Update hwloc to v1.11.12

[charm.git] / contrib / hwloc / NEWS

Copyright © 2009 CNRS
Copyright © 2009-2018 Inria.  All rights reserved.
Copyright © 2009-2013 Université Bordeaux
Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.

$COPYRIGHT$

Additional copyrights may follow

$HEADER$

===========================================================================

This file contains the main features as well as overviews of specific
bug fixes (and other actions) for each version of hwloc since version
0.9 (as initially released as "libtopology", then re-branded to "hwloc"
in v0.9.1).


Version 1.11.12 (also included in 2.0.3)
---------------
* Fix a corner case of hwloc_topology_restrict() where children would
  become out-of-order.
* Fix the return length of export_xmlbuffer() functions to always
  include the ending \0.


Version 1.11.11 (also included in 2.0.2)
---------------
* Add support for Hygon Dhyana processors in the x86 backend,
  thanks to Pu Wen for the patch.
* Fix symbol renaming to also rename internal components,
  thanks to Evan Ramos for the patch.
* Fix build on HP-UX, thanks to Richard Lloyd for reporting the issues.
* Detect PCI link speed without being root on Linux >= 4.13.


Version 1.11.10 (also included in 2.0.1)
---------------
* Fix detection of cores and hyperthreads on Mac OS X.
* Serialize pciaccess discovery to fix concurrent topology loads in
  multiple threads.
* Fix first touch area memory binding on Linux when thread memory
  binding is different.
* Some minor fixes to memory binding.
* Fix hwloc-dump-hwdata to only process SMBIOS information that correspond
  to the KNL and KNM configuration.
* Add a heuristic for guessing KNL/KNM memory and cluster modes when
  hwloc-dump-hwdata could not run as root earlier.
* Fix discovery of NVMe OS devices on Linux >= 4.0.
* Add get_area_memlocation() on Windows.
* Add CPUVendor, Model, ... attributes on Mac OS X.


Version 1.11.9
--------------
* Add support for Zhaoxin ZX-C and ZX-D processors in the x86 backend,
  thanks to Jeff Zhao for the patch.
* Fix AMD Epyc 24-core L3 cache locality in the x86 backend.
* Don't crash in the x86 backend when the CPUID vendor string is unknown.
* Fix the missing pu discovery support bit on some OS.
* Fix the management of the lstopoStyle info attribute for custom colors.
* Add verbose warnings when failing to load hwloc v2.0+ XMLs.


Version 1.11.8
--------------
* Multiple Solaris improvements, thanks to Maureen Chew for the help:
  + Detect caches on Sparc.
  + Properly detect allowed/disallowed PUs and NUMA nodes with processor sets.
  + Add hwloc_get_last_cpu_location() support for the current thread.
* Add support for CUDA compute capability 7.0 and fix support for 6.[12].
* Tools improvements
  + Fix search for objects by physical index in command-line tools.
  + Add missing "cpubind:get_thisthread_last_cpu_location" in the output
    of hwloc-info --support.
  + Add --pid and --name to specify target processes in hwloc-ps.
  + Display thread names in lstopo and hwloc-ps on Linux.
* Doc improvements
  + Add a FAQ entry about building on Windows.
  + Install missing sub-manpage for hwloc_obj_add_info() and
    hwloc_obj_get_info_by_name().


Version 1.11.7
--------------
* Fix hwloc-bind --membind for CPU-less NUMA nodes (again).
  Thanks to Gilles Gouaillardet for reporting the issue.
* Fix a memory leak on IBM S/390 platforms running Linux.
* Fix a memory leak when forcing the x86 backend first on amd64/topoext
  platforms running Linux.
* Command-line tools now support "hbm" instead "numanode" for filtering
  only high-bandwidth memory nodes when selecting locations.
  + hwloc-bind also support --hbm and --no-hbm for filtering only or
    no HBM nodes.
  Thanks to Nicolas Denoyelle for the suggestion.
* Add --children and --descendants to hwloc-info for listing object
  children or object descendants of a specific type.
* Add --no-index, --index, --no-attrs, --attrs to disable/enable display
  of index numbers or attributes in the graphical lstopo output.
* Try to gather hwloc-dump-hwdata output from all possible locations
  in hwloc-gather-topology.
* Updates to the documentation of locations in hwloc(7) and
  command-line tools manpages.


Version 1.11.6
--------------
* Make the Linux discovery about twice faster, especially on the CPU side,
  by trying to avoid sysfs file accesses as much as possible.
* Add support for AMD Family 17h processors (Zen) SMT cores in the Linux
  and x86 backends.
* Add the HWLOC_TOPOLOGY_FLAG_THISSYSTEM_ALLOWED_RESOURCES flag (and the
  HWLOC_THISSYSTEM_ALLOWED_RESOURCES environment variable) for reading the
  set of allowed resources from the local operating system even if the
  topology was loaded from XML or synthetic.
* Fix hwloc_bitmap_set/clr_range() for infinite ranges that do not
  overlap currently defined ranges in the bitmap.
* Don't reset the lstopo zoom scale when moving the X11 window.
* lstopo now has --flags for manually setting topology flags.
* hwloc_get_depth_type() returns HWLOC_TYPE_DEPTH_UNKNOWN for Misc objects.


Version 1.11.5
--------------
* Add support for Knights Mill Xeon Phi, thanks to Piotr Luc for the patch.
* Reenable distance gathering on Solaris, disabled by mistake since v1.0.
  Thanks to TU Wien for the help.
* Fix hwloc_get_*obj*_inside_cpuset() functions to ignore objects with
  empty CPU sets, for instance, CPU-less NUMA nodes such as KNL MCDRAM.
  Thanks to Nicolas Denoyelle for the report.
* Fix XML import of multiple distance matrices.
* Add a FAQ entry about "hwloc is only a structural model, it ignores
  performance models, memory bandwidth, etc.?"


Version 1.11.4
--------------
* Add MemoryMode and ClusterMode attributes in the Machine object on KNL.
  Add doc/examples/get-knl-modes.c for an example of retrieving them.
  Thanks to Grzegorz Andrejczuk.
* Fix Linux build with -m32 with respect to libudev.
  Thanks to Paul Hargrove for reporting the issue.
* Fix build with Visual Studio 2015, thanks to Eloi Gaudry for reporting
  the issue and providing the patch.
* Don't forget to display OS device children in the graphical lstopo.
* Fix a memory leak on Solaris, thanks to Bryon Gloden for the patch.
* Properly handle realloc() failures, thanks to Bryon Gloden for reporting
  the issue.
* Fix lstopo crash in ascii/fig/windows outputs when some objects have a
  lstopoStyle info attribute.


Version 1.11.3
--------------
* Bug fixes
  + Fix a memory leak on Linux S/390 hosts with books.
  + Fix /proc/mounts parsing on Linux by using mntent.h.
    Thanks to Nathan Hjelm for reporting the issue.
  + Fix a x86 infinite loop on VMware due to the x2APIC feature being
    advertised without actually being fully supported.
    Thanks to Jianjun Wen for reporting the problem and testing the patch.
  + Fix the return value of hwloc_alloc() on mmap() failure.
    Thanks to Hugo Brunie for reporting the issue.
  + Fix the return value of command-line tools in some error cases.
  + Do not break individual thread bindings during x86 backend discovery in a
    multithreaded process. Thanks to Farouk Mansouri for the report.
  + Fix hwloc-bind --membind for CPU-less NUMA nodes.
  + Fix some corner cases in the XML export/import of application userdata.
* API Improvements
  + Add HWLOC_MEMBIND_BYNODESET flag so that membind() functions accept
    either cpusets or nodesets.
  + Add hwloc_get_area_memlocation() to check where pages are actually
    allocated. Only implemented on Linux for now.
    - There's no _nodeset() variant, but the new flag HWLOC_MEMBIND_BYNODESET
      is supported.
  + Make hwloc_obj_type_sscanf() parse back everything that may be outputted
    by hwloc_obj_type_snprintf().
* Detection Improvements
  + Allow the x86 backend to add missing cache levels, so that it completes
    what the Solaris backend lacks.
    Thanks to Ryan Zezeski for reporting the issue.
  + Do not filter-out FibreChannel PCI adapters by default anymore.
    Thanks to Matt Muggeridge for the report.
  + Add support for CUDA compute capability 6.x.
* Tools
  + Add --support to hwloc-info to list supported features, just like with
    hwloc_topology_get_support().
    - Also add --objects and --topology to explicitly switch between the
      default modes.
  + Add --tid to let hwloc-bind operate on individual threads on Linux.
  + Add --nodeset to let hwloc-bind report memory binding as NUMA node sets.
  + hwloc-annotate and lstopo don't drop application userdata from XMLs anymore.
    - Add --cu to hwloc-annotate to drop these application userdata.
  + Make the hwloc-dump-hwdata dump directory configurable through configure
    options such as --runstatedir or --localstatedir.
* Misc Improvements
  + Add systemd service template contrib/systemd/hwloc-dump-hwdata.service
    for launching hwloc-dump-hwdata at boot on Linux.
    Thanks to Grzegorz Andrejczuk.
  + Add HWLOC_PLUGINS_BLACKLIST environment variable to prevent some plugins
    from being loaded. Thanks to Alexandre Denis for the suggestion.
  + Small improvements for various Windows build systems,
    thanks to Jonathan L Peyton and Marco Atzeri.


Version 1.11.2
--------------
* Improve support for Intel Knights Landing Xeon Phi on Linux:
  + Group local NUMA nodes of normal memory (DDR) and high-bandwidth memory
    (MCDRAM) together through "Cluster" groups so that the local MCDRAM is
    easy to find.
    - See "How do I find the local MCDRAM NUMA node on Intel Knights
      Landing Xeon Phi?" in the documentation.
    - For uniformity across all KNL configurations, always have a NUMA node
      object even if the host is UMA.
  + Fix the detection of the memory-side cache:
    - Add the hwloc-dump-hwdata superuser utility to dump SMBIOS information
      into /var/run/hwloc/ as root during boot, and load this dumped
      information from the hwloc library at runtime.
    - See "Why do I need hwloc-dump-hwdata for caches on Intel Knights
      Landing Xeon Phi?" in the documentation.
  Thanks to Grzegorz Andrejczuk for the patches and for the help.
* The x86 and linux backends may now be combined for discovering CPUs
  through x86 CPUID and memory from the Linux kernel.
  This is useful for working around buggy CPU information reported by Linux
  (for instance the AMD Bulldozer/Piledriver bug below).
  Combination is enabled by passing HWLOC_COMPONENTS=x86 in the environment.
* Fix L3 cache sharing on AMD Opteron 63xx (Piledriver) and 62xx (Bulldozer)
  in the x86 backend. Thanks to many users who helped.
* Fix the overzealous L3 cache sharing fix added to the x86 backend in 1.11.1
  for AMD Opteron 61xx (Magny-Cours) processors.
* The x86 backend may now add the info attribute Inclusive=0 or 1 to caches
  it discovers, or to caches discovered by other backends earlier.
  Thanks to Guillaume Beauchamp for the patch.
* Fix the management on alloc_membind() allocation failures on AIX, HP-UX
  and OSF/Tru64.
* Fix spurious failures to load with ENOMEM on AIX in case of Misc objects
  below PUs.
* lstopo improvements in X11 and Windows graphical mode:
  + Add + - f 1 shortcuts to manually zoom-in, zoom-out, reset the scale,
    or fit the entire window.
  + Display all keyboard shortcuts in the console.
* Debug messages may be disabled at runtime by passing HWLOC_DEBUG_VERBOSE=0
  in the environment when --enable-debug was passed to configure.
* Add a FAQ entry "What are these Group objects in my topology?".


Version 1.11.1
--------------
* Detection fixes
  + Hardwire the topology of Fujitsu K-computer, FX10, FX100 servers to
    workaround buggy Linux kernels.
    Thanks to Takahiro Kawashima and Gilles Gouaillardet.
  + Fix L3 cache information on AMD Opteron 61xx Magny-Cours processors
    in the x86 backend. Thanks to Guillaume Beauchamp for the patch.
  + Detect block devices directly attached to PCI without a controller,
    for instance NVMe disks. Thanks to Barry M. Tannenbaum.
  + Add the PCISlot attribute to all PCI functions instead of only the
    first one.
* Miscellaneous internal fixes
  + Ignore PCI bridges that could fail assertions by reporting buggy
    secondary-subordinate bus numbers
    Thanks to George Bosilca for reporting the issue.
  + Fix an overzealous assertion when inserting an intermediate Group object
    while Groups are totally ignored.
  + Fix a memory leak on Linux on AMD processors with dual-core compute units.
    Thanks to Bob Benner.
  + Fix a memory leak on failure to load a xml diff file.
  + Fix some segfaults when inputting an invalid synthetic description.
  + Fix a segfault when plugins fail to find core symbols.
    Thanks to Guy Streeter.
* Many fixes and improvements in the Windows backend:
  + Fix the discovery of more than 32 processors and multiple processor
    groups. Thanks to Barry M. Tannenbaum for the help.
  + Add thread binding set support in case of multiple process groups.
  + Add thread binding get support.
  + Add get_last_cpu_location() support for the current thread.
  + Disable the unsupported process binding in case of multiple processor
    groups.
  + Fix/update the Visual Studio support under contrib/windows.
    Thanks to Eloi Gaudry for the help.
* Tools fixes
  + Fix a segfault when displaying logical indexes in the graphical lstopo.
    Thanks to Guillaume Mercier for reporting the issue.
  + Fix lstopo linking with X11 libraries, for instance on Mac OS X.
    Thanks to Scott Atchley and Pierre Ramet for reporting the issue.
  + hwloc-annotate, hwloc-diff and hwloc-patch do not drop unavailable
    resources from the output anymore and those may be annotated as well.
  + Command-line tools may now import XML from the standard input with -i -.xml
  + Add missing documentation for the hwloc-info --no-icaches option.


Version 1.11.0
--------------
* API
  + Socket objects are renamed into Package to align with the terminology
    used by processor vendors. The old HWLOC_OBJ_SOCKET type and "Socket"
    name are still supported for backward compatibility.
  + HWLOC_OBJ_NODE is replaced with HWLOC_OBJ_NUMANODE for clarification.
    HWLOC_OBJ_NODE is still supported for backward compatibility.
    "Node" and "NUMANode" strings are supported as in earlier releases.
* Detection improvements
  + Add support for Intel Knights Landing Xeon Phi.
    Thanks to Grzegorz Andrejczuk and Lukasz Anaczkowski.
  + Add Vendor, Model, Revision, SerialNumber, Type and LinuxDeviceID
    info attributes to Block OS devices on Linux. Thanks to Vineet Pedaballe
    for the help.
    - Add --disable-libudev to avoid dependency on the libudev library.
  + Add "MemoryModule" Misc objects with information about DIMMs, on Linux
    when privileged and when I/O is enabled.
    Thanks to Vineet Pedaballe for the help.
  + Add a PCISlot attribute to PCI devices on Linux when supported to
    identify the physical PCI slot where the board is plugged.
  + Add CPUStepping info attribute on x86 processors,
    thanks to Thomas Röhl for the suggestion.
  + Ignore the device-tree on non-Power architectures to avoid buggy
    detection on ARM. Thanks to Orion Poplawski for reporting the issue.
  + Work-around buggy Xeon E5v3 BIOS reporting invalid PCI-NUMA affinity
    for the PCI links on the second processor.
  + Add support for CUDA compute capability 5.x, thanks Benjamin Worpitz.
  + Many fixes to the x86 backend
    - Add L1i and fix L2/L3 type on old AMD processors without topoext support.
    - Fix Intel CPU family and model numbers when basic family isn't 6 or 15.
    - Fix package IDs on recent AMD processors.
    - Fix misc issues due to incomplete APIC IDs on x2APIC processors.
    - Avoid buggy discovery on old SGI Altix UVs with non-unique APIC IDs.
  + Gather total machine memory on NetBSD.
* Tools
  + lstopo
    - Collapse identical PCI devices unless --no-collapse is given.
      This avoids gigantic outputs when a PCI device contains dozens of
      identical virtual functions.
    - The ASCII art output is now called "ascii", for instance in
      "lstopo -.ascii".
      The former "txt" extension is retained for backward compatibility.
    - Automatically scales graphical box width to the inner text in Cairo,
      ASCII and Windows outputs.
    - Add --rect to lstopo to force rectangular layout even for NUMA nodes.
    - Add --restrict-flags to configure the behavior of --restrict.
    - Objects may have a "Type" info attribute to specify a better type name
      and display it in lstopo.
    - Really export all verbose information to the given output file.
  + hwloc-annotate
    - May now operate on all types of objects, including I/O.
    - May now insert Misc objects in the topology.
    - Do not drop instruction caches and I/O devices from the output anymore.
  + Fix lstopo path in hwloc-gather-topology after install.
* Misc
  + Fix hwloc/cudart.h for machines with multiple PCI domains,
    thanks to Imre Kerr for reporting the problem.
  + Fix PCI Bridge-specific depth attribute.
  + Fix hwloc_bitmap_intersect() for two infinite bitmaps.
  + Fix some corner cases in the building of levels on large NUMA machines
    with non-uniform NUMA groups and I/Os.
  + Improve the performance of object insertion by cpuset for large
    topologies.
  + Prefix verbose XML import errors with the source name.
  + Improve pkg-config checks and error messages.
  + Fix excluding after a component with an argument in the HWLOC_COMPONENTS
    environment variable.
* Documentation
  + Fix the recommended way in documentation and examples to allocate memory
    on some node, it should use HWLOC_MEMBIND_BIND.
    Thanks to Nicolas Bouzat for reporting the issue.
  + Add a "Miscellaneous objects" section in the documentation.
  + Add a FAQ entry "What happens to my topology if I disable symmetric
    multithreading, hyper-threading, etc. ?" to the documentation.


Version 1.10.1
--------------
* Actually remove disallowed NUMA nodes from nodesets when the whole-system
  flag isn't enabled.
* Fix the gathering of PCI domains. Thanks to James Custer for reporting
  the issue and providing a patch.
* Fix the merging of identical parent and child in presence of Misc objects.
  Thanks to Dave Love for reporting the issue.
* Fix some misordering of children when merging with ignore_keep_structure()
  in partially allowed topologies.
* Fix an overzealous assertion in the debug code when running on a single-PU
  host with I/O. Thanks to Thomas Van Doren for reporting the issue.
* Don't forget to setup NUMA node object nodesets in x86 backend (for BSDs)
  and OSF/Tru64 backend.
* Fix cpuid-x86 build error with gcc -O3 on x86-32. Thanks to Thomas Van Doren
  for reporting the issue.
* Fix support for future very large caches in the x86 backend.
* Fix vendor/device names for SR-IOV PCI devices on Linux.
* Fix an unlikely crash in case of buggy hierarchical distance matrix.
* Fix PU os_index on some AIX releases. Thanks to Hendryk Bockelmann and
  Erik Schnetter for helping debugging.
* Fix hwloc_bitmap_isincluded() in case of infinite sets.
* Change hwloc-ls.desktop into a lstopo.desktop and only install it if
  lstopo is built with Cairo/X11 support. It cannot work with a non-graphical
  lstopo or hwloc-ls.
* Add support for the renaming of Socket into Package in future releases.
* Add support for the replacement of HWLOC_OBJ_NODE with HWLOC_OBJ_NUMANODE
  in future releases.
* Clarify the documentation of distance matrices in hwloc.h and in the manpage
  of the hwloc-distances. Thanks to Dave Love for the suggestion.
* Improve some error messages by displaying more information about the
  hwloc library in use.
* Document how to deal with the ABI break when upgrading to the upcoming 2.0
  See "How do I handle ABI breaks and API upgrades ?" in the FAQ.


Version 1.10.0
--------------
* API
  + Add hwloc_topology_export_synthetic() to export a topology to a
    synthetic string without using lstopo. See the Synthetic topologies
    section in the documentation.
  + Add hwloc_topology_set/get_userdata() to let the application save
    a private pointer in the topology whenever it needs a way to find
    its own object corresponding to a topology.
  + Add hwloc_get_numanode_obj_by_os_index() and document that this function
    as well as hwloc_get_pu_obj_by_os_index() are good at converting
    nodesets and cpusets into objects.
  + hwloc_distrib() does not ignore any objects anymore when there are
    too many of them. They get merged with others instead.
    Thanks to Tim Creech for reporting the issue.
* Tools
  + hwloc-bind --get <command-line> now executes the command after displaying
    the binding instead of ignoring the command entirely.
    Thanks to John Donners for the suggestion.
  + Clarify that memory sizes shown in lstopo are local by default
    unless specified (total memory added in the root object).
* Synthetic topologies
  + Synthetic topology descriptions may now specify attributes such as
    memory sizes and OS indexes. See the Synthetic topologies section
    in the documentation.
  + lstopo now exports in this fully-detailed format by default.
    The new option --export-synthetic-flags may be used to revert
    back the old format.
* Documentation
  + Add the doc/examples/ subdirectory with several real-life examples,
    including the already existing hwloc-hello.C for basics.
    Thanks to Rob Aulwes for the suggestion.
  + Improve the documentation of CPU and memory binding in the API.
  + Add a FAQ entry about operating system errors, especially on AMD
    platforms with buggy cache information.
  + Add a FAQ entry about loading many topologies in a single program.
* Misc
  + Work around buggy Linux kernels reporting 2 sockets instead
    1 socket with 2 NUMA nodes for each Xeon E5 v3 (Haswell) processor.
  + pciutils/libpci support is now removed since libpciaccess works
    well and there's also a Linux-specific PCI backend. For the record,
    pciutils was GPL and therefore disabled by default since v1.6.2.
  + Add --disable-cpuid configure flag to work around buggy processor
    simulators reporting invalid CPUID information.
    Thanks for Andrew Friedley for reporting the issue.
  + Fix a racy use of libltdl when manipulating multiple topologies in
    different threads.
    Thanks to Andra Hugo for reporting the issue and testing patches.
  + Fix some build failures in private/misc.h.
    Thanks to Pavan Balaji and Ralph Castain for the reports.
  + Fix failures to detect X11/Xutil.h on some Solaris platforms.
    Thanks to Siegmar Gross for reporting the failure.
  + The plugin ABI has changed, this release will not load plugins
    built against previous hwloc releases.


Version 1.9.1
-------------
* Fix a crash when the PCI locality is invalid. Attach to the root object
  instead. Thanks to Nicolas Denoyelle for reporting the issue.
* Fix -f in lstopo manpage. Thanks to Jirka Hladky for reporting the issue.
* Fix hwloc_obj_type_sscanf() and others when strncasecmp() is not properly
  available. Thanks to Nick Papior Andersen for reporting the problem.
* Mark Linux file descriptors as close-on-exec to avoid leaks on exec.
* Fix some minor memory leaks.


Version 1.9.0
-------------
* API
  + Add hwloc_obj_type_sscanf() to extend hwloc_obj_type_of_string() with
    type-specific attributes such as Cache/Group depth and Cache type.
    hwloc_obj_type_of_string() is moved to hwloc/deprecated.h.
  + Add hwloc_linux_get_tid_last_cpu_location() for retrieving the
    last CPU where a Linux thread given by TID ran.
  + Add hwloc_distrib() to extend the old hwloc_distribute[v]() functions.
    hwloc_distribute[v]() is moved to hwloc/deprecated.h.
  + Don't mix total and local memory when displaying verbose object attributes
    with hwloc_obj_attr_snprintf() or in lstopo.
* Backends
  + Add CPUVendor, CPUModelNumber and CPUFamilyNumber info attributes for
    x86, ia64 and Xeon Phi sockets on Linux, to extend the x86-specific
    support added in v1.8.1. Requested by Ralph Castain.
  + Add many CPU- and Platform-related info attributes on ARM and POWER
    platforms, in the Machine and Socket objects.
  + Add CUDA info attributes describing the number of multiprocessors and
    cores and the size of the global, shared and L2 cache memories in CUDA
    OS devices.
  + Add OpenCL info attributes describing the number of compute units and
    the global memory size in OpenCL OS devices.
  + The synthetic backend now accepts extended types such as L2Cache, L1i or
    Group3. lstopo also exports synthetic strings using these extended types.
* Tools
  + lstopo
    - Do not overwrite output files by default anymore.
      Pass -f or --force to enforce it.
    - Display OpenCL, CUDA and Xeon Phi numbers of cores and memory sizes
      in the graphical output.
    - Fix export to stdout when specifying a Cairo-based output type
      with --of.
  + hwloc-ps
    - Add -e or --get-last-cpu-location to report where processes/threads
      run instead of where they are bound.
    - Report locations as likely-more-useful objects such as Cores or Sockets
      instead of Caches when possible.
  + hwloc-bind
    - Fix failure on Windows when not using --pid.
    - Add -e as a synonym to --get-last-cpu-location.
  + hwloc-distrib
    - Add --reverse to distribute using last objects first and singlify
      into last bits first. Thanks to Jirka Hladky for the suggestion.
  + hwloc-info
    - Report unified caches when looking for data or instruction cache
      ancestor objects.
* Misc
  + Add experimental Visual Studio support under contrib/windows.
    Thanks to Eloi Gaudry for his help and for providing the first draft.
  + Fix some overzealous assertions and warnings about the ordering of
    objects on a level with respect to cpusets. The ordering is only
    guaranteed for complete cpusets (based on the first bit in sets).
  + Fix some memory leaks when importing xml diffs and when exporting a
    "too complex" entry.


Version 1.8.1
-------------
* Fix the cpuid code on Windows 64bits so that the x86 backend gets
  enabled as expected and can populate CPU information.
  Thanks to Robin Scher for reporting the problem.
* Add CPUVendor/CPUModelNumber/CPUFamilyNumber attributes when running
  on x86 architecture. Thanks to Ralph Castain for the suggestion.
* Work around buggy BIOS reporting duplicate NUMA nodes on Linux.
  Thanks to Jeff Becker for reporting the problem and testing the patch.
* Add a name to the lstopo graphical window. Thanks to Michael Prokop
  for reporting the issue.


Version 1.8.0
-------------
* New components
  + Add the "linuxpci" component that always works on Linux even when
    libpciaccess and libpci aren't available (and even with a modified
    file-system root). By default the old "pci" component runs first
    because "linuxpci" lacks device names (obj->name is always NULL).
* API
  + Add the topology difference API in hwloc/diff.h for manipulating
    many similar topologies.
  + Add hwloc_topology_dup() for duplicating an entire topology.
  + hwloc.h and hwloc/helper.h have been reorganized to clarify the
    documentation sections. The actual inline code has moved out of hwloc.h
    into the new hwloc/inlines.h.
  + Deprecated functions are now in hwloc/deprecated.h, and not in the
    official documentation anymore.
* Tools
  + Add hwloc-diff and hwloc-patch tools together with the new diff API.
  + Add hwloc-compress-dir to (de)compress an entire directory of XML files
    using hwloc-diff and hwloc-patch.
  + Object colors in the graphical output of lstopo may be changed by adding
    a "lstopoStyle" info attribute. See CUSTOM COLORS in the lstopo(1) manpage
    for details. Thanks to Jirka Hladky for discussing the idea.
  + hwloc-gather-topology may now gather I/O-related files on Linux when
    --io is given. Only the linuxpci component supports discovering I/O
    objects from these extended tarballs.
  + hwloc-annotate now supports --ri to remove/replace info attributes with
    a given name.
  + hwloc-info supports "root" and "all" special locations for dumping
    information about the root object.
  + lstopo now supports --append-legend to append custom lines of text
    to the legend in the graphical output. Thanks to Jirka Hladky for
    discussing the idea.
  + hwloc-calc and friends have a more robust parsing of locations given
    on the command-line and they report useful error messages about it.
  + Add --whole-system to hwloc-bind, hwloc-calc, hwloc-distances and
    hwloc-distrib, and add --restrict to hwloc-bind for uniformity among
    tools.
* Misc
  + Calling hwloc_topology_load() or hwloc_topology_set_*() on an already
    loaded topology now returns an error (deprecated since release 1.6.1).
  + Fix the initialisation of cpusets and nodesets in Group objects added
    when inserting PCI hostbridges.
  + Never merge Group objects that were added explicitly by the user with
    hwloc_custom_insert_group_object_by_parent().
  + Add a sanity check during dynamic plugin loading to prevent some
    crashes when hwloc is dynamically loaded by another plugin mechanisms.
  + Add --with-hwloc-plugins-path to specify the install/load directories
    of plugins.
  + Add the MICSerialNumber info attribute to the root object when running
    hwloc inside a Xeon Phi to match the same attribute in the MIC OS device
    when running in the host.


Version 1.7.2
-------------
* Do not create invalid block OS devices on very old Linux kernel such
  as RHEL4 2.6.9.
* Fix PCI subvendor/device IDs.
* Fix the management of Misc objects inserted by parent.
  Thanks to Jirka Hladky for reporting the problem.
* Add a Port<n>State into attribute to OpenFabrics OS devices.
* Add a MICSerialNumber info attribute to Xeon PHI/MIC OS devices.
* Improve verbose error messages when failing to load from XML.


Version 1.7.1
-------------
* Fix a failed assertion in the distance grouping code when loading a XML
  file that already contains some groups.
  Thanks to Laercio Lima Pilla for reporting the problem.
* Remove unexpected Group objects when loading XML topologies with I/O
  objects and NUMA distances.
  Thanks to Elena Elkina for reporting the problem and testing patches.
* Fix PCI link speed discovery when using libpciaccess.
* Fix invalid libpciaccess virtual function device/vendor IDs when using
  SR-IOV PCI devices on Linux.
* Fix GL component build with old NVCtrl releases.
  Thanks to Jirka Hladky for reporting the problem.
* Fix embedding breakage caused by libltdl.
  Thanks to Pavan Balaji for reporting the problem.
* Always use the system-wide libltdl instead of shipping one inside hwloc.
* Document issues when enabling plugins while embedding hwloc in another
  project, in the documentation section Embedding hwloc in Other Software.
* Add a FAQ entry "How to get useful topology information on NetBSD?"
  in the documentation.
* Somes fixes in the renaming code for embedding.
* Miscellaneous minor build fixes.


Version 1.7.0
-------------
* New operating system backends
  + Add BlueGene/Q compute node kernel (CNK) support. See the FAQ in the
    documentation for details. Thanks to Jeff Hammond, Christopher Samuel
    and Erik Schnetter for their help.
  + Add NetBSD support, thanks to Aleksej Saushev.
* New I/O device discovery
  + Add co-processor OS devices such as "mic0" for Intel Xeon Phi (MIC)
    on Linux. Thanks to Jerome Vienne for helping.
  + Add co-processor OS devices such as "cuda0" for NVIDIA CUDA-capable GPUs.
  + Add co-processor OS devices such as "opencl0d0" for OpenCL GPU devices
    on the AMD OpenCL implementation.
  + Add GPU OS devices such as ":0.0" for NVIDIA X11 displays.
  + Add GPU OS devices such as "nvml0" for NVIDIA GPUs.
    Thanks to Marwan Abdellah and Stefan Eilemann for helping.
  These new OS devices have some string info attributes such as CoProcType,
  GPUModel, etc. to better identify them.
  See the I/O Devices and Attributes documentation sections for details.
* New components
  + Add the "opencl", "cuda", "nvml" and "gl" components for I/O device
    discovery.
  + "nvml" also improves the discovery of NVIDIA GPU PCIe link speed.
  All of these new components may be built as plugins. They may also be
  disabled entirely by passing --disable-opencl/cuda/nvml/gl to configure.
  See the I/O Devices, Components and Plugins, and FAQ documentation
  sections for details.
* API
  + Add hwloc_topology_get_flags().
  + Add hwloc/plugins.h for building external plugins.
    See the Adding new discovery components and plugins section.
* Interoperability
  + Add hwloc/opencl.h, hwloc/nvml.h, hwloc/gl.h and hwloc/intel-mic.h
    to retrieve the locality of OS devices that correspond to AMD OpenCL
    GPU devices or indexes, to NVML devices or indexes, to NVIDIA X11
    displays, or to Intel Xeon Phi (MIC) device indexes.
  + Add new helpers in hwloc/cuda.h and hwloc/cudart.h to convert
    between CUDA devices or indexes and hwloc OS devices.
  + Add hwloc_ibv_get_device_osdev() and clarify the requirements
    of the OpenFabrics Verbs helpers in hwloc/openfabrics-verbs.h.
* Tools
  + hwloc-info is not only a synonym of lstopo -s anymore, it also
    dumps information about objects given on the command-line.
* Documentation
  + Add a section "Existing components and plugins".
  + Add a list of common OS devices in section "Software devices".
  + Add a new FAQ entry "Why is lstopo slow?" about lstopo slowness
    issues because of GPUs.
  + Clarify the documentation of inline helpers in hwloc/myriexpress.h
    and hwloc/openfabrics-verbs.h.
* Misc
  + Improve cache detection on AIX.
  + The HWLOC_COMPONENTS variable now excludes the components whose
    names are prefixed with '-'.
  + lstopo --ignore PU now works when displaying the topology in
    graphical and textual mode (not when exporting to XML).
  + Make sure I/O options always appear in lstopo usage, not only when
    using pciutils/libpci.
  + Remove some unneeded Linux specific includes from some interoperability
    headers.
  + Fix some inconsistencies in hwloc-distrib and hwloc-assembler-remote
    manpages. Thanks to Guy Streeter for the report.
  + Fix a memory leak on AIX when getting memory binding.
  + Fix many small memory leaks on Linux.
  + The `libpci' component is now called `pci' but the old name is still
    accepted in the HWLOC_COMPONENTS variable for backward compatibility.


Version 1.6.2
-------------
* Use libpciaccess instead of pciutils/libpci by default for I/O discovery.
  pciutils/libpci is only used if --enable-libpci is given to configure
  because its GPL license may taint hwloc. See the Installation section
  in the documentation for details.
* Fix get_cpubind on Solaris when bound to a single PU with
  processor_bind(). Thanks to Eugene Loh for reporting the problem
  and providing a patch.


Version 1.6.1
-------------
* Fix some crash or buggy detection in the x86 backend when Linux
  cgroups/cpusets restrict the available CPUs.
* Fix the pkg-config output with --libs --static.
  Thanks to Erik Schnetter for reporting one of the problems.
* Fix the output of hwloc-calc -H --hierarchical when using logical
  indexes in the output.
* Calling hwloc_topology_load() multiple times on the same topology
  is officially deprecated. hwloc will warn in such cases.
* Add some documentation about existing plugins/components, package
  dependencies, and I/O devices specification on the command-line.


Version 1.6.0
-------------
* Major changes
  + Reorganize the backend infrastructure to support dynamic selection
    of components and dynamic loading of plugins. For details, see the
    new documentation section Components and plugins.
    - The HWLOC_COMPONENTS variable lets one replace the default discovery
      components.
    - Dynamic loading of plugins may be enabled with --enable-plugins
      (except on AIX and Windows). It will build libxml2 and libpci
      support as separated modules. This helps reducing the dependencies
      of the core hwloc library when distributed as a binary package.
* Backends
  + Add CPUModel detection on Darwin and x86/FreeBSD.
    Thanks to Robin Scher for providing ways to implement this.
  + The x86 backend now adds CPUModel info attributes to socket objects
    created by other backends that do not natively support this attribute.
  + Fix detection on FreeBSD in case of cpuset restriction. Thanks to
    Sebastian Kuzminsky for reporting the problem.
* XML
  + Add hwloc_topology_set_userdata_import/export_callback(),
    hwloc_export_obj_userdata() and _userdata_base64() to let
    applications specify how to save/restore the custom data they placed
    in the userdata private pointer field of hwloc objects.
* Tools
  + Add hwloc-annotate program to add string info attributes to XML
    topologies.
  + Add --pid-cmd to hwloc-ps to append the output of a command to each
    PID line. May be used for showing Open MPI process ranks, see the
    hwloc-ps(1) manpage for details.
  + hwloc-bind now exits with an error if binding fails; the executable
    is not launched unless binding suceeeded or --force was given.
  + Add --quiet to hwloc-calc and hwloc-bind to hide non-fatal error
    messages.
  + Fix command-line pid support in windows tools.
  + All programs accept --verbose as a synonym to -v.
* Misc
  + Fix some DIR descriptor leaks on Linux.
  + Fix I/O device lists when some were filtered out after a XML import.
  + Fix the removal of I/O objects when importing a I/O-enabled XML topology
    without any I/O topology flag.
  + When merging objects with HWLOC_IGNORE_TYPE_KEEP_STRUCTURE or
    lstopo --merge, compare object types before deciding which one of two
    identical object to remove (e.g. keep sockets in favor of caches).
  + Add some GUID- and LID-related info attributes to OpenFabrics
    OS devices.
  + Only add CPUType socket attributes on Solaris/Sparc. Other cases
    don't report reliable information (Solaris/x86), and a replacement
    is available as the Architecture string info in the Machine object.
  + Add missing Backend string info on Solaris in most cases.
  + Document object attributes and string infos in a new Attributes
    section in the documentation.
  + Add a section about Synthetic topologies in the documentation.


Version 1.5.2 (some of these changes are in v1.6.2 but not in v1.6)
-------------
* Use libpciaccess instead of pciutils/libpci by default for I/O discovery.
  pciutils/libpci is only used if --enable-libpci is given to configure
  because its GPL license may taint hwloc. See the Installation section
  in the documentation for details.
* Fix get_cpubind on Solaris when bound to a single PU with
  processor_bind(). Thanks to Eugene Loh for reporting the problem
  and providing a patch.
* Fix some DIR descriptor leaks on Linux.
* Fix I/O device lists when some were filtered out after a XML import.
* Add missing Backend string info on Solaris in most cases.
* Fix the removal of I/O objects when importing a I/O-enabled XML topology
  without any I/O topology flag.
* Fix the output of hwloc-calc -H --hierarchical when using logical
  indexes in the output.
* Fix the pkg-config output with --libs --static.
  Thanks to Erik Schnetter for reporting one of the problems.


Version 1.5.1
-------------
* Fix block OS device detection on Linux kernel 3.3 and later.
  Thanks to Guy Streeter for reporting the problem and testing the fix.
* Fix the cpuid code in the x86 backend (for FreeBSD). Thanks to
  Sebastian Kuzminsky for reporting problems and testing patches.
* Fix 64bit detection on FreeBSD.
* Fix some corner cases in the management of the thissystem flag with
  respect to topology flags and environment variables.
* Fix some corner cases in command-line parsing checks in hwloc-distrib
  and hwloc-distances.
* Make sure we do not miss some block OS devices on old Linux kernels
  when a single PCI device has multiple IDE hosts/devices behind it.
* Do not disable I/O devices or instruction caches in hwloc-assembler output.


Version 1.5.0
-------------
* Backends
  + Do not limit the number of processors to 1024 on Solaris anymore.
  + Gather total machine memory on FreeBSD. Thanks to Cyril Roelandt.
  + XML topology files do not depend on the locale anymore. Float numbers
    such as NUMA distances or PCI link speeds now always use a dot as a
    decimal separator.
  + Add instruction caches detection on Linux, AIX, Windows and Darwin.
  + Add get_last_cpu_location() support for the current thread on AIX.
  + Support binding on AIX when threads or processes were bound with
    bindprocessor(). Thanks to Hendryk Bockelmann for reporting the issue
    and testing patches, and to Farid Parpia for explaining the binding
    interfaces.
  + Improve AMD topology detection in the x86 backend (for FreeBSD) using
    the topoext feature.
* API
  + Increase HWLOC_API_VERSION to 0x00010500 so that API changes may be
    detected at build-time.
  + Add a cache type attribute describind Data, Instruction and Unified
    caches. Caches with different types but same depth (for instance L1d
    and L1i) are placed on different levels.
  + Add hwloc_get_cache_type_depth() to retrieve the hwloc level depth of
    of the given cache depth and type, for instance L1i or L2.
    It helps  disambiguating the case where hwloc_get_type_depth() returns
    HWLOC_TYPE_DEPTH_MULTIPLE.
  + Instruction caches are ignored unless HWLOC_TOPOLOGY_FLAG_ICACHES is
    passed to hwloc_topology_set_flags() before load.
  + Add hwloc_ibv_get_device_osdev_by_name() OpenFabrics helper in
    openfabrics-verbs.h to find the hwloc OS device object corresponding to
    an OpenFabrics device.
* Tools
  + Add lstopo-no-graphics, a lstopo built without graphical support to
    avoid dependencies on external libraries such as Cairo and X11. When
    supported, graphical outputs are only available in the original lstopo
    program.
    - Packagers splitting lstopo and lstopo-no-graphics into different
      packages are advised to use the alternatives system so that lstopo
      points to the best available binary.
  + Instruction caches are enabled in lstopo by default. Use --no-icaches
    to disable them.
  + Add -t/--threads to show threads in hwloc-ps.
* Removal of obsolete components
  + Remove the old cpuset interface (hwloc/cpuset.h) which is deprecated and
    superseded by the bitmap API (hwloc/bitmap.h) since v1.1.
    hwloc_cpuset and nodeset types are still defined, but all hwloc_cpuset_*
    compatibility wrappers are now gone.
  + Remove Linux libnuma conversion helpers for the deprecated and
    broken nodemask_t interface.
  + Remove support for "Proc" type name, it was superseded by "PU" in v1.0.
  + Remove hwloc-mask symlinks, it was replaced by hwloc-calc in v1.0.
* Misc
  + Fix PCIe 3.0 link speed computation.
  + Non-printable characters are dropped from strings during XML export.
  + Fix importing of escaped characters with the minimalistic XML backend.
  + Assert hwloc_is_thissystem() in several I/O related helpers.
  + Fix some memory leaks in the x86 backend for FreeBSD.
  + Minor fixes to ease native builds on Windows.
  + Limit the number of retries when operating on all threads within a
    process on Linux if the list of threads is heavily getting modified.


Version 1.4.3
-------------
* This release is only meant to fix the pciutils license issue when upgrading
  to hwloc v1.5 or later is not possible. It contains several other minor
  fixes but ignores many of them that are only in v1.5 or later.
* Use libpciaccess instead of pciutils/libpci by default for I/O discovery.
  pciutils/libpci is only used if --enable-libpci is given to configure
  because its GPL license may taint hwloc. See the Installation section
  in the documentation for details.
* Fix PCIe 3.0 link speed computation.
* Fix importing of escaped characters with the minimalistic XML backend.
* Fix a memory leak in the x86 backend.


Version 1.4.2
-------------
* Fix build on Solaris 9 and earlier when fabsf() is not a compiler
  built-in. Thanks to Igor Galić for reporting the problem.
* Fix support for more than 32 processors on Windows. Thanks to Hartmut
  Kaiser for reporting the problem.
* Fix process-wide binding and cpulocation routines on Linux when some
  threads disappear in the meantime. Thanks to Vlad Roubtsov for reporting
  the issue.
* Make installed scripts executable. Thanks to Jirka Hladky for reporting
  the problem.
* Fix libtool revision management when building for Windows. This fix was
  also released as hwloc v1.4.1.1 Windows builds. Thanks to Hartmut Kaiser
  for reporting the problem.
* Fix the __hwloc_inline keyword in public headers when compiling with a
  C++ compiler.
* Add Port info attribute to network OS devices inside OpenFabrics PCI
  devices so as to identify which interface corresponds to which port.
* Document requirements for interoperability helpers: I/O devices discovery
  is required for some of them; the topology must match the current host
  for most of them.


Version 1.4.1
-------------
* This release contains all changes from v1.3.2.
* Fix hwloc_alloc_membind, thanks Karl Napf for reporting the issue.
* Fix memory leaks in some get_membind() functions.
* Fix helpers converting from Linux libnuma to hwloc (hwloc/linux-libnuma.h)
  in case of out-of-order NUMA node ids.
* Fix some overzealous assertions in the distance grouping code.
* Workaround BIOS reporting empty I/O locality in CUDA and OpenFabrics
  helpers on Linux. Thanks to Albert Solernou for reporting the problem.
* Install a valgrind suppressions file hwloc-valgrind.supp (see the FAQ).
* Fix memory binding documentation. Thanks to Karl Napf for reporting the
  issues.


Version 1.4.0 (does not contain all v1.3.2 changes)
-------------
* Major features
  + Add "custom" interface and "assembler" tools to build multi-node
    topology. See the Multi-node Topologies section in the documentation
    for details.
* Interface improvements
  + Add symmetric_subtree object attribute to ease assumptions when consulting
    regular symmetric topologies.
  + Add a CPUModel and CPUType info attribute to Socket objects on Linux
    and Solaris.
  + Add hwloc_get_obj_index_inside_cpuset() to retrieve the "logical" index
    of an object within a subtree of the topology.
  + Add more NVIDIA CUDA helpers in cuda.h and cudart.h to find hwloc objects
    corresponding to CUDA devices.
* Discovery improvements
  + Add a group object above partial distance matrices to make sure
    the matrices are available in the final topology, except when this
    new object would contradict the existing hierarchy.
  + Grouping by distances now also works when loading from XML.
  + Fix some corner cases in object insertion, for instance when dealing
    with NUMA nodes without any CPU.
* Backends
  + Implement hwloc_get_area_membind() on Linux.
  + Honor I/O topology flags when importing from XML.
  + Further improve XML-related error checking and reporting.
  + Hide synthetic topology error messages unless HWLOC_SYNTHETIC_VERBOSE=1.
* Tools
  + Add synthetic exporting of symmetric topologies to lstopo.
  + lstopo --horiz and --vert can now be applied to some specific object types.
  + lstopo -v -p now displays distance matrices with physical indexes.
  + Add hwloc-distances utility to list distances.
* Documentation
  + Fix and/or document the behavior of most inline functions in hwloc/helper.h
    when the topology contains some I/O or Misc objects.
  + Backend documentation enhancements.
* Bug fixes
  + Fix missing last bit in hwloc_linux_get_thread_cpubind().
    Thanks to Carolina Gómez-Tostón Gutiérrez for reporting the issue.
  + Fix FreeBSD build without cpuid support.
  + Fix several Windows build issues.
  + Fix inline keyword definition in public headers.
  + Fix dependencies in the embedded library.
  + Improve visibility support detection. Thanks to Dave Love for providing
    the patch.
  + Remove references to internal symbols in the tools.


Version 1.3.3
-------------
* This release is only meant to fix the pciutils license issue when upgrading
  to hwloc v1.4 or later is not possible. It contains several other minor
  fixes but ignores many of them that are only in v1.4 or later.
* Use libpciaccess instead of pciutils/libpci by default for I/O discovery.
  pciutils/libpci is only used if --enable-libpci is given to configure
  because its GPL license may taint hwloc. See the Installation section
  in the documentation for details.


Version 1.3.2
-------------
* Fix missing last bit in hwloc_linux_get_thread_cpubind().
  Thanks to Carolina Gómez-Tostón Gutiérrez for reporting the issue.
* Fix build with -mcmodel=medium. Thanks to Devendar Bureddy for reporting
  the issue.
* Fix build with Solaris Studio 12 compiler when XML is disabled.
  Thanks to Paul H. Hargrove for reporting the problem.
* Fix installation with old GNU sed, for instance on Red Hat 8.
  Thanks to Paul H. Hargrove for reporting the problem.
* Fix PCI locality when Linux cgroups restrict the available CPUs.
* Fix floating point issue when grouping by distance on mips64 architecture.
  Thanks to Paul H. Hargrove for reporting the problem.
* Fix conversion from/to Linux libnuma when some NUMA nodes have no memory.
* Fix support for gccfss compilers with broken ffs() support. Thanks to
  Paul H. Hargrove for reporting the problem and providing a patch.
* Fix FreeBSD build without cpuid support.
* Fix several Windows build issues.
* Fix inline keyword definition in public headers.
* Fix dependencies in the embedded library.
* Detect when a compiler such as xlc may not report compile errors
  properly, causing some configure checks to be wrong. Thanks to
  Paul H. Hargrove for reporting the problem and providing a patch.
* Improve visibility support detection. Thanks to Dave Love for providing
  the patch.
* Remove references to internal symbols in the tools.
* Fix installation on systems with limited command-line size.
  Thanks to Paul H. Hargrove for reporting the problem.
* Further improve XML-related error checking and reporting.


Version 1.3.1
-------------
* Fix pciutils detection with pkg-config when not installed in standard
  directories.
* Fix visibility options detection with the Solaris Studio compiler.
  Thanks to Igor Galić and Terry Dontje for reporting the problems.
* Fix support for old Linux sched.h headers such as those found
  on Red Hat 8. Thanks to Paul H. Hargrove for reporting the problems.
* Fix inline and attribute support for Solaris compilers. Thanks to
  Dave Love for reporting the problems.
* Print a short summary at the end of the configure output. Thanks to
  Stefan Eilemann for the suggestion.
* Add --disable-libnuma configure option to disable libnuma-based
  memory binding support on Linux.  Thanks to Rayson Ho for the
  suggestion.
* Make hwloc's configure script properly obey $PKG_CONFIG.  Thanks to
  Nathan Phillip Brink for raising the issue.
* Silence some harmless pciutils warnings, thanks to Paul H. Hargrove
  for reporting the problem.
* Fix the documentation with respect to hwloc_pid_t and hwloc_thread_t
  being either pid_t and pthread_t on Unix, or HANDLE on Windows.


Version 1.3.0
-------------
* Major features
  + Add I/O devices and bridges to the topology using the pciutils
    library. Only enabled after setting the relevant flag with
    hwloc_topology_set_flags() before hwloc_topology_load(). See the
    I/O Devices section in the documentation for details.
* Discovery improvements
  + Add associativity to the cache attributes.
  + Add support for s390/z11 "books" on Linux.
  + Add the HWLOC_GROUPING_ACCURACY environment variable to relax
    distance-based grouping constraints. See the Environment Variables
    section in the documentation for details about grouping behavior
    and configuration.
  + Allow user-given distance matrices to remove or replace those
    discovered by the OS backend.
* XML improvements
  + XML is now always supported: a minimalistic custom import/export
    code is used when libxml2 is not available. It is only guaranteed
    to read XML files generated by hwloc.
  + hwloc_topology_export_xml() and export_xmlbuffer() now return an
    integer.
  + Add hwloc_free_xmlbuffer() to free the buffer allocated by
    hwloc_topology_export_xmlbuffer().
  + Hide XML topology error messages unless HWLOC_XML_VERBOSE=1.
* Minor API updates
  + Add hwloc_obj_add_info to customize object info attributes.
* Tools
  + lstopo now displays I/O devices by default. Several options are
    added to configure the I/O discovery.
  + hwloc-calc and hwloc-bind now accept I/O devices as input.
  + Add --restrict option to hwloc-calc and hwloc-distribute.
  + Add --sep option to change the output field separator in hwloc-calc.
  + Add --whole-system option to hwloc-ps.


Version 1.2.2
-------------
* Fix build on AIX 5.2, thanks Utpal Kumar Ray for the report.
* Fix XML import of very large page sizes or counts on 32bits platform,
  thanks to Karsten Hopp for the RedHat ticket.
* Fix crash when administrator limitations such as Linux cgroup require
  to restrict distance matrices. Thanks to Ake Sandgren for reporting the
  problem.
* Fix the removal of objects such as AMD Magny-Cours dual-node sockets
  in case of administrator restrictions.
* Improve error reporting and messages in case of wrong synthetic topology
  description.
* Several other minor internal fixes and documentation improvements.


Version 1.2.1
-------------
* Improve support of AMD Bulldozer "Compute-Unit" modules by detecting
  logical processors with different core IDs on Linux.
* Fix hwloc-ps crash when listing processes from another Linux cpuset.
  Thanks to Carl Smith for reporting the problem.
* Fix build on AIX and Solaris. Thanks to Carl Smith and Andreas Kupries
  for reporting the problems.
* Fix cache size detection on Darwin. Thanks to Erkcan Özcan for reporting
  the problem.
* Make configure fail if --enable-xml or --enable-cairo is given and
  proper support cannot be found. Thanks to Andreas Kupries for reporting
  the XML problem.
* Fix spurious L1 cache detection on AIX. Thanks to Hendryk Bockelmann
  for reporting the problem.
* Fix hwloc_get_last_cpu_location(THREAD) on Linux. Thanks to Gabriele
  Fatigati for reporting the problem.
* Fix object distance detection on Solaris.
* Add pthread_self weak symbol to ease static linking.
* Minor documentation fixes.


Version 1.2.0
-------------
* Major features
  + Expose latency matrices in the API as an array of distance structures
    within objects. Add several helpers to find distances.
  + Add hwloc_topology_set_distance_matrix() and environment variables
    to provide a matrix of distances between a given set of objects.
  + Add hwloc_get_last_cpu_location() and hwloc_get_proc_last_cpu_location()
    to retrieve the processors where a process or thread recently ran.
    - Add the corresponding --get-last-cpu-location option to hwloc-bind.
  + Add hwloc_topology_restrict() to restrict an existing topology to a
    given cpuset.
    - Add the corresponding --restrict option to lstopo.
* Minor API updates
  + Add hwloc_bitmap_list_sscanf/snprintf/asprintf to convert between bitmaps
    and strings such as 4-5,7-9,12,15-
  + hwloc_bitmap_set/clr_range() now support infinite ranges.
  + Clarify the difference between inserting Misc objects by cpuset or by
    parent.
  + hwloc_insert_misc_object_by_cpuset() now returns NULL in case of error.
* Discovery improvements
  + x86 backend (for freebsd): add x2APIC support
  + Support standard device-tree phandle, to get better support on e.g. ARM
    systems providing it.
  + Detect cache size on AIX. Thanks Christopher and IBM.
  + Improve grouping to support asymmetric topologies.
* Tools
  + Command-line tools now support "all" and "root" special locations
    consisting in the entire topology, as well as type names with depth
    attributes such as L2 or Group4.
  + hwloc-calc improvements:
    - Add --number-of/-N option to report the number of objects of a given
      type or depth.
    - -I is now equivalent to --intersect for listing the indexes of
      objects of a given type or depth that intersects the input.
    - Add -H to report the output as a hierarchical combination of types
      and depths.
  + Add --thissystem to lstopo.
  + Add lstopo-win, a console-less lstopo variant on Windows.
* Miscellaneous
  + Remove C99 usage from code base.
  + Rename hwloc-gather-topology.sh into hwloc-gather-topology
  + Fix AMD cache discovery on freebsd when there is no L3 cache, thanks
    Andriy Gapon for the fix.


Version 1.1.2
-------------
* Fix a segfault in the distance-based grouping code when some objects
  are not placed in any group. Thanks to Bernd Kallies for reporting
  the problem and providing a patch.
* Fix the command-line parsing of hwloc-bind --mempolicy interleave.
  Thanks to Guy Streeter for reporting the problem.
* Stop truncating the output in hwloc_obj_attr_snprintf() and in the
  corresponding lstopo output. Thanks to Guy Streeter for reporting the
  problem.
* Fix object levels ordering in synthetic topologies.
* Fix potential incoherency between device tree and kernel information,
  when SMT is disabled on Power machines.
* Fix and document the behavior of hwloc_topology_set_synthetic() in case
  of invalid argument. Thanks to Guy Streeter for reporting the problem.
* Add some verbose error message reporting when it looks like the OS
  gives erroneous information.
* Do not include unistd.h and stdint.h in public headers on Windows.
* Move config.h files into their own subdirectories to avoid name
  conflicts when AC_CONFIG_HEADERS adds -I's for them.
* Remove the use of declaring variables inside "for" loops.
* Some other minor fixes.
* Many minor documentation fixes.


Version 1.1.1
-------------
* Add hwloc_get_api_version() which returns the version of hwloc used
  at runtime. Thanks to Guy Streeter for the suggestion.
* Fix the number of hugepages reported for NUMA nodes on Linux.
* Fix hwloc_bitmap_to_ulong() right after allocating the bitmap.
  Thanks to Bernd Kallies for reporting the problem.
* Fix hwloc_bitmap_from_ith_ulong() to properly zero the first ulong.
  Thanks to Guy Streeter for reporting the problem.
* Fix hwloc_get_membind_nodeset() on Linux.
  Thanks to Bernd Kallies for reporting the problem and providing a patch.
* Fix some file descriptor leaks in the Linux discovery.
* Fix the minimum width of NUMA nodes, caches and the legend in the graphical
  lstopo output. Thanks to Jirka Hladky for reporting the problem.
* Various fixes to bitmap conversion from/to taskset-strings.
* Fix and document snprintf functions behavior when the buffer size is too
  small or zero. Thanks to Guy Streeter for reporting the problem.
* Fix configure to avoid spurious enabling of the cpuid backend.
  Thanks to Tim Anderson for reporting the problem.
* Cleanup error management in hwloc-gather-topology.sh.
  Thanks to Jirka Hladky for reporting the problem and providing a patch.
* Add a manpage and usage for hwloc-gather-topology.sh on Linux.
  Thanks to Jirka Hladky for providing a patch.
* Memory binding documentation enhancements.


Version 1.1.0
-------------

* API
  + Increase HWLOC_API_VERSION to 0x00010100 so that API changes may be
    detected at build-time.
  + Add a memory binding interface.
  + The cpuset API (hwloc/cpuset.h) is now deprecated. It is replaced by
    the bitmap API (hwloc/bitmap.h) which offers the same features with more
    generic names since it applies to CPU sets, node sets and more.
    Backward compatibility with the cpuset API and ABI is still provided but
    it will be removed in a future release.
    Old types (hwloc_cpuset_t, ...) are still available as a way to clarify
    what kind of hwloc_bitmap_t each API function manipulates.
    Upgrading to the new API only requires to replace hwloc_cpuset_ function
    calls with the corresponding hwloc_bitmap_ calls, with the following
    renaming exceptions:
    - hwloc_cpuset_cpu -> hwloc_bitmap_only
    - hwloc_cpuset_all_but_cpu -> hwloc_bitmap_allbut
    - hwloc_cpuset_from_string -> hwloc_bitmap_sscanf
  + Add an `infos' array in each object to store couples of info names and
    values. It enables generic storage of things like the old dmi board infos
    that were previously stored in machine specific attributes.
  + Add linesize cache attribute.
* Features
  + Bitmaps (and thus CPU sets and node sets) are dynamically (re-)allocated,
    the maximal number of CPUs (HWLOC_NBMAXCPUS) has been removed.
  + Improve the distance-based grouping code to better support irregular
    distance matrices.
  + Add support for device-tree to get cache information (useful on Power
    architectures).
* Helpers
  + Add NVIDIA CUDA helpers in cuda.h and cudart.h to ease interoperability
    with CUDA Runtime and Driver APIs.
  + Add Myrinet Express helper in myriexpress.h to ease interoperability.
* Tools
  + lstopo now displays physical/OS indexes by default in graphical mode
    (use -l to switch back to logical indexes). The textual output still uses
    logical by default (use -p to switch to physical indexes).
  + lstopo prefixes logical indexes with `L#' and physical indexes with `P#'.
    Physical indexes are also printed as `P#N' instead of `phys=N' within
    object attributes (in parentheses).
  + Add a legend at the bottom of the lstopo graphical output, use --no-legend
    to remove it.
  + Add hwloc-ps to list process' bindings.
  + Add --membind and --mempolicy options to hwloc-bind.
  + Improve tools command-line options by adding a generic --input option
    (and more) which replaces the old --xml, --synthetic and --fsys-root.
  + Cleanup lstopo output configuration by adding --output-format.
  + Add --intersect in hwloc-calc, and replace --objects with --largest.
  + Add the ability to work on standard input in hwloc-calc.
  + Add --from, --to and --at in hwloc-distrib.
  + Add taskset-specific functions and command-line tools options to
    manipulate CPU set strings in the format of the taskset program.
  + Install hwloc-gather-topology.sh on Linux.


Version 1.0.3
-------------

* Fix support for Linux cpuset when emulated by a cgroup mount point.
* Remove unneeded runtime dependency on libibverbs.so in the library and
  all utils programs.
* Fix hwloc_cpuset_to_linux_libnuma_ulongs in case of non-linear OS-indexes
  for NUMA nodes.
* lstopo now displays physical/OS indexes by default in graphical mode
  (use -l to switch back to logical indexes). The textual output still uses
  logical by default (use -p to switch to physical indexes).


Version 1.0.2
-------------

* Public headers can now be included directly from C++ programs.
* Solaris fix for non-contiguous cpu numbers.  Thanks to Rolf vandeVaart for
  reporting the issue.
* Darwin 10.4 fix.  Thanks to Olivier Cessenat for reporting the issue.
* Revert 1.0.1 patch that ignored sockets with unknown ID values since it
  only slightly helped POWER7 machines with old Linux kernels while it
  prevents recent kernels from getting the complete POWER7 topology.
* Fix hwloc_get_common_ancestor_obj().
* Remove arch-specific bits in public headers.
* Some fixes in the lstopo graphical output.
* Various man page clarifications and minor updates.


Version 1.0.1
-------------

* Various Solaris fixes.  Thanks to Yannick Martin for reporting the issue.
* Fix "non-native" builds on x86 platforms (e.g., when building 32
  bit executables with compilers that natively build 64 bit).
* Ignore sockets with unknown ID values (which fixes issues on POWER7
  machines).  Thanks to Greg Bauer for reporting the issue.
* Various man page clarifications and minor updates.
* Fixed memory leaks in hwloc_setup_group_from_min_distance_clique().
* Fix cache type filtering on MS Windows 7.  Thanks to Αλέξανδρος
  Παπαδογιαννάκ for reporting the issue.
* Fixed warnings when compiling with -DNDEBUG.


Version 1.0.0
-------------

* The ABI of the library has changed.
* Backend updates
  + Add FreeBSD support.
  + Add x86 cpuid based backend.
  + Add Linux cgroup support to the Linux cpuset code.
  + Support binding of entire multithreaded process on Linux.
  + Fix and enable Group support in Windows.
  + Cleanup XML export/import.
* Objects
  + HWLOC_OBJ_PROC is renamed into HWLOC_OBJ_PU for "Processing Unit",
    its stringified type name is now "PU".
  + Use new HWLOC_OBJ_GROUP objects instead of MISC when grouping
    objects according to NUMA distances or arbitrary OS aggregation.
  + Rework memory attributes.
  + Add different cpusets in each object to specify processors that
    are offline, unavailable, ...
  + Cleanup the storage of object names and DMI infos.
* Features
  + Add support for looking up specific PID topology information.
  + Add hwloc_topology_export_xml() to export the topology in a XML file.
  + Add hwloc_topology_get_support() to retrieve the supported features
    for the current topology context.
  + Support non-SYSTEM object as the root of the tree, use MACHINE in
    most common cases.
  + Add hwloc_get_*cpubind() routines to retrieve the current binding
    of processes and threads.
* API
  + Add HWLOC_API_VERSION to help detect the currently used API version.
  + Add missing ending "e" to *compare* functions.
  + Add several routines to emulate PLPA functions.
  + Rename and rework the cpuset and/or/xor/not/clear operators to output
    their result in a dedicated argument instead of modifying one input.
  + Deprecate hwloc_obj_snprintf() in favor of hwloc_obj_type/attr_snprintf().
  + Clarify the use of parent and ancestor in the API, do not use father.
  + Replace hwloc_get_system_obj() with hwloc_get_root_obj().
  + Return -1 instead of HWLOC_OBJ_TYPE_MAX in the API since the latter
    isn't public.
  + Relax constraints in hwloc_obj_type_of_string().
  + Improve displaying of memory sizes.
  + Add 0x prefix to cpuset strings.
* Tools
  + lstopo now displays logical indexes by default, use --physical to
    revert back to OS/physical indexes.
  + Add colors in the lstopo graphical outputs to distinguish between online,
    offline, reserved, ... objects.
  + Extend lstopo to show cpusets, filter objects by type, ...
  + Renamed hwloc-mask into hwloc-calc which supports many new options.
* Documentation
  + Add a hwloc(7) manpage containing general information.
  + Add documentation about how to switch from PLPA to hwloc.
  + Cleanup the distributed documentation files.
* Miscellaneous
  + Many compilers warning fixes.
  + Cleanup the ABI by using the visibility attribute.
  + Add project embedding support.


Version 0.9.4 (unreleased)
--------------------------

* Fix reseting colors to normal in lstopo -.txt output.
* Fix Linux pthread_t binding error report.


Version 0.9.3
-------------

* Fix autogen.sh to work with Autoconf 2.63.
* Fix various crashes in particular conditions:
  - xml files with root attributes
  - offline CPUs
  - partial sysfs support
  - unparseable /proc/cpuinfo
  - ignoring NUMA level while Misc level have been generated
* Tweak documentation a bit
* Do not require the pthread library for binding the current thread on Linux
* Do not erroneously consider the sched_setaffinity prototype is the old version
  when there is actually none.
* Fix _syscall3 compilation on archs for which we do not have the
  sched_setaffinity system call number.
* Fix AIX binding.
* Fix libraries dependencies: now only lstopo depends on libtermcap, fix
  binutils-gold link
* Have make check always build and run hwloc-hello.c
* Do not limit size of a cpuset.


Version 0.9.2
-------------

* Trivial documentation changes.


Version 0.9.1
-------------

* Re-branded to "hwloc" and moved to the Open MPI project, relicensed under the
  BSD license.
* The prefix of all functions and tools is now hwloc, and some public
  functions were also renamed for real.
* Group NUMA nodes into Misc objects according to their physical distance
  that may be reported by the OS/BIOS.
  May be ignored by setting HWLOC_IGNORE_DISTANCES=1 in the environment.
* Ignore offline CPUs on Solaris.
* Improved binding support on AIX.
* Add HP-UX support.
* CPU sets are now allocated/freed dynamically.
* Add command line options to tune the lstopo graphical output, add
  semi-graphical textual output
* Extend topobind to support multiple cpusets or objects on the command
  line as topomask does.
* Add an Infiniband-specific helper hwloc/openfabrics-verbs.h to retrieve
  the physical location of IB devices.


Version 0.9 (libtopology)
-------------------------

* First release.