : > yhanks for yout quick reply! > > But i have a litte doubt. in a non SMT machine, Is it better use this: > > hwloc_obj_t core = hwloc_get_obj_by_type(topology, HWLOC_OBJ_CORE, tid); > hwloc_cpuset_t set =

Re: [hwloc-users] Thread core affinity

2011-07-29 Thread Samuel Thibault
Gabriele Fatigati, le Fri 29 Jul 2011 13:34:29 +0200, a écrit : > I forgot to tell you these code block is inside a parallel OpenMP region. This > is the complete code: > > #pragma omp parallel num_threads(6) > { > int tid = omp_get_thread_num(); > > hwloc_obj_t core =

Re: [hwloc-users] Thread core affinity

2011-08-01 Thread Samuel Thibault
Gabriele Fatigati, le Mon 01 Aug 2011 14:48:11 +0200, a écrit : > so, if I inderstand well, PU P# numbers are not  the same specified  as > HWLOC_OBJ_PU flag? They are, in the os_index (aka physical index) field. Samuel

Re: [hwloc-users] [hwloc-announce] Hardware Locality (hwloc) v1.2.1rc1 released

2011-08-02 Thread Samuel Thibault
Hello, Hendryk Bockelmann, le Tue 02 Aug 2011 10:54:54 +0200, a écrit : > I will test hwloc-1.2.1rc1r3567.tar.gz in the next days on our POWER6 > cluster running AIX6.1 and report the results to you resp. to the list Maybe rather wait for next nightly snapshot, as I've just fixed a bug with xml

Re: [hwloc-users] Multiple thread binding

2011-08-02 Thread Samuel Thibault
Gabriele Fatigati, le Tue 02 Aug 2011 16:23:12 +0200, a écrit : > hwloc_set_cpubind(*topology, set,  HWLOC_CPUBIND_THREAD | HWLOC_CPUBIND_STRICT > |   HWLOC_CPUBIND_NOMEMBIND); > > is it possible do multiple call to hwloc_set_cpubind passing each flag per > time?  > >

Re: [hwloc-users] Multiple thread binding

2011-08-02 Thread Samuel Thibault
Gabriele Fatigati, le Tue 02 Aug 2011 17:13:15 +0200, a écrit : > $pragma omp parallel num_thread(1) > { > hwloc_set_cpubind(*topology, set,  HWLOC_CPUBIND_THREAD | > HWLOC_CPUBIND_STRICT  > |   HWLOC_CPUBIND_NOMEMBIND); > } > > is equivalent to? > > $pragma omp parallel num_thread(1) > { >

Re: [hwloc-users] Multiple thread binding

2011-08-02 Thread Samuel Thibault
Gabriele Fatigati, le Tue 02 Aug 2011 17:22:31 +0200, a écrit : > and in this way are equivalent? > > #pragma omp parallel num_threads(1) > { > hwloc_obj_t core = hwloc_get_obj_by_type(*topology, HWLOC_OBJ_PU, 0); > hwloc_cpuset_t set = hwloc_bitmap_dup(core->cpuset); >

Re: [hwloc-users] Thread core affinity

2011-08-04 Thread Samuel Thibault
Hello, Gabriele Fatigati, le Mon 01 Aug 2011 12:32:44 +0200, a écrit : > So, are not physically near. I aspect that with Hyperthreading, and 2 hardware > threads each core, PU P#0 and PU P#1 are on the same core. Since these are P#0 and 1, they may not be indeed (physical indexes). That's the

Re: [hwloc-users] Thread core affinity

2011-08-04 Thread Samuel Thibault
Gabriele Fatigati, le Thu 04 Aug 2011 15:52:09 +0200, a écrit : > how the topology gave by lstopo is built? In particolar, how the logical index > P# are initialized? P# are not logical indexes, they are physical indexes, as displayed in /proc/cpuinfo & such. The logical indexes, L#, displayed

Re: [hwloc-users] Thread core affinity

2011-08-04 Thread Samuel Thibault
Gabriele Fatigati, le Thu 04 Aug 2011 16:14:35 +0200, a écrit : >     Socket: >         __ >        |            | >        |     |core |  |core |    | >        |              | >        |     |core | |core |     | >        |              | >        |     

Re: [hwloc-users] Thread core affinity

2011-08-04 Thread Samuel Thibault
Gabriele Fatigati, le Thu 04 Aug 2011 16:35:36 +0200, a écrit : > so physical OS index 0 and 1 are not true are physically near on the die. They quite often aren't. See the updated glossary of the documentation: "The index that the operating system (OS) uses to identify the object. This may be

Re: [hwloc-users] Thread core affinity

2011-08-04 Thread Samuel Thibault
Gabriele Fatigati, le Thu 04 Aug 2011 16:56:22 +0200, a écrit : > L#0 and L#1 are physically near because hwloc consider shared caches map when > build topology? Yes. That's the whole point of sorting objects topologically first, and numbering them afterwards. See the glossary entry for "logical

Re: [hwloc-users] Difference between HWLOC_OBJ_CORE and HWLOC_OBJ_PU

2011-08-09 Thread Samuel Thibault
Gabriele Fatigati, le Tue 09 Aug 2011 16:58:33 +0200, a écrit : > in a non SMT machine, what's the difference between HWLOC_OBJ_CORE > and HWLOC_OBJ_PU? There is no difference concerning the cpuset. > can I exchange one to other? If you are absolutely sure that your machine is non SMT, yes. But

Re: [hwloc-users] Difference between HWLOC_OBJ_CORE and HWLOC_OBJ_PU

2011-08-09 Thread Samuel Thibault
Gabriele Fatigati, le Tue 09 Aug 2011 17:04:04 +0200, a écrit : > >There is no difference concerning the cpuset. > > It means they have the same logical index? Since there is exactly one pu per core and they'll be sorted the same, yes, by construction they will have the same logical index.

Re: [hwloc-users] hwloc get cpubind function

2011-08-09 Thread Samuel Thibault
Gabriele Fatigati, le Tue 09 Aug 2011 18:14:55 +0200, a écrit : > hwloc_get_cpubind() function, return, according to the manual, "current > process > or thread binding". What does it means? The cpuset to which the current process or thread (according to flags) was last bound to. That is, the

Re: [hwloc-users] hwloc get cpubind function

2011-08-10 Thread Samuel Thibault
Gabriele Fatigati, le Wed 10 Aug 2011 09:35:19 +0200, a écrit : > these lines, doesn't works: > > set = hwloc_bitmap_alloc(); > hwloc_get_cpubind(topology, , 0); > > hwloc_get_cpubind() crash, because I have to pass set, not i suppose. Right, of course. > I think hwloc_get_last_cpu_location()

Re: [hwloc-users] hwloc get cpubind function

2011-08-10 Thread Samuel Thibault
Gabriele Fatigati, le Wed 10 Aug 2011 15:29:43 +0200, a écrit : > hwloc_obj_t core = hwloc_get_obj_by_type(topology, HWLOC_OBJ_MACHINE, 0); > > int return_value = hwloc_get_last_cpu_location(topology, core->cpuset, > HWLOC_CPUBIND_THREAD); > > and now in "core->cpuset" I get the new cpuset

Re: [hwloc-users] hwloc get cpubind function

2011-08-10 Thread Samuel Thibault
Gabriele Fatigati, le Wed 10 Aug 2011 15:41:19 +0200, a écrit : > hwloc_cpuset_t set = hwloc_bitmap_alloc(); > > int return_value = hwloc_get_last_cpu_location(topology, set, >  HWLOC_CPUBIND_THREAD); > > printf( " bitmap_string: %s \n", bitmap_string[0]); > > give me: > > 0x0800 > >

Re: [hwloc-users] hwloc get cpubind function

2011-08-10 Thread Samuel Thibault
Gabriele Fatigati, le Wed 10 Aug 2011 16:13:27 +0200, a écrit : > there is something wrong. I'm using two thread, the first one is bound on > HWLOC_OBJ_PU number 2, the second one on  HWLOC_OBJ_PU number 10, It seems that hwloc_linux_get_tid_last_cpu_location erroneously assume that

Re: [hwloc-users] hwloc get cpubind function

2011-08-10 Thread Samuel Thibault
Samuel Thibault, le Wed 10 Aug 2011 16:24:39 +0200, a écrit : > Gabriele Fatigati, le Wed 10 Aug 2011 16:13:27 +0200, a écrit : > > there is something wrong. I'm using two thread, the first one is bound on > > HWLOC_OBJ_PU number 2, the second one on  HWLOC_OBJ_PU number 10

Re: [hwloc-users] hwloc get cpubind function

2011-08-11 Thread Samuel Thibault
Gabriele Fatigati, le Thu 11 Aug 2011 10:32:23 +0200, a écrit : > I'm using hwloc-1.3a1r3606.  Now hwloc_get_last_cpu_location() works well: > > thread 0  bind:  0x0008   as core number 3 > thread 1 bind: 0x0800 as core number 11 Good. > but hwloc_linux_get_tid_cpubind() has still some

Re: [hwloc-users] hwloc get cpubind function

2011-08-11 Thread Samuel Thibault
Gabriele Fatigati, le Thu 11 Aug 2011 18:05:25 +0200, a écrit : > char* bitmap_string=(char*)malloc(256); > > hwloc_bitmap_t set = hwloc_bitmap_alloc(); > > hwloc_linux_get_tid_cpubind(, tid, set); Where does "tid" come from? hwloc_linux_get_tid_cpubind() only takes Linux tids (as in gettid()),

Re: [hwloc-users] hwloc get cpubind function

2011-08-11 Thread Samuel Thibault
Gabriele Fatigati, le Thu 11 Aug 2011 18:26:28 +0200, a écrit : > Gabriele Fatigati, le Thu 11 Aug 2011 18:05:25 +0200, a écrit : > > char* bitmap_string=(char*)malloc(256); > > > > hwloc_bitmap_t set = hwloc_bitmap_alloc(); > > > > hwloc_linux_get_tid_cpubind(, tid, set);

Re: [hwloc-users] Get CPU associated to a thread

2011-08-12 Thread Samuel Thibault
Hello, PULVERAIL Sébastien, le Fri 12 Aug 2011 13:59:46 +0200, a écrit : > Does a such function exist ? See hwloc_get_last_cpu_location() Samuel

Re: [hwloc-users] Re : lstopo on multiple machines

2011-08-16 Thread Samuel Thibault
Jeff Squyres, le Tue 16 Aug 2011 16:09:24 +0200, a écrit : > I'd be against hwloc automatically spreading across multiple machines. I > think there are plenty of tools to do that already. I fully agree. There is no way to be able to interact with each and every job scheduler anyway. > That

Re: [hwloc-users] Magny Cours L3 cache issue

2011-08-16 Thread Samuel Thibault
Wheeler, Kyle Bruce, le Tue 16 Aug 2011 16:52:54 +0200, a écrit : > hwloc-gather-topology doesn't seem to work on my compute nodes... not sure > why. It doesn't report any failures, but it doesn't create the tarball either > (just spits out more lstopo output). Maybe try to replace /bin/sh with

Re: [hwloc-users] [hwloc-announce] Hardware Locality (hwloc) v1.2.1rc3 released

2011-08-16 Thread Samuel Thibault
Brice Goglin, le Tue 16 Aug 2011 19:49:10 +0200, a écrit : > hwloc 1.2.1 *rc3* is out (web mirrors will update shortly). It fixes > hwloc_get_last_cpu_location() for Linux threads. Apart from that, > nothing important. Let's hope this one will become the final 1.2.1 > within a couple days. Since

Re: [hwloc-users] Numa availability

2011-08-28 Thread Samuel Thibault
Brice Goglin, le Sun 28 Aug 2011 12:36:31 +0200, a écrit : > > Is there a hwloc routine to check this? > > get_nbobjs_by_type(topology, HWLOC_OBJ_NODE) tells how many NUMA node > objects exist. > If you get >1, the machine is NUMA. > If the non-NUMA case, I think you can get 0 or 1 depending on

Re: [hwloc-users] Numa availability

2011-08-28 Thread Samuel Thibault
Gabriele Fatigati, le Sun 28 Aug 2011 14:47:33 +0200, a écrit : > in each case, if get_nbobjs_by_type return 0, also if the machine is NUMA, > hwloc can't build the NUMA-aware topolog, so the NUMA capability is not > usable. > Is it right? I'm not sure to understand how you relate these

Re: [hwloc-users] hwloc_get_last_cpu_location and PU

2011-08-29 Thread Samuel Thibault
Gabriele Fatigati, le Mon 29 Aug 2011 16:16:25 +0200, a écrit : > hwloc_get_last_cpu_location() return last CPU where process/thread ran.On  SMT > machine, it return the PU where   process/thread ran ? Yes, sure, since what it returns is an OS CPU bitmask. Samuel

Re: [hwloc-users] Re : Re : hwloc topology check initializing

2011-09-03 Thread Samuel Thibault
Gabriele Fatigati, le Sat 03 Sep 2011 16:09:11 +0200, a écrit : > What about hwloc_topology check()? > > What types of check does? Mostly that the hwloc library itself didn't do anything wrong. Samuel

Re: [hwloc-users] Process and thread binding

2011-09-12 Thread Samuel Thibault
Gabriele Fatigati, le Mon 12 Sep 2011 15:50:45 +0200, a écrit : > thanks very much for your explanations. But I don't understand why a process > inherits core bound of his threads On Linux, there is no such thing as "process binding", only "thread binding". hwloc emulates the former by using the

Re: [hwloc-users] GPU/NIC/CPU locality

2011-11-29 Thread Samuel Thibault
Stefan Eilemann, le Tue 29 Nov 2011 11:40:18 +0100, a écrit : > Maybe I'm missing something, but I don't see any PCI-related output with > lstopo. You are probably missing the libpci-devel package. Samuel

Re: [hwloc-users] Compiling hwloc into a static library on Windows and Linux

2012-01-09 Thread Samuel Thibault
Andrew Helwer, le Tue 10 Jan 2012 02:08:46 +0100, a écrit : > First of all, is Windows 64-bit supported? There is only a 32-bit release on > the downloads page. I have never tried to build a 64bit binary, but there is little reason it should fail. > However, when I specify the

Re: [hwloc-users] Compiling hwloc into a static library on Windows and Linux

2012-01-12 Thread Samuel Thibault
Hello, Andrew Helwer, le Thu 12 Jan 2012 02:11:58 +0100, a écrit : > If I run the command manually, it can't find the libhwloc.def file. Which is > reasonable, as it does not appear to exist in the .lib directory. Am I > missing something? In principle the .def file is generated by the linker.

Re: [hwloc-users] Compiling hwloc into a static library on Windows and Linux

2012-01-12 Thread Samuel Thibault
Hello, Andrew Helwer, le Tue 10 Jan 2012 02:08:46 +0100, a écrit : > First of all, is Windows 64-bit supported? There is only a 32-bit release on > the downloads page. I have tried mingw-w64, and it does seem to work, I have added a 64-bit release on the download page (pending mirror push).

Re: [hwloc-users] Compiling hwloc into a static library on Windows and Linux

2012-01-12 Thread Samuel Thibault
Andrew Helwer, le Tue 10 Jan 2012 02:08:46 +0100, a écrit : > the Visual Studio compiler runs into a lot of issues. What kind of issues for instance? Samuel

Re: [hwloc-users] Compiling hwloc into a static library on Windows and Linux

2012-01-12 Thread Samuel Thibault
Andrew Helwer, le Fri 13 Jan 2012 01:35:27 +0100, a écrit : > It fails with the following: > > *** Warning: linker path does not have real file for library -lgdi32. Ah, that's a dark bug in libtool. > gcc -I/cygdrive/c/hwloc-asdf/include -I/cygdrive/c/hwloc-asdf/include > -I/cygdriv >

Re: [hwloc-users] Compiling hwloc into a static library on Windows and Linux

2012-01-12 Thread Samuel Thibault
Andrew Helwer, le Fri 13 Jan 2012 01:51:15 +0100, a écrit : > I'm not sure I understand. Can you link to .a files with VS? I don't know, but what's sure is that .a files are static libraries in mingw. > I tried linking to the .lib file in the 64-bit release. I get only unresolved > external

Re: [hwloc-users] Compiling hwloc into a static library on Windows and Linux

2012-01-12 Thread Samuel Thibault
Samuel Thibault, le Fri 13 Jan 2012 02:01:12 +0100, a écrit : > Andrew Helwer, le Fri 13 Jan 2012 01:51:15 +0100, a écrit : > > I'm not sure I understand. Can you link to .a files with VS? > > I don't know, but what's sure is that .a files are static libraries in > mingw. Y

Re: [hwloc-users] Compiling hwloc into a static library on Windows and Linux

2012-01-13 Thread Samuel Thibault
Andrew Helwer, le Fri 13 Jan 2012 18:09:11 +0100, a écrit : > > You can perhaps try to rename it into a .lib file and give that to VS. > > Didn't work. What errors do you get? Samuel

Re: [hwloc-users] Compiling hwloc into a static library on Windows and Linux

2012-01-13 Thread Samuel Thibault
Andrew Helwer, le Fri 13 Jan 2012 18:16:16 +0100, a écrit : > libhwloc.lib(traversal.o) : error LNK2019: unresolved external symbol > __ms_vsnpr > intf referenced in function snprintf Do you also link msvcrt in? mingw needs it for almost everything. Samuel

Re: [hwloc-users] hwloc_get_last_cpu_location and hwloc_get_cpubind

2012-01-16 Thread Samuel Thibault
Hello, Marc-André Hermanns, le Mon 16 Jan 2012 14:01:23 +0100, a écrit : > hwloc_get_last_cpu_location(topology, cpuset, 0); > > and I am at a total loss on what I should make of this. It seems I am > doing something fundamentally wrong, You need to check the value returned by the

Re: [hwloc-users] hwloc_get_last_cpu_location and hwloc_get_cpubind

2012-01-17 Thread Samuel Thibault
Marc-André Hermanns, le Tue 17 Jan 2012 11:47:43 +0100, a écrit : > It seems now that it has the whole system in the cpuset. How can I > really infer the PU this process was run on? I would have expected the > cpuset to have only 1 element per level to indicate the path from > machine to PU.

Re: [hwloc-users] hwloc_get_last_cpu_location and hwloc_get_cpubind

2012-01-17 Thread Samuel Thibault
Marc-André Hermanns, le Tue 17 Jan 2012 15:15:12 +0100, a écrit : > write(1, "This system has 4 levels\n", 25) = 25 > open("/proc/self/task", > O_RDONLY|O_NONBLOCK|O_LARGEFILE|O_DIRECTORY|O_CLOEXEC) = 4 > fcntl64(4, F_GETFD) = 0x1 (flags FD_CLOEXEC) > fstat64(4,

Re: [hwloc-users] Bogus files in 64bit Windows binary distribution (1.4rc1)

2012-01-19 Thread Samuel Thibault
Hartmut Kaiser, le Fri 20 Jan 2012 00:43:32 +0100, a écrit : > > Hartmut Kaiser, le Thu 19 Jan 2012 22:48:50 +0100, a écrit : > > > We are using hwloc with VS2010 and were happy to realize that after > > > the (for > > > us) totally broken Windows binary distribution in V1.3 > > > > Broken? How

Re: [hwloc-users] creation and destruction of bound threads

2012-01-30 Thread Samuel Thibault
Albert Solernou, le Mon 30 Jan 2012 12:37:31 +0100, a écrit : > I am working on a threaded code, and want to bind threads to cores. However, > the process creates and destroys the threads, so here is the question: > What happens if I enter on a threaded part of the code, bind "thread X" to > a

Re: [hwloc-users] build issue with CFLAGS='-mcmodel=medium'

2012-01-31 Thread Samuel Thibault
Could you try the attached patch? Samuel Index: include/private/cpuid.h === --- include/private/cpuid.h (révision 4210) +++ include/private/cpuid.h (copie de travail) @@ -1,5 +1,5 @@ /* - * Copyright © 2010-2011 Université

Re: [hwloc-users] [hwloc-announce] Hardware locality (hwloc) v1.4 released

2012-02-14 Thread Samuel Thibault
Hello, Jiri Hladky, le Wed 15 Feb 2012 01:38:44 +0100, a écrit : > I have found one minor issue - file hwloc-assembler-remote does not have > executable bit set. I had to add following to the RPM SPEC file to fix it: > > %{__chmod} 0755 %{buildroot}%{_bindir}/hwloc-assembler-remote That's odd:

  1   2   >