[hwloc-devel] Create success (hwloc r1.2.1rc1r3540)
Creating nightly hwloc snapshot SVN tarball was a success. Snapshot: hwloc 1.2.1rc1r3540 Start time: Mon Jul 4 21:03:32 EDT 2011 End time: Mon Jul 4 21:05:48 EDT 2011 Your friendly daemon, Cyrador
[hwloc-devel] Create success (hwloc r1.3a1r3537)
Creating nightly hwloc snapshot SVN tarball was a success. Snapshot: hwloc 1.3a1r3537 Start time: Mon Jul 4 21:01:02 EDT 2011 End time: Mon Jul 4 21:03:31 EDT 2011 Your friendly daemon, Cyrador
Re: [hwloc-devel] hwloc trunk nightly 1.3a1r3511 fails to build on CentOS 5.6 & RHEL 5.6
All this should be fixed now, and the configure output is now clear (it doesn't change its mind about pci_init/cleanup or pci_lookup_name without any obvious reason anymore). FC7: checking for pci/pci.h... yes checking for pci_init in -lpci... no checking for pci_init in -lpci with -lz... yes checking for pci_lookup_name in -lpci... no checking for inet_ntoa in -lresolv... yes checking for pci_lookup_name in -lpci with -lresolv... yes RHEL5.6: checking for pci/pci.h... yes checking for pci_init in -lpci... yes checking for pci_lookup_name in -lpci... no checking for inet_ntoa in -lresolv... yes checking for pci_lookup_name in -lpci with -lresolv... yes RHEL5.3: checking for pci/pci.h... yes checking for pci_init in -lpci... yes checking for pci_lookup_name in -lpci... yes Christopher, it should work starting with trunk r3535. Brice Le 30/06/2011 07:50, Brice Goglin a écrit : > Le 29/06/2011 13:18, Brice Goglin a écrit : >> I don't think we finally fixed this. >> >> IIRC, we need either a way to bypass the cache, or always add -lresolv >> even if it's useless (or find another way to detect if lresolv is needed). > Redefining our own HWLOC_AC_CHECK_LIB_NO_CACHE looks possible. > > Otherwise, we could use something different from AC_CHECK_LIB for the > second check (AC_SEARCH_LIBS uses a different cache name). > Or even use AC_LINK_IFELSE/AC_TRY_LINK which never cache anything. > > Brice > > ___ > hwloc-devel mailing list > hwloc-de...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-devel
Re: [hwloc-devel] hwloc_distances as utility?
Le 03/07/2011 23:55, Jiri Hladky a écrit : > Hi all, > > I have come across tests/hwloc_distances test and I believe that it > would be great to convert this into the utility > "hwloc-report-instances" published under utils/ directory. Please let > me know what you think about it. > > It would take the same input as hwloc-info (read topology from > different formats instead of discovering the topology on the local > machine), support both logical and physical indexes (-l and -p) switch. By the way, lstopo shows distance information, but it does not change it depending on -l/-p. We may want to fix this. > I have used stream memory bandwidth benchmark > (http://www.cs.virginia.edu/stream/) in the past to produce the > similar output as tests/hwloc_distances. It was interesting to see > that numactl and kernel scheduler are both using number of hopes > instead of memory bandwidth. Actually, Linux only uses the number of hops on one specific MIPS architecture (SGI IP27 Origin 200/2000). In other cases, it uses the cpu-to-memory latency (usually reported by ACPI or so). > On some systems number of hops does not represent memory bandwidth. I > have reported this in BZ 655041 > > https://bugzilla.redhat.com/show_bug.cgi?id=655041 This bug is private unfortunately. > In any case I believe that hwloc-report-instances would be useful > utility. Please let me know your opinion. Agreed. There are still several things to improve regarding distances. Everything should be in https://svn.open-mpi.org/trac/hwloc/ticket/43 Brice