Re: [hwloc-users] Puzzled by the number of cores on i5-7500
I assume you need other people to answer as well, but here is what I get: $ sysctl -a | grep ^hw hw.ncpu: 4 hw.byteorder: 1234 hw.memsize: 8589934592 hw.activecpu: 4 hw.physicalcpu: 4 hw.physicalcpu_max: 4 hw.logicalcpu: 4 hw.logicalcpu_max: 4 hw.cputype: 7 hw.cpusubtype: 8 hw.cpu64bit_capable: 1 hw.cpufamily: 260141638 hw.cacheconfig: 4 1 1 4 0 0 0 0 0 0 hw.cachesize: 8589934592 32768 262144 6291456 0 0 0 0 0 0 hw.pagesize: 4096 hw.pagesize32: 4096 hw.busfrequency: 1 hw.busfrequency_min: 1 hw.busfrequency_max: 1 hw.cpufrequency: 34 hw.cpufrequency_min: 34 hw.cpufrequency_max: 34 hw.cachelinesize: 64 hw.l1icachesize: 32768 hw.l1dcachesize: 32768 hw.l2cachesize: 262144 hw.l3cachesize: 6291456 hw.tbfrequency: 10 hw.packages: 1 hw.optional.floatingpoint: 1 hw.optional.mmx: 1 hw.optional.sse: 1 hw.optional.sse2: 1 hw.optional.sse3: 1 hw.optional.supplementalsse3: 1 hw.optional.sse4_1: 1 hw.optional.sse4_2: 1 hw.optional.x86_64: 1 hw.optional.aes: 1 hw.optional.avx1_0: 1 hw.optional.rdrand: 1 hw.optional.f16c: 1 hw.optional.enfstrg: 1 hw.optional.fma: 1 hw.optional.avx2_0: 1 hw.optional.bmi1: 1 hw.optional.bmi2: 1 hw.optional.rtm: 1 hw.optional.hle: 1 hw.optional.adx: 1 hw.optional.mpx: 0 hw.optional.sgx: 0 hw.optional.avx512f: 0 hw.optional.avx512cd: 0 hw.optional.avx512dq: 0 hw.optional.avx512bw: 0 hw.optional.avx512vl: 0 hw.optional.avx512ifma: 0 hw.optional.avx512vbmi: 0 hw.targettype: Mac $ sysctl -a | grep ^machdep.cpu machdep.cpu.max_basic: 22 machdep.cpu.max_ext: 2147483656 machdep.cpu.vendor: GenuineIntel machdep.cpu.brand_string: Intel(R) Core(TM) i5-7500 CPU @ 3.40GHz machdep.cpu.family: 6 machdep.cpu.model: 158 machdep.cpu.extmodel: 9 machdep.cpu.extfamily: 0 machdep.cpu.stepping: 9 machdep.cpu.feature_bits: 9221960262849657855 machdep.cpu.leaf7_feature_bits: 43806655 machdep.cpu.extfeature_bits: 1241984796928 machdep.cpu.signature: 591593 machdep.cpu.brand: 0 machdep.cpu.features: FPU VME DE PSE TSC MSR PAE MCE CX8 APIC SEP MTRR PGE MCA CMOV PAT PSE36 CLFSH DS ACPI MMX FXSR SSE SSE2 SS HTT TM PBE SSE3 PCLMULQDQ DTES64 MON DSCPL VMX SMX EST TM2 SSSE3 FMA CX16 TPR PDCM SSE4.1 SSE4.2 x2APIC MOVBE POPCNT AES PCID XSAVE OSXSAVE SEGLIM64 TSCTMR AVX1.0 RDRAND F16C machdep.cpu.leaf7_features: SMEP ERMS RDWRFSGS TSC_THREAD_OFFSET BMI1 HLE AVX2 BMI2 INVPCID RTM SMAP RDSEED ADX IPT SGX FPU_CSDS MPX CLFSOPT machdep.cpu.extfeatures: SYSCALL XD 1GBPAGE EM64T LAHF LZCNT PREFETCHW RDTSCP TSCI machdep.cpu.logical_per_package: 16 machdep.cpu.cores_per_package: 8 machdep.cpu.microcode_version: 88 machdep.cpu.processor_flag: 1 machdep.cpu.mwait.linesize_min: 64 machdep.cpu.mwait.linesize_max: 64 machdep.cpu.mwait.extensions: 3 machdep.cpu.mwait.sub_Cstates: 1319200 machdep.cpu.thermal.sensor: 1 machdep.cpu.thermal.dynamic_acceleration: 1 machdep.cpu.thermal.invariant_APIC_timer: 1 machdep.cpu.thermal.thresholds: 2 machdep.cpu.thermal.ACNT_MCNT: 1 machdep.cpu.thermal.core_power_limits: 1 machdep.cpu.thermal.fine_grain_clock_mod: 1 machdep.cpu.thermal.package_thermal_intr: 1 machdep.cpu.thermal.hardware_feedback: 0 machdep.cpu.thermal.energy_policy: 1 machdep.cpu.xsave.extended_state: 31 832 1088 0 machdep.cpu.xsave.extended_state1: 15 832 256 0 machdep.cpu.arch_perf.version: 4 machdep.cpu.arch_perf.number: 8 machdep.cpu.arch_perf.width: 48 machdep.cpu.arch_perf.events_number: 7 machdep.cpu.arch_perf.events: 0 machdep.cpu.arch_perf.fixed_number: 3 machdep.cpu.arch_perf.fixed_width: 48 machdep.cpu.cache.linesize: 64 machdep.cpu.cache.L2_associativity: 4 machdep.cpu.cache.size: 256 machdep.cpu.tlb.inst.large: 8 machdep.cpu.tlb.data.small: 64 machdep.cpu.tlb.data.small_level1: 128 machdep.cpu.address_bits.physical: 39 machdep.cpu.address_bits.virtual: 48 machdep.cpu.core_count: 4 machdep.cpu.thread_count: 4 machdep.cpu.tsc_ccc.numerator: 284 machdep.cpu.tsc_ccc.denominator: 2 $ lstopo - Machine (8192MB total) + NUMANode L#0 (P#0 8192MB) + L3 L#0 (6144KB) Core L#0 L2 L#0 (256KB) + L1d L#0 (32KB) + L1i L#0 (32KB) + PU L#0 (P#0) L2 L#1 (256KB) + L1d L#1 (32KB) + L1i L#1 (32KB) + PU L#1 (P#1) Core L#1 L2 L#2 (256KB) + L1d L#2 (32KB) + L1i L#2 (32KB) + PU L#2 (P#2) L2 L#3 (256KB) + L1d L#3 (32KB) + L1i L#3 (32KB) + PU L#3 (P#3) > Le 25 janv. 2018 à 19:18, Brice Goglin a écrit : > > lstopo - ___ hwloc-users mailing list hwloc-users@lists.open-mpi.org https://lists.open-mpi.org/mailman/listinfo/hwloc-users
[hwloc-users] Puzzled by the number of cores on i5-7500
Hello, I’m puzzled by the report from lstopo about the number of physical cores on an iMac with I5-7500. It is specified by Intel as a quad core processor and lstopo reports only 2 cores: lstopo << Machine (8192MB total) + NUMANode L#0 (P#0 8192MB) + L3 L#0 (6144KB) Core L#0 L2 L#0 (256KB) + L1d L#0 (32KB) + L1i L#0 (32KB) + PU L#0 (P#0) L2 L#1 (256KB) + L1d L#1 (32KB) + L1i L#1 (32KB) + PU L#1 (P#1) Core L#1 L2 L#2 (256KB) + L1d L#2 (32KB) + L1i L#2 (32KB) + PU L#2 (P#2) L2 L#3 (256KB) + L1d L#3 (32KB) + L1i L#3 (32KB) + PU L#3 (P#3) >> When running system_profiler SPHardwareDataType I obtain: << Hardware: Hardware Overview: Model Name: iMac Model Identifier: iMac18,3 Processor Name: Intel Core i5 Processor Speed: 3,4 GHz Number of Processors: 1 Total Number of Cores: 4 L2 Cache (per Core): 256 KB L3 Cache: 6 MB Memory: 8 GB Boot ROM Version: IM183.0151.B00 SMC Version (system): 2.41f1 Serial Number (system): DGKV7HJCJ1GN Hardware UUID: 3FDAD77B-F4E8-50AB-B0FF-AA5C41CA35FA >> Is there a trick ? Thanks for you help, Olivier Cessenat ___ hwloc-users mailing list hwloc-users@lists.open-mpi.org https://lists.open-mpi.org/mailman/listinfo/hwloc-users
Re: [hwloc-users] How do I access CPUModel info string
Hello, Sorry for not replying to your thread but my free zimbra box is broken so I fetched your answer from http://www.open-mpi.org/community/lists/hwloc-users/2012/10/0754.php Please include my orange box if you reply so that I get the answer instantly... So, here is the output: mac:/tmp/hwloc-1.6a1r4928 cessenat$ ./utils/lstopo-no-graphics Machine (3072MB) + NUMANode L#0 (P#0 3072MB) + L2 L#0 (4096KB) L1d L#0 (32KB) + L1i L#0 (32KB) + PU L#0 (P#0) L1d L#1 (32KB) + L1i L#1 (32KB) + PU L#1 (P#1) Olivier Cessenat. PS: Just in case, I also provide the output of sysctl hw: << hw.ncpu: 2 hw.byteorder: 1234 hw.memsize: 3221225472 hw.activecpu: 2 hw.physicalcpu: 2 hw.physicalcpu_max: 2 hw.logicalcpu: 2 hw.logicalcpu_max: 2 hw.cputype: 7 hw.cpusubtype: 4 hw.cpufamily: 1114597871 hw.cacheconfig: 2 1 2 0 0 0 0 0 0 0 hw.pagesize: 4096 hw.busfrequency: 66400 hw.busfrequency_min: 66400 hw.busfrequency_max: 66400 hw.cpufrequency: 216000 hw.cpufrequency_min: 216000 hw.cpufrequency_max: 216000 hw.cachelinesize: 64 hw.l1icachesize: 32768 hw.l1dcachesize: 32768 hw.l2cachesize: 4194304 hw.tbfrequency: 10 hw.optional.floatingpoint: 1 hw.optional.mmx: 1 hw.optional.sse: 1 hw.optional.sse2: 1 hw.optional.sse3: 1 hw.optional.x86_64: 1 hw.optional.supplementalsse3: 1 hw.machine = i386 hw.model = iMac5,1 hw.ncpu = 2 hw.byteorder = 1234 hw.physmem = 2147483648 hw.usermem = 1789140992 hw.pagesize = 4096 hw.epoch = 0 hw.vectorunit = 1 hw.busfrequency = 66400 hw.cpufrequency = 216000 hw.cachelinesize = 64 hw.l1icachesize = 32768 hw.l1dcachesize = 32768 hw.l2settings = 1 hw.l2cachesize = 4194304 hw.tbfrequency = 10 hw.memsize = 3221225472 hw.availcpu = 2 >> << Brice Goglin wrote: Can you send your lstopo output? preferably with latest trunk tarball http://www.open-mpi.org/software/hwloc/nightly/trunk/hwloc-1.6a1r4928.tar.gz One way to solve this problem (which may also occur on old Linux distribs) would be to store the CPU model in the machine object. But we'll have to make sure all processors in the machine are indeed of the same model. On MacOSX, it looks like sysctl reports a single socket description anyway, so no problem. Brice >> Le samedi 27 octobre 2012 à 11:37 +0200, Olivier Cessenat a écrit : > Hello, > > Robin Scher indicated how to get the info on a Mac. > > At least on mine (OSX 10.4) with darwin 8.11.1 > where > $ sysctl -a machdep.cpu.brand_string > machdep.cpu.brand_string: Intel(R) Core(TM)2 CPU T7400 @ > 2.16GHz > I unfortunately have no socket: > *** The number of sockets is unknown > [ from Third example: Print the number of sockets. of > http://www.open-mpi.org/projects/hwloc/doc/v1.5.1/ > ] > I see objects type 1,2,4 and 6 only. > > So, will there be another (non socket hwloc object based) way to get > CPUModel or will it find sockets as on Linux ? > > Thanks. > > Olivier Cessenat. > > > Le jeudi 25 octobre 2012 à 23:42 +0200, Brice Goglin a écrit : > > Hello, > > > > Assuming you found the socket hwloc object whose name you want, do > > hwloc_obj_get_info_by_name(obj, "CPUModel"); > > you'll get const char * pointing to what you want. > > > > However, this info is only available on Linux and Solaris for now. If > > you have any idea of to discover such info on other OS, please let us > > know. > > > > Brice > > > > > > > > Le 25/10/2012 23:39, Robin Scher a écrit : > > > Is there a way to get this string (e.g. "Intel(R) Core(TM) i7 CPU M > > > 620 @ 2.67GHz") consistently on Windows, Linux, OS-X and Solaris? > > > > > > Thanks, > > > -robin > > > > > > -- > > > Robin Scher Uberware > > > ro...@uberware.net > > > +1 (213) 448-0443 > > > > > > > > > > > > > > > ___ > > > hwloc-users mailing list > > > hwloc-us...@open-mpi.org > > > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users > > > > ___ > > hwloc-users mailing list > > hwloc-us...@open-mpi.org > > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] How do I access CPUModel info string
Hello, Robin Scher indicated how to get the info on a Mac. At least on mine (OSX 10.4) with darwin 8.11.1 where $ sysctl -a machdep.cpu.brand_string machdep.cpu.brand_string: Intel(R) Core(TM)2 CPU T7400 @ 2.16GHz I unfortunately have no socket: *** The number of sockets is unknown [ from Third example: Print the number of sockets. of http://www.open-mpi.org/projects/hwloc/doc/v1.5.1/ ] I see objects type 1,2,4 and 6 only. So, will there be another (non socket hwloc object based) way to get CPUModel or will it find sockets as on Linux ? Thanks. Olivier Cessenat. Le jeudi 25 octobre 2012 à 23:42 +0200, Brice Goglin a écrit : > Hello, > > Assuming you found the socket hwloc object whose name you want, do > hwloc_obj_get_info_by_name(obj, "CPUModel"); > you'll get const char * pointing to what you want. > > However, this info is only available on Linux and Solaris for now. If > you have any idea of to discover such info on other OS, please let us > know. > > Brice > > > > Le 25/10/2012 23:39, Robin Scher a écrit : > > Is there a way to get this string (e.g. "Intel(R) Core(TM) i7 CPU M > > 620 @ 2.67GHz") consistently on Windows, Linux, OS-X and Solaris? > > > > Thanks, > > -robin > > > > -- > > Robin Scher Uberware > > ro...@uberware.net > > +1 (213) 448-0443 > > > > > > > > > > ___ > > hwloc-users mailing list > > hwloc-us...@open-mpi.org > > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users > > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Is OSX a supported platform ?
Le dimanche 06 juin 2010 à 22:55 +0200, Samuel Thibault a écrit : > 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 support --xml, sorry. > ? If so, did you try lstopo file.xml anyway? checking for was said by configure. So, configure on iliana (x86_64) says no XML, but --xml works fine (at least with official 1.0 release) ! If the ".fig" file can be created on Tera 10, then I do not need the XML stuff; just want to get a nice picture ! > > > Is'nt that weird ? > > Can you tell me which is the XML lib needed to write lstopo xml files ? > > Just something like libxml2-devel should be fine. > > > Further, do you know where to download them from - If I dare asking... > > Depends on your distribution. OK. Olivier.
Re: [hwloc-users] Is OSX a supported platform ?
Ouaouh ! Great, so easy ! Thank you very much indeed for all your help. It now fits my needs on OSX, very likely Tera 10 as I will check tomorrow. There only remains i686; I shall ask a friend with an Ubuntu next week. Sincerely, Olivier Cessenat. Le dimanche 06 juin 2010 à 22:40 +0200, Samuel Thibault a écrit : > Olivier Cessenat, le Sun 06 Jun 2010 22:31:32 +0200, a écrit : > > so I cannot get the graphics view, even with my x86_64 -brand new from > > 2008... > > You can use the .fig output and open it with xfig, or convert to pdf by > using > > fig2dev -L pdf file.fig file.pdf > > Samuel > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Is OSX a supported platform ?
By the way, my x86_64 configure says: << checking for XML... no >> I see I have "libxml2-utils" installed... and the --xml mechanism works. Is'nt that weird ? Can you tell me which is the XML lib needed to write lstopo xml files ? Further, do you know where to download them from - If I dare asking... Cheers, Olivier. Le dimanche 06 juin 2010 à 22:31 +0200, Olivier Cessenat a écrit : > Second to none service ! Marvellous ! > << > mac:/tmp/hwloc-1.1a1-1 root# hwloc-ls > Machine (1024MB) + NUMANode #0 (phys=0 1024MB) + L2 #0 (4096KB) > L1 #0 (32KB) + PU #0 (phys=0) > L1 #1 (32KB) + PU #1 (phys=1) > >> > I believed I had 2 MB L2 cache, I'm happy to see it's more than I > thought ! > > Unfortunately, I do not have XML on Mac: > << > checking for XML... no > >> > so I cannot get the graphics view, even with my x86_64 -brand new from > 2008... > > Cheers, > > Olivier. > > > Le dimanche 06 juin 2010 à 22:20 +0200, Samuel Thibault a écrit : > > 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 > > ___ > > hwloc-users mailing list > > hwloc-us...@open-mpi.org > > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users > > > > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Is OSX a supported platform ?
Second to none service ! Marvellous ! << mac:/tmp/hwloc-1.1a1-1 root# hwloc-ls Machine (1024MB) + NUMANode #0 (phys=0 1024MB) + L2 #0 (4096KB) L1 #0 (32KB) + PU #0 (phys=0) L1 #1 (32KB) + PU #1 (phys=1) >> I believed I had 2 MB L2 cache, I'm happy to see it's more than I thought ! Unfortunately, I do not have XML on Mac: << checking for XML... no >> so I cannot get the graphics view, even with my x86_64 -brand new from 2008... Cheers, Olivier. Le dimanche 06 juin 2010 à 22:20 +0200, Samuel Thibault a écrit : > 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 > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Getting the cache hierarchy
Le dimanche 06 juin 2010 à 22:13 +0200, Samuel Thibault a écrit : > Olivier Cessenat, le Sun 06 Jun 2010 22:06:51 +0200, a écrit : > > [cessenat@valerie hwloc-1.0.1]$ which gcc > > /usr/bin/gcc > > > > It's only gfortran that I have in opt. > > And its bin/ directory only contains bin/gfortran? or does it perhaps > also contain cpp? Oups... << [cessenat@valerie hwloc-1.0.1]$ ls -al /opt/gfortran/irun/bin total 3012 drwxr-xr-x 2 1005 1011 4096 oct 30 2007 ./ drwxr-xr-x 9 1005 1011 4096 oct 30 2007 ../ -rwxr-xr-x 1 1005 1011 485379 oct 30 2007 cpp* -rwxr-xr-x 3 1005 1011 482904 oct 30 2007 gcc* -rwxr-xr-x 1 1005 1011 15977 oct 30 2007 gccbug* -rwxr-xr-x 1 1005 1011 100177 oct 30 2007 gcov* -rwxr-xr-x 2 1005 1011 491995 oct 30 2007 gfortran* -rwxr-xr-x 3 1005 1011 482904 oct 30 2007 i386-pc-linux-gnu-gcc* -rwxr-xr-x 3 1005 1011 482904 oct 30 2007 i386-pc-linux-gnu-gcc-4.3.0* -rwxr-xr-x 2 1005 1011 491995 oct 30 2007 i386-pc-linux-gnu-gfortran* [cessenat@valerie hwloc-1.0.1]$ /opt/gfortran/irun/bin/gcc -dumpversion 4.3.0 [cessenat@valerie hwloc-1.0.1]$ gcc -dumpversion 4.0.1 >> > > Removing it from the path makes it compile. > > Ok. I really believe installing a very new compiler on a very old > system was the culprit :) I agree ! Olivier.
Re: [hwloc-users] Is OSX a supported platform ?
Great, my newest system is with autoconf 2.61: << [cessenat@iliana trunk]$ autoconf --version autoconf (GNU Autoconf) 2.61 Copyright (C) 2006 Free Software Foundation, Inc. This is free software. You may redistribute copies of it under the terms of the GNU General Public License <http://www.gnu.org/licenses/gpl.html>. There is NO WARRANTY, to the extent permitted by law. Written by David J. MacKenzie and Akim Demaille. >> I shall try at the end of next week - on travel this week. I keep it in mind. Olivier. Le dimanche 06 juin 2010 à 21:59 +0200, Samuel Thibault a écrit : > Olivier Cessenat, le Sun 06 Jun 2010 21:52:34 +0200, a écrit : > > I'm not sure my technical skills in computer science will allow me to > > update the autoconf stuff - > > No need to. Run autoconf on a newer system, then transfer the result. Or > you can also wait for tomorrow and use the nightly snapshot. > > Samuel > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Getting the cache hierarchy
[cessenat@valerie hwloc-1.0.1]$ which gcc /usr/bin/gcc It's only gfortran that I have in opt. Removing it from the path makes it compile. Olivier. Le dimanche 06 juin 2010 à 21:52 +0200, Samuel Thibault a écrit : > Olivier Cessenat, le Sun 06 Jun 2010 21:40:03 +0200, a écrit : > > [root@valerie hwloc-1.0.1]# /usr/bin/gcc > > gcc: no input files > > No, I said: what does > > which gcc > > return? I guess you are currently getting some gcc from /opt, which > leads to all the kinds of errors you are getting in config.log. Please > remove that from your PATH. > > > /opt/gfortran/irun/bin/../lib/gcc/i386-pc-linux-gnu/4.3.0/include-fixed/sys/stat.h:345: > > error: expected ',' or ';' before '__wur' > > Samuel > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Getting a graphics view for a non graphic system...
Hi Samuel, OK, the answer, to my unclear question is: << [cessenat@valerie hwloc-1.0.1]# lstopo file.xml [cessenat@iliana ~]$ hwloc-ls --xml file.xml >> comp1 is the computer with no graphics lib, comp2 is the one with the libs. What you write is clear to computer scientists, but I failed to figure out what it meant. Sorry, it is clear now ! Olivier. Le dimanche 06 juin 2010 à 21:42 +0200, Samuel Thibault a écrit : > Olivier Cessenat, le Sun 06 Jun 2010 21:34:49 +0200, a écrit : > > Sure. It does not explain how. > > “ > Usage: lt-lstopo [ options ] ... [ filename ] > > See lstopo(1) for more details. > > Supported output file formats: .txt, .fig, .pdf, .ps, .png, .svg, .xml > ” > > How should we write it instead? > > > Should I perform on comp1 the no-graphics machine and comp2 the one with > > graphics : > > $ comp1: hwloc-ls > toto.txt > > $ comp2: hwloc-ls toto.txt > > What is comp1 and comp2, and what do you want to achieve precisely? > > Samuel > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Is OSX a supported platform ?
Hi Samuel, I made the checkout. I seem to have too old an autoconf. I ran autogen.sh as rexplained in README line 70. << $ ./autogen.sh autoreconf: Entering directory `.' autoreconf: configure.ac: not using Gettext autoreconf: running: aclocal -I ./config --output=aclocal.m4t autoreconf: `aclocal.m4' is unchanged autoreconf: configure.ac: tracing configure.ac:16: error: Autoconf version 2.63 or higher is required configure.ac:16: the top level autom4te: /usr/bin/gm4 failed with exit status: 63 autoreconf: configure.ac: not using Libtool autoreconf: running: /usr/bin/autoconf --force configure.ac:16: error: Autoconf version 2.63 or higher is required configure.ac:16: the top level autom4te: /usr/bin/gm4 failed with exit status: 63 autoreconf: /usr/bin/autoconf failed with exit status: 63 >> << $ autoconf --version autoconf (GNU Autoconf) 2.59 Written by David J. MacKenzie and Akim Demaille. Copyright (C) 2003 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. >> I'm not sure my technical skills in computer science will allow me to update the autoconf stuff - as well as it may be preferable to keep an old but stable system... What do you think ? Olivier. Le dimanche 06 juin 2010 à 21:32 +0200, Samuel Thibault a écrit : > 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 > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Getting the cache hierarchy
Hi Samuel, I checked the variables: [root@valerie hwloc-1.0.1]# echo $CPATH [root@valerie hwloc-1.0.1]# echo $C_INCLUDE_PATH [root@valerie hwloc-1.0.1]# /usr/bin/gcc gcc: no input files My system is only an old Mandriva (for old processors, but I've got many of them) with a compiled gfortran from the gfortran download page in 2007. Cheers, Olivier. Le dimanche 06 juin 2010 à 21:31 +0200, Samuel Thibault a écrit : > 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: > > error: expecte > > does which gcc return you > > /usr/bin/gcc > > ? Do you perhaps have some CPATH or C_INCLUDE_PATH variable in your > environment ? > > > checking for sys/param.h... no > > checking for sys/sysctl.h... no > > These also aren't supposed to happen on any sane Linux system. Could you > send the config.log? > > Samuel > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users This file contains any messages produced by compilers while running configure, to aid debugging if configure makes a mistake. It was created by hwloc configure 1.0.1, which was generated by GNU Autoconf 2.65. Invocation command line was $ ./configure --enable-debug ## - ## ## Platform. ## ## - ## hostname = valerie.magic uname -m = i686 uname -r = 2.6.12-12mdk uname -s = Linux uname -v = #1 Fri Sep 9 18:15:22 CEST 2005 /usr/bin/uname -p = unknown /bin/uname -X = unknown /bin/arch = i686 /usr/bin/arch -k = unknown /usr/convex/getsysinfo = unknown /usr/bin/hostinfo = unknown /bin/machine = unknown /usr/bin/oslevel = unknown /bin/universe = unknown PATH: /opt/intel/fc/10.1.018/bin PATH: /opt/intel/cc/10.1.018/bin PATH: /opt/gfortran/irun/bin PATH: /sbin PATH: /usr/sbin PATH: /bin PATH: /usr/bin PATH: /usr/X11R6/bin PATH: /usr/local/bin PATH: /usr/local/sbin PATH: . PATH: /opt/lmpi/bin PATH: /opt/visit/bin PATH: /opt/silo-4.7/bin PATH: /opt/intel/vtune/bin PATH: /opt/intel/vtune/shared/bin PATH: /opt/intel/vtune/analyzer/bin PATH: /opt/intel/vtune/rdc/analyzer/bin PATH: /opt/intel/vtune/rdc/shared/bin PATH: /opt/sag/exx/v721/bin ## --- ## ## Core tests. ## ## --- ## configure:2803: checking build system type configure:2817: result: i686-pc-linux-gnu configure:2837: checking host system type configure:2850: result: i686-pc-linux-gnu configure:2870: checking target system type configure:2883: result: i686-pc-linux-gnu configure:2927: checking for a BSD-compatible install configure:2995: result: /usr/bin/install -c configure:3006: checking whether build environment is sane configure:3056: result: yes configure:3197: checking for a thread-safe mkdir -p configure:3236: result: /bin/mkdir -p configure:3249: checking for gawk configure:3265: found /bin/gawk configure:3276: result: gawk configure:3287: checking whether make sets $(MAKE) configure:3309: result: yes configure:3384: checking how to create a ustar tar archive configure:3397: tar --version tar (GNU tar) 1.15.1 configure:3400: $? = 0 configure:3440: tardir=conftest.dir && eval tar --format=ustar -chf - "$tardir" >conftest.tar configure:3443: $? = 0 configure:3447: tar -xf - &5 gcc (GCC) 4.3.0 20071030 (experimental) [trunk revision 129762] Copyright (C) 2007 Free Software Foundation, Inc. This is free software; see the source for copying conditions. There is NO warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. configure:3868: $? = 0 configure:3857: gcc -v >&5 Using built-in specs. Target: i386-pc-linux-gnu Configured with: /home/fx/gfortran_nightbuild/trunk/configure --prefix=/home/fx/gfortran_nightbuild/irun-20071030 --enable-languages=c,fortran --build=i386-pc-linux-gnu --enable-checking=release --with-gmp=/home/fx/gfortran_nightbuild/software Thread model: posix gcc version 4.3.0 20071030 (experimental) [trunk revision 129762] (GCC) configure:3868: $? = 0 configure:3857: gcc -V >&5 gcc: '-V' option must have argument configure:3868: $? = 1 configure:3857: gcc -qversion >&5 gcc: unrecognized option '-qversion' gcc: no input files configure:3868: $? = 1 configure:3888: checking whether the C compiler works configure:3910: gccconftest.c >&5 configure:3914: $? = 0 configure:3963: result: yes configure:3966: checking for C compiler default output file name configure:3968: result: a.out configure:3974: checking for suffix of executables configure:3981: gcc -o conftestconftest.c >&5 configure:3985:
Re: [hwloc-users] Getting a graphics view for a non graphic system...
Le dimanche 06 juin 2010 à 19:21 +0200, Samuel Thibault a écrit : > Olivier Cessenat, le Sun 06 Jun 2010 19:07:40 +0200, a écrit : > > I installed hwloc on a system where there is no such libpng or freetype > > libraries. I thus get a text as an output to hwloc-ls. > > Is there a way to make that output read by an hwloc program on a system > > where there are the graphic packages ? > > You can still use the .fig output. You can also use the semigraphical > .txt output. > > > Sorry if the question is silly, but I failed to get that info. > > Doesn't lstopo --help say that .txt and .fig are available? Sure. It does not explain how. Should I perform on comp1 the no-graphics machine and comp2 the one with graphics : $ comp1: hwloc-ls > toto.txt $ comp2: hwloc-ls toto.txt Could you give me the command lines full instructions ? Thanks, Olivier. > > Samuel > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Getting a graphics view for a non graphic system...
Le dimanche 06 juin 2010 à 20:37 +0200, Brice Goglin a écrit : > Le 06/06/2010 19:21, Samuel Thibault a écrit : > > Olivier Cessenat, le Sun 06 Jun 2010 19:07:40 +0200, a écrit : > > > >> I installed hwloc on a system where there is no such libpng or freetype > >> libraries. I thus get a text as an output to hwloc-ls. > >> Is there a way to make that output read by an hwloc program on a system > >> where there are the graphic packages ? > >> > > You can still use the .fig output. You can also use the semigraphical > > .txt output. > > > > If you have XML libs, you can export as XML and later reload the XML and > display it graphically on another machine I do not know how to export to XML. I see that --xml can be used to read an XML file, but what should I do to write a file ? Olivier. > > Brice > > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Is OSX a supported platform ?
Hi, svn checkout from where ? Olivier. Le dimanche 06 juin 2010 à 20:06 +0200, Samuel Thibault a écrit : > Samuel Thibault, le Sun 06 Jun 2010 18:37:00 +0200, a écrit : > > Olivier Cessenat, le Sun 06 Jun 2010 18:19:40 +0200, a écrit : > > > Then, here are the outputs of the commands as you asked. > > > > > hw.l1icachesize: 32768 > > > hw.l1dcachesize: 32768 > > > hw.l2cachesize: 4194304 > > > > Mmm, so it seems they changed the sysctl output :/ . Which version of > > OSX is this? > > Could you try the current svn version? > > Samuel > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Getting the cache hierarchy
/usr/bin/makeindex checking for fig2dev... /usr/X11R6/bin/fig2dev checking if can build doxygen docs... no checking for w3m... no checking for lynx... /usr/bin/lynx checking if can build top-level README... yes checking if will build doxygen docs... no checking if will install doxygen docs... yes checking whether to enable "picky" compiler mode... no (default) ### ### Configuring hwloc command line utilities ### checking for CAIRO... no checking for XML... yes checking for xmlNewDoc... yes checking for final XML support... yes checking for xmllint... xmllint ### ### Configuring hwloc tests ### checking for a sed that does not truncate output... /bin/sed checking for fgrep... /bin/grep -F checking for ld used by gcc... /usr/bin/ld checking if the linker (/usr/bin/ld) is GNU ld... yes checking for BSD- or MS-compatible name lister (nm)... /usr/bin/nm -B checking the name lister (/usr/bin/nm -B) interface... BSD nm checking whether ln -s works... yes checking the maximum length of command line arguments... 98304 checking whether the shell understands some XSI constructs... yes checking whether the shell understands "+="... no checking for /usr/bin/ld option to reload object files... -r checking for objdump... objdump checking how to recognize dependent libraries... pass_all checking for ar... ar checking for strip... strip checking for ranlib... ranlib checking command to parse /usr/bin/nm -B output from gcc object... ok checking for dlfcn.h... no checking for objdir... .libs checking if gcc supports -fno-rtti -fno-exceptions... no checking for gcc option to produce PIC... -fPIC -DPIC checking if gcc PIC flag -fPIC -DPIC works... yes checking if gcc static flag -static works... no checking if gcc supports -c -o file.o... yes checking if gcc supports -c -o file.o... (cached) yes checking whether the gcc linker (/usr/bin/ld) supports shared libraries... yes checking whether -lc should be explicitly linked in... no checking dynamic linker characteristics... GNU/Linux ld.so checking how to hardcode library paths into programs... immediate checking whether stripping libraries is possible... yes checking if libtool supports shared libraries... yes checking whether to build shared libraries... yes checking whether to build static libraries... no configure: creating ./config.status config.status: creating Makefile config.status: creating include/Makefile config.status: creating src/Makefile config.status: creating doc/Makefile config.status: creating doc/doxygen-config.cfg config.status: creating utils/Makefile config.status: creating hwloc.pc config.status: creating tests/Makefile config.status: creating tests/linux/Makefile config.status: creating tests/xml/Makefile config.status: creating tests/ports/Makefile config.status: creating tests/linux/gather-topology.sh config.status: creating tests/linux/test-topology.sh config.status: creating tests/xml/test-topology.sh config.status: creating utils/test-hwloc-distrib.sh config.status: creating include/private/config.h config.status: creating include/hwloc/config.h config.status: linking src/topology.c to tests/ports/topology.c config.status: linking src/traversal.c to tests/ports/traversal.c config.status: linking src/topology-synthetic.c to tests/ports/topology-synthetic.c config.status: linking src/topology-solaris.c to tests/ports/topology-solaris.c config.status: linking src/topology-aix.c to tests/ports/topology-aix.c config.status: linking src/topology-osf.c to tests/ports/topology-osf.c config.status: linking src/topology-windows.c to tests/ports/topology-windows.c config.status: linking src/topology-darwin.c to tests/ports/topology-darwin.c config.status: linking src/topology-freebsd.c to tests/ports/topology-freebsd.c config.status: linking src/topology-hpux.c to tests/ports/topology-hpux.c config.status: executing depfiles commands config.status: executing chmoding-scripts commands config.status: executing libtool commands Making all in src make[1]: Entering directory `/tmp/hwloc-1.0.1/src' CC topology.lo In file included from topology.c:17: /opt/gfortran/irun/bin/../lib/gcc/i386-pc-linux-gnu/4.3.0/include-fixed/sys/stat.h:345: error: expecte d ',' or ';' before '__wur' In file included from /tmp/hwloc-1.0.1/include/hwloc.h:17, from topology.c:21: /tmp/hwloc-1.0.1/include/hwloc/config.h:115:2: error: #error "unknown size for unsigned long." /tmp/hwloc-1.0.1/include/hwloc/config.h:119:2: error: #error "unknown size for unsigned int." topology.c: In function 'hwloc_get_sysctl': topology.c:66: warning: implicit declaration of function 'sysctl' make[1]: *** [topology.lo] Erreur 1 make[1]: Leaving directory `/tmp/hwloc-1.0.1/src' make: *** [all-recursive] Erreur 1 >> Cheers, Olivier. Le dimanche 06 juin 2010 à 20:13 +0200, Samuel Thibault a écrit : > Olivier Cessenat, le Sun 06 Jun 2010 19:02:21 +0200, a écrit : > > Le di
[hwloc-users] Getting a graphics view for a non graphic system...
Hello, I installed hwloc on a system where there is no such libpng or freetype libraries. I thus get a text as an output to hwloc-ls. Is there a way to make that output read by an hwloc program on a system where there are the graphic packages ? Sorry if the question is silly, but I failed to get that info. Cheers, Olivier Cessenat.
Re: [hwloc-users] Getting the cache hierarchy
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/../lib/gcc/i386-pc-linux-gnu/4.3.0/include-fixed/sys/stat.h:345:
> > error: expected ',' or ';' before '__wur'
>
> Wow, how odd. Could you send us the file? I really wonder what they
> put there that errors out like this.
==>
Yes, joined. I do not know why this header is used instead of the
standard one... I do not see the connection with gfortran !
> > In file included from /tmp/hwloc-1.0.1/include/hwloc.h:17,
> > from topology.c:21:
> > /tmp/hwloc-1.0.1/include/hwloc/config.h:115:2: error: #error "unknown
> > size for unsigned long."
> > /tmp/hwloc-1.0.1/include/hwloc/config.h:119:2: error: #error "unknown
> > size for unsigned int."
>
> Could you tell us how much HWLOC_SIZEOF_UNSIGNED_LONG is defined to?
> This looks like autoconf wasn't able to properly determine it actually.
==>
What should I do exactly ? I do not see HWLOC_SIZEOF_UNSIGNED_LONG from
configure ouput.
Here is what find gives:
$ find . -name \*.h -exec grep HWLOC_SIZEOF_UNSIGNED_LONG {} /dev/null
\;
./include/hwloc/config.h:#define HWLOC_SIZEOF_UNSIGNED_LONG 4
./include/hwloc/config.h:#define HWLOC_BITS_PER_LONG
(HWLOC_SIZEOF_UNSIGNED_LONG * 8)
./include/private/config.h:#define HWLOC_SIZEOF_UNSIGNED_LONG 4
Oh, by the way, there are some messages provided by configure:
<<
checking locale.h presence... yes
configure: WARNING: locale.h: present but cannot be compiled
configure: WARNING: locale.h: check for missing prerequisite
headers?
configure: WARNING: locale.h: see the Autoconf documentation
configure: WARNING: locale.h: section "Present But Cannot Be
Compiled"
configure: WARNING: locale.h: proceeding with the compiler's result
configure: WARNING: ##
-- ##
configure: WARNING: ## Report this to
http://www.open-mpi.org/community/help/ ##
configure: WARNING: ##
-- ##
checking for locale.h... no
checking langinfo.h usability... no
checking langinfo.h presence... yes
configure: WARNING: langinfo.h: present but cannot be compiled
configure: WARNING: langinfo.h: check for missing prerequisite
headers?
configure: WARNING: langinfo.h: see the Autoconf documentation
configure: WARNING: langinfo.h: section "Present But Cannot Be
Compiled"
configure: WARNING: langinfo.h: proceeding with the compiler's result
configure: WARNING: ##
-- ##
configure: WARNING: ## Report this to
http://www.open-mpi.org/community/help/ ##
configure: WARNING: ##
-- ##
checking for langinfo.h... no
checking curses.h usability... no
checking curses.h presence... yes
configure: WARNING: curses.h: present but cannot be compiled
configure: WARNING: curses.h: check for missing prerequisite
headers?
configure: WARNING: curses.h: see the Autoconf documentation
configure: WARNING: curses.h: section "Present But Cannot Be
Compiled"
configure: WARNING: curses.h: proceeding with the compiler's result
configure: WARNING: ##
-- ##
configure: WARNING: ## Report this to
http://www.open-mpi.org/community/help/ ##
configure: WARNING: ##
-- ##
checking for curses.h... no
... blablabla ...
checking sys/param.h presence... yes
configure: WARNING: sys/param.h: present but cannot be compiled
configure: WARNING: sys/param.h: check for missing prerequisite
headers?
configure: WARNING: sys/param.h: see the Autoconf documentation
configure: WARNING: sys/param.h: section "Present But Cannot Be
Compiled"
configure: WARNING: sys/param.h: proceeding with the compiler's result
configure: WARNING: ##
-- ##
configure: WARNING: ## Report this to
http://www.open-mpi.org/community/help/ ##
configure: WARNING: ##
-- ##
checking for sys/param.h... no
>>
>
> Samuel
> ___
> hwloc-users mailing list
> hwloc-us...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
/* DO NOT EDIT THIS FILE.
It has been auto-edited by fixincludes from:
"/usr/include/sys/stat.h"
This had to be done to correct non-standard usages in the
original, manufacturer supplied header file. */
/* Copyright (C) 1991,1992,1995-2004,2005,2006 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Re: [hwloc-users] Is OSX a supported platform ?
OSX 10.4.11 Darwin mac.magic 8.11.1 Darwin Kernel Version 8.11.1: Wed Oct 10 18:23:28 PDT 2007; root:xnu-792.25.20~1/RELEASE_I386 i386 i386 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. Olivier. Le dimanche 06 juin 2010 à 18:37 +0200, Samuel Thibault a écrit : > Olivier Cessenat, le Sun 06 Jun 2010 18:19:40 +0200, a écrit : > > Then, here are the outputs of the commands as you asked. > > > hw.l1icachesize: 32768 > > hw.l1dcachesize: 32768 > > hw.l2cachesize: 4194304 > > Mmm, so it seems they changed the sysctl output :/ . Which version of > OSX is this? > > > Occasion for yet another question, when --enable-debug is set, is there > > some way to remove the messages to stderr ? > > It wasn't considered yet, but why not. > > Samuel > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
Re: [hwloc-users] Is OSX a supported platform ?
0x0003 complete 0x0003 online 0x0003 allowed 0x0003 L1Cache#0(0KB) cpuset 0x0003 complete 0x0003 online 0x0003 allowed 0x0003 PU#0 cpuset 0x0001 complete 0x0001 online 0x0001 allowed 0x0001 PU#1 cpuset 0x0002 complete 0x0002 online 0x0002 allowed 0x0002 Ok, finished tweaking, now connect Machine#0 cpuset 0x0003 complete 0x0003 online 0x0003 allowed 0x0003 arity 1 L1Cache#0(0KB) cpuset 0x0003 complete 0x0003 online 0x0003 allowed 0x0003 arity 2 PU#0 cpuset 0x0001 complete 0x0001 online 0x0001 allowed 0x0001 PU#1 cpuset 0x0002 complete 0x0002 online 0x0002 allowed 0x0002 --- Cache level depth 1 has number 1 --- PU level has number 2 Propagate total memory up Machine + L1 #0 (0KB) PU #0 (phys=0) PU #1 (phys=1) Le dimanche 06 juin 2010 à 17:44 +0200, Samuel Thibault a écrit : > 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 OS says. > > > Is this an already known behaviour ? > > Could you run > > sysctl hw > > to check what the OS says? Also, please build with --enable-debug to > enable the debugging output of hwloc. > > Samuel > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
[hwloc-users] Getting the cache hierarchy
Hello, I get in troubles on my i686 system when compiling hwloc: << Making all in src make[1]: Entering directory `/tmp/hwloc-1.0.1/src' CC topology.lo In file included from topology.c:17: /opt/gfortran/irun/bin/../lib/gcc/i386-pc-linux-gnu/4.3.0/include-fixed/sys/stat.h:345: error: expected ',' or ';' before '__wur' In file included from /tmp/hwloc-1.0.1/include/hwloc.h:17, from topology.c:21: /tmp/hwloc-1.0.1/include/hwloc/config.h:115:2: error: #error "unknown size for unsigned long." /tmp/hwloc-1.0.1/include/hwloc/config.h:119:2: error: #error "unknown size for unsigned int." topology.c: In function 'hwloc_get_sysctl': topology.c:66: warning: implicit declaration of function 'sysctl' make[1]: *** [topology.lo] Erreur 1 make[1]: Leaving directory `/tmp/hwloc-1.0.1/src' make: *** [all-recursive] Erreur 1 >> I removed "/opt/gfortran/irun/bin" from my PATH environment, and compilation passed. I now get infos such as << hwloc-info depth 0:1 Machine (type #1) depth 1: 1 PU (type #6) >> and my cache sizes are not detected. My system is Mandriva 2006.0, uname -a provides: Linux papitou 2.6.12-12mdk #1 Fri Sep 9 18:15:22 CEST 2005 i686 Pentium III (Katmai) unknown GNU/Linux and gcc -dumpversion is 4.3.0, 4.0.1 and 4.2.2 - I've got a few systems. What do you think ? Cheers, Olivier Cessenat.
Re: [hwloc-users] Is OSX a supported platform ?
Hello Samuel, 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. Is this an already known behaviour ? Thanks, Cheers, Olivier Cessenat. Le dimanche 06 juin 2010 à 16:01 +0200, Samuel Thibault a écrit : > 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 > ___ > hwloc-users mailing list > hwloc-us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/hwloc-users
[hwloc-users] Is OSX a supported platform ?
Hello hwloc users, I'm brand new to hwloc and I'm very happy to get a tool to get an API for getting cache hierarchies. I try the API on MacOSX, compiling hwloc-hello.c as provided at http://www.open-mpi.org/projects/hwloc/doc/hwloc-v1.0.1-a4.pdf page 20, and there is: << *** First Example *** *** Objects at level 0 Index 0: Machine#0 *** Objects at level 1 Index 0: L1#0(0KB) *** Objects at level 2 Index 0: PU#0 Index 1: PU#1 *** Second Example *** *** Printing overall tree Machine#0 L1#0(0KB) PU#0 PU#1 *** Third Example *** *** The number of sockets is unknown *** Fourth Example *** *** Logical processor 0 has 1 caches totaling 0KB *** Fifth Example *** Couldn't bind to cpuset 0x0002 >> Is hwloc supported on OSX 10.4 platform ? I took a look at the archives, but did not find the answer. Thanks for help. Sincerely, Olivier Cessenat.
