v6.7.1

RandomX x86 JIT: remove redundant CFROUND

.gitignore

@@ -1,4 +1,6 @@
 /build
+scripts/build
+scripts/deps
 /CMakeLists.txt.user
 /.idea
 /src/backend/opencl/cl/cn/cryptonight_gen.cl

CHANGELOG.md

@@ -1,3 +1,21 @@
+# v6.7.1
+- [#1995](https://github.com/xmrig/xmrig/issues/1995) Fixed log initialization.
+- [#1998](https://github.com/xmrig/xmrig/pull/1998) Added hashrate in the benchmark finished message.
+- [#2009](https://github.com/xmrig/xmrig/pull/2009) AstroBWT OpenCL fixes.
+- [#2028](https://github.com/xmrig/xmrig/pull/2028) RandomX x86 JIT: removed redundant `CFROUND`.
+
+# v6.7.0
+- **[#1991](https://github.com/xmrig/xmrig/issues/1991) Added Apple M1 processor support.**
+- **[#1986](https://github.com/xmrig/xmrig/pull/1986) Up to 20-30% faster RandomX dataset initialization with AVX2 on some CPUs.**
+- [#1964](https://github.com/xmrig/xmrig/pull/1964) Cleanup and refactoring.
+- [#1966](https://github.com/xmrig/xmrig/pull/1966) Removed libcpuid support.
+- [#1968](https://github.com/xmrig/xmrig/pull/1968) Added virtual machine detection.
+- [#1969](https://github.com/xmrig/xmrig/pull/1969) [#1970](https://github.com/xmrig/xmrig/pull/1970) Fixed errors found by static analysis.
+- [#1977](https://github.com/xmrig/xmrig/pull/1977) Fixed: secure JIT and huge pages are incompatible on Windows.
+- [#1979](https://github.com/xmrig/xmrig/pull/1979) Term `x64` replaced to `64-bit`.
+- [#1980](https://github.com/xmrig/xmrig/pull/1980) Fixed build on gcc 11.
+- [#1989](https://github.com/xmrig/xmrig/pull/1989) Fixed broken Dero solo mining.
+
 # v6.6.2
 - [#1958](https://github.com/xmrig/xmrig/pull/1958) Added example mining scripts to help new miners.
 - [#1959](https://github.com/xmrig/xmrig/pull/1959) Optimized JIT compiler.

CMakeLists.txt

@@ -1,7 +1,6 @@
-cmake_minimum_required(VERSION 2.8)
+cmake_minimum_required(VERSION 2.8.12)
 project(xmrig)
 
-option(WITH_LIBCPUID        "Enable libcpuid support" ON)
 option(WITH_HWLOC           "Enable hwloc support" ON)
 option(WITH_CN_LITE         "Enable CryptoNight-Lite algorithms family" ON)
 option(WITH_CN_HEAVY        "Enable CryptoNight-Heavy algorithms family" ON)
@@ -26,6 +25,7 @@ option(WITH_INTERLEAVE_DEBUG_LOG "Enable debug log for threads interleave" OFF)
 option(WITH_PROFILING       "Enable profiling for developers" OFF)
 option(WITH_SSE4_1          "Enable SSE 4.1 for Blake2" ON)
 option(WITH_BENCHMARK       "Enable builtin RandomX benchmark and stress test" ON)
+option(WITH_SECURE_JIT      "Enable secure access to JIT memory" OFF)
 
 option(BUILD_STATIC         "Build static binary" OFF)
 option(ARM_TARGET           "Force use specific ARM target 8 or 7" 0)
@@ -168,7 +168,7 @@ else()
     endif()
 endif()
 
-add_definitions(-DXMRIG_MINER_PROJECT)
+add_definitions(-DXMRIG_MINER_PROJECT -DXMRIG_JSON_SINGLE_LINE_ARRAY)
 add_definitions(-D__STDC_FORMAT_MACROS -DUNICODE)
 
 find_package(UV REQUIRED)
@@ -205,7 +205,7 @@ if (WITH_DEBUG_LOG)
     add_definitions(/DAPP_DEBUG)
 endif()
 
-add_executable(${CMAKE_PROJECT_NAME} ${HEADERS} ${SOURCES} ${SOURCES_OS} ${SOURCES_CPUID} ${HEADERS_CRYPTO} ${SOURCES_CRYPTO} ${SOURCES_SYSLOG} ${TLS_SOURCES} ${XMRIG_ASM_SOURCES})
+add_executable(${CMAKE_PROJECT_NAME} ${HEADERS} ${SOURCES} ${SOURCES_OS} ${HEADERS_CRYPTO} ${SOURCES_CRYPTO} ${SOURCES_SYSLOG} ${TLS_SOURCES} ${XMRIG_ASM_SOURCES})
 target_link_libraries(${CMAKE_PROJECT_NAME} ${XMRIG_ASM_LIBRARY} ${OPENSSL_LIBRARIES} ${UV_LIBRARIES} ${EXTRA_LIBS} ${CPUID_LIB} ${ARGON2_LIBRARY} ${ETHASH_LIBRARY})
 
 if (WIN32)
@@ -216,6 +216,6 @@ if (WIN32)
     add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/scripts/solo_mine_example.cmd" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
 endif()
 
-if (CMAKE_CXX_COMPILER_ID MATCHES Clang AND CMAKE_BUILD_TYPE STREQUAL Release)
+if (CMAKE_CXX_COMPILER_ID MATCHES Clang AND CMAKE_BUILD_TYPE STREQUAL Release AND NOT CMAKE_GENERATOR STREQUAL Xcode)
     add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_STRIP} ${CMAKE_PROJECT_NAME})
 endif()

cmake/cpu.cmake

@@ -18,7 +18,6 @@ endif()
 
 if (ARM_TARGET AND ARM_TARGET GREATER 6)
     set(XMRIG_ARM     ON)
-    set(WITH_LIBCPUID OFF)
     add_definitions(/DXMRIG_ARM)
 
     message(STATUS "Use ARM_TARGET=${ARM_TARGET} (${CMAKE_SYSTEM_PROCESSOR})")

cmake/os.cmake

@@ -32,6 +32,10 @@ elseif(XMRIG_OS_APPLE)
     else()
         add_definitions(/DXMRIG_OS_MACOS)
     endif()
+
+    if (XMRIG_ARM)
+        set(WITH_SECURE_JIT ON)
+    endif()
 elseif(XMRIG_OS_UNIX)
     add_definitions(/DXMRIG_OS_UNIX)
 
@@ -43,3 +47,7 @@ elseif(XMRIG_OS_UNIX)
         add_definitions(/DXMRIG_OS_FREEBSD)
     endif()
 endif()
+
+if (WITH_SECURE_JIT)
+    add_definitions(/DXMRIG_SECURE_JIT)
+endif()

cmake/randomx.cmake

@@ -61,7 +61,11 @@ if (WITH_RANDOMX)
              src/crypto/randomx/jit_compiler_a64.cpp
             )
         # cheat because cmake and ccache hate each other
-        set_property(SOURCE src/crypto/randomx/jit_compiler_a64_static.S PROPERTY LANGUAGE C)
+        if (CMAKE_GENERATOR STREQUAL Xcode)
+            set_property(SOURCE src/crypto/randomx/jit_compiler_a64_static.S PROPERTY LANGUAGE ASM)
+        else()
+            set_property(SOURCE src/crypto/randomx/jit_compiler_a64_static.S PROPERTY LANGUAGE C)
+        endif()
     else()
         list(APPEND SOURCES_CRYPTO
              src/crypto/randomx/jit_compiler_fallback.cpp
@@ -108,6 +112,13 @@ if (WITH_RANDOMX)
         remove_definitions(/DXMRIG_FIX_RYZEN)
         message("-- WITH_MSR=OFF")
     endif()
+
+    if (WITH_PROFILING)
+        add_definitions(/DXMRIG_FEATURE_PROFILING)
+
+        list(APPEND HEADERS_CRYPTO src/crypto/rx/Profiler.h)
+        list(APPEND SOURCES_CRYPTO src/crypto/rx/Profiler.cpp)
+    endif()
 else()
     remove_definitions(/DXMRIG_ALGO_RANDOMX)
 endif()

scripts/benchmark_10M.cmd

@@ -1,3 +1,4 @@
 @echo off
+cd %~dp0
 xmrig.exe --bench=10M --submit
 pause

scripts/benchmark_1M.cmd

@@ -1,3 +1,4 @@
 @echo off
+cd %~dp0
 xmrig.exe --bench=1M --submit
 pause

scripts/build.hwloc.sh

@@ -1,6 +1,6 @@
 #!/bin/bash -e
 
-HWLOC_VERSION="2.2.0"
+HWLOC_VERSION="2.4.0"
 
 mkdir -p deps
 mkdir -p deps/include
@@ -8,7 +8,7 @@ mkdir -p deps/lib
 
 mkdir -p build && cd build
 
-wget https://download.open-mpi.org/release/hwloc/v2.2/hwloc-${HWLOC_VERSION}.tar.gz -O hwloc-${HWLOC_VERSION}.tar.gz
+wget https://download.open-mpi.org/release/hwloc/v2.4/hwloc-${HWLOC_VERSION}.tar.gz -O hwloc-${HWLOC_VERSION}.tar.gz
 tar -xzf hwloc-${HWLOC_VERSION}.tar.gz
 
 cd hwloc-${HWLOC_VERSION}

scripts/build.openssl.sh

@@ -1,6 +1,6 @@
 #!/bin/bash -e
 
-OPENSSL_VERSION="1.1.1h"
+OPENSSL_VERSION="1.1.1i"
 
 mkdir -p deps
 mkdir -p deps/include

scripts/pool_mine_example.cmd

@@ -15,5 +15,6 @@
 :: Choose pools outside of top 5 to help Monero network be more decentralized!
 :: Smaller pools also often have smaller fees/payout limits.
 
+cd %~dp0
 xmrig.exe -o pool.hashvault.pro:3333 -u 48edfHu7V9Z84YzzMa6fUueoELZ9ZRXq9VetWzYGzKt52XU5xvqgzYnDK9URnRoJMk1j8nLwEVsaSWJ4fhdUyZijBGUicoD -p x
 pause

scripts/solo_mine_example.cmd

@@ -11,5 +11,6 @@
 :: Mining solo is the best way to help Monero network be more decentralized!
 :: But you will only get a payout when you find a block which can take more than a year for a single low-end PC.
 
+cd %~dp0
 xmrig.exe -o node.xmr.to:18081 -a rx/0 -u 48edfHu7V9Z84YzzMa6fUueoELZ9ZRXq9VetWzYGzKt52XU5xvqgzYnDK9URnRoJMk1j8nLwEVsaSWJ4fhdUyZijBGUicoD --daemon
 pause

src/3rdparty/argon2/CMakeLists.txt

@@ -1,4 +1,4 @@
-cmake_minimum_required(VERSION 2.8)
+cmake_minimum_required(VERSION 2.8.12)
 
 project(argon2 C)
 set(CMAKE_C_STANDARD 99)

src/3rdparty/fmt/format-inl.h

@@ -1754,7 +1754,7 @@ inline bool divisible_by_power_of_2(uint64_t x, int exp) FMT_NOEXCEPT {
 #ifdef FMT_BUILTIN_CTZLL
   return FMT_BUILTIN_CTZLL(x) >= exp;
 #else
-  return exp < num_bits<uint64_t>()) && x == ((x >> exp) << exp);
+  return (exp < num_bits<uint64_t>()) && x == ((x >> exp) << exp);
 #endif
 }
 

src/3rdparty/hwloc/CMakeLists.txt

@@ -1,4 +1,4 @@
-cmake_minimum_required (VERSION 2.8)
+cmake_minimum_required (VERSION  2.8.12)
 project (hwloc C)
 
 include_directories(include)
@@ -13,23 +13,25 @@ set(HEADERS
     )
 
 set(SOURCES
-	src/base64.c
-	src/bind.c
-	src/bitmap.c
-	src/components.c
-	src/diff.c
-	src/distances.c
-	src/misc.c
-	src/pci-common.c
-	src/shmem.c
-	src/topology.c
-	src/topology-noos.c
-	src/topology-synthetic.c
-	src/topology-windows.c
-	src/topology-x86.c
-	src/topology-xml.c
-	src/topology-xml-nolibxml.c
+    src/base64.c
+    src/bind.c
+    src/bitmap.c
+    src/components.c
+    src/diff.c
+    src/distances.c
+    src/misc.c
+    src/pci-common.c
+    src/shmem.c
+    src/topology.c
+    src/topology-noos.c
+    src/topology-synthetic.c
+    src/topology-windows.c
+    src/topology-x86.c
+    src/topology-xml.c
+    src/topology-xml-nolibxml.c
     src/traversal.c
+    src/memattrs.c
+    src/cpukinds.c
    )
 
 add_library(hwloc STATIC

src/3rdparty/hwloc/NEWS

@@ -2,6 +2,7 @@ Copyright © 2009 CNRS
 Copyright © 2009-2020 Inria.  All rights reserved.
 Copyright © 2009-2013 Université Bordeaux
 Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
+Copyright © 2020 Hewlett Packard Enterprise.  All rights reserved.
 
 $COPYRIGHT$
 
@@ -16,6 +17,76 @@ bug fixes (and other actions) for each version of hwloc since version
 0.9.
 
 
+Version 2.4.0
+-------------
+* API
+  + Add hwloc/cpukinds.h for reporting information about hybrid CPUs.
+    - Use Linux cpufreq frequencies to rank cores by efficiency.
+    - Use x86 CPUID hybrid leaf and future Linux kernels sysfs CPU type
+      files to identify Intel Atom and Core cores.
+    - Use the Windows native EfficiencyClass to separate kinds.
+* Backends
+  + Properly handle Linux kernel 5.10+ exposing ACPI HMAT information
+    with knowledge of Generic Initiators.
+* Tools
+  + lstopo has new --cpukinds and --no-cpukinds options for showing
+    CPU kinds or not in textual and graphical modes respectively.
+  + hwloc-calc has a new --cpukind option for filtering PUs by kind.
+  + hwloc-annotate has a new cpukind command for modifying CPU kinds.
+* Misc
+  + Fix hwloc_bitmap_nr_ulongs(), thanks to Norbert Eicker.
+  + Add a documentation section about
+    "Topology Attributes: Distances, Memory Attributes and CPU Kinds".
+  + Silence some spurious warnings in the OpenCL backend and when showing
+    process binding with lstopo --ps.
+
+
+Version 2.3.0
+-------------
+* API
+  + Add hwloc/memattrs.h for exposing latency/bandwidth information
+    between initiators (CPU sets for now) and target NUMA nodes,
+    typically on heterogeneous platforms.
+    - When available, bandwidths and latencies are read from the ACPI HMAT
+      table exposed by Linux kernel 5.2+.
+    - Attributes may also be customized to expose user-defined performance
+      information.
+  + Add hwloc_get_local_numanode_objs() for listing NUMA nodes that are
+    local to some locality.
+  + The new topology flag HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT causes
+    support arrays to be loaded from XML exported with hwloc 2.3+.
+    - hwloc_topology_get_support() now returns an additional "misc"
+      array with feature "imported_support" set when support was imported.
+  + Add hwloc_topology_refresh() to refresh internal caches after modifying
+    the topology and before consulting the topology in a multithread context.
+* Backends
+  + Add a ROCm SMI backend and a hwloc/rsmi.h helper file for getting
+    the locality of AMD GPUs, now exposed as "rsmi" OS devices.
+    Thanks to Mike Li.
+  + Remove POWER device-tree-based topology on Linux,
+    (it was disabled by default since 2.1).
+* Tools
+  + Command-line options for specifying flags now understand comma-separated
+    lists of flag names (substrings).
+  + hwloc-info and hwloc-calc have new --local-memory --local-memory-flags
+    and --best-memattr options for reporting local memory nodes and filtering
+    by memory attributes.
+  + hwloc-bind has a new --best-memattr option for filtering by memory attributes
+    among the memory binding set.
+  + Tools that have a --restrict option may now receive a nodeset or
+    some custom flags for restricting the topology.
+  + lstopo now has a --thickness option for changing line thickness in the
+    graphical output.
+  + Fix lstopo drawing when autoresizing on Windows 10.
+  + Pressing the F5 key in lstopo X11 and Windows graphical/interactive outputs
+    now refreshes the display according to the current topology and binding.
+  + Add a tikz lstopo graphical backend to generate picture easily included into
+    LaTeX documents. Thanks to Clement Foyer.
+* Misc
+  + The default installation path of the Bash completion file has changed to
+    ${datadir}/bash-completion/completions/hwloc. Thanks to Tomasz Kłoczko.
+
+
 Version 2.2.0
 -------------
 * API

src/3rdparty/hwloc/README

@@ -23,9 +23,9 @@ APIs are documented after these sections.
 
 Installation
 
-hwloc (http://www.open-mpi.org/projects/hwloc/) is available under the BSD
-license. It is hosted as a sub-project of the overall Open MPI project (http://
-www.open-mpi.org/). Note that hwloc does not require any functionality from
+hwloc (https://www.open-mpi.org/projects/hwloc/) is available under the BSD
+license. It is hosted as a sub-project of the overall Open MPI project (https:/
+/www.open-mpi.org/). Note that hwloc does not require any functionality from
 Open MPI -- it is a wholly separate (and much smaller!) project and code base.
 It just happens to be hosted as part of the overall Open MPI project.
 
@@ -75,7 +75,7 @@ Bugs should be reported in the tracker (https://github.com/open-mpi/hwloc/
 issues). Opening a new issue automatically displays lots of hints about how to
 debug and report issues.
 
-Questions may be sent to the users or developers mailing lists (http://
+Questions may be sent to the users or developers mailing lists (https://
 www.open-mpi.org/community/lists/hwloc.php).
 
 There is also a #hwloc IRC channel on Freenode (irc.freenode.net).

src/3rdparty/hwloc/VERSION

@@ -8,7 +8,7 @@
 # Please update HWLOC_VERSION* in contrib/windows/hwloc_config.h too.
 
 major=2
-minor=2
+minor=4
 release=0
 
 # greek is used for alpha or beta release tags.  If it is non-empty,
@@ -22,7 +22,7 @@ greek=
 
 # The date when this release was created
 
-date="Mar 30, 2020"
+date="Nov 26, 2020"
 
 # If snapshot=1, then use the value from snapshot_version as the
 # entire hwloc version (i.e., ignore major, minor, release, and
@@ -41,7 +41,7 @@ snapshot_version=${major}.${minor}.${release}${greek}-git
 # 2. Version numbers are described in the Libtool current:revision:age
 # format.
 
-libhwloc_so_version=17:0:2
+libhwloc_so_version=19:0:4
 libnetloc_so_version=0:0:0
 
 # Please also update the <TargetName> lines in contrib/windows/libhwloc.vcxproj

src/3rdparty/hwloc/include/hwloc.h

@@ -2,7 +2,7 @@
  * Copyright © 2009 CNRS
  * Copyright © 2009-2020 Inria.  All rights reserved.
  * Copyright © 2009-2012 Université Bordeaux
- * Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
+ * Copyright © 2009-2020 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -11,7 +11,7 @@
  *         ------------------------------------------------
  *               $tarball_directory/doc/doxygen-doc/
  *                                or
- *           http://www.open-mpi.org/projects/hwloc/doc/
+ *           https://www.open-mpi.org/projects/hwloc/doc/
  *=====================================================================
  *
  * FAIR WARNING: Do NOT expect to be able to figure out all the
@@ -93,7 +93,7 @@ extern "C" {
  * Two stable releases of the same series usually have the same ::HWLOC_API_VERSION
  * even if their HWLOC_VERSION are different.
  */
-#define HWLOC_API_VERSION 0x00020100
+#define HWLOC_API_VERSION 0x00020400
 
 /** \brief Indicate at runtime which hwloc API version was used at build time.
  *
@@ -102,7 +102,7 @@ extern "C" {
 HWLOC_DECLSPEC unsigned hwloc_get_api_version(void);
 
 /** \brief Current component and plugin ABI version (see hwloc/plugins.h) */
-#define HWLOC_COMPONENT_ABI 6
+#define HWLOC_COMPONENT_ABI 7
 
 /** @} */
 
@@ -196,7 +196,7 @@ typedef enum {
 			  */
   HWLOC_OBJ_CORE,	/**< \brief Core.
 			  * A computation unit (may be shared by several
-			  * logical processors).
+			  * PUs, aka logical processors).
 			  */
   HWLOC_OBJ_PU,		/**< \brief Processing Unit, or (Logical) Processor.
 			  * An execution unit (may share a core with some
@@ -257,22 +257,31 @@ typedef enum {
   HWLOC_OBJ_BRIDGE,	/**< \brief Bridge (filtered out by default).
 			  * Any bridge (or PCI switch) that connects the host or an I/O bus,
 			  * to another I/O bus.
-			  * They are not added to the topology unless I/O discovery
-			  * is enabled with hwloc_topology_set_flags().
+			  *
+			  * Bridges are not added to the topology unless their
+			  * filtering is changed (see hwloc_topology_set_type_filter()
+			  * and hwloc_topology_set_io_types_filter()).
+			  *
 			  * I/O objects are not listed in the main children list,
 			  * but rather in the dedicated io children list.
 			  * I/O objects have NULL CPU and node sets.
 			  */
   HWLOC_OBJ_PCI_DEVICE,	/**< \brief PCI device (filtered out by default).
-			  * They are not added to the topology unless I/O discovery
-			  * is enabled with hwloc_topology_set_flags().
+			  *
+			  * PCI devices are not added to the topology unless their
+			  * filtering is changed (see hwloc_topology_set_type_filter()
+			  * and hwloc_topology_set_io_types_filter()).
+			  *
 			  * I/O objects are not listed in the main children list,
 			  * but rather in the dedicated io children list.
 			  * I/O objects have NULL CPU and node sets.
 			  */
   HWLOC_OBJ_OS_DEVICE,	/**< \brief Operating system device (filtered out by default).
-			  * They are not added to the topology unless I/O discovery
-			  * is enabled with hwloc_topology_set_flags().
+			  *
+			  * OS devices are not added to the topology unless their
+			  * filtering is changed (see hwloc_topology_set_type_filter()
+			  * and hwloc_topology_set_io_types_filter()).
+			  *
 			  * I/O objects are not listed in the main children list,
 			  * but rather in the dedicated io children list.
 			  * I/O objects have NULL CPU and node sets.
@@ -282,6 +291,10 @@ typedef enum {
 			  * Objects without particular meaning, that can e.g. be
 			  * added by the application for its own use, or by hwloc
 			  * for miscellaneous objects such as MemoryModule (DIMMs).
+			  *
+			  * They are not added to the topology unless their filtering
+			  * is changed (see hwloc_topology_set_type_filter()).
+			  *
 			  * These objects are not listed in the main children list,
 			  * but rather in the dedicated misc children list.
 			  * Misc objects may only have Misc objects as children,
@@ -304,7 +317,6 @@ typedef enum {
 
   HWLOC_OBJ_DIE,	/**< \brief Die within a physical package.
 			 * A subpart of the physical package, that contains multiple cores.
-			 * \hideinitializer
 			 */
 
   HWLOC_OBJ_TYPE_MAX    /**< \private Sentinel value */
@@ -338,8 +350,7 @@ typedef enum hwloc_obj_osdev_type_e {
   HWLOC_OBJ_OSDEV_DMA,		/**< \brief Operating system dma engine device.
 				  * For instance the "dma0chan0" DMA channel on Linux. */
   HWLOC_OBJ_OSDEV_COPROC	/**< \brief Operating system co-processor device.
-				  * For instance "mic0" for a Xeon Phi (MIC) on Linux,
-				  * "opencl0d0" for a OpenCL device,
+				  * For instance "opencl0d0" for a OpenCL device,
 				  * "cuda0" for a CUDA device. */
 } hwloc_obj_osdev_type_t;
 
@@ -512,7 +523,7 @@ struct hwloc_obj {
 					  *
                                           * \note Its value must not be changed, hwloc_bitmap_dup() must be used instead.
                                           */
-  hwloc_cpuset_t complete_cpuset;       /**< \brief The complete CPU set of logical processors of this object,
+  hwloc_cpuset_t complete_cpuset;       /**< \brief The complete CPU set of processors of this object,
                                           *
                                           * This may include not only the same as the cpuset field, but also some CPUs for
                                           * which topology information is unknown or incomplete, some offlines CPUs, and
@@ -533,6 +544,8 @@ struct hwloc_obj {
                                           * between this object and the NUMA node objects).
                                           *
                                           * In the end, these nodes are those that are close to the current object.
+                                          * Function hwloc_get_local_numanode_objs() may be used to list those NUMA
+                                          * nodes more precisely.
                                           *
                                           * If the ::HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED configuration flag is set,
                                           * some of these nodes may not be allowed for allocation,
@@ -1929,7 +1942,31 @@ enum hwloc_topology_flags_e {
    * would result in the same behavior.
    * \hideinitializer
    */
-  HWLOC_TOPOLOGY_FLAG_THISSYSTEM_ALLOWED_RESOURCES = (1UL<<2)
+  HWLOC_TOPOLOGY_FLAG_THISSYSTEM_ALLOWED_RESOURCES = (1UL<<2),
+
+  /** \brief Import support from the imported topology.
+   *
+   * When importing a XML topology from a remote machine, binding is
+   * disabled by default (see ::HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM).
+   * This disabling is also marked by putting zeroes in the corresponding
+   * supported feature bits reported by hwloc_topology_get_support().
+   *
+   * The flag ::HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT actually imports
+   * support bits from the remote machine. It also sets the flag
+   * \p imported_support in the struct hwloc_topology_misc_support array.
+   * If the imported XML did not contain any support information
+   * (exporter hwloc is too old), this flag is not set.
+   *
+   * Note that these supported features are only relevant for the hwloc
+   * installation that actually exported the XML topology
+   * (it may vary with the operating system, or with how hwloc was compiled).
+   *
+   * Note that setting this flag however does not enable binding for the
+   * locally imported hwloc topology, it only reports what the remote
+   * hwloc and machine support.
+   *
+   */
+  HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT = (1UL<<3)
 };
 
 /** \brief Set OR'ed flags to non-yet-loaded topology.
@@ -1972,6 +2009,8 @@ struct hwloc_topology_discovery_support {
   unsigned char disallowed_pu;
   /** \brief Detecting and identifying NUMA nodes that are not available to the current process is supported. */
   unsigned char disallowed_numa;
+  /** \brief Detecting the efficiency of CPU kinds is supported, see \ref hwlocality_cpukinds. */
+  unsigned char cpukind_efficiency;
 };
 
 /** \brief Flags describing actual PU binding support for this topology.
@@ -2042,6 +2081,13 @@ struct hwloc_topology_membind_support {
   unsigned char get_area_memlocation;
 };
 
+/** \brief Flags describing miscellaneous features.
+ */
+struct hwloc_topology_misc_support {
+  /** Support was imported when importing another topology, see ::HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT. */
+  unsigned char imported_support;
+};
+
 /** \brief Set of flags describing actual support for this topology.
  *
  * This is retrieved with hwloc_topology_get_support() and will be valid until
@@ -2052,6 +2098,7 @@ struct hwloc_topology_support {
   struct hwloc_topology_discovery_support *discovery;
   struct hwloc_topology_cpubind_support *cpubind;
   struct hwloc_topology_membind_support *membind;
+  struct hwloc_topology_misc_support *misc;
 };
 
 /** \brief Retrieve the topology support.
@@ -2062,6 +2109,18 @@ struct hwloc_topology_support {
  * call may still fail in some corner cases.
  *
  * These features are also listed by hwloc-info \--support
+ *
+ * The reported features are what the current topology supports
+ * on the current machine. If the topology was exported to XML
+ * from another machine and later imported here, support still
+ * describes what is supported for this imported topology after
+ * import. By default, binding will be reported as unsupported
+ * in this case (see ::HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM).
+ *
+ * Topology flag ::HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT may be used
+ * to report the supported features of the original remote machine
+ * instead. If it was successfully imported, \p imported_support
+ * will be set in the struct hwloc_topology_misc_support array.
  */
 HWLOC_DECLSPEC const struct hwloc_topology_support *hwloc_topology_get_support(hwloc_topology_t __hwloc_restrict topology);
 
@@ -2108,8 +2167,8 @@ enum hwloc_type_filter_e {
    *
    * It is only useful for I/O object types.
    * For ::HWLOC_OBJ_PCI_DEVICE and ::HWLOC_OBJ_OS_DEVICE, it means that only objects
-   * of major/common kinds are kept (storage, network, OpenFabrics, Intel MICs, CUDA,
-   * OpenCL, NVML, and displays).
+   * of major/common kinds are kept (storage, network, OpenFabrics, CUDA,
+   * OpenCL, RSMI, NVML, and displays).
    * Also, only OS devices directly attached on PCI (e.g. no USB) are reported.
    * For ::HWLOC_OBJ_BRIDGE, it means that bridges are kept only if they have children.
    *
@@ -2371,6 +2430,22 @@ HWLOC_DECLSPEC hwloc_obj_t hwloc_topology_insert_group_object(hwloc_topology_t t
  */
 HWLOC_DECLSPEC int hwloc_obj_add_other_obj_sets(hwloc_obj_t dst, hwloc_obj_t src);
 
+/** \brief Refresh internal structures after topology modification.
+ *
+ * Modifying the topology (by restricting, adding objects, modifying structures
+ * such as distances or memory attributes, etc.) may cause some internal caches
+ * to become invalid. These caches are automatically refreshed when accessed
+ * but this refreshing is not thread-safe.
+ *
+ * This function is not thread-safe either, but it is a good way to end a
+ * non-thread-safe phase of topology modification. Once this refresh is done,
+ * multiple threads may concurrently consult the topology, objects, distances,
+ * attributes, etc.
+ *
+ * See also \ref threadsafety
+ */
+HWLOC_DECLSPEC int hwloc_topology_refresh(hwloc_topology_t topology);
+
 /** @} */
 
 
@@ -2386,6 +2461,12 @@ HWLOC_DECLSPEC int hwloc_obj_add_other_obj_sets(hwloc_obj_t dst, hwloc_obj_t src
 /* inline code of some functions above */
 #include "hwloc/inlines.h"
 
+/* memory attributes */
+#include "hwloc/memattrs.h"
+
+/* kinds of CPU cores */
+#include "hwloc/cpukinds.h"
+
 /* exporting to XML or synthetic */
 #include "hwloc/export.h"
 

src/3rdparty/hwloc/include/hwloc/autogen/config.h

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2019 Inria.  All rights reserved.
+ * Copyright © 2009-2020 Inria.  All rights reserved.
  * Copyright © 2009-2012 Université Bordeaux
  * Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -11,9 +11,9 @@
 #ifndef HWLOC_CONFIG_H
 #define HWLOC_CONFIG_H
 
-#define HWLOC_VERSION "2.2.0"
+#define HWLOC_VERSION "2.4.0"
 #define HWLOC_VERSION_MAJOR 2
-#define HWLOC_VERSION_MINOR 2
+#define HWLOC_VERSION_MINOR 4
 #define HWLOC_VERSION_RELEASE 0
 #define HWLOC_VERSION_GREEK ""
 

src/3rdparty/hwloc/include/hwloc/bitmap.h

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2018 Inria.  All rights reserved.
+ * Copyright © 2009-2020 Inria.  All rights reserved.
  * Copyright © 2009-2012 Université Bordeaux
  * Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -231,7 +231,7 @@ HWLOC_DECLSPEC int hwloc_bitmap_clr_range(hwloc_bitmap_t bitmap, unsigned begin,
 /** \brief Keep a single index among those set in bitmap \p bitmap
  *
  * May be useful before binding so that the process does not
- * have a chance of migrating between multiple logical CPUs
+ * have a chance of migrating between multiple processors
  * in the original mask.
  * Instead of running the task on any PU inside the given CPU set,
  * the operating system scheduler will be forced to run it on a single

src/3rdparty/hwloc/include/hwloc/cpukinds.h

@@ -0,0 +1,188 @@
+/*
+ * Copyright © 2020 Inria.  All rights reserved.
+ * See COPYING in top-level directory.
+ */
+
+/** \file
+ * \brief Kinds of CPU cores.
+ */
+
+#ifndef HWLOC_CPUKINDS_H
+#define HWLOC_CPUKINDS_H
+
+#include "hwloc.h"
+
+#ifdef __cplusplus
+extern "C" {
+#elif 0
+}
+#endif
+
+/** \defgroup hwlocality_cpukinds Kinds of CPU cores
+ *
+ * Platforms with heterogeneous CPUs may have some cores with
+ * different features or frequencies.
+ * This API exposes identical PUs in sets called CPU kinds.
+ * Each PU of the topology may only be in a single kind.
+ *
+ * The number of kinds may be obtained with hwloc_cpukinds_get_nr().
+ * If the platform is homogeneous, there may be a single kind
+ * with all PUs.
+ * If the platform or operating system does not expose any
+ * information about CPU cores, there may be no kind at all.
+ *
+ * The index of the kind that describes a given CPU set
+ * (if any, and not partially)
+ * may be obtained with hwloc_cpukinds_get_by_cpuset().
+ *
+ * From the index of a kind, it is possible to retrieve information
+ * with hwloc_cpukinds_get_info():
+ * an abstracted efficiency value,
+ * and an array of info attributes
+ * (for instance the "CoreType" and "FrequencyMaxMHz",
+ *  see \ref topoattrs_cpukinds).
+ *
+ * A higher efficiency value means intrinsic greater performance
+ * (and possibly less performance/power efficiency).
+ * Kinds with lower efficiency are ranked first:
+ * Passing 0 as \p kind_index to hwloc_cpukinds_get_info() will
+ * return information about the less efficient CPU kind.
+ *
+ * When available, efficiency values are gathered from the operating
+ * system (when \p cpukind_efficiency is set in the
+ * struct hwloc_topology_discovery_support array, only on Windows 10 for now).
+ * Otherwise hwloc tries to compute efficiencies
+ * by comparing CPU kinds using frequencies (on ARM),
+ * or core types and frequencies (on other architectures).
+ * The environment variable HWLOC_CPUKINDS_RANKING may be used
+ * to change this heuristics, see \ref envvar.
+ *
+ * If hwloc fails to rank any kind, for instance because the operating
+ * system does not expose efficiencies and core frequencies,
+ * all kinds will have an unknown efficiency (\c -1),
+ * and they are not indexed/ordered in any specific way.
+ *
+ * @{
+ */
+
+/** \brief Get the number of different kinds of CPU cores in the topology.
+ *
+ * \p flags must be \c 0 for now.
+ *
+ * \return The number of CPU kinds (positive integer) on success.
+ * \return \c 0 if no information about kinds was found.
+ * \return \c -1 with \p errno set to \c EINVAL if \p flags is invalid.
+ */
+HWLOC_DECLSPEC int
+hwloc_cpukinds_get_nr(hwloc_topology_t topology,
+                      unsigned long flags);
+
+/** \brief Get the index of the CPU kind that contains CPUs listed in \p cpuset.
+ *
+ * \p flags must be \c 0 for now.
+ *
+ * \return The index of the CPU kind (positive integer or 0) on success.
+ * \return \c -1 with \p errno set to \c EXDEV if \p cpuset is
+ * only partially included in the some kind.
+ * \return \c -1 with \p errno set to \c ENOENT if \p cpuset is
+ * not included in any kind, even partially.
+ * \return \c -1 with \p errno set to \c EINVAL if parameters are invalid.
+ */
+HWLOC_DECLSPEC int
+hwloc_cpukinds_get_by_cpuset(hwloc_topology_t topology,
+                             hwloc_const_bitmap_t cpuset,
+                             unsigned long flags);
+
+/** \brief Get the CPU set and infos about a CPU kind in the topology.
+ *
+ * \p kind_index identifies one kind of CPU between 0 and the number
+ * of kinds returned by hwloc_cpukinds_get_nr() minus 1.
+ *
+ * If not \c NULL, the bitmap \p cpuset will be filled with
+ * the set of PUs of this kind.
+ *
+ * The integer pointed by \p efficiency, if not \c NULL will, be filled
+ * with the ranking of this kind of CPU in term of efficiency (see above).
+ * It ranges from \c 0 to the number of kinds
+ * (as reported by hwloc_cpukinds_get_nr()) minus 1.
+ *
+ * Kinds with lower efficiency are reported first.
+ *
+ * If there is a single kind in the topology, its efficiency \c 0.
+ * If the efficiency of some kinds of cores is unknown,
+ * the efficiency of all kinds is set to \c -1,
+ * and kinds are reported in no specific order.
+ *
+ * The array of info attributes (for instance the "CoreType",
+ * "FrequencyMaxMHz" or "FrequencyBaseMHz", see \ref topoattrs_cpukinds)
+ * and its length are returned in \p infos or \p nr_infos.
+ * The array belongs to the topology, it should not be freed or modified.
+ *
+ * If \p nr_infos or \p infos is \c NULL, no info is returned.
+ *
+ * \p flags must be \c 0 for now.
+ *
+ * \return \c 0 on success.
+ * \return \c -1 with \p errno set to \c ENOENT if \p kind_index does not match any CPU kind.
+ * \return \c -1 with \p errno set to \c EINVAL if parameters are invalid.
+ */
+HWLOC_DECLSPEC int
+hwloc_cpukinds_get_info(hwloc_topology_t topology,
+                        unsigned kind_index,
+                        hwloc_bitmap_t cpuset,
+                        int *efficiency,
+                        unsigned *nr_infos, struct hwloc_info_s **infos,
+                        unsigned long flags);
+
+/** \brief Register a kind of CPU in the topology.
+ *
+ * Mark the PUs listed in \p cpuset as being of the same kind
+ * with respect to the given attributes.
+ *
+ * \p forced_efficiency should be \c -1 if unknown.
+ * Otherwise it is an abstracted efficiency value to enforce
+ * the ranking of all kinds if all of them have valid (and
+ * different) efficiencies.
+ *
+ * The array \p infos of size \p nr_infos may be used to provide
+ * info names and values describing this kind of PUs.
+ *
+ * \p flags must be \c 0 for now.
+ *
+ * Parameters \p cpuset and \p infos will be duplicated internally,
+ * the caller is responsible for freeing them.
+ *
+ * If \p cpuset overlaps with some existing kinds, those might get
+ * modified or split. For instance if existing kind A contains
+ * PUs 0 and 1, and one registers another kind for PU 1 and 2,
+ * there will be 3 resulting kinds:
+ * existing kind A is restricted to only PU 0;
+ * new kind B contains only PU 1 and combines information from A
+ * and from the newly-registered kind;
+ * new kind C contains only PU 2 and only gets information from
+ * the newly-registered kind.
+ *
+ * \note The efficiency \p forced_efficiency provided to this function
+ * may be different from the one reported later by hwloc_cpukinds_get_info()
+ * because hwloc will scale efficiency values down to
+ * between 0 and the number of kinds minus 1.
+ *
+ * \return \c 0 on success.
+ * \return \c -1 with \p errno set to \c EINVAL if some parameters are invalid,
+ * for instance if \p cpuset is \c NULL or empty.
+ */
+HWLOC_DECLSPEC int
+hwloc_cpukinds_register(hwloc_topology_t topology,
+                        hwloc_bitmap_t cpuset,
+                        int forced_efficiency,
+                        unsigned nr_infos, struct hwloc_info_s *infos,
+                        unsigned long flags);
+
+/** @} */
+
+#ifdef __cplusplus
+} /* extern "C" */
+#endif
+
+
+#endif /* HWLOC_CPUKINDS_H */

src/3rdparty/hwloc/include/hwloc/cuda.h

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2010-2017 Inria.  All rights reserved.
+ * Copyright © 2010-2020 Inria.  All rights reserved.
  * Copyright © 2010-2011 Université Bordeaux
  * Copyright © 2011 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -72,7 +72,7 @@ hwloc_cuda_get_device_pci_ids(hwloc_topology_t topology __hwloc_attribute_unused
   return 0;
 }
 
-/** \brief Get the CPU set of logical processors that are physically
+/** \brief Get the CPU set of processors that are physically
  * close to device \p cudevice.
  *
  * Return the CPU set describing the locality of the CUDA device \p cudevice.

src/3rdparty/hwloc/include/hwloc/cudart.h

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2010-2017 Inria.  All rights reserved.
+ * Copyright © 2010-2020 Inria.  All rights reserved.
  * Copyright © 2010-2011 Université Bordeaux
  * Copyright © 2011 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -69,7 +69,7 @@ hwloc_cudart_get_device_pci_ids(hwloc_topology_t topology __hwloc_attribute_unus
   return 0;
 }
 
-/** \brief Get the CPU set of logical processors that are physically
+/** \brief Get the CPU set of processors that are physically
  * close to device \p idx.
  *
  * Return the CPU set describing the locality of the CUDA device

src/3rdparty/hwloc/include/hwloc/diff.h

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2013-2018 Inria.  All rights reserved.
+ * Copyright © 2013-2020 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -110,7 +110,7 @@ union hwloc_topology_diff_obj_attr_u {
  */
 typedef enum hwloc_topology_diff_type_e {
   /** \brief An object attribute was changed.
-   * The union is a hwloc_topology_diff_obj_attr_u::hwloc_topology_diff_obj_attr_s.
+   * The union is a hwloc_topology_diff_u::hwloc_topology_diff_obj_attr_s.
    */
   HWLOC_TOPOLOGY_DIFF_OBJ_ATTR,
 
@@ -119,7 +119,7 @@ typedef enum hwloc_topology_diff_type_e {
    * this object has not been checked.
    * hwloc_topology_diff_build() will return 1.
    *
-   * The union is a hwloc_topology_diff_obj_attr_u::hwloc_topology_diff_too_complex_s.
+   * The union is a hwloc_topology_diff_u::hwloc_topology_diff_too_complex_s.
    */
   HWLOC_TOPOLOGY_DIFF_TOO_COMPLEX
 } hwloc_topology_diff_type_t;

src/3rdparty/hwloc/include/hwloc/distances.h

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2010-2019 Inria.  All rights reserved.
+ * Copyright © 2010-2020 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -34,6 +34,7 @@ extern "C" {
  * It corresponds to the latency for accessing the memory of one node
  * from a core in another node.
  * The corresponding kind is ::HWLOC_DISTANCES_KIND_FROM_OS | ::HWLOC_DISTANCES_KIND_FROM_USER.
+ * The name of this distances structure is "NUMALatency".
  *
  * The matrix may also contain bandwidths between random sets of objects,
  * possibly provided by the user, as specified in the \p kind attribute.
@@ -144,6 +145,8 @@ hwloc_distances_get_by_type(hwloc_topology_t topology, hwloc_obj_type_t type,
 /** \brief Retrieve a distance matrix with the given name.
  *
  * Usually only one distances structure may match a given name.
+ *
+ * The name of the most common structure is "NUMALatency".
  */
 HWLOC_DECLSPEC int
 hwloc_distances_get_by_name(hwloc_topology_t topology, const char *name,

src/3rdparty/hwloc/include/hwloc/glibc-sched.h

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2013 inria.  All rights reserved.
+ * Copyright © 2009-2020 Inria.  All rights reserved.
  * Copyright © 2009-2011 Université Bordeaux
  * Copyright © 2011 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -22,7 +22,7 @@
 
 #include <assert.h>
 
-#if !defined _GNU_SOURCE || !defined _SCHED_H || (!defined CPU_SETSIZE && !defined sched_priority)
+#if !defined _GNU_SOURCE || (!defined _SCHED_H && !defined _SCHED_H_) || (!defined CPU_SETSIZE && !defined sched_priority)
 #error Please make sure to include sched.h before including glibc-sched.h, and define _GNU_SOURCE before any inclusion of sched.h
 #endif
 

src/3rdparty/hwloc/include/hwloc/helper.h

@@ -872,8 +872,8 @@ hwloc_distrib(hwloc_topology_t topology,
     unsigned chunk, weight;
     hwloc_obj_t root = roots[flags & HWLOC_DISTRIB_FLAG_REVERSE ? n_roots-1-i : i];
     hwloc_cpuset_t cpuset = root->cpuset;
-    if (root->type == HWLOC_OBJ_NUMANODE)
-      /* NUMANodes have same cpuset as their parent, but we need normal objects below */
+    while (!hwloc_obj_type_is_normal(root->type))
+      /* If memory/io/misc, walk up to normal parent */
       root = root->parent;
     weight = (unsigned) hwloc_bitmap_weight(cpuset);
     if (!weight)
@@ -919,7 +919,7 @@ hwloc_distrib(hwloc_topology_t topology,
 
 /** \brief Get complete CPU set
  *
- * \return the complete CPU set of logical processors of the system.
+ * \return the complete CPU set of processors of the system.
  *
  * \note The returned cpuset is not newly allocated and should thus not be
  * changed or freed; hwloc_bitmap_dup() must be used to obtain a local copy.
@@ -931,7 +931,7 @@ hwloc_topology_get_complete_cpuset(hwloc_topology_t topology) __hwloc_attribute_
 
 /** \brief Get topology CPU set
  *
- * \return the CPU set of logical processors of the system for which hwloc
+ * \return the CPU set of processors of the system for which hwloc
  * provides topology information. This is equivalent to the cpuset of the
  * system object.
  *
@@ -945,7 +945,7 @@ hwloc_topology_get_topology_cpuset(hwloc_topology_t topology) __hwloc_attribute_
 
 /** \brief Get allowed CPU set
  *
- * \return the CPU set of allowed logical processors of the system.
+ * \return the CPU set of allowed processors of the system.
  *
  * \note If the topology flag ::HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED was not set,
  * this is identical to hwloc_topology_get_topology_cpuset(), which means

src/3rdparty/hwloc/include/hwloc/nvml.h

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2012-2016 Inria.  All rights reserved.
+ * Copyright © 2012-2020 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -36,7 +36,7 @@ extern "C" {
  * @{
  */
 
-/** \brief Get the CPU set of logical processors that are physically
+/** \brief Get the CPU set of processors that are physically
  * close to NVML device \p device.
  *
  * Return the CPU set describing the locality of the NVML device \p device.