Merge branch 'Spudz76-dev-addApiRebind' into dev

fix(cuda): receive CUDA loader error on linux too.

CHANGELOG.md

@@ -1,3 +1,34 @@
+# v6.19.3
+- [#3245](https://github.com/xmrig/xmrig/issues/3245) Improved algorithm negotiation for donation rounds by sending extra information about current mining job.
+- [#3254](https://github.com/xmrig/xmrig/pull/3254) Tweaked auto-tuning for Intel CPUs.
+- [#3271](https://github.com/xmrig/xmrig/pull/3271) RandomX: optimized program generation.
+- [#3273](https://github.com/xmrig/xmrig/pull/3273) RandomX: fixed undefined behavior.
+- [#3275](https://github.com/xmrig/xmrig/pull/3275) RandomX: fixed `jccErratum` list.
+- [#3280](https://github.com/xmrig/xmrig/pull/3280) Updated example scripts.
+
+# v6.19.2
+- [#3230](https://github.com/xmrig/xmrig/pull/3230) Fixed parsing of `TX_EXTRA_MERGE_MINING_TAG`.
+- [#3232](https://github.com/xmrig/xmrig/pull/3232) Added new `X-Hash-Difficulty` HTTP header.
+- [#3240](https://github.com/xmrig/xmrig/pull/3240) Improved .cmd files when run by shortcuts on another drive.
+- [#3241](https://github.com/xmrig/xmrig/pull/3241) Added view tag calculation (fixes Wownero solo mining issue).
+
+# v6.19.1
+- Resolved deprecated methods warnings with OpenSSL 3.0.
+- [#3213](https://github.com/xmrig/xmrig/pull/3213) Fixed build with 32-bit clang 15.
+- [#3218](https://github.com/xmrig/xmrig/pull/3218) Fixed: `--randomx-wrmsr=-1` worked only on Intel.
+- [#3228](https://github.com/xmrig/xmrig/pull/3228) Fixed build with gcc 13.
+
+# v6.19.0
+- [#3144](https://github.com/xmrig/xmrig/pull/3144) Update to latest `sse2neon.h`.
+- [#3161](https://github.com/xmrig/xmrig/pull/3161) MSVC build: enabled parallel compilation.
+- [#3163](https://github.com/xmrig/xmrig/pull/3163) Improved Zen 3 MSR mod.
+- [#3176](https://github.com/xmrig/xmrig/pull/3176) Update cmake required version to 3.1.
+- [#3182](https://github.com/xmrig/xmrig/pull/3182) DragonflyBSD compilation fixes.
+- [#3196](https://github.com/xmrig/xmrig/pull/3196) Show IP address for failed connections.
+- [#3185](https://github.com/xmrig/xmrig/issues/3185) Fixed macOS DMI reader.
+- [#3198](https://github.com/xmrig/xmrig/pull/3198) Fixed broken RandomX light mode mining.
+- [#3202](https://github.com/xmrig/xmrig/pull/3202) Solo mining: added job timeout (default is 15 seconds).
+
 # v6.18.1
 - [#3129](https://github.com/xmrig/xmrig/pull/3129) Fix: protectRX flushed CPU cache only on MacOS/iOS.
 - [#3126](https://github.com/xmrig/xmrig/pull/3126) Don't reset when pool sends the same job blob.

CMakeLists.txt

@@ -1,4 +1,4 @@
-cmake_minimum_required(VERSION 2.8.12)
+cmake_minimum_required(VERSION 3.1)
 project(xmrig)
 
 option(WITH_HWLOC           "Enable hwloc support" ON)
@@ -34,7 +34,8 @@ option(WITH_SECURE_JIT      "Enable secure access to JIT memory" OFF)
 option(WITH_DMI             "Enable DMI/SMBIOS reader" ON)
 
 option(BUILD_STATIC         "Build static binary" OFF)
-option(ARM_TARGET           "Force use specific ARM target 8 or 7" 0)
+option(ARM_V8               "Force ARMv8 (64 bit) architecture, use with caution if automatic detection fails, but you sure it may work" OFF)
+option(ARM_V7               "Force ARMv7 (32 bit) architecture, use with caution if automatic detection fails, but you sure it may work" OFF)
 option(HWLOC_DEBUG          "Enable hwloc debug helpers and log" OFF)
 
 

README.md

@@ -10,7 +10,7 @@
 XMRig is a high performance, open source, cross platform RandomX, KawPow, CryptoNight and [GhostRider](https://github.com/xmrig/xmrig/tree/master/src/crypto/ghostrider#readme) unified CPU/GPU miner and [RandomX benchmark](https://xmrig.com/benchmark). Official binaries are available for Windows, Linux, macOS and FreeBSD.
 
 ## Mining backends
-- **CPU** (x64/ARMv7/ARMv8)
+- **CPU** (x86/x64/ARMv7/ARMv8)
 - **OpenCL** for AMD GPUs.
 - **CUDA** for NVIDIA GPUs via external [CUDA plugin](https://github.com/xmrig/xmrig-cuda).
 

cmake/cpu.cmake

@@ -29,6 +29,12 @@ else()
     set(WITH_VAES OFF)
 endif()
 
+if (ARM_V8)
+    set(ARM_TARGET 8)
+elseif (ARM_V7)
+    set(ARM_TARGET 7)
+endif()
+
 if (NOT ARM_TARGET)
     if (CMAKE_SYSTEM_PROCESSOR MATCHES "^(aarch64|arm64|armv8-a)$")
         set(ARM_TARGET 8)

cmake/flags.cmake

@@ -10,7 +10,7 @@ if ("${CMAKE_BUILD_TYPE}" STREQUAL "")
 endif()
 
 if (CMAKE_BUILD_TYPE STREQUAL "Release")
-    add_definitions(/DNDEBUG)
+    add_definitions(-DNDEBUG)
 endif()
 
 include(CheckSymbolExists)
@@ -32,7 +32,7 @@ if (CMAKE_CXX_COMPILER_ID MATCHES GNU)
         set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -maes")
         set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -maes")
 
-        add_definitions(/DHAVE_ROTR)
+        add_definitions(-DHAVE_ROTR)
     endif()
 
     if (WIN32)
@@ -49,28 +49,16 @@ if (CMAKE_CXX_COMPILER_ID MATCHES GNU)
         set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -static")
     endif()
 
-    add_definitions(/D_GNU_SOURCE)
-
-    if (${CMAKE_VERSION} VERSION_LESS "3.1.0")
-        set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -std=c99")
-        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
-    endif()
-
-    #set(CMAKE_C_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -gdwarf-2")
-
-    add_definitions(/DHAVE_BUILTIN_CLEAR_CACHE)
+    add_definitions(-D_GNU_SOURCE -DHAVE_BUILTIN_CLEAR_CACHE)
 
 elseif (CMAKE_CXX_COMPILER_ID MATCHES MSVC)
-    set(CMAKE_C_FLAGS_RELEASE "/MT /O2 /Oi /DNDEBUG /GL")
-    set(CMAKE_CXX_FLAGS_RELEASE "/MT /O2 /Oi /DNDEBUG /GL")
+    set(CMAKE_C_FLAGS_RELEASE "/MP /MT /O2 /Oi /DNDEBUG /GL")
+    set(CMAKE_CXX_FLAGS_RELEASE "/MP /MT /O2 /Oi /DNDEBUG /GL")
 
-    set(CMAKE_C_FLAGS_RELWITHDEBINFO "/Ob1 /Zi /DRELWITHDEBINFO")
-    set(CMAKE_CXX_FLAGS_RELWITHDEBINFO "/Ob1 /Zi /DRELWITHDEBINFO")
+    set(CMAKE_C_FLAGS_RELWITHDEBINFO "/MP /Ob1 /Zi /DRELWITHDEBINFO")
+    set(CMAKE_CXX_FLAGS_RELWITHDEBINFO "/MP /Ob1 /Zi /DRELWITHDEBINFO")
 
-    add_definitions(/D_CRT_SECURE_NO_WARNINGS)
-    add_definitions(/D_CRT_NONSTDC_NO_WARNINGS)
-    add_definitions(/DNOMINMAX)
-    add_definitions(/DHAVE_ROTR)
+    add_definitions(-D_CRT_SECURE_NO_WARNINGS -D_CRT_NONSTDC_NO_WARNINGS -DNOMINMAX -DHAVE_ROTR)
 
 elseif (CMAKE_CXX_COMPILER_ID MATCHES Clang)
 
@@ -92,7 +80,7 @@ elseif (CMAKE_CXX_COMPILER_ID MATCHES Clang)
 
         check_symbol_exists("_rotr" "x86intrin.h" HAVE_ROTR)
         if (HAVE_ROTR)
-            add_definitions(/DHAVE_ROTR)
+            add_definitions(-DHAVE_ROTR)
         endif()
     endif()
 
@@ -105,6 +93,6 @@ endif()
 if (NOT WIN32)
     check_symbol_exists("__builtin___clear_cache" "stdlib.h" HAVE_BUILTIN_CLEAR_CACHE)
     if (HAVE_BUILTIN_CLEAR_CACHE)
-        add_definitions(/DHAVE_BUILTIN_CLEAR_CACHE)
+        add_definitions(-DHAVE_BUILTIN_CLEAR_CACHE)
     endif()
 endif()

cmake/os.cmake

@@ -15,7 +15,7 @@ else()
         set(XMRIG_OS_ANDROID ON)
     elseif(CMAKE_SYSTEM_NAME MATCHES "Linux")
         set(XMRIG_OS_LINUX ON)
-    elseif(CMAKE_SYSTEM_NAME STREQUAL FreeBSD)
+    elseif(CMAKE_SYSTEM_NAME STREQUAL FreeBSD OR CMAKE_SYSTEM_NAME STREQUAL DragonFly)
         set(XMRIG_OS_FREEBSD ON)
     endif()
 endif()

scripts/benchmark_10M.cmd

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

scripts/benchmark_1M.cmd

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

scripts/build.hwloc.sh

@@ -1,8 +1,8 @@
 #!/bin/bash -e
 
 HWLOC_VERSION_MAJOR="2"
-HWLOC_VERSION_MINOR="7"
-HWLOC_VERSION_PATCH="1"
+HWLOC_VERSION_MINOR="9"
+HWLOC_VERSION_PATCH="0"
 
 HWLOC_VERSION="${HWLOC_VERSION_MAJOR}.${HWLOC_VERSION_MINOR}.${HWLOC_VERSION_PATCH}"
 

scripts/build.openssl.sh

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

scripts/build.openssl3.sh

@@ -1,6 +1,6 @@
 #!/bin/bash -e
 
-OPENSSL_VERSION="3.0.3"
+OPENSSL_VERSION="3.0.7"
 
 mkdir -p deps
 mkdir -p deps/include

scripts/build.uv.sh

@@ -1,6 +1,6 @@
 #!/bin/bash -e
 
-UV_VERSION="1.44.1"
+UV_VERSION="1.44.2"
 
 mkdir -p deps
 mkdir -p deps/include

scripts/pool_mine_example.cmd

@@ -15,6 +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
+cd /d "%~dp0"
+xmrig.exe -o xmrpool.eu:3333 -u 48edfHu7V9Z84YzzMa6fUueoELZ9ZRXq9VetWzYGzKt52XU5xvqgzYnDK9URnRoJMk1j8nLwEVsaSWJ4fhdUyZijBGUicoD -p x
 pause

scripts/randomx_boost.sh

@@ -24,8 +24,8 @@ if grep -E 'AMD Ryzen|AMD EPYC' /proc/cpuinfo > /dev/null;
 					echo "Detected Zen3 CPU"
 					wrmsr -a 0xc0011020 0x4480000000000
 					wrmsr -a 0xc0011021 0x1c000200000040
-					wrmsr -a 0xc0011022 0xc000000401500000
-					wrmsr -a 0xc001102b 0x2000cc14
+					wrmsr -a 0xc0011022 0xc000000401570000
+					wrmsr -a 0xc001102b 0x2000cc10
 					echo "MSR register values for Zen3 applied"
 				fi
 		else

scripts/rtm_ghostrider_example.cmd

@@ -15,7 +15,7 @@
 :: Choose pools outside of top 5 to help Raptoreum network be more decentralized!
 :: Smaller pools also often have smaller fees/payout limits.
 
-cd %~dp0
+cd /d "%~dp0"
 :: Use this command line to connect to non-SSL port
 xmrig.exe -a gr -o raptoreumemporium.com:3008 -u WALLET_ADDRESS -p x
 :: Or use this command line to connect to an SSL port

scripts/solo_mine_example.cmd

@@ -11,6 +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
+cd /d "%~dp0"
+xmrig.exe -o YOUR_NODE_IP:18081 -a rx/0 -u 48edfHu7V9Z84YzzMa6fUueoELZ9ZRXq9VetWzYGzKt52XU5xvqgzYnDK9URnRoJMk1j8nLwEVsaSWJ4fhdUyZijBGUicoD --daemon
 pause

src/3rdparty/argon2/CMakeLists.txt

@@ -1,4 +1,4 @@
-cmake_minimum_required(VERSION 2.8.12)
+cmake_minimum_required(VERSION 3.1)
 
 project(argon2 C)
 set(CMAKE_C_STANDARD 99)

src/3rdparty/hwloc/CMakeLists.txt

@@ -1,4 +1,4 @@
-cmake_minimum_required (VERSION  2.8.12)
+cmake_minimum_required(VERSION 3.1)
 project (hwloc C)
 
 include_directories(include)

src/3rdparty/hwloc/NEWS

@@ -17,6 +17,50 @@ bug fixes (and other actions) for each version of hwloc since version
 0.9.
 
 
+Version 2.9.0
+-------------
+* Backends
+  + Expose the memory size of CXL memory devices (Type 3) on Linux.
+  + The LevelZero backend now reports the "XeLinkBandwidth" distance
+    matrix between L0 devices (and subdevices) when available.
+  + Add support for CUDA compute capability up to 9.0.
+* Tools
+  + lstopo now switches to console mode when its output is redirected.
+    Graphical window mode may be forced back with --of window.
+  + hwloc-calc now accepts "numa" in -H, and I/O subtypes such as "gpu"
+    in -I and -N.
+
+
+Version 2.8.0
+-------------
+* API
+  + Add HWLOC_TOPOLOGY_FLAG_NO_DISTANCES, _NO_MEMATTRS and _NO_CPUKINDS
+    to reduce the overhead when unneeded.
+  + Add separate Read/Write Bandwidth/Latency memory attributes and
+    implement them on Linux.
+* Backends
+  + NUMA nodes may now have a subtype such as DRAM, HBM, SPM, or NVM
+    on heterogeneous memory platforms on Linux.
+    - Add DAXType and DAXParent attributes on Linux to tell where a
+      DAX device or its corresponding NUMA node come from (SPM for
+      Specific-Purpose or NVM for Non-Volatile Memory).
+  + Detect heterogeneous caches in hybrid CPUs on MacOS X,
+    thanks to Paul Bone for the help.
+  + Max frequencies are not ignored in Linux cpukinds anymore (they were
+    ignored in hwloc 2.7.0), but they may be slightly adjusted to avoid
+    reporting hybrid CPUs because Intel Turbo Boost Max 3.0.
+    - See the documentation of environment variable HWLOC_CPUKINDS_MAXFREQ.
+  + Hardwire the PCI locality of HPE Cray EX235a nodes.
+* Tools
+  + lstopo and other tools may now load Linux and x86 cpuid topology files
+    from a tarball.
+  + lstopo may now replace the P# and L# index prefixes with custom strings
+    thanks to --os-index-prefix and --logical-index-prefix options.
+* Misc
+  + Add --disable-readme to avoid regenerating the top-level hwloc README
+    file from the documentation.
+
+
 Version 2.7.1
 -------------
 * Workaround crashes when virtual machines report incoherent x86 CPUID

src/3rdparty/hwloc/README

@@ -78,7 +78,7 @@ debug and report issues.
 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).
+There is also a #hwloc IRC channel on Libera Chat (irc.libera.chat).
 
 
 

src/3rdparty/hwloc/VERSION

@@ -8,8 +8,8 @@
 # Please update HWLOC_VERSION* in contrib/windows/hwloc_config.h too.
 
 major=2
-minor=7
-release=1
+minor=9
+release=0
 
 # greek is used for alpha or beta release tags.  If it is non-empty,
 # it will be appended to the version number.  It does not have to be
@@ -22,7 +22,7 @@ greek=
 
 # The date when this release was created
 
-date="Mar 20, 2022"
+date="Dec 14, 2022"
 
 # 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=20:3:5
+libhwloc_so_version=21:1:6
 libnetloc_so_version=0:0:0
 
 # Please also update the <TargetName> lines in contrib/windows/libhwloc.vcxproj

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

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2021 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * Copyright © 2009-2012 Université Bordeaux
  * Copyright © 2009-2020 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -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 0x00020500
+#define HWLOC_API_VERSION 0x00020800
 
 /** \brief Indicate at runtime which hwloc API version was used at build time.
  *
@@ -971,7 +971,7 @@ HWLOC_DECLSPEC const char * hwloc_obj_type_string (hwloc_obj_type_t type) __hwlo
  *
  * If \p size is 0, \p string may safely be \c NULL.
  *
- * \return the number of character that were actually written if not truncating,
+ * \return the number of characters that were actually written if not truncating,
  * or that would have been written (not including the ending \\0).
  */
 HWLOC_DECLSPEC int hwloc_obj_type_snprintf(char * __hwloc_restrict string, size_t size,
@@ -986,7 +986,7 @@ HWLOC_DECLSPEC int hwloc_obj_type_snprintf(char * __hwloc_restrict string, size_
  *
  * If \p size is 0, \p string may safely be \c NULL.
  *
- * \return the number of character that were actually written if not truncating,
+ * \return the number of characters that were actually written if not truncating,
  * or that would have been written (not including the ending \\0).
  */
 HWLOC_DECLSPEC int hwloc_obj_attr_snprintf(char * __hwloc_restrict string, size_t size,
@@ -2060,7 +2060,26 @@ enum hwloc_topology_flags_e {
    * not change to due thread binding changes on Windows
    * (see ::HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING).
    */
-  HWLOC_TOPOLOGY_FLAG_DONT_CHANGE_BINDING = (1UL<<6)
+  HWLOC_TOPOLOGY_FLAG_DONT_CHANGE_BINDING = (1UL<<6),
+
+  /** \brief Ignore distances.
+   *
+   * Ignore distance information from the operating systems (and from XML)
+   * and hence do not use distances for grouping.
+   */
+  HWLOC_TOPOLOGY_FLAG_NO_DISTANCES = (1UL<<7),
+
+  /** \brief Ignore memory attributes.
+   *
+   * Ignore memory attribues from the operating systems (and from XML).
+   */
+  HWLOC_TOPOLOGY_FLAG_NO_MEMATTRS = (1UL<<8),
+
+  /** \brief Ignore CPU Kinds.
+   *
+   * Ignore CPU kind information from the operating systems (and from XML).
+   */
+  HWLOC_TOPOLOGY_FLAG_NO_CPUKINDS = (1UL<<9)
 };
 
 /** \brief Set OR'ed flags to non-yet-loaded topology.

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

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2021 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * Copyright © 2009-2012 Université Bordeaux
  * Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -11,10 +11,10 @@
 #ifndef HWLOC_CONFIG_H
 #define HWLOC_CONFIG_H
 
-#define HWLOC_VERSION "2.7.1"
+#define HWLOC_VERSION "2.9.0"
 #define HWLOC_VERSION_MAJOR 2
-#define HWLOC_VERSION_MINOR 7
-#define HWLOC_VERSION_RELEASE 1
+#define HWLOC_VERSION_MINOR 9
+#define HWLOC_VERSION_RELEASE 0
 #define HWLOC_VERSION_GREEK ""
 
 #define __hwloc_restrict

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

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2020 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * Copyright © 2009-2012 Université Bordeaux
  * Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -112,7 +112,7 @@ HWLOC_DECLSPEC int hwloc_bitmap_copy(hwloc_bitmap_t dst, hwloc_const_bitmap_t sr
  *
  * If \p buflen is 0, \p buf may safely be \c NULL.
  *
- * \return the number of character that were actually written if not truncating,
+ * \return the number of characters that were actually written if not truncating,
  * or that would have been written (not including the ending \\0).
  */
 HWLOC_DECLSPEC int hwloc_bitmap_snprintf(char * __hwloc_restrict buf, size_t buflen, hwloc_const_bitmap_t bitmap);
@@ -137,7 +137,7 @@ HWLOC_DECLSPEC int hwloc_bitmap_sscanf(hwloc_bitmap_t bitmap, const char * __hwl
  *
  * If \p buflen is 0, \p buf may safely be \c NULL.
  *
- * \return the number of character that were actually written if not truncating,
+ * \return the number of characters that were actually written if not truncating,
  * or that would have been written (not including the ending \\0).
  */
 HWLOC_DECLSPEC int hwloc_bitmap_list_snprintf(char * __hwloc_restrict buf, size_t buflen, hwloc_const_bitmap_t bitmap);
@@ -161,7 +161,7 @@ HWLOC_DECLSPEC int hwloc_bitmap_list_sscanf(hwloc_bitmap_t bitmap, const char *
  *
  * If \p buflen is 0, \p buf may safely be \c NULL.
  *
- * \return the number of character that were actually written if not truncating,
+ * \return the number of characters that were actually written if not truncating,
  * or that would have been written (not including the ending \\0).
  */
 HWLOC_DECLSPEC int hwloc_bitmap_taskset_snprintf(char * __hwloc_restrict buf, size_t buflen, hwloc_const_bitmap_t bitmap);
@@ -357,11 +357,11 @@ HWLOC_DECLSPEC int hwloc_bitmap_last_unset(hwloc_const_bitmap_t bitmap) __hwloc_
  * The loop must start with hwloc_bitmap_foreach_begin() and end
  * with hwloc_bitmap_foreach_end() followed by a terminating ';'.
  *
- * \p index is the loop variable; it should be an unsigned int.  The
- * first iteration will set \p index to the lowest index in the bitmap.
+ * \p id is the loop variable; it should be an unsigned int.  The
+ * first iteration will set \p id to the lowest index in the bitmap.
  * Successive iterations will iterate through, in order, all remaining
  * indexes set in the bitmap.  To be specific: each iteration will return a
- * value for \p index such that hwloc_bitmap_isset(bitmap, index) is true.
+ * value for \p id such that hwloc_bitmap_isset(bitmap, id) is true.
  *
  * The assert prevents the loop from being infinite if the bitmap is infinitely set.
  *

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

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2021 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * Copyright © 2009-2012 Université Bordeaux
  * Copyright © 2009-2010 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -55,7 +55,7 @@ hwloc_topology_insert_misc_object_by_parent(hwloc_topology_t topology, hwloc_obj
  *
  * If \p size is 0, \p string may safely be \c NULL.
  *
- * \return the number of character that were actually written if not truncating,
+ * \return the number of characters that were actually written if not truncating,
  * or that would have been written (not including the ending \\0).
  */
 static __hwloc_inline int

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

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2010-2021 Inria.  All rights reserved.
+ * Copyright © 2010-2022 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -35,8 +35,8 @@ extern "C" {
  * 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".
- * Others distance structures include and "XGMIBandwidth", "XGMIHops"
- * and "NVLinkBandwidth".
+ * Others distance structures include and "XGMIBandwidth", "XGMIHops",
+ * "XeLinkBandwidth" and "NVLinkBandwidth".
  *
  * The matrix may also contain bandwidths between random sets of objects,
  * possibly provided by the user, as specified in the \p kind attribute.
@@ -160,7 +160,8 @@ hwloc_distances_get_by_type(hwloc_topology_t topology, hwloc_obj_type_t type,
  * Usually only one distances structure may match a given name.
  *
  * The name of the most common structure is "NUMALatency".
- * Others include "XGMIBandwidth", "XGMIHops" and "NVLinkBandwidth".
+ * Others include "XGMIBandwidth", "XGMIHops", "XeLinkBandwidth",
+ * and "NVLinkBandwidth".
  */
 HWLOC_DECLSPEC int
 hwloc_distances_get_by_name(hwloc_topology_t topology, const char *name,

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

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2021 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * Copyright © 2009-2012 Université Bordeaux
  * Copyright © 2009-2010 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -886,9 +886,6 @@ enum hwloc_distrib_flags_e {
  * \p flags should be 0 or a OR'ed set of ::hwloc_distrib_flags_e.
  *
  * \note This function requires the \p roots objects to have a CPU set.
- *
- * \note This function replaces the now deprecated hwloc_distribute()
- * and hwloc_distributev() functions.
  */
 static __hwloc_inline int
 hwloc_distrib(hwloc_topology_t topology,

src/3rdparty/hwloc/include/hwloc/intel-mic.h

@@ -1,136 +0,0 @@
-/*
- * Copyright © 2013-2016 Inria.  All rights reserved.
- * See COPYING in top-level directory.
- */
-
-/** \file
- * \brief Macros to help interaction between hwloc and Intel Xeon Phi (MIC).
- *
- * Applications that use both hwloc and Intel Xeon Phi (MIC) may want to
- * include this file so as to get topology information for MIC devices.
- */
-
-#ifndef HWLOC_INTEL_MIC_H
-#define HWLOC_INTEL_MIC_H
-
-#include "hwloc.h"
-#include "hwloc/autogen/config.h"
-#include "hwloc/helper.h"
-
-#ifdef HWLOC_LINUX_SYS
-#include "hwloc/linux.h"
-
-#include <dirent.h>
-#include <string.h>
-#endif
-
-#include <stdio.h>
-#include <stdlib.h>
-
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-
-/** \defgroup hwlocality_intel_mic Interoperability with Intel Xeon Phi (MIC)
- *
- * This interface offers ways to retrieve topology information about
- * Intel Xeon Phi (MIC) devices.
- *
- * @{
- */
-
-/** \brief Get the CPU set of logical processors that are physically
- * close to MIC device whose index is \p idx.
- *
- * Return the CPU set describing the locality of the MIC device whose index is \p idx.
- *
- * Topology \p topology and device index \p idx must match the local machine.
- * I/O devices detection is not needed in the topology.
- *
- * The function only returns the locality of the device.
- * If more information about the device is needed, OS objects should
- * be used instead, see hwloc_intel_mic_get_device_osdev_by_index().
- *
- * This function is currently only implemented in a meaningful way for
- * Linux; other systems will simply get a full cpuset.
- */
-static __hwloc_inline int
-hwloc_intel_mic_get_device_cpuset(hwloc_topology_t topology __hwloc_attribute_unused,
-				  int idx __hwloc_attribute_unused,
-				  hwloc_cpuset_t set)
-{
-#ifdef HWLOC_LINUX_SYS
-	/* If we're on Linux, use the sysfs mechanism to get the local cpus */
-#define HWLOC_INTEL_MIC_DEVICE_SYSFS_PATH_MAX 128
-	char path[HWLOC_INTEL_MIC_DEVICE_SYSFS_PATH_MAX];
-	DIR *sysdir = NULL;
-	struct dirent *dirent;
-	unsigned pcibus, pcidev, pcifunc;
-
-	if (!hwloc_topology_is_thissystem(topology)) {
-		errno = EINVAL;
-		return -1;
-	}
-
-	sprintf(path, "/sys/class/mic/mic%d", idx);
-	sysdir = opendir(path);
-	if (!sysdir)
-		return -1;
-
-	while ((dirent = readdir(sysdir)) != NULL) {
-		if (sscanf(dirent->d_name, "pci_%02x:%02x.%02x", &pcibus, &pcidev, &pcifunc) == 3) {
-			sprintf(path, "/sys/class/mic/mic%d/pci_%02x:%02x.%02x/local_cpus", idx, pcibus, pcidev, pcifunc);
-			if (hwloc_linux_read_path_as_cpumask(path, set) < 0
-			    || hwloc_bitmap_iszero(set))
-				hwloc_bitmap_copy(set, hwloc_topology_get_complete_cpuset(topology));
-			break;
-		}
-	}
-
-	closedir(sysdir);
-#else
-	/* Non-Linux systems simply get a full cpuset */
-	hwloc_bitmap_copy(set, hwloc_topology_get_complete_cpuset(topology));
-#endif
-	return 0;
-}
-
-/** \brief Get the hwloc OS device object corresponding to the
- * MIC device for the given index.
- *
- * Return the OS device object describing the MIC device whose index is \p idx.
- * Return NULL if there is none.
- *
- * The topology \p topology does not necessarily have to match the current
- * machine. For instance the topology may be an XML import of a remote host.
- * I/O devices detection must be enabled in the topology.
- *
- * \note The corresponding PCI device object can be obtained by looking
- * at the OS device parent object.
- */
-static __hwloc_inline hwloc_obj_t
-hwloc_intel_mic_get_device_osdev_by_index(hwloc_topology_t topology,
-					  unsigned idx)
-{
-	hwloc_obj_t osdev = NULL;
-	while ((osdev = hwloc_get_next_osdev(topology, osdev)) != NULL) {
-		if (HWLOC_OBJ_OSDEV_COPROC == osdev->attr->osdev.type
-                    && osdev->name
-		    && !strncmp("mic", osdev->name, 3)
-		    && atoi(osdev->name + 3) == (int) idx)
-                        return osdev;
-        }
-        return NULL;
-}
-
-/** @} */
-
-
-#ifdef __cplusplus
-} /* extern "C" */
-#endif
-
-
-#endif /* HWLOC_INTEL_MIC_H */

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

@@ -54,6 +54,8 @@ extern "C" {
  * Attribute values for these nodes, if any, may then be obtained with
  * hwloc_memattr_get_value() and manually compared with the desired criteria.
  *
+ * \sa An example is available in doc/examples/memory-attributes.c in the source tree.
+ *
  * \note The API also supports specific objects as initiator,
  * but it is currently not used internally by hwloc.
  * Users may for instance use it to provide custom performance
@@ -65,19 +67,19 @@ extern "C" {
 
 /** \brief Memory node attributes. */
 enum hwloc_memattr_id_e {
-  /** \brief "Capacity".
-   * The capacity is returned in bytes
-   * (local_memory attribute in objects).
+  /** \brief
+   * The \"Capacity\" is returned in bytes (local_memory attribute in objects).
    *
    * Best capacity nodes are nodes with <b>higher capacity</b>.
    *
    * No initiator is involved when looking at this attribute.
    * The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_HIGHER_FIRST.
+   * \hideinitializer
    */
   HWLOC_MEMATTR_ID_CAPACITY = 0,
 
-  /** \brief "Locality".
-   * The locality is returned as the number of PUs in that locality
+  /** \brief
+   * The \"Locality\" is returned as the number of PUs in that locality
    * (e.g. the weight of its cpuset).
    *
    * Best locality nodes are nodes with <b>smaller locality</b>
@@ -87,26 +89,87 @@ enum hwloc_memattr_id_e {
    *
    * No initiator is involved when looking at this attribute.
    * The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_HIGHER_FIRST.
+   * \hideinitializer
    */
   HWLOC_MEMATTR_ID_LOCALITY = 1,
 
-  /** \brief "Bandwidth".
-   * The bandwidth is returned in MiB/s, as seen from the given initiator location.
+  /** \brief
+   * The \"Bandwidth\" is returned in MiB/s, as seen from the given initiator location.
+   *
    * Best bandwidth nodes are nodes with <b>higher bandwidth</b>.
+   *
    * The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_HIGHER_FIRST
    * and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
+   *
+   * This is the average bandwidth for read and write accesses. If the platform
+   * provides individual read and write bandwidths but no explicit average value,
+   * hwloc computes and returns the average.
+   * \hideinitializer
    */
   HWLOC_MEMATTR_ID_BANDWIDTH = 2,
 
-  /** \brief "Latency".
-   * The latency is returned as nanoseconds, as seen from the given initiator location.
+  /** \brief
+   * The \"ReadBandwidth\" is returned in MiB/s, as seen from the given initiator location.
+   *
+   * Best bandwidth nodes are nodes with <b>higher bandwidth</b>.
+   *
+   * The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_HIGHER_FIRST
+   * and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
+   * \hideinitializer
+   */
+  HWLOC_MEMATTR_ID_READ_BANDWIDTH = 4,
+
+  /** \brief
+   * The \"WriteBandwidth\" is returned in MiB/s, as seen from the given initiator location.
+   *
+   * Best bandwidth nodes are nodes with <b>higher bandwidth</b>.
+   *
+   * The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_HIGHER_FIRST
+   * and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
+   * \hideinitializer
+   */
+  HWLOC_MEMATTR_ID_WRITE_BANDWIDTH = 5,
+
+  /** \brief
+   * The \"Latency\" is returned as nanoseconds, as seen from the given initiator location.
+   *
    * Best latency nodes are nodes with <b>smaller latency</b>.
+   *
    * The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_LOWER_FIRST
    * and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
+   *
+   * This is the average latency for read and write accesses. If the platform
+   * provides individual read and write latencies but no explicit average value,
+   * hwloc computes and returns the average.
+   * \hideinitializer
    */
-  HWLOC_MEMATTR_ID_LATENCY = 3
+  HWLOC_MEMATTR_ID_LATENCY = 3,
 
-  /* TODO read vs write, persistence? */
+  /** \brief
+   * The \"ReadLatency\" is returned as nanoseconds, as seen from the given initiator location.
+   *
+   * Best latency nodes are nodes with <b>smaller latency</b>.
+   *
+   * The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_LOWER_FIRST
+   * and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
+   * \hideinitializer
+   */
+  HWLOC_MEMATTR_ID_READ_LATENCY = 6,
+
+  /** \brief
+   * The \"WriteLatency\" is returned as nanoseconds, as seen from the given initiator location.
+   *
+   * Best latency nodes are nodes with <b>smaller latency</b>.
+   *
+   * The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_LOWER_FIRST
+   * and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
+   * \hideinitializer
+   */
+  HWLOC_MEMATTR_ID_WRITE_LATENCY = 7,
+
+  /* TODO persistence? */
+
+  HWLOC_MEMATTR_ID_MAX /**< \private Sentinel value */
 };
 
 /** \brief A memory attribute identifier.

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

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2013-2021 Inria.  All rights reserved.
+ * Copyright © 2013-2022 Inria.  All rights reserved.
  * Copyright © 2016 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
  */
@@ -338,9 +338,15 @@ struct hwloc_component {
  * This function return 1 by default (show critical only),
  * 0 in lstopo (show all),
  * or anything set in HWLOC_HIDE_ERRORS in the environment.
+ *
+ * Use macros HWLOC_SHOW_CRITICAL_ERRORS() and HWLOC_SHOW_ALL_ERRORS()
+ * for clarity.
  */
 HWLOC_DECLSPEC int hwloc_hide_errors(void);
 
+#define HWLOC_SHOW_CRITICAL_ERRORS() (hwloc_hide_errors() < 2)
+#define HWLOC_SHOW_ALL_ERRORS() (hwloc_hide_errors() == 0)
+
 /** \brief Add an object to the topology.
  *
  * Insert new object \p obj in the topology starting under existing object \p root
@@ -501,6 +507,7 @@ hwloc_filter_check_pcidev_subtype_important(unsigned classid)
 	  || baseclass == 0x0b /* PCI_BASE_CLASS_PROCESSOR */
 	  || classid == 0x0c04 /* PCI_CLASS_SERIAL_FIBER */
 	  || classid == 0x0c06 /* PCI_CLASS_SERIAL_INFINIBAND */
+          || classid == 0x0502 /* PCI_CLASS_MEMORY_CXL */
           || baseclass == 0x06 /* PCI_BASE_CLASS_BRIDGE with non-PCI downstream. the core will drop the useless ones later */
 	  || baseclass == 0x12 /* Processing Accelerators */);
 }

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

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
- * Copyright © 2010-2021 Inria.  All rights reserved.
+ * Copyright © 2010-2022 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -123,6 +123,9 @@ extern "C" {
 #define HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING HWLOC_NAME_CAPS(TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING)
 #define HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_MEMBINDING HWLOC_NAME_CAPS(TOPOLOGY_FLAG_RESTRICT_TO_MEMBINDING)
 #define HWLOC_TOPOLOGY_FLAG_DONT_CHANGE_BINDING HWLOC_NAME_CAPS(TOPOLOGY_FLAG_DONT_CHANGE_BINDING)
+#define HWLOC_TOPOLOGY_FLAG_NO_DISTANCES HWLOC_NAME_CAPS(TOPOLOGY_FLAG_NO_DISTANCES)
+#define HWLOC_TOPOLOGY_FLAG_NO_MEMATTRS HWLOC_NAME_CAPS(TOPOLOGY_FLAG_NO_MEMATTRS)
+#define HWLOC_TOPOLOGY_FLAG_NO_CPUKINDS HWLOC_NAME_CAPS(TOPOLOGY_FLAG_NO_CPUKINDS)
 
 #define hwloc_topology_set_pid HWLOC_NAME(topology_set_pid)
 #define hwloc_topology_set_synthetic HWLOC_NAME(topology_set_synthetic)
@@ -381,6 +384,11 @@ extern "C" {
 #define HWLOC_MEMATTR_ID_LOCALITY HWLOC_NAME_CAPS(MEMATTR_ID_LOCALITY)
 #define HWLOC_MEMATTR_ID_BANDWIDTH HWLOC_NAME_CAPS(MEMATTR_ID_BANDWIDTH)
 #define HWLOC_MEMATTR_ID_LATENCY HWLOC_NAME_CAPS(MEMATTR_ID_LATENCY)
+#define HWLOC_MEMATTR_ID_READ_BANDWIDTH HWLOC_NAME_CAPS(MEMATTR_ID_READ_BANDWIDTH)
+#define HWLOC_MEMATTR_ID_WRITE_BANDWIDTH HWLOC_NAME_CAPS(MEMATTR_ID_WRITE_BANDWIDTH)
+#define HWLOC_MEMATTR_ID_READ_LATENCY HWLOC_NAME_CAPS(MEMATTR_ID_READ_LATENCY)
+#define HWLOC_MEMATTR_ID_WRITE_LATENCY HWLOC_NAME_CAPS(MEMATTR_ID_WRITE_LATENCY)
+#define HWLOC_MEMATTR_ID_MAX HWLOC_NAME_CAPS(MEMATTR_ID_MAX)
 
 #define hwloc_memattr_id_t HWLOC_NAME(memattr_id_t)
 #define hwloc_memattr_get_by_name HWLOC_NAME(memattr_get_by_name)
@@ -862,6 +870,7 @@ extern "C" {
 #define hwloc_internal_memattrs_destroy HWLOC_NAME(internal_memattrs_destroy)
 #define hwloc_internal_memattrs_need_refresh HWLOC_NAME(internal_memattrs_need_refresh)
 #define hwloc_internal_memattrs_refresh HWLOC_NAME(internal_memattrs_refresh)
+#define hwloc_internal_memattrs_guess_memory_tiers HWLOC_NAME(internal_memattrs_guess_memory_tiers)
 
 #define hwloc_internal_cpukind_s HWLOC_NAME(internal_cpukind_s)
 #define hwloc_internal_cpukinds_init HWLOC_NAME(internal_cpukinds_init)

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

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009      CNRS
- * Copyright © 2009-2021 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * Copyright © 2009-2012, 2020 Université Bordeaux
  * Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
  *
@@ -259,6 +259,7 @@ struct hwloc_topology {
     unsigned bus_first, bus_last;
     hwloc_bitmap_t cpuset;
   } * pci_forced_locality;
+  hwloc_uint64_t pci_locality_quirks;
 
   /* component blacklisting */
   unsigned nr_blacklisted_components;
@@ -419,6 +420,7 @@ extern void hwloc_internal_memattrs_need_refresh(hwloc_topology_t topology);
 extern void hwloc_internal_memattrs_refresh(hwloc_topology_t topology);
 extern int hwloc_internal_memattrs_dup(hwloc_topology_t new, hwloc_topology_t old);
 extern int hwloc_internal_memattr_set_value(hwloc_topology_t topology, hwloc_memattr_id_t id, hwloc_obj_type_t target_type, hwloc_uint64_t target_gp_index, unsigned target_os_index, struct hwloc_internal_location_s *initiator, hwloc_uint64_t value);
+extern int hwloc_internal_memattrs_guess_memory_tiers(hwloc_topology_t topology);
 
 extern void hwloc_internal_cpukinds_init(hwloc_topology_t topology);
 extern int hwloc_internal_cpukinds_rank(hwloc_topology_t topology);

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

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 Université Bordeaux
- * Copyright © 2020 Inria.  All rights reserved.
+ * Copyright © 2020-2022 Inria.  All rights reserved.
  *
  * See COPYING in top-level directory.
  */
@@ -8,13 +8,22 @@
 #ifndef HWLOC_PRIVATE_WINDOWS_H
 #define HWLOC_PRIVATE_WINDOWS_H
 
+#ifndef _ANONYMOUS_UNION
 #ifdef __GNUC__
 #define _ANONYMOUS_UNION __extension__
-#define _ANONYMOUS_STRUCT __extension__
 #else
 #define _ANONYMOUS_UNION
+#endif /* __GNUC__ */
+#endif /* _ANONYMOUS_UNION */
+
+#ifndef _ANONYMOUS_STRUCT
+#ifdef __GNUC__
+#define _ANONYMOUS_STRUCT __extension__
+#else
 #define _ANONYMOUS_STRUCT
 #endif /* __GNUC__ */
+#endif /* _ANONYMOUS_STRUCT */
+
 #define DUMMYUNIONNAME
 #define DUMMYSTRUCTNAME
 

src/3rdparty/hwloc/src/components.c

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2009-2021 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * Copyright © 2012 Université Bordeaux
  * See COPYING in top-level directory.
  */
@@ -386,7 +386,7 @@ hwloc_disc_component_register(struct hwloc_disc_component *component,
 				   |HWLOC_DISC_PHASE_MISC
 				   |HWLOC_DISC_PHASE_ANNOTATE
 				   |HWLOC_DISC_PHASE_TWEAK))) {
-    if (hwloc_hide_errors() < 2)
+    if (HWLOC_SHOW_CRITICAL_ERRORS())
       fprintf(stderr, "hwloc: Cannot register discovery component `%s' with invalid phases 0x%x\n",
               component->name, component->phases);
     return -1;
@@ -476,7 +476,7 @@ hwloc_components_init(void)
   /* hwloc_static_components is created by configure in static-components.h */
   for(i=0; NULL != hwloc_static_components[i]; i++) {
     if (hwloc_static_components[i]->flags) {
-      if (hwloc_hide_errors() < 2)
+      if (HWLOC_SHOW_CRITICAL_ERRORS())
         fprintf(stderr, "hwloc: Ignoring static component with invalid flags %lx\n",
                 hwloc_static_components[i]->flags);
       continue;
@@ -505,7 +505,7 @@ hwloc_components_init(void)
 #ifdef HWLOC_HAVE_PLUGINS
   for(desc = hwloc_plugins; NULL != desc; desc = desc->next) {
     if (desc->component->flags) {
-      if (hwloc_hide_errors() < 2)
+      if (HWLOC_SHOW_CRITICAL_ERRORS())
         fprintf(stderr, "hwloc: Ignoring plugin `%s' component with invalid flags %lx\n",
                 desc->name, desc->component->flags);
       continue;
@@ -738,7 +738,7 @@ hwloc_disc_component_try_enable(struct hwloc_topology *topology,
   backend = comp->instantiate(topology, comp, topology->backend_excluded_phases | blacklisted_phases,
 			      NULL, NULL, NULL);
   if (!backend) {
-    if (hwloc_components_verbose || (envvar_forced && hwloc_hide_errors() < 2))
+    if (hwloc_components_verbose || (envvar_forced && HWLOC_SHOW_CRITICAL_ERRORS()))
       fprintf(stderr, "hwloc: Failed to instantiate discovery component `%s'\n", comp->name);
     return -1;
   }
@@ -835,7 +835,7 @@ hwloc_disc_components_enable_others(struct hwloc_topology *topology)
 	  if (comp->phases & ~blacklisted_phases)
 	    hwloc_disc_component_try_enable(topology, comp, 1 /* envvar forced */, blacklisted_phases);
 	} else {
-          if (hwloc_hide_errors() < 2)
+          if (HWLOC_SHOW_CRITICAL_ERRORS())
             fprintf(stderr, "hwloc: Cannot find discovery component `%s'\n", name);
 	}
 
@@ -967,7 +967,7 @@ hwloc_backend_enable(struct hwloc_backend *backend)
 
   /* check backend flags */
   if (backend->flags) {
-    if (hwloc_hide_errors() < 2)
+    if (HWLOC_SHOW_CRITICAL_ERRORS())
       fprintf(stderr, "hwloc: Cannot enable discovery component `%s' phases 0x%x with unknown flags %lx\n",
               backend->component->name, backend->component->phases, backend->flags);
     return -1;

src/3rdparty/hwloc/src/cpukinds.c

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2020-2021 Inria.  All rights reserved.
+ * Copyright © 2020-2022 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -504,7 +504,7 @@ hwloc_internal_cpukinds_rank(struct hwloc_topology *topology)
       heuristics = HWLOC_CPUKINDS_RANKING_FORCED_EFFICIENCY;
     else if (!strcmp(env, "no_forced_efficiency"))
       heuristics = HWLOC_CPUKINDS_RANKING_NO_FORCED_EFFICIENCY;
-    else if (hwloc_hide_errors() < 2)
+    else if (HWLOC_SHOW_CRITICAL_ERRORS())
       fprintf(stderr, "hwloc: Failed to recognize HWLOC_CPUKINDS_RANKING value %s\n", env);
   }
 

src/3rdparty/hwloc/src/diff.c

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2013-2020 Inria.  All rights reserved.
+ * Copyright © 2013-2022 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -218,7 +218,7 @@ hwloc_diff_trees(hwloc_topology_t topo1, hwloc_obj_t obj1,
 		struct hwloc_info_s *info1 = &obj1->infos[i], *info2 = &obj2->infos[i];
 		if (strcmp(info1->name, info2->name))
 			goto out_too_complex;
-		if (strcmp(obj1->infos[i].value, obj2->infos[i].value)) {
+		if (strcmp(info1->value, info2->value)) {
 			err = hwloc_append_diff_obj_attr_string(obj1,
 								HWLOC_TOPOLOGY_DIFF_OBJ_ATTR_INFO,
 								info1->name,

src/3rdparty/hwloc/src/distances.c

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2010-2021 Inria.  All rights reserved.
+ * Copyright © 2010-2022 Inria.  All rights reserved.
  * Copyright © 2011-2012 Université Bordeaux
  * Copyright © 2011 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -860,7 +860,7 @@ struct hwloc_distances_container_s {
   struct hwloc_distances_s distances;
 };
 
-#define HWLOC_DISTANCES_CONTAINER_OFFSET ((char*)&((struct hwloc_distances_container_s*)NULL)->distances - (char*)NULL)
+#define HWLOC_DISTANCES_CONTAINER_OFFSET ((uintptr_t)(&((struct hwloc_distances_container_s*)NULL)->distances) - (uintptr_t)NULL)
 #define HWLOC_DISTANCES_CONTAINER(_d) (struct hwloc_distances_container_s *) ( ((char*)_d) - HWLOC_DISTANCES_CONTAINER_OFFSET )
 
 static struct hwloc_internal_distances_s *

src/3rdparty/hwloc/src/memattrs.c

@@ -1,11 +1,12 @@
 /*
- * Copyright © 2020-2021 Inria.  All rights reserved.
+ * Copyright © 2020-2022 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
 #include "private/autogen/config.h"
 #include "hwloc.h"
 #include "private/private.h"
+#include "private/debug.h"
 
 
 /*****************************
@@ -49,36 +50,51 @@ hwloc__setup_memattr(struct hwloc_internal_memattr_s *imattr,
 void
 hwloc_internal_memattrs_prepare(struct hwloc_topology *topology)
 {
-#define NR_DEFAULT_MEMATTRS 4
-  topology->memattrs = malloc(NR_DEFAULT_MEMATTRS * sizeof(*topology->memattrs));
+  topology->memattrs = malloc(HWLOC_MEMATTR_ID_MAX * sizeof(*topology->memattrs));
   if (!topology->memattrs)
     return;
 
-  assert(HWLOC_MEMATTR_ID_CAPACITY < NR_DEFAULT_MEMATTRS);
   hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_CAPACITY],
                        (char *) "Capacity",
                        HWLOC_MEMATTR_FLAG_HIGHER_FIRST,
                        HWLOC_IMATTR_FLAG_STATIC_NAME|HWLOC_IMATTR_FLAG_CONVENIENCE);
 
-  assert(HWLOC_MEMATTR_ID_LOCALITY < NR_DEFAULT_MEMATTRS);
   hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_LOCALITY],
                        (char *) "Locality",
                        HWLOC_MEMATTR_FLAG_LOWER_FIRST,
                        HWLOC_IMATTR_FLAG_STATIC_NAME|HWLOC_IMATTR_FLAG_CONVENIENCE);
 
-  assert(HWLOC_MEMATTR_ID_BANDWIDTH < NR_DEFAULT_MEMATTRS);
   hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_BANDWIDTH],
                        (char *) "Bandwidth",
                        HWLOC_MEMATTR_FLAG_HIGHER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
                        HWLOC_IMATTR_FLAG_STATIC_NAME);
 
-  assert(HWLOC_MEMATTR_ID_LATENCY < NR_DEFAULT_MEMATTRS);
+  hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_READ_BANDWIDTH],
+                       (char *) "ReadBandwidth",
+                       HWLOC_MEMATTR_FLAG_HIGHER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
+                       HWLOC_IMATTR_FLAG_STATIC_NAME);
+
+  hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_WRITE_BANDWIDTH],
+                       (char *) "WriteBandwidth",
+                       HWLOC_MEMATTR_FLAG_HIGHER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
+                       HWLOC_IMATTR_FLAG_STATIC_NAME);
+
   hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_LATENCY],
                        (char *) "Latency",
                        HWLOC_MEMATTR_FLAG_LOWER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
                        HWLOC_IMATTR_FLAG_STATIC_NAME);
 
-  topology->nr_memattrs = NR_DEFAULT_MEMATTRS;
+  hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_READ_LATENCY],
+                       (char *) "ReadLatency",
+                       HWLOC_MEMATTR_FLAG_LOWER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
+                       HWLOC_IMATTR_FLAG_STATIC_NAME);
+
+  hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_WRITE_LATENCY],
+                       (char *) "WriteLatency",
+                       HWLOC_MEMATTR_FLAG_LOWER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
+                       HWLOC_IMATTR_FLAG_STATIC_NAME);
+
+  topology->nr_memattrs = HWLOC_MEMATTR_ID_MAX;
 }
 
 static void
@@ -1197,3 +1213,214 @@ hwloc_get_local_numanode_objs(hwloc_topology_t topology,
   *nrp = i;
   return 0;
 }
+
+
+/**************************************
+ * Using memattrs to identify HBM/DRAM
+ */
+
+struct hwloc_memory_tier_s {
+  hwloc_obj_t node;
+  uint64_t local_bw;
+  enum hwloc_memory_tier_type_e {
+    /* warning the order is important for guess_memory_tiers() after qsort() */
+    HWLOC_MEMORY_TIER_UNKNOWN,
+    HWLOC_MEMORY_TIER_DRAM,
+    HWLOC_MEMORY_TIER_HBM,
+    HWLOC_MEMORY_TIER_SPM, /* Specific-Purpose Memory is usually HBM, we'll use BW to confirm */
+    HWLOC_MEMORY_TIER_NVM,
+    HWLOC_MEMORY_TIER_GPU,
+  } type;
+};
+
+static int compare_tiers(const void *_a, const void *_b)
+{
+  const struct hwloc_memory_tier_s *a = _a, *b = _b;
+  /* sort by type of tier first */
+  if (a->type != b->type)
+    return a->type - b->type;
+  /* then by bandwidth */
+  if (a->local_bw > b->local_bw)
+    return -1;
+  else if (a->local_bw < b->local_bw)
+    return 1;
+  return 0;
+}
+
+int
+hwloc_internal_memattrs_guess_memory_tiers(hwloc_topology_t topology)
+{
+  struct hwloc_internal_memattr_s *imattr;
+  struct hwloc_memory_tier_s *tiers;
+  unsigned i, j, n;
+  const char *env;
+  int spm_is_hbm = -1; /* -1 will guess from BW, 0 no, 1 forced */
+  int mark_dram = 1;
+  unsigned first_spm, first_nvm;
+  hwloc_uint64_t max_unknown_bw, min_spm_bw;
+
+  env = getenv("HWLOC_MEMTIERS_GUESS");
+  if (env) {
+    if (!strcmp(env, "none")) {
+      return 0;
+    } else if (!strcmp(env, "default")) {
+      /* nothing */
+    } else if (!strcmp(env, "spm_is_hbm")) {
+      hwloc_debug("Assuming SPM-tier is HBM, ignore bandwidth\n");
+      spm_is_hbm = 1;
+    } else if (HWLOC_SHOW_CRITICAL_ERRORS()) {
+      fprintf(stderr, "hwloc: Failed to recognize HWLOC_MEMTIERS_GUESS value %s\n", env);
+    }
+  }
+
+  imattr = &topology->memattrs[HWLOC_MEMATTR_ID_BANDWIDTH];
+
+  if (!(imattr->iflags & HWLOC_IMATTR_FLAG_CACHE_VALID))
+    hwloc__imattr_refresh(topology, imattr);
+
+  n = hwloc_get_nbobjs_by_depth(topology, HWLOC_TYPE_DEPTH_NUMANODE);
+  assert(n);
+
+  tiers = malloc(n * sizeof(*tiers));
+  if (!tiers)
+    return -1;
+
+  for(i=0; i<n; i++) {
+    hwloc_obj_t node;
+    const char *daxtype;
+    struct hwloc_internal_location_s iloc;
+    struct hwloc_internal_memattr_target_s *imtg = NULL;
+    struct hwloc_internal_memattr_initiator_s *imi;
+
+    node = hwloc_get_obj_by_depth(topology, HWLOC_TYPE_DEPTH_NUMANODE, i);
+    assert(node);
+    tiers[i].node = node;
+
+    /* defaults */
+    tiers[i].type = HWLOC_MEMORY_TIER_UNKNOWN;
+    tiers[i].local_bw = 0; /* unknown */
+
+    daxtype = hwloc_obj_get_info_by_name(node, "DAXType");
+    /* mark NVM, SPM and GPU nodes */
+    if (daxtype && !strcmp(daxtype, "NVM"))
+      tiers[i].type = HWLOC_MEMORY_TIER_NVM;
+    if (daxtype && !strcmp(daxtype, "SPM"))
+      tiers[i].type = HWLOC_MEMORY_TIER_SPM;
+    if (node->subtype && !strcmp(node->subtype, "GPUMemory"))
+      tiers[i].type = HWLOC_MEMORY_TIER_GPU;
+
+    if (spm_is_hbm == -1) {
+      for(j=0; j<imattr->nr_targets; j++)
+        if (imattr->targets[j].obj == node) {
+          imtg = &imattr->targets[j];
+          break;
+        }
+      if (imtg && !hwloc_bitmap_iszero(node->cpuset)) {
+        iloc.type = HWLOC_LOCATION_TYPE_CPUSET;
+        iloc.location.cpuset = node->cpuset;
+        imi = hwloc__memattr_target_get_initiator(imtg, &iloc, 0);
+        if (imi)
+          tiers[i].local_bw = imi->value;
+      }
+    }
+  }
+
+  /* sort tiers */
+  qsort(tiers, n, sizeof(*tiers), compare_tiers);
+  hwloc_debug("Sorting memory tiers...\n");
+  for(i=0; i<n; i++)
+    hwloc_debug("  tier %u = node L#%u P#%u with tier type %d and local BW #%llu\n",
+                i,
+                tiers[i].node->logical_index, tiers[i].node->os_index,
+                tiers[i].type, (unsigned long long) tiers[i].local_bw);
+
+  /* now we have UNKNOWN tiers (sorted by BW), then SPM tiers (sorted by BW), then NVM, then GPU */
+
+  /* iterate over UNKNOWN tiers, and find their BW */
+  for(i=0; i<n; i++) {
+    if (tiers[i].type > HWLOC_MEMORY_TIER_UNKNOWN)
+      break;
+  }
+  first_spm = i;
+  /* get max BW from first */
+  if (first_spm > 0)
+    max_unknown_bw = tiers[0].local_bw;
+  else
+    max_unknown_bw = 0;
+
+  /* there are no DRAM or HBM tiers yet */
+
+  /* iterate over SPM tiers, and find their BW */
+  for(i=first_spm; i<n; i++) {
+    if (tiers[i].type > HWLOC_MEMORY_TIER_SPM)
+      break;
+  }
+  first_nvm = i;
+  /* get min BW from last */
+  if (first_nvm > first_spm)
+    min_spm_bw = tiers[first_nvm-1].local_bw;
+  else
+    min_spm_bw = 0;
+
+  /* FIXME: if there's more than 10% between some sets of nodes inside a tier, split it? */
+  /* FIXME: if there are cpuset-intersecting nodes in same tier, abort? */
+
+  if (spm_is_hbm == -1) {
+    /* if we have BW for all SPM and UNKNOWN
+     * and all SPM BW are 2x superior to all UNKNOWN BW
+     */
+    hwloc_debug("UNKNOWN-memory-tier max bandwidth %llu\n", (unsigned long long) max_unknown_bw);
+    hwloc_debug("SPM-memory-tier min bandwidth %llu\n", (unsigned long long) min_spm_bw);
+    if (max_unknown_bw > 0 && min_spm_bw > 0 && max_unknown_bw*2 < min_spm_bw) {
+      hwloc_debug("assuming SPM means HBM and !SPM means DRAM since bandwidths are very different\n");
+      spm_is_hbm = 1;
+    } else {
+      hwloc_debug("cannot assume SPM means HBM\n");
+      spm_is_hbm = 0;
+    }
+  }
+
+  if (spm_is_hbm) {
+    for(i=0; i<first_spm; i++)
+      tiers[i].type = HWLOC_MEMORY_TIER_DRAM;
+    for(i=first_spm; i<first_nvm; i++)
+      tiers[i].type = HWLOC_MEMORY_TIER_HBM;
+  }
+
+  if (first_spm == n)
+    mark_dram = 0;
+
+    /* now apply subtypes */
+  for(i=0; i<n; i++) {
+    const char *type = NULL;
+    if (tiers[i].node->subtype) /* don't overwrite the existing subtype */
+      continue;
+    switch (tiers[i].type) {
+    case HWLOC_MEMORY_TIER_DRAM:
+      if (mark_dram)
+        type = "DRAM";
+      break;
+    case HWLOC_MEMORY_TIER_HBM:
+      type = "HBM";
+      break;
+    case HWLOC_MEMORY_TIER_SPM:
+      type = "SPM";
+      break;
+    case HWLOC_MEMORY_TIER_NVM:
+      type = "NVM";
+      break;
+    default:
+      /* GPU memory is already marked with subtype="GPUMemory",
+       * UNKNOWN doesn't deserve any subtype
+       */
+      break;
+    }
+    if (type) {
+      hwloc_debug("Marking node L#%u P#%u as %s\n", tiers[i].node->logical_index, tiers[i].node->os_index, type);
+      tiers[i].node->subtype = strdup(type);
+    }
+  }
+
+  free(tiers);
+  return 0;
+}

src/3rdparty/hwloc/src/pci-common.c

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2009-2021 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -119,6 +119,13 @@ hwloc_pci_discovery_init(struct hwloc_topology *topology)
   topology->pci_forced_locality = NULL;
 
   topology->first_pci_locality = topology->last_pci_locality = NULL;
+
+#define HWLOC_PCI_LOCALITY_QUIRK_CRAY_EX235A (1ULL<<0)
+#define HWLOC_PCI_LOCALITY_QUIRK_FAKE (1ULL<<62)
+  topology->pci_locality_quirks = (uint64_t) -1;
+  /* -1 is unknown, 0 is disabled, >0 is bitmask of enabled quirks.
+   * bit 63 should remain unused so that -1 is unaccessible as a bitmask.
+   */
 }
 
 void
@@ -146,7 +153,7 @@ hwloc_pci_discovery_prepare(struct hwloc_topology *topology)
 	  }
 	  free(buffer);
 	} else {
-          if (hwloc_hide_errors() < 2)
+          if (HWLOC_SHOW_CRITICAL_ERRORS())
             fprintf(stderr, "hwloc/pci: Ignoring HWLOC_PCI_LOCALITY file `%s' too large (%lu bytes)\n",
                     env, (unsigned long) st.st_size);
 	}
@@ -333,7 +340,7 @@ hwloc_pci_add_object(struct hwloc_obj *parent, struct hwloc_obj **parent_io_firs
     }
     case HWLOC_PCI_BUSID_EQUAL: {
       static int reported = 0;
-      if (!reported && hwloc_hide_errors() < 2) {
+      if (!reported && HWLOC_SHOW_CRITICAL_ERRORS()) {
         fprintf(stderr, "*********************************************************\n");
         fprintf(stderr, "* hwloc %s received invalid PCI information.\n", HWLOC_VERSION);
         fprintf(stderr, "*\n");
@@ -442,13 +449,90 @@ hwloc_pcidisc_add_hostbridges(struct hwloc_topology *topology,
   return new;
 }
 
-static struct hwloc_obj *
-hwloc_pci_fixup_busid_parent(struct hwloc_topology *topology __hwloc_attribute_unused,
-			     struct hwloc_pcidev_attr_s *busid __hwloc_attribute_unused,
-			     struct hwloc_obj *parent __hwloc_attribute_unused)
+/* return 1 if a quirk was applied */
+static int
+hwloc__pci_find_busid_parent_quirk(struct hwloc_topology *topology,
+                                   struct hwloc_pcidev_attr_s *busid,
+                                   hwloc_cpuset_t cpuset)
 {
-  /* no quirk for now */
-  return parent;
+  if (topology->pci_locality_quirks == (uint64_t)-1 /* unknown */) {
+    const char *dmi_board_name, *env;
+
+    /* first invokation, detect which quirks are needed */
+    topology->pci_locality_quirks = 0; /* no quirk yet */
+
+    dmi_board_name = hwloc_obj_get_info_by_name(hwloc_get_root_obj(topology), "DMIBoardName");
+    if (dmi_board_name && !strcmp(dmi_board_name, "HPE CRAY EX235A")) {
+      hwloc_debug("enabling for PCI locality quirk for HPE Cray EX235A\n");
+      topology->pci_locality_quirks |= HWLOC_PCI_LOCALITY_QUIRK_CRAY_EX235A;
+    }
+
+    env = getenv("HWLOC_PCI_LOCALITY_QUIRK_FAKE");
+    if (env && atoi(env)) {
+      hwloc_debug("enabling for PCI locality fake quirk (attaching everything to last PU)\n");
+      topology->pci_locality_quirks |= HWLOC_PCI_LOCALITY_QUIRK_FAKE;
+    }
+  }
+
+  if (topology->pci_locality_quirks & HWLOC_PCI_LOCALITY_QUIRK_FAKE) {
+    unsigned last = hwloc_bitmap_last(hwloc_topology_get_topology_cpuset(topology));
+    hwloc_bitmap_set(cpuset, last);
+    return 1;
+  }
+
+  if (topology->pci_locality_quirks & HWLOC_PCI_LOCALITY_QUIRK_CRAY_EX235A) {
+    /* AMD Trento has xGMI ports connected to individual CCDs (8 cores + L3)
+     * instead of NUMA nodes (pairs of CCDs within Trento) as is usual in AMD EPYC CPUs.
+     * This is not described by the ACPI tables, hence we need to manually hardwire
+     * the xGMI locality for the (currently single) server that currently uses that CPU.
+     * It's not clear if ACPI tables can/will ever be fixed (would require one initiator
+     * proximity domain per CCD), or if Linux can/will work around the issue.
+     */
+    if (busid->domain == 0) {
+      if (busid->bus >= 0xd0 && busid->bus <= 0xd1) {
+        hwloc_bitmap_set_range(cpuset, 0, 7);
+        hwloc_bitmap_set_range(cpuset, 64, 71);
+        return 1;
+      }
+      if (busid->bus >= 0xd4 && busid->bus <= 0xd6) {
+        hwloc_bitmap_set_range(cpuset, 8, 15);
+        hwloc_bitmap_set_range(cpuset, 72, 79);
+        return 1;
+      }
+      if (busid->bus >= 0xc8 && busid->bus <= 0xc9) {
+        hwloc_bitmap_set_range(cpuset, 16, 23);
+        hwloc_bitmap_set_range(cpuset, 80, 87);
+        return 1;
+      }
+      if (busid->bus >= 0xcc && busid->bus <= 0xce) {
+        hwloc_bitmap_set_range(cpuset, 24, 31);
+        hwloc_bitmap_set_range(cpuset, 88, 95);
+        return 1;
+      }
+      if (busid->bus >= 0xd8 && busid->bus <= 0xd9) {
+        hwloc_bitmap_set_range(cpuset, 32, 39);
+        hwloc_bitmap_set_range(cpuset, 96, 103);
+        return 1;
+      }
+      if (busid->bus >= 0xdc && busid->bus <= 0xde) {
+        hwloc_bitmap_set_range(cpuset, 40, 47);
+        hwloc_bitmap_set_range(cpuset, 104, 111);
+        return 1;
+      }
+      if (busid->bus >= 0xc0 && busid->bus <= 0xc1) {
+        hwloc_bitmap_set_range(cpuset, 48, 55);
+        hwloc_bitmap_set_range(cpuset, 112, 119);
+        return 1;
+      }
+      if (busid->bus >= 0xc4 && busid->bus <= 0xc6) {
+        hwloc_bitmap_set_range(cpuset, 56, 63);
+        hwloc_bitmap_set_range(cpuset, 120, 127);
+        return 1;
+      }
+    }
+  }
+
+  return 0;
 }
 
 static struct hwloc_obj *
@@ -457,7 +541,7 @@ hwloc__pci_find_busid_parent(struct hwloc_topology *topology, struct hwloc_pcide
   hwloc_bitmap_t cpuset = hwloc_bitmap_alloc();
   hwloc_obj_t parent;
   int forced = 0;
-  int noquirks = 0;
+  int noquirks = 0, got_quirked = 0;
   unsigned i;
   int err;
 
@@ -490,7 +574,7 @@ hwloc__pci_find_busid_parent(struct hwloc_topology *topology, struct hwloc_pcide
     if (env) {
       static int reported = 0;
       if (!topology->pci_has_forced_locality && !reported) {
-        if (!hwloc_hide_errors())
+        if (HWLOC_SHOW_ALL_ERRORS())
           fprintf(stderr, "hwloc/pci: Environment variable %s is deprecated, please use HWLOC_PCI_LOCALITY instead.\n", env);
 	reported = 1;
       }
@@ -505,7 +589,13 @@ hwloc__pci_find_busid_parent(struct hwloc_topology *topology, struct hwloc_pcide
     }
   }
 
-  if (!forced) {
+  if (!forced && !noquirks && topology->pci_locality_quirks /* either quirks are unknown yet, or some are enabled */) {
+    err = hwloc__pci_find_busid_parent_quirk(topology, busid, cpuset);
+    if (err > 0)
+      got_quirked = 1;
+  }
+
+  if (!forced && !got_quirked) {
     /* get the cpuset by asking the backend that provides the relevant hook, if any. */
     struct hwloc_backend *backend = topology->get_pci_busid_cpuset_backend;
     if (backend)
@@ -520,11 +610,7 @@ hwloc__pci_find_busid_parent(struct hwloc_topology *topology, struct hwloc_pcide
   hwloc_debug_bitmap("  will attach PCI bus to cpuset %s\n", cpuset);
 
   parent = hwloc_find_insert_io_parent_by_complete_cpuset(topology, cpuset);
-  if (parent) {
-    if (!noquirks)
-      /* We found a valid parent. Check that the OS didn't report invalid locality */
-      parent = hwloc_pci_fixup_busid_parent(topology, busid, parent);
-  } else {
+  if (!parent) {
     /* Fallback to root */
     parent = hwloc_get_root_obj(topology);
   }
@@ -805,19 +891,28 @@ hwloc_pcidisc_find_linkspeed(const unsigned char *config,
   memcpy(&linksta, &config[offset + HWLOC_PCI_EXP_LNKSTA], 4);
   speed = linksta & HWLOC_PCI_EXP_LNKSTA_SPEED; /* PCIe generation */
   width = (linksta & HWLOC_PCI_EXP_LNKSTA_WIDTH) >> 4; /* how many lanes */
-  /* PCIe Gen1 = 2.5GT/s signal-rate per lane with 8/10 encoding    = 0.25GB/s data-rate per lane
-   * PCIe Gen2 = 5  GT/s signal-rate per lane with 8/10 encoding    = 0.5 GB/s data-rate per lane
-   * PCIe Gen3 = 8  GT/s signal-rate per lane with 128/130 encoding = 1   GB/s data-rate per lane
-   * PCIe Gen4 = 16 GT/s signal-rate per lane with 128/130 encoding = 2   GB/s data-rate per lane
-   * PCIe Gen5 = 32 GT/s signal-rate per lane with 128/130 encoding = 4   GB/s data-rate per lane
-   * PCIe Gen6 = 64 GT/s signal-rate per lane with 128/130 encoding = 8   GB/s data-rate per lane
+  /*
+   * These are single-direction bandwidths only.
+   *
+   * Gen1 used NRZ with 8/10 encoding.
+   * PCIe Gen1 = 2.5GT/s signal-rate per lane x 8/10    =  0.25GB/s data-rate per lane
+   * PCIe Gen2 = 5  GT/s signal-rate per lane x 8/10    =  0.5 GB/s data-rate per lane
+   * Gen3 switched to NRZ with 128/130 encoding.
+   * PCIe Gen3 = 8  GT/s signal-rate per lane x 128/130 =  1   GB/s data-rate per lane
+   * PCIe Gen4 = 16 GT/s signal-rate per lane x 128/130 =  2   GB/s data-rate per lane
+   * PCIe Gen5 = 32 GT/s signal-rate per lane x 128/130 =  4   GB/s data-rate per lane
+   * Gen6 switched to PAM with with 242/256 FLIT (242B payload protected by 8B CRC + 6B FEC).
+   * PCIe Gen6 = 64 GT/s signal-rate per lane x 242/256 =  8   GB/s data-rate per lane
+   * PCIe Gen7 = 128GT/s signal-rate per lane x 242/256 = 16   GB/s data-rate per lane
    */
 
   /* lanespeed in Gbit/s */
   if (speed <= 2)
     lanespeed = 2.5f * speed * 0.8f;
+  else if (speed <= 5)
+    lanespeed = 8.0f * (1<<(speed-3)) * 128/130;
   else
-    lanespeed = 8.0f * (1<<(speed-3)) * 128/130; /* assume Gen7 will be 128 GT/s and so on */
+    lanespeed = 8.0f * (1<<(speed-3)) * 242/256; /* assume Gen8 will be 256 GT/s and so on */
 
   /* linkspeed in GB/s */
   *linkspeed = lanespeed * width / 8;
@@ -944,6 +1039,7 @@ hwloc_pci_class_string(unsigned short class_id)
       switch (class_id) {
 	case 0x0500: return "RAM";
 	case 0x0501: return "Flash";
+        case 0x0502: return "CXLMem";
       }
       return "Memory";
     case 0x06:

src/3rdparty/hwloc/src/topology-synthetic.c

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2020 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * Copyright © 2009-2010 Université Bordeaux
  * Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -323,17 +323,29 @@ hwloc_synthetic_parse_memory_attr(const char *attr, const char **endp)
   hwloc_uint64_t size;
   size = strtoull(attr, (char **) &endptr, 0);
   if (!hwloc_strncasecmp(endptr, "TB", 2)) {
+    size *= 1000ULL*1000ULL*1000ULL*1000ULL;
+    endptr += 2;
+  } else if (!hwloc_strncasecmp(endptr, "TiB", 3)) {
     size <<= 40;
-    endptr += 2;
+    endptr += 3;
   } else if (!hwloc_strncasecmp(endptr, "GB", 2)) {
+    size *= 1000ULL*1000ULL*1000ULL;
+    endptr += 2;
+  } else if (!hwloc_strncasecmp(endptr, "GiB", 3)) {
     size <<= 30;
-    endptr += 2;
+    endptr += 3;
   } else if (!hwloc_strncasecmp(endptr, "MB", 2)) {
+    size *= 1000ULL*1000ULL;
+    endptr += 2;
+  } else if (!hwloc_strncasecmp(endptr, "MiB", 3)) {
     size <<= 20;
-    endptr += 2;
+    endptr += 3;
   } else if (!hwloc_strncasecmp(endptr, "kB", 2)) {
-    size <<= 10;
+    size *= 1000ULL;
     endptr += 2;
+  } else if (!hwloc_strncasecmp(endptr, "kiB", 3)) {
+    size <<= 10;
+    endptr += 3;
   }
   *endp = endptr;
   return size;
@@ -802,15 +814,15 @@ hwloc_backend_synthetic_init(struct hwloc_synthetic_backend_data_s *data,
     } else if (hwloc__obj_type_is_cache(type)) {
       if (!curlevel->attr.memorysize) {
 	if (1 == curlevel->attr.depth)
-	  /* 32Kb in L1 */
+	  /* 32KiB in L1 */
 	  curlevel->attr.memorysize = 32*1024;
 	else
-	  /* *4 at each level, starting from 1MB for L2, unified */
+	  /* *4 at each level, starting from 1MiB for L2, unified */
 	  curlevel->attr.memorysize = 256ULL*1024 << (2*curlevel->attr.depth);
       }
 
     } else if (type == HWLOC_OBJ_NUMANODE && !curlevel->attr.memorysize) {
-      /* 1GB in memory nodes. */
+      /* 1GiB in memory nodes. */
       curlevel->attr.memorysize = 1024*1024*1024;
     }
 

src/3rdparty/hwloc/src/topology-windows.c

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2021 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * Copyright © 2009-2012, 2020 Université Bordeaux
  * Copyright © 2011 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -366,7 +366,7 @@ hwloc_win_get_processor_groups(void)
   hwloc_debug("found %lu windows processor groups\n", nr_processor_groups);
 
   if (nr_processor_groups > 1 && SIZEOF_VOID_P == 4) {
-    if (!hwloc_hide_errors())
+    if (HWLOC_SHOW_ALL_ERRORS())
       fprintf(stderr, "hwloc: multiple processor groups found on 32bits Windows, topology may be invalid/incomplete.\n");
   }
 

src/3rdparty/hwloc/src/topology-x86.c

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2010-2021 Inria.  All rights reserved.
+ * Copyright © 2010-2022 Inria.  All rights reserved.
  * Copyright © 2010-2013 Université Bordeaux
  * Copyright © 2010-2011 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -1349,7 +1349,7 @@ look_procs(struct hwloc_backend *backend, struct procinfo *infos, unsigned long
   if (data->apicid_unique) {
     summarize(backend, infos, flags);
 
-    if (has_hybrid(features)) {
+    if (has_hybrid(features) && !(topology->flags & HWLOC_TOPOLOGY_FLAG_NO_CPUKINDS)) {
       /* use hybrid info for cpukinds */
       hwloc_bitmap_t atomset = hwloc_bitmap_alloc();
       hwloc_bitmap_t coreset = hwloc_bitmap_alloc();

src/3rdparty/hwloc/src/topology-xml.c

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2021 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * Copyright © 2009-2011, 2020 Université Bordeaux
  * Copyright © 2009-2018 Cisco Systems, Inc.  All rights reserved.
  * See COPYING in top-level directory.
@@ -123,6 +123,17 @@ hwloc__xml_import_object_attr(struct hwloc_topology *topology,
       fprintf(stderr, "%s: unexpected zero gp_index, topology may be invalid\n", state->global->msgprefix);
     if (obj->gp_index >= topology->next_gp_index)
       topology->next_gp_index = obj->gp_index + 1;
+  } else if (!strcmp(name, "id")) { /* forward compat */
+    if (!strncmp(value, "obj", 3)) {
+      obj->gp_index = strtoull(value+3, NULL, 10);
+      if (!obj->gp_index && hwloc__xml_verbose())
+        fprintf(stderr, "%s: unexpected zero id, topology may be invalid\n", state->global->msgprefix);
+      if (obj->gp_index >= topology->next_gp_index)
+        topology->next_gp_index = obj->gp_index + 1;
+    } else {
+      if (hwloc__xml_verbose())
+        fprintf(stderr, "%s: unexpected id `%s' not-starting with `obj', ignoring\n", state->global->msgprefix, value);
+    }
   } else if (!strcmp(name, "cpuset")) {
     if (!obj->cpuset)
       obj->cpuset = hwloc_bitmap_alloc();
@@ -263,7 +274,7 @@ hwloc__xml_import_object_attr(struct hwloc_topology *topology,
 #ifndef HWLOC_HAVE_32BITS_PCI_DOMAIN
       } else if (domain > 0xffff) {
 	static int warned = 0;
-	if (!warned && hwloc_hide_errors() < 2)
+	if (!warned && HWLOC_SHOW_ALL_ERRORS())
 	  fprintf(stderr, "hwloc/xml: Ignoring PCI device with non-16bit domain.\nPass --enable-32bits-pci-domain to configure to support such devices\n(warning: it would break the library ABI, don't enable unless really needed).\n");
 	warned = 1;
 	*ignore = 1;
@@ -363,7 +374,7 @@ hwloc__xml_import_object_attr(struct hwloc_topology *topology,
 #ifndef HWLOC_HAVE_32BITS_PCI_DOMAIN
       } else if (domain > 0xffff) {
 	static int warned = 0;
-	if (!warned && hwloc_hide_errors() < 2)
+	if (!warned && HWLOC_SHOW_ALL_ERRORS())
 	  fprintf(stderr, "hwloc/xml: Ignoring bridge to PCI with non-16bit domain.\nPass --enable-32bits-pci-domain to configure to support such devices\n(warning: it would break the library ABI, don't enable unless really needed).\n");
 	warned = 1;
 	*ignore = 1;
@@ -1235,7 +1246,7 @@ hwloc__xml_import_object(hwloc_topology_t topology,
 	/* next should be before cur */
 	if (!childrengotignored) {
 	  static int reported = 0;
-	  if (!reported && hwloc_hide_errors() < 2) {
+	  if (!reported && HWLOC_SHOW_CRITICAL_ERRORS()) {
 	    hwloc__xml_import_report_outoforder(topology, next, cur);
 	    reported = 1;
 	  }
@@ -1568,6 +1579,9 @@ hwloc__xml_v2import_distances(hwloc_topology_t topology,
     }
   }
 
+  if (topology->flags & HWLOC_TOPOLOGY_FLAG_NO_DISTANCES)
+    goto out_ignore;
+
   hwloc_internal_distances_add_by_index(topology, name, unique_type, different_types, nbobjs, indexes, u64values, kind, 0 /* assume grouping was applied when this matrix was discovered before exporting to XML */);
 
   /* prevent freeing below */
@@ -1722,7 +1736,8 @@ hwloc__xml_import_memattr(hwloc_topology_t topology,
     }
   }
 
-  if (name && flags != (unsigned long) -1) {
+  if (name && flags != (unsigned long) -1
+      && !(topology->flags & HWLOC_TOPOLOGY_FLAG_NO_MEMATTRS)) {
     hwloc_memattr_id_t _id;
 
     ret = hwloc_memattr_get_by_name(topology, name, &_id);
@@ -1833,7 +1848,13 @@ hwloc__xml_import_cpukind(hwloc_topology_t topology,
     goto error;
   }
 
-  hwloc_internal_cpukinds_register(topology, cpuset, forced_efficiency, infos, nr_infos, HWLOC_CPUKINDS_REGISTER_FLAG_OVERWRITE_FORCED_EFFICIENCY);
+  if (topology->flags & HWLOC_TOPOLOGY_FLAG_NO_CPUKINDS) {
+    hwloc__free_infos(infos, nr_infos);
+    hwloc_bitmap_free(cpuset);
+  } else {
+    hwloc_internal_cpukinds_register(topology, cpuset, forced_efficiency, infos, nr_infos, HWLOC_CPUKINDS_REGISTER_FLAG_OVERWRITE_FORCED_EFFICIENCY);
+    hwloc__free_infos(infos, nr_infos);
+  }
 
   return state->global->close_tag(state);
 
@@ -2168,7 +2189,8 @@ done:
        * but it would require to have those objects in the original XML order (like the first_numanode cousin-list).
        * because the topology order can be different if some parents are ignored during load.
        */
-      if (nbobjs == data->nbnumanodes) {
+      if (nbobjs == data->nbnumanodes
+          && !(topology->flags & HWLOC_TOPOLOGY_FLAG_NO_DISTANCES)) {
 	hwloc_obj_t *objs = malloc(nbobjs*sizeof(hwloc_obj_t));
 	uint64_t *values = malloc(nbobjs*nbobjs*sizeof(*values));
         assert(data->nbnumanodes > 0); /* v1dist->nbobjs is >0 after import */
@@ -2650,7 +2672,7 @@ hwloc__xml_export_object_contents (hwloc__xml_export_state_t state, hwloc_topolo
 
       logical_to_v2array = malloc(nbobjs * sizeof(*logical_to_v2array));
       if (!logical_to_v2array) {
-        if (!hwloc_hide_errors())
+        if (HWLOC_SHOW_ALL_ERRORS())
           fprintf(stderr, "hwloc/xml/export/v1: failed to allocated logical_to_v2array\n");
 	continue;
       }
@@ -3124,9 +3146,11 @@ hwloc__xml_export_memattrs(hwloc__xml_export_state_t state, hwloc_topology_t top
       continue;
 
     imattr = &topology->memattrs[id];
-    if ((id == HWLOC_MEMATTR_ID_LATENCY || id == HWLOC_MEMATTR_ID_BANDWIDTH)
-        && !imattr->nr_targets)
-      /* no need to export target-less attributes for initial attributes, no release support attributes without those definitions */
+    if (id < HWLOC_MEMATTR_ID_MAX && !imattr->nr_targets)
+      /* no need to export standard attributes without any target,
+       * their definition is now standardized,
+       * the old hwloc importing this XML may recreate these attributes just like it would for a non-imported topology.
+       */
       continue;
 
     state->new_child(state, &mstate, "memattr");

src/3rdparty/hwloc/src/topology.c

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2021 Inria.  All rights reserved.
+ * Copyright © 2009-2022 Inria.  All rights reserved.
  * Copyright © 2009-2012, 2020 Université Bordeaux
  * Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
  * Copyright © 2022 IBM Corporation.  All rights reserved.
@@ -114,14 +114,25 @@ int hwloc_topology_abi_check(hwloc_topology_t topology)
   return topology->topology_abi != HWLOC_TOPOLOGY_ABI ? -1 : 0;
 }
 
+/* callers should rather use wrappers HWLOC_SHOW_ALL_ERRORS() and HWLOC_SHOW_CRITICAL_ERRORS() for clarity */
 int hwloc_hide_errors(void)
 {
   static int hide = 1; /* only show critical errors by default. lstopo will show others */
   static int checked = 0;
   if (!checked) {
     const char *envvar = getenv("HWLOC_HIDE_ERRORS");
-    if (envvar)
+    if (envvar) {
       hide = atoi(envvar);
+#ifdef HWLOC_DEBUG
+    } else {
+      /* if debug is enabled and HWLOC_DEBUG_VERBOSE isn't forced to 0,
+       * show all errors jus like we show all debug messages.
+       */
+      envvar = getenv("HWLOC_DEBUG_VERBOSE");
+      if (!envvar || atoi(envvar))
+        hide = 0;
+#endif
+    }
     checked = 1;
   }
   return hide;
@@ -158,7 +169,7 @@ static void report_insert_error(hwloc_obj_t new, hwloc_obj_t old, const char *ms
 {
   static int reported = 0;
 
-  if (reason && !reported && hwloc_hide_errors() < 2) {
+  if (reason && !reported && HWLOC_SHOW_CRITICAL_ERRORS()) {
     char newstr[512];
     char oldstr[512];
     report_insert_error_format_obj(newstr, sizeof(newstr), new);
@@ -3178,7 +3189,7 @@ hwloc_connect_levels(hwloc_topology_t topology)
       tmpnbobjs = realloc(topology->level_nbobjects,
 			  2 * topology->nb_levels_allocated * sizeof(*topology->level_nbobjects));
       if (!tmplevels || !tmpnbobjs) {
-        if (hwloc_hide_errors() < 2)
+        if (HWLOC_SHOW_CRITICAL_ERRORS())
           fprintf(stderr, "hwloc: failed to realloc level arrays to %u\n", topology->nb_levels_allocated * 2);
 
 	/* if one realloc succeeded, make sure the caller will free the new buffer */
@@ -3536,6 +3547,8 @@ hwloc_discover(struct hwloc_topology *topology,
   /*
    * Additional discovery
    */
+  hwloc_pci_discovery_prepare(topology);
+
   if (topology->backend_phases & HWLOC_DISC_PHASE_PCI) {
     dstatus->phase = HWLOC_DISC_PHASE_PCI;
     hwloc_discover_by_phase(topology, dstatus, "PCI");
@@ -3553,6 +3566,8 @@ hwloc_discover(struct hwloc_topology *topology,
     hwloc_discover_by_phase(topology, dstatus, "ANNOTATE");
   }
 
+  hwloc_pci_discovery_exit(topology); /* pci needed up to annotate */
+
   if (getenv("HWLOC_DEBUG_SORT_CHILDREN"))
     hwloc_debug_sort_children(topology->levels[0][0]);
 
@@ -3565,17 +3580,17 @@ hwloc_discover(struct hwloc_topology *topology,
   hwloc_debug("%s", "\nRemoving empty objects\n");
   remove_empty(topology, &topology->levels[0][0]);
   if (!topology->levels[0][0]) {
-    if (hwloc_hide_errors() < 2)
+    if (HWLOC_SHOW_CRITICAL_ERRORS())
       fprintf(stderr, "hwloc: Topology became empty, aborting!\n");
     return -1;
   }
   if (hwloc_bitmap_iszero(topology->levels[0][0]->cpuset)) {
-    if (hwloc_hide_errors() < 2)
+    if (HWLOC_SHOW_CRITICAL_ERRORS())
       fprintf(stderr, "hwloc: Topology does not contain any PU, aborting!\n");
     return -1;
   }
   if (hwloc_bitmap_iszero(topology->levels[0][0]->nodeset)) {
-    if (hwloc_hide_errors() < 2)
+    if (HWLOC_SHOW_CRITICAL_ERRORS())
       fprintf(stderr, "hwloc: Topology does not contain any NUMA node, aborting!\n");
     return -1;
   }
@@ -3811,7 +3826,16 @@ hwloc_topology_set_flags (struct hwloc_topology *topology, unsigned long flags)
     return -1;
   }
 
-  if (flags & ~(HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED|HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM|HWLOC_TOPOLOGY_FLAG_THISSYSTEM_ALLOWED_RESOURCES|HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT|HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING|HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_MEMBINDING|HWLOC_TOPOLOGY_FLAG_DONT_CHANGE_BINDING)) {
+  if (flags & ~(HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED
+                |HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM
+                |HWLOC_TOPOLOGY_FLAG_THISSYSTEM_ALLOWED_RESOURCES
+                |HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT
+                |HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING
+                |HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_MEMBINDING
+                |HWLOC_TOPOLOGY_FLAG_DONT_CHANGE_BINDING
+                |HWLOC_TOPOLOGY_FLAG_NO_DISTANCES
+                |HWLOC_TOPOLOGY_FLAG_NO_MEMATTRS
+                |HWLOC_TOPOLOGY_FLAG_NO_CPUKINDS)) {
     errno = EINVAL;
     return -1;
   }
@@ -4076,15 +4100,11 @@ hwloc_topology_load (struct hwloc_topology *topology)
    */
   hwloc_set_binding_hooks(topology);
 
-  hwloc_pci_discovery_prepare(topology);
-
   /* actual topology discovery */
   err = hwloc_discover(topology, &dstatus);
   if (err < 0)
     goto out;
 
-  hwloc_pci_discovery_exit(topology);
-
 #ifndef HWLOC_DEBUG
   if (getenv("HWLOC_DEBUG_CHECK"))
 #endif
@@ -4106,6 +4126,7 @@ hwloc_topology_load (struct hwloc_topology *topology)
   /* Same for memattrs */
   hwloc_internal_memattrs_need_refresh(topology);
   hwloc_internal_memattrs_refresh(topology);
+  hwloc_internal_memattrs_guess_memory_tiers(topology);
 
   topology->is_loaded = 1;
 

src/3rdparty/libethash/CMakeLists.txt

@@ -1,4 +1,4 @@
-cmake_minimum_required (VERSION 2.8.12)
+cmake_minimum_required(VERSION 3.1)
 project (ethash C)
 
 set(CMAKE_C_FLAGS_RELEASE "${CMAKE_C_FLAGS_RELEASE} -Os")

src/backend/cpu/Cpu.h

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2020 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -37,7 +37,7 @@ public:
 };
 
 
-} /* namespace xmrig */
+} // namespace xmrig
 
 
-#endif /* XMRIG_CPU_H */
+#endif // XMRIG_CPU_H

src/backend/cpu/CpuWorker.cpp

@@ -33,6 +33,7 @@
 #include "crypto/common/Nonce.h"
 #include "crypto/common/VirtualMemory.h"
 #include "crypto/rx/Rx.h"
+#include "crypto/rx/RxCache.h"
 #include "crypto/rx/RxDataset.h"
 #include "crypto/rx/RxVm.h"
 #include "crypto/ghostrider/ghostrider.h"
@@ -145,6 +146,11 @@ void xmrig::CpuWorker<N>::allocateRandomX_VM()
         uint8_t* scratchpad = m_memory->isHugePages() ? m_memory->scratchpad() : dataset->tryAllocateScrathpad();
         m_vm = RxVm::create(dataset, scratchpad ? scratchpad : m_memory->scratchpad(), !m_hwAES, m_assembly, node());
     }
+    else if (!dataset->get() && (m_job.currentJob().seed() != m_seed)) {
+        // Update RandomX light VM with the new seed
+        randomx_vm_set_cache(m_vm, dataset->cache()->get());
+    }
+    m_seed = m_job.currentJob().seed();
 }
 #endif
 

src/backend/cpu/CpuWorker.h

@@ -97,6 +97,7 @@ private:
 
 #   ifdef XMRIG_ALGO_RANDOMX
     randomx_vm *m_vm        = nullptr;
+    Buffer m_seed;
 #   endif
 
 #   ifdef XMRIG_ALGO_GHOSTRIDER

src/backend/cpu/interfaces/ICpuInfo.h

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -26,6 +26,12 @@
 #include "crypto/common/Assembly.h"
 
 
+#ifdef XMRIG_FEATURE_HWLOC
+using hwloc_const_bitmap_t  = const struct hwloc_bitmap_s *;
+using hwloc_topology_t      = struct hwloc_topology *;
+#endif
+
+
 namespace xmrig {
 
 
@@ -116,10 +122,16 @@ public:
     virtual size_t threads() const                                                  = 0;
     virtual Vendor vendor() const                                                   = 0;
     virtual uint32_t model() const                                                  = 0;
+
+#   ifdef XMRIG_FEATURE_HWLOC
+    virtual bool membind(hwloc_const_bitmap_t nodeset)                              = 0;
+    virtual const std::vector<uint32_t> &nodeset() const                            = 0;
+    virtual hwloc_topology_t topology() const                                       = 0;
+#   endif
 };
 
 
-} /* namespace xmrig */
+} // namespace xmrig
 
 
 #endif // XMRIG_CPUINFO_H

src/backend/cpu/platform/BasicCpuInfo.cpp

@@ -296,7 +296,7 @@ xmrig::BasicCpuInfo::BasicCpuInfo() :
                 // Affected CPU models and stepping numbers are taken from https://www.intel.com/content/dam/support/us/en/documents/processors/mitigations-jump-conditional-code-erratum.pdf
                 m_jccErratum =
                     ((model == 0x4E) && (stepping == 0x3)) ||
-                    ((model == 0x55) && (stepping == 0x4)) ||
+                    ((model == 0x55) && ((stepping == 0x4) || (stepping == 0x7))) ||
                     ((model == 0x5E) && (stepping == 0x3)) ||
                     ((model == 0x8E) && (stepping >= 0x9) && (stepping <= 0xC)) ||
                     ((model == 0x9E) && (stepping >= 0x9) && (stepping <= 0xD)) ||

src/backend/cpu/platform/BasicCpuInfo.h

@@ -1,7 +1,7 @@
 /* XMRig
  * Copyright (c) 2017-2019 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -72,11 +72,10 @@ protected:
 #   endif
     }
 
-protected:
     Arch m_arch             = ARCH_UNKNOWN;
     bool m_jccErratum       = false;
     char m_brand[64 + 6]{};
-    size_t m_threads;
+    size_t m_threads        = 0;
     std::vector<int32_t> m_units;
     Vendor m_vendor         = VENDOR_UNKNOWN;
 
@@ -94,7 +93,7 @@ private:
 };
 
 
-} /* namespace xmrig */
+} // namespace xmrig
 
 
-#endif /* XMRIG_BASICCPUINFO_H */
+#endif // XMRIG_BASICCPUINFO_H

src/backend/cpu/platform/BasicCpuInfo_arm.cpp

@@ -27,7 +27,7 @@
 
 #if __ARM_FEATURE_CRYPTO && !defined(__APPLE__)
 #   include <sys/auxv.h>
-#   ifndef __FreeBSD__
+#   if !defined(XMRIG_OS_FREEBSD)
 #       include <asm/hwcap.h>
 #   else
 #       include <stdint.h>
@@ -71,7 +71,7 @@ xmrig::BasicCpuInfo::BasicCpuInfo() :
 #   if __ARM_FEATURE_CRYPTO
 #   if defined(__APPLE__)
     m_flags.set(FLAG_AES, true);
-#   elif defined(__FreeBSD__)
+#   elif defined(XMRIG_OS_FREEBSD)
     uint64_t isar0 = READ_SPECIALREG(id_aa64isar0_el1);
     m_flags.set(FLAG_AES, ID_AA64ISAR0_AES_VAL(isar0) >= ID_AA64ISAR0_AES_BASE);
 #   else

src/backend/cpu/platform/HwlocCpuInfo.cpp

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -36,27 +36,22 @@
 #include "base/io/log/Log.h"
 
 
-namespace xmrig {
-
-
-uint32_t HwlocCpuInfo::m_features = 0;
-
-
-static inline bool isCacheObject(hwloc_obj_t obj)
+#if HWLOC_API_VERSION < 0x20000
+static inline int hwloc_obj_type_is_cache(hwloc_obj_type_t type)
 {
-#   if HWLOC_API_VERSION >= 0x20000
-    return hwloc_obj_type_is_cache(obj->type);
-#   else
-    return obj->type == HWLOC_OBJ_CACHE;
-#   endif
+    return type == HWLOC_OBJ_CACHE;
 }
+#endif
+
+
+namespace xmrig {
 
 
 template <typename func>
 static inline void findCache(hwloc_obj_t obj, unsigned min, unsigned max, func lambda)
 {
     for (size_t i = 0; i < obj->arity; i++) {
-        if (isCacheObject(obj->children[i])) {
+        if (hwloc_obj_type_is_cache(obj->children[i]->type)) {
             const unsigned depth = obj->children[i]->attr->cache.depth;
             if (depth < min || depth > max) {
                 continue;
@@ -174,10 +169,6 @@ xmrig::HwlocCpuInfo::HwlocCpuInfo()
     m_packages  = countByType(m_topology, HWLOC_OBJ_PACKAGE);
 
     if (m_nodes > 1) {
-        if (hwloc_topology_get_support(m_topology)->membind->set_thisthread_membind) {
-            m_features |= SET_THISTHREAD_MEMBIND;
-        }
-
         m_nodeset.reserve(m_nodes);
         hwloc_obj_t node = nullptr;
 
@@ -298,8 +289,10 @@ void xmrig::HwlocCpuInfo::processTopLevelCache(hwloc_obj_t cache, const Algorith
     cores.reserve(m_cores);
     findByType(cache, HWLOC_OBJ_CORE, [&cores](hwloc_obj_t found) { cores.emplace_back(found); });
 
+    const bool L3_exclusive = isCacheExclusive(cache);
+
 #   ifdef XMRIG_ALGO_GHOSTRIDER
-    if ((algorithm == Algorithm::GHOSTRIDER_RTM) && (PUs > cores.size()) && (PUs < cores.size() * 2)) {
+    if ((algorithm == Algorithm::GHOSTRIDER_RTM) && L3_exclusive && (PUs > cores.size()) && (PUs < cores.size() * 2)) {
         // Don't use E-cores on Alder Lake
         cores.erase(std::remove_if(cores.begin(), cores.end(), [](hwloc_obj_t c) { return hwloc_bitmap_weight(c->cpuset) == 1; }), cores.end());
 
@@ -311,7 +304,6 @@ void xmrig::HwlocCpuInfo::processTopLevelCache(hwloc_obj_t cache, const Algorith
 #   endif
 
     size_t L3               = cache->attr->cache.size;
-    const bool L3_exclusive = isCacheExclusive(cache);
     size_t L2               = 0;
     int L2_associativity    = 0;
     size_t extra            = 0;
@@ -321,7 +313,7 @@ void xmrig::HwlocCpuInfo::processTopLevelCache(hwloc_obj_t cache, const Algorith
     if (cache->attr->cache.depth == 3) {
         for (size_t i = 0; i < cache->arity; ++i) {
             hwloc_obj_t l2 = cache->children[i];
-            if (!isCacheObject(l2) || l2->attr == nullptr) {
+            if (!hwloc_obj_type_is_cache(l2->type) || l2->attr == nullptr) {
                 continue;
             }
 
@@ -349,6 +341,10 @@ void xmrig::HwlocCpuInfo::processTopLevelCache(hwloc_obj_t cache, const Algorith
     }
 
 #   ifdef XMRIG_ALGO_RANDOMX
+    if ((algorithm.family() == Algorithm::RANDOM_X) && L3_exclusive && (PUs > cores.size()) && (PUs < cores.size() * 2)) {
+        // Use all L3+L2 on latest Intel CPUs with P-cores, E-cores and exclusive L3 cache
+        cacheHashes = (L3 + L2) / scratchpad;
+    }
     if (extra == 0 && algorithm.l2() > 0) {
         cacheHashes = std::min<size_t>(std::max<size_t>(L2 / algorithm.l2(), cores.size()), cacheHashes);
     }

src/backend/cpu/platform/HwlocCpuInfo.h

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -21,12 +21,9 @@
 
 
 #include "backend/cpu/platform/BasicCpuInfo.h"
-#include "base/tools/Object.h"
 
 
-using hwloc_const_bitmap_t  = const struct hwloc_bitmap_s *;
-using hwloc_obj_t           = struct hwloc_obj *;
-using hwloc_topology_t      = struct hwloc_topology *;
+using hwloc_obj_t = struct hwloc_obj *;
 
 
 namespace xmrig {
@@ -37,39 +34,27 @@ class HwlocCpuInfo : public BasicCpuInfo
 public:
     XMRIG_DISABLE_COPY_MOVE(HwlocCpuInfo)
 
-
-    enum Feature : uint32_t {
-        SET_THISTHREAD_MEMBIND = 1
-    };
-
-
     HwlocCpuInfo();
     ~HwlocCpuInfo() override;
 
-    static inline bool hasFeature(Feature feature)              { return m_features & feature; }
-
-    inline const std::vector<uint32_t> &nodeset() const         { return m_nodeset; }
-    inline hwloc_topology_t topology() const                    { return m_topology; }
-
-    bool membind(hwloc_const_bitmap_t nodeset);
-
 protected:
+    bool membind(hwloc_const_bitmap_t nodeset) override;
     CpuThreads threads(const Algorithm &algorithm, uint32_t limit) const override;
 
-    inline const char *backend() const override     { return m_backend; }
-    inline size_t cores() const override            { return m_cores; }
-    inline size_t L2() const override               { return m_cache[2]; }
-    inline size_t L3() const override               { return m_cache[3]; }
-    inline size_t nodes() const override            { return m_nodes; }
-    inline size_t packages() const override         { return m_packages; }
+    inline const char *backend() const override                     { return m_backend; }
+    inline const std::vector<uint32_t> &nodeset() const override    { return m_nodeset; }
+    inline hwloc_topology_t topology() const override               { return m_topology; }
+    inline size_t cores() const override                            { return m_cores; }
+    inline size_t L2() const override                               { return m_cache[2]; }
+    inline size_t L3() const override                               { return m_cache[3]; }
+    inline size_t nodes() const override                            { return m_nodes; }
+    inline size_t packages() const override                         { return m_packages; }
 
 private:
     CpuThreads allThreads(const Algorithm &algorithm, uint32_t limit) const;
     void processTopLevelCache(hwloc_obj_t cache, const Algorithm &algorithm, CpuThreads &threads, size_t limit) const;
     void setThreads(size_t threads);
 
-    static uint32_t m_features;
-
     char m_backend[20]          = { 0 };
     hwloc_topology_t m_topology = nullptr;
     size_t m_cache[5]           = { 0 };
@@ -80,7 +65,7 @@ private:
 };
 
 
-} /* namespace xmrig */
+} // namespace xmrig
 
 
-#endif /* XMRIG_HWLOCCPUINFO_H */
+#endif // XMRIG_HWLOCCPUINFO_H

src/backend/cpu/platform/lscpu_arm.cpp

@@ -1,7 +1,7 @@
 /* XMRig
  * Copyright (c) 2018      Riku Voipio <riku.voipio@iki.fi>
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -17,7 +17,6 @@
  *   along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
-
 #include "base/tools/String.h"
 #include "3rdparty/fmt/core.h"
 
@@ -84,6 +83,7 @@ static const id_part arm_part[] = {
     { 0xc27, "Cortex-M7" },
     { 0xc60, "Cortex-M0+" },
     { 0xd01, "Cortex-A32" },
+    { 0xd02, "Cortex-A34" },
     { 0xd03, "Cortex-A53" },
     { 0xd04, "Cortex-A35" },
     { 0xd05, "Cortex-A55" },
@@ -97,40 +97,60 @@ static const id_part arm_part[] = {
     { 0xd0d, "Cortex-A77" },
     { 0xd0e, "Cortex-A76AE" },
     { 0xd13, "Cortex-R52" },
+    { 0xd15, "Cortex-R82" },
     { 0xd20, "Cortex-M23" },
     { 0xd21, "Cortex-M33" },
+    { 0xd40, "Neoverse-V1" },
     { 0xd41, "Cortex-A78" },
     { 0xd42, "Cortex-A78AE" },
+    { 0xd43, "Cortex-A65AE" },
+    { 0xd44, "Cortex-X1" },
+    { 0xd46, "Cortex-A510" },
+    { 0xd47, "Cortex-A710" },
+    { 0xd48, "Cortex-X2" },
+    { 0xd49, "Neoverse-N2" },
     { 0xd4a, "Neoverse-E1" },
     { 0xd4b, "Cortex-A78C" },
-    { -1, nullptr },
+    { 0xd4c, "Cortex-X1C" },
+    { 0xd4d, "Cortex-A715" },
+    { 0xd4e, "Cortex-X3" },
+    { 0xd4f, "Neoverse-V2" },
+    { -1, nullptr }
 };
 
 static const id_part brcm_part[] = {
-    { 0x0f, "Brahma B15" },
-    { 0x100, "Brahma B53" },
+    { 0x0f, "Brahma-B15" },
+    { 0x100, "Brahma-B53" },
     { 0x516, "ThunderX2" },
-    { -1, nullptr },
+    { -1, nullptr }
 };
 
 static const id_part dec_part[] = {
     { 0xa10, "SA110" },
     { 0xa11, "SA1100" },
-    { -1, nullptr },
+    { -1, nullptr }
 };
 
 static const id_part cavium_part[] = {
     { 0x0a0, "ThunderX" },
-    { 0x0a1, "ThunderX 88XX" },
-    { 0x0a2, "ThunderX 81XX" },
-    { 0x0a3, "ThunderX 83XX" },
-    { 0x0af, "ThunderX2 99xx" },
-    { -1, nullptr },
+    { 0x0a1, "ThunderX-88XX" },
+    { 0x0a2, "ThunderX-81XX" },
+    { 0x0a3, "ThunderX-83XX" },
+    { 0x0af, "ThunderX2-99xx" },
+    { 0x0b0, "OcteonTX2" },
+    { 0x0b1, "OcteonTX2-98XX" },
+    { 0x0b2, "OcteonTX2-96XX" },
+    { 0x0b3, "OcteonTX2-95XX" },
+    { 0x0b4, "OcteonTX2-95XXN" },
+    { 0x0b5, "OcteonTX2-95XXMM" },
+    { 0x0b6, "OcteonTX2-95XXO" },
+    { 0x0b8, "ThunderX3-T110" },
+    { -1, nullptr }
 };
 
 static const id_part apm_part[] = {
     { 0x000, "X-Gene" },
-    { -1, nullptr },
+    { -1, nullptr }
 };
 
 static const id_part qcom_part[] = {
@@ -141,36 +161,43 @@ static const id_part qcom_part[] = {
     { 0x201, "Kryo" },
     { 0x205, "Kryo" },
     { 0x211, "Kryo" },
-    { 0x800, "Falkor V1/Kryo" },
-    { 0x801, "Kryo V2" },
+    { 0x800, "Falkor-V1/Kryo" },
+    { 0x801, "Kryo-V2" },
+    { 0x802, "Kryo-3XX-Gold" },
+    { 0x803, "Kryo-3XX-Silver" },
+    { 0x804, "Kryo-4XX-Gold" },
+    { 0x805, "Kryo-4XX-Silver" },
     { 0xc00, "Falkor" },
     { 0xc01, "Saphira" },
-    { -1, nullptr },
+    { -1, nullptr }
 };
 
 static const id_part samsung_part[] = {
     { 0x001, "exynos-m1" },
-    { -1, nullptr },
+    { 0x002, "exynos-m3" },
+    { 0x003, "exynos-m4" },
+    { 0x004, "exynos-m5" },
+    { -1, nullptr }
 };
 
 static const id_part nvidia_part[] = {
     { 0x000, "Denver" },
     { 0x003, "Denver 2" },
     { 0x004, "Carmel" },
-    { -1, nullptr },
+    { -1, nullptr }
 };
 
 static const id_part marvell_part[] = {
-    { 0x131, "Feroceon 88FR131" },
+    { 0x131, "Feroceon-88FR131" },
     { 0x581, "PJ4/PJ4b" },
     { 0x584, "PJ4B-MP" },
-    { -1, nullptr },
+    { -1, nullptr }
 };
 
 static const id_part faraday_part[] = {
     { 0x526, "FA526" },
     { 0x626, "FA626" },
-    { -1, nullptr },
+    { -1, nullptr }
 };
 
 static const id_part intel_part[] = {
@@ -195,23 +222,50 @@ static const id_part intel_part[] = {
     { 0x689, "PXA31x" },
     { 0xb11, "SA1110" },
     { 0xc12, "IPX1200" },
-    { -1, nullptr },
+    { -1, nullptr }
 };
 
 static const struct id_part fujitsu_part[] = {
     { 0x001, "A64FX" },
-    { -1, "unknown" },
+    { -1, nullptr }
 };
 
 static const id_part hisi_part[] = {
-    { 0xd01, "Kunpeng-920" }, /* aka tsv110 */
-    { -1, nullptr },
+    { 0xd01, "Kunpeng-920" },	/* aka tsv110 */
+    { 0xd40, "Cortex-A76" },	/* HiSilicon uses this ID though advertises A76 */
+    { -1, nullptr }
 };
 
 static const id_part apple_part[] = {
     { 0x022, "M1" },
     { 0x023, "M1" },
-    { -1, nullptr },
+    { 0x024, "M1-Pro" },
+    { 0x025, "M1-Pro" },
+    { 0x028, "M1-Max" },
+    { 0x029, "M1-Max" },
+    { 0x032, "M2" },
+    { 0x033, "M2" },
+    { 0x034, "M2-Pro" },
+    { 0x035, "M2-Pro" },
+    { 0x038, "M2-Max" },
+    { 0x039, "M2-Max" },
+    { -1, nullptr }
+};
+
+
+static const struct id_part ft_part[] = {
+    { 0x660, "FTC660" },
+    { 0x661, "FTC661" },
+    { 0x662, "FTC662" },
+    { 0x663, "FTC663" },
+    { -1, nullptr }
+};
+
+
+static const struct id_part ampere_part[] = {
+    { 0xac3, "Ampere-1" },
+    { 0xac4, "Ampere-1a" },
+    { -1, nullptr }
 };
 
 
@@ -229,7 +283,9 @@ static const hw_impl hw_implementer[] = {
     { 0x56, marvell_part, "Marvell" },
     { 0x61, apple_part,   "Apple" },
     { 0x66, faraday_part, "Faraday" },
-    { 0x69, intel_part,   "Intel" }
+    { 0x69, intel_part,   "Intel" },
+    { 0x70, ft_part,      "Phytium" },
+    { 0xc0, ampere_part,  "Ampere" }
 };
 
 

src/backend/cuda/wrappers/CudaLib.cpp

@@ -353,13 +353,9 @@ bool xmrig::CudaLib::open()
 #   ifdef XMRIG_OS_LINUX
     if (m_loader == defaultLoader) {
         m_loader = Process::location(Process::ExeLocation, m_loader);
-    }
-    else {
-        return false;
-    }
-
-    if (uv_dlopen(m_loader, &cudaLib) == 0) {
-        return true;
+        if (uv_dlopen(m_loader, &cudaLib) == 0) {
+            return true;
+        }
     }
 #   endif
 

src/backend/opencl/runners/OclBaseRunner.cpp

@@ -23,6 +23,9 @@
  */
 
 
+#include <stdexcept>
+
+
 #include "backend/opencl/runners/OclBaseRunner.h"
 #include "backend/opencl/cl/OclSource.h"
 #include "backend/opencl/OclCache.h"

src/backend/opencl/runners/OclCnRunner.cpp

@@ -16,6 +16,9 @@
  *   along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <stdexcept>
+
+
 #include "backend/opencl/runners/OclCnRunner.h"
 #include "backend/opencl/kernels/Cn0Kernel.h"
 #include "backend/opencl/kernels/Cn1Kernel.h"

src/backend/opencl/runners/OclKawPowRunner.cpp

@@ -16,6 +16,9 @@
  *   along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <stdexcept>
+
+
 #include "backend/opencl/runners/OclKawPowRunner.h"
 #include "backend/common/Tags.h"
 #include "3rdparty/libethash/ethash_internal.h"

src/backend/opencl/runners/OclRxJitRunner.cpp

@@ -16,6 +16,9 @@
  *   along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <stdexcept>
+
+
 #include "backend/opencl/runners/OclRxJitRunner.h"
 #include "backend/opencl/cl/rx/randomx_run_gfx803.h"
 #include "backend/opencl/cl/rx/randomx_run_gfx900.h"

src/base/api/Api.cpp

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -123,6 +123,21 @@ void xmrig::Api::stop()
 }
 
 
+void xmrig::Api::tick()
+{
+#   ifdef XMRIG_FEATURE_HTTP
+    if (m_httpd->isBound() || !m_base->config()->http().isEnabled()) {
+        return;
+    }
+
+    if (++m_ticks % 10 == 0) {
+        m_ticks = 0;
+        m_httpd->start();
+    }
+#   endif
+}
+
+
 void xmrig::Api::onConfigChanged(Config *config, Config *previousConfig)
 {
     if (config->apiId() != previousConfig->apiId()) {

src/base/api/Api.h

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -21,7 +21,6 @@
 
 
 #include <vector>
-#include <cstdint>
 
 
 #include "base/kernel/interfaces/IBaseListener.h"
@@ -44,7 +43,7 @@ class Api : public IBaseListener
 public:
     XMRIG_DISABLE_COPY_MOVE_DEFAULT(Api)
 
-    Api(Base *base);
+    explicit Api(Base *base);
     ~Api() override;
 
     inline const char *id() const                   { return m_id; }
@@ -54,6 +53,7 @@ public:
     void request(const HttpData &req);
     void start();
     void stop();
+    void tick();
 
 protected:
     void onConfigChanged(Config *config, Config *previousConfig) override;
@@ -65,14 +65,15 @@ private:
 
     Base *m_base;
     char m_id[32]{};
-    String m_workerId;
     const uint64_t m_timestamp;
-    Httpd *m_httpd = nullptr;
+    Httpd *m_httpd  = nullptr;
     std::vector<IApiListener *> m_listeners;
+    String m_workerId;
+    uint8_t m_ticks = 0;
 };
 
 
 } // namespace xmrig
 
 
-#endif /* XMRIG_API_H */
+#endif // XMRIG_API_H

src/base/api/Httpd.h

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -22,11 +22,6 @@
 
 #include "base/kernel/interfaces/IBaseListener.h"
 #include "base/net/http/HttpListener.h"
-#include "base/tools/Object.h"
-
-
-#include <cstdint>
-#include <memory>
 
 
 namespace xmrig {
@@ -43,9 +38,11 @@ class Httpd : public IBaseListener, public IHttpListener
 public:
     XMRIG_DISABLE_COPY_MOVE_DEFAULT(Httpd)
 
-    Httpd(Base *base);
+    explicit Httpd(Base *base);
     ~Httpd() override;
 
+    inline bool isBound() const { return m_server != nullptr; }
+
     bool start();
     void stop();
 
@@ -69,7 +66,7 @@ private:
 };
 
 
-} /* namespace xmrig */
+} // namespace xmrig
 
 
-#endif /* XMRIG_HTTPD_H */
+#endif // XMRIG_HTTPD_H

src/base/kernel/Platform.cpp

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -16,7 +16,6 @@
  *   along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
-
 #include "base/kernel/Platform.h"
 
 
@@ -42,9 +41,12 @@ void xmrig::Platform::init(const char *userAgent)
 #   ifdef XMRIG_FEATURE_TLS
     SSL_library_init();
     SSL_load_error_strings();
+
+#   if OPENSSL_VERSION_NUMBER < 0x30000000L || defined(LIBRESSL_VERSION_NUMBER)
     ERR_load_BIO_strings();
     ERR_load_crypto_strings();
-    SSL_load_error_strings();
+#   endif
+
     OpenSSL_add_all_digests();
 #   endif
 

src/base/kernel/Platform_hwloc.cpp

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2020 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -16,9 +16,7 @@
  *   along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
-
 #include "base/kernel/Platform.h"
-#include "backend/cpu/platform/HwlocCpuInfo.h"
 #include "backend/cpu/Cpu.h"
 
 
@@ -29,20 +27,21 @@
 #ifndef XMRIG_OS_APPLE
 bool xmrig::Platform::setThreadAffinity(uint64_t cpu_id)
 {
-    auto cpu       = static_cast<HwlocCpuInfo *>(Cpu::info());
-    hwloc_obj_t pu = hwloc_get_pu_obj_by_os_index(cpu->topology(), static_cast<unsigned>(cpu_id));
+    auto topology = Cpu::info()->topology();
+    auto pu       = hwloc_get_pu_obj_by_os_index(topology, static_cast<unsigned>(cpu_id));
 
     if (pu == nullptr) {
         return false;
     }
 
-    if (hwloc_set_cpubind(cpu->topology(), pu->cpuset, HWLOC_CPUBIND_THREAD | HWLOC_CPUBIND_STRICT) >= 0) {
+    if (hwloc_set_cpubind(topology, pu->cpuset, HWLOC_CPUBIND_THREAD | HWLOC_CPUBIND_STRICT) >= 0) {
         std::this_thread::sleep_for(std::chrono::milliseconds(1));
         return true;
     }
 
-    const bool result = (hwloc_set_cpubind(cpu->topology(), pu->cpuset, HWLOC_CPUBIND_THREAD) >= 0);
+    const bool result = (hwloc_set_cpubind(topology, pu->cpuset, HWLOC_CPUBIND_THREAD) >= 0);
     std::this_thread::sleep_for(std::chrono::milliseconds(1));
+
     return result;
 }
 #endif

src/base/kernel/Platform_unix.cpp

@@ -16,10 +16,12 @@
  *   along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
-#ifdef __FreeBSD__
+#ifdef XMRIG_OS_FREEBSD
 #   include <sys/types.h>
 #   include <sys/param.h>
-#   include <sys/cpuset.h>
+#   ifndef __DragonFly__
+#       include <sys/cpuset.h>
+#   endif
 #   include <pthread_np.h>
 #endif
 
@@ -41,11 +43,6 @@
 #include "version.h"
 
 
-#ifdef __FreeBSD__
-typedef cpuset_t cpu_set_t;
-#endif
-
-
 char *xmrig::Platform::createUserAgent()
 {
     constexpr const size_t max = 256;
@@ -74,6 +71,19 @@ char *xmrig::Platform::createUserAgent()
 
 
 #ifndef XMRIG_FEATURE_HWLOC
+#ifdef __DragonFly__
+
+bool xmrig::Platform::setThreadAffinity(uint64_t cpu_id)
+{
+    return true;
+}
+
+#else
+
+#ifdef XMRIG_OS_FREEBSD
+typedef cpuset_t cpu_set_t;
+#endif
+
 bool xmrig::Platform::setThreadAffinity(uint64_t cpu_id)
 {
     cpu_set_t mn;
@@ -89,7 +99,9 @@ bool xmrig::Platform::setThreadAffinity(uint64_t cpu_id)
     std::this_thread::sleep_for(std::chrono::milliseconds(1));
     return result;
 }
-#endif
+
+#endif // __DragonFly__
+#endif // XMRIG_FEATURE_HWLOC
 
 
 void xmrig::Platform::setProcessPriority(int)

src/base/kernel/config/BaseTransform.cpp

@@ -247,6 +247,7 @@ void xmrig::BaseTransform::transform(rapidjson::Document &doc, int key, const ch
     case IConfig::HttpPort:         /* --http-port */
     case IConfig::DonateLevelKey:   /* --donate-level */
     case IConfig::DaemonPollKey:    /* --daemon-poll-interval */
+    case IConfig::DaemonJobTimeoutKey: /* --daemon-job-timeout */
     case IConfig::DnsTtlKey:        /* --dns-ttl */
     case IConfig::DaemonZMQPortKey: /* --daemon-zmq-port */
         return transformUint64(doc, key, static_cast<uint64_t>(strtol(arg, nullptr, 10)));
@@ -360,6 +361,9 @@ void xmrig::BaseTransform::transformUint64(rapidjson::Document &doc, int key, ui
     case IConfig::DaemonPollKey:  /* --daemon-poll-interval */
         return add(doc, Pools::kPools, Pool::kDaemonPollInterval, arg);
 
+    case IConfig::DaemonJobTimeoutKey:  /* --daemon-job-timeout */
+        return add(doc, Pools::kPools, Pool::kDaemonJobTimeout, arg);
+
     case IConfig::DaemonZMQPortKey:  /* --daemon-zmq-port */
         return add(doc, Pools::kPools, Pool::kDaemonZMQPort, arg);
 #   endif

src/base/kernel/interfaces/IConfig.h

@@ -88,6 +88,7 @@ public:
         DaemonZMQPortKey     = 1056,
         HugePagesJitKey      = 1057,
         RotationKey          = 1058,
+        DaemonJobTimeoutKey  = 1059,
 
         // xmrig common
         CPUPriorityKey       = 1021,

src/base/net/dns/DnsRecord.cpp

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -46,11 +46,11 @@ xmrig::String xmrig::DnsRecord::ip() const
 
     if (m_type == AAAA) {
         buf = new char[45]();
-        uv_ip6_name(reinterpret_cast<sockaddr_in6*>(m_data), buf, 45);
+        uv_ip6_name(reinterpret_cast<const sockaddr_in6*>(m_data), buf, 45);
     }
     else {
         buf = new char[16]();
-        uv_ip4_name(reinterpret_cast<sockaddr_in*>(m_data), buf, 16);
+        uv_ip4_name(reinterpret_cast<const sockaddr_in*>(m_data), buf, 16);
     }
 
     return buf;

src/base/net/dns/DnsUvBackend.cpp

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -28,18 +28,19 @@
 
 namespace xmrig {
 
-static Storage<DnsUvBackend>* storage = nullptr;
 
-Storage<DnsUvBackend>& DnsUvBackend::getStorage()
+static Storage<DnsUvBackend> *storage = nullptr;
+
+
+Storage<DnsUvBackend> &DnsUvBackend::getStorage()
 {
-    if (storage == nullptr) storage = new Storage<DnsUvBackend>();
+    if (storage == nullptr) {
+        storage = new Storage<DnsUvBackend>();
+    }
+
     return *storage;
 }
 
-void DnsUvBackend::releaseStorage()
-{
-    delete storage;
-}
 
 static addrinfo hints{};
 
@@ -61,8 +62,14 @@ xmrig::DnsUvBackend::DnsUvBackend()
 
 xmrig::DnsUvBackend::~DnsUvBackend()
 {
-    getStorage().release(m_key);
-    releaseStorage();
+    assert(storage);
+
+    storage->release(m_key);
+
+    if (storage->isEmpty()) {
+        delete storage;
+        storage = nullptr;
+    }
 }
 
 

src/base/net/http/HttpResponse.h

@@ -21,6 +21,7 @@
 #define XMRIG_HTTPRESPONSE_H
 
 
+#include <cstdint>
 #include <map>
 #include <string>
 

src/base/net/stratum/Client.cpp

@@ -1018,7 +1018,7 @@ void xmrig::Client::onConnect(uv_connect_t *req, int status)
 
     if (status < 0) {
         if (!client->isQuiet()) {
-            LOG_ERR("%s " RED("connect error: ") RED_BOLD("\"%s\""), client->tag(), uv_strerror(status));
+            LOG_ERR("%s %s " RED("connect error: ") RED_BOLD("\"%s\""), client->tag(), client->ip().data(), uv_strerror(status));
         }
 
         if (client->state() == ReconnectingState || client->state() == ClosingState) {

src/base/net/stratum/DaemonClient.cpp

@@ -148,6 +148,11 @@ int64_t xmrig::DaemonClient::submit(const JobResult &result)
         memcpy(data + sig_offset * 2, result.sig, 64 * 2);
         memcpy(data + m_blocktemplate.offset(BlockTemplate::TX_PUBKEY_OFFSET) * 2, result.sig_data, 32 * 2);
         memcpy(data + m_blocktemplate.offset(BlockTemplate::EPH_PUBLIC_KEY_OFFSET) * 2, result.sig_data + 32 * 2, 32 * 2);
+
+        // Handle view tag for txout_to_tagged_key outputs
+        if (m_blocktemplate.outputType() == 3) {
+            Cvt::toHex(data + m_blocktemplate.offset(BlockTemplate::EPH_PUBLIC_KEY_OFFSET) * 2 + 32 * 2, 2, &result.view_tag, 1);
+        }
     }
 
     if (result.extra_nonce >= 0) {
@@ -178,7 +183,10 @@ int64_t xmrig::DaemonClient::submit(const JobResult &result)
     m_results[m_sequence] = SubmitResult(m_sequence, result.diff, result.actualDiff(), 0, result.backend);
 #   endif
 
-    return rpcSend(doc);
+    std::map<std::string, std::string> headers;
+    headers.insert({"X-Hash-Difficulty", std::to_string(result.actualDiff())});
+
+    return rpcSend(doc, headers);
 }
 
 
@@ -303,6 +311,18 @@ void xmrig::DaemonClient::onHttpData(const HttpData &data)
 
 void xmrig::DaemonClient::onTimer(const Timer *)
 {
+    if (m_pool.zmq_port() >= 0) {
+        m_prevHash = nullptr;
+        m_blocktemplateRequestHash = nullptr;
+        send(kGetHeight);
+        return;
+    }
+
+    if (Chrono::steadyMSecs() >= m_jobSteadyMs + m_pool.jobTimeout()) {
+        m_prevHash = nullptr;
+        m_blocktemplateRequestHash = nullptr;
+    }
+
     if (m_state == ConnectingState) {
         connect();
     }
@@ -352,7 +372,7 @@ void xmrig::DaemonClient::onResolved(const DnsRecords &records, int status, cons
 
 bool xmrig::DaemonClient::isOutdated(uint64_t height, const char *hash) const
 {
-    return m_job.height() != height || m_prevHash != hash;
+    return m_job.height() != height || m_prevHash != hash || Chrono::steadyMSecs() >= m_jobSteadyMs + m_pool.jobTimeout();
 }
 
 
@@ -389,7 +409,8 @@ bool xmrig::DaemonClient::parseJob(const rapidjson::Value &params, int *code)
         m_blocktemplate.offset(BlockTemplate::TX_PUBKEY_OFFSET) - k,
         m_blocktemplate.offset(BlockTemplate::TX_EXTRA_NONCE_OFFSET) - k,
         m_blocktemplate.txExtraNonce().size(),
-        m_blocktemplate.minerTxMerkleTreeBranch()
+        m_blocktemplate.minerTxMerkleTreeBranch(),
+        m_blocktemplate.outputType() == 3
     );
 #   endif
 
@@ -426,7 +447,7 @@ bool xmrig::DaemonClient::parseJob(const rapidjson::Value &params, int *code)
         }
 
         uint8_t derivation[32];
-        if (!generate_key_derivation(m_blocktemplate.blob(BlockTemplate::TX_PUBKEY_OFFSET), secret_viewkey, derivation)) {
+        if (!generate_key_derivation(m_blocktemplate.blob(BlockTemplate::TX_PUBKEY_OFFSET), secret_viewkey, derivation, nullptr)) {
             return jobError("Failed to generate key derivation for miner signature.");
         }
 
@@ -468,6 +489,7 @@ bool xmrig::DaemonClient::parseJob(const rapidjson::Value &params, int *code)
     m_job              = std::move(job);
     m_blocktemplateStr = std::move(blocktemplate);
     m_prevHash         = Json::getString(params, "prev_hash");
+    m_jobSteadyMs      = Chrono::steadyMSecs();
 
     if (m_state == ConnectingState) {
         setState(ConnectedState);
@@ -540,9 +562,13 @@ int64_t xmrig::DaemonClient::getBlockTemplate()
 }
 
 
-int64_t xmrig::DaemonClient::rpcSend(const rapidjson::Document &doc)
+int64_t xmrig::DaemonClient::rpcSend(const rapidjson::Document &doc, const std::map<std::string, std::string> &headers)
 {
     FetchRequest req(HTTP_POST, m_pool.host(), m_pool.port(), kJsonRPC, doc, m_pool.isTLS(), isQuiet());
+    for (const auto &header : headers) {
+        req.headers.insert(header);
+    }
+
     fetch(tag(), std::move(req), m_httpListener);
 
     return m_sequence++;
@@ -596,6 +622,10 @@ void xmrig::DaemonClient::setState(SocketState state)
                 const uint64_t interval = std::max<uint64_t>(20, m_pool.pollInterval());
                 m_timer->start(interval, interval);
             }
+            else {
+                const uint64_t t = m_pool.jobTimeout();
+                m_timer->start(t, t);
+            }
         }
         break;
 
@@ -865,7 +895,12 @@ void xmrig::DaemonClient::ZMQParse()
     // Clear previous hash and check daemon height to guarantee that xmrig will call get_block_template RPC later
     // We can't call get_block_template directly because daemon is not ready yet
     m_prevHash = nullptr;
+    m_blocktemplateRequestHash = nullptr;
     send(kGetHeight);
+
+    const uint64_t t = m_pool.jobTimeout();
+    m_timer->stop();
+    m_timer->start(t, t);
 }
 
 

src/base/net/stratum/DaemonClient.h

@@ -86,7 +86,7 @@ private:
     bool parseJob(const rapidjson::Value &params, int *code);
     bool parseResponse(int64_t id, const rapidjson::Value &result, const rapidjson::Value &error);
     int64_t getBlockTemplate();
-    int64_t rpcSend(const rapidjson::Document &doc);
+    int64_t rpcSend(const rapidjson::Document &doc, const std::map<std::string, std::string> &headers = {});
     void retry();
     void send(const char *path);
     void setState(SocketState state);
@@ -104,6 +104,7 @@ private:
     String m_blocktemplateStr;
     String m_currentJobId;
     String m_prevHash;
+    uint64_t m_jobSteadyMs = 0;
     String m_tlsFingerprint;
     String m_tlsVersion;
     Timer *m_timer;

src/base/net/stratum/Job.cpp

@@ -245,6 +245,7 @@ void xmrig::Job::copy(const Job &other)
     m_minerTxExtraNonceOffset = other.m_minerTxExtraNonceOffset;
     m_minerTxExtraNonceSize = other.m_minerTxExtraNonceSize;
     m_minerTxMerkleTreeBranch = other.m_minerTxMerkleTreeBranch;
+    m_hasViewTag = other.m_hasViewTag;
 #   else
     memcpy(m_ephPublicKey, other.m_ephPublicKey, sizeof(m_ephPublicKey));
     memcpy(m_ephSecretKey, other.m_ephSecretKey, sizeof(m_ephSecretKey));
@@ -300,6 +301,7 @@ void xmrig::Job::move(Job &&other)
     m_minerTxExtraNonceOffset   = other.m_minerTxExtraNonceOffset;
     m_minerTxExtraNonceSize     = other.m_minerTxExtraNonceSize;
     m_minerTxMerkleTreeBranch   = std::move(other.m_minerTxMerkleTreeBranch);
+    m_hasViewTag                = other.m_hasViewTag;
 #   else
     memcpy(m_ephPublicKey, other.m_ephPublicKey, sizeof(m_ephPublicKey));
     memcpy(m_ephSecretKey, other.m_ephSecretKey, sizeof(m_ephSecretKey));
@@ -323,7 +325,7 @@ void xmrig::Job::setSpendSecretKey(const uint8_t *key)
 }
 
 
-void xmrig::Job::setMinerTx(const uint8_t *begin, const uint8_t *end, size_t minerTxEphPubKeyOffset, size_t minerTxPubKeyOffset, size_t minerTxExtraNonceOffset, size_t minerTxExtraNonceSize, const Buffer &minerTxMerkleTreeBranch)
+void xmrig::Job::setMinerTx(const uint8_t *begin, const uint8_t *end, size_t minerTxEphPubKeyOffset, size_t minerTxPubKeyOffset, size_t minerTxExtraNonceOffset, size_t minerTxExtraNonceSize, const Buffer &minerTxMerkleTreeBranch, bool hasViewTag)
 {
     m_minerTxPrefix.assign(begin, end);
     m_minerTxEphPubKeyOffset    = minerTxEphPubKeyOffset;
@@ -331,6 +333,13 @@ void xmrig::Job::setMinerTx(const uint8_t *begin, const uint8_t *end, size_t min
     m_minerTxExtraNonceOffset   = minerTxExtraNonceOffset;
     m_minerTxExtraNonceSize     = minerTxExtraNonceSize;
     m_minerTxMerkleTreeBranch   = minerTxMerkleTreeBranch;
+    m_hasViewTag                = hasViewTag;
+}
+
+
+void xmrig::Job::setViewTagInMinerTx(uint8_t view_tag)
+{
+    memcpy(m_minerTxPrefix.data() + m_minerTxEphPubKeyOffset + 32, &view_tag, 1);
 }
 
 
@@ -340,7 +349,7 @@ void xmrig::Job::setExtraNonceInMinerTx(uint32_t extra_nonce)
 }
 
 
-void xmrig::Job::generateSignatureData(String &signatureData) const
+void xmrig::Job::generateSignatureData(String &signatureData, uint8_t& view_tag) const
 {
     uint8_t* eph_public_key = m_minerTxPrefix.data() + m_minerTxEphPubKeyOffset;
     uint8_t* txkey_pub = m_minerTxPrefix.data() + m_minerTxPubKeyOffset;
@@ -351,14 +360,14 @@ void xmrig::Job::generateSignatureData(String &signatureData) const
 
     uint8_t derivation[32];
 
-    generate_key_derivation(m_viewPublicKey, txkey_sec, derivation);
+    generate_key_derivation(m_viewPublicKey, txkey_sec, derivation, &view_tag);
     derive_public_key(derivation, 0, m_spendPublicKey, eph_public_key);
 
     uint8_t buf[32 * 3] = {};
     memcpy(buf, txkey_pub, 32);
     memcpy(buf + 32, eph_public_key, 32);
 
-    generate_key_derivation(txkey_pub, m_viewSecretKey, derivation);
+    generate_key_derivation(txkey_pub, m_viewSecretKey, derivation, nullptr);
     derive_secret_key(derivation, 0, m_spendSecretKey, buf + 64);
 
     signatureData = Cvt::toHex(buf, sizeof(buf));

src/base/net/stratum/Job.h

@@ -120,10 +120,13 @@ public:
 #   endif
 
 #   ifdef XMRIG_PROXY_PROJECT
+    inline bool hasViewTag() const                      { return m_hasViewTag; }
+
     void setSpendSecretKey(const uint8_t* key);
-    void setMinerTx(const uint8_t* begin, const uint8_t* end, size_t minerTxEphPubKeyOffset, size_t minerTxPubKeyOffset, size_t minerTxExtraNonceOffset, size_t minerTxExtraNonceSize, const Buffer& minerTxMerkleTreeBranch);
+    void setMinerTx(const uint8_t* begin, const uint8_t* end, size_t minerTxEphPubKeyOffset, size_t minerTxPubKeyOffset, size_t minerTxExtraNonceOffset, size_t minerTxExtraNonceSize, const Buffer& minerTxMerkleTreeBranch, bool hasViewTag);
+    void setViewTagInMinerTx(uint8_t view_tag);
     void setExtraNonceInMinerTx(uint32_t extra_nonce);
-    void generateSignatureData(String& signatureData) const;
+    void generateSignatureData(String& signatureData, uint8_t& view_tag) const;
     void generateHashingBlob(String& blob) const;
 #   else
     inline const uint8_t* ephSecretKey() const { return m_hasMinerSignature ? m_ephSecretKey : nullptr; }
@@ -178,6 +181,7 @@ private:
     size_t m_minerTxExtraNonceOffset = 0;
     size_t m_minerTxExtraNonceSize = 0;
     Buffer m_minerTxMerkleTreeBranch;
+    bool m_hasViewTag = false;
 #   else
     // Miner signatures
     uint8_t m_ephPublicKey[32]{};

src/base/net/stratum/Pool.cpp

@@ -65,6 +65,7 @@ const char *Pool::kAlgo                   = "algo";
 const char *Pool::kCoin                   = "coin";
 const char *Pool::kDaemon                 = "daemon";
 const char *Pool::kDaemonPollInterval     = "daemon-poll-interval";
+const char *Pool::kDaemonJobTimeout       = "daemon-job-timeout";
 const char *Pool::kDaemonZMQPort          = "daemon-zmq-port";
 const char *Pool::kEnabled                = "enabled";
 const char *Pool::kFingerprint            = "tls-fingerprint";
@@ -88,6 +89,7 @@ const char *Pool::kNicehashHost           = "nicehash.com";
 xmrig::Pool::Pool(const char *url) :
     m_flags(1 << FLAG_ENABLED),
     m_pollInterval(kDefaultPollInterval),
+    m_jobTimeout(kDefaultJobTimeout),
     m_url(url)
 {
 }
@@ -101,6 +103,7 @@ xmrig::Pool::Pool(const char *host, uint16_t port, const char *user, const char
     m_user(user),
     m_spendSecretKey(spendSecretKey),
     m_pollInterval(kDefaultPollInterval),
+    m_jobTimeout(kDefaultJobTimeout),
     m_url(host, port, tls)
 {
     m_flags.set(FLAG_NICEHASH, nicehash || strstr(host, kNicehashHost));
@@ -111,6 +114,7 @@ xmrig::Pool::Pool(const char *host, uint16_t port, const char *user, const char
 xmrig::Pool::Pool(const rapidjson::Value &object) :
     m_flags(1 << FLAG_ENABLED),
     m_pollInterval(kDefaultPollInterval),
+    m_jobTimeout(kDefaultJobTimeout),
     m_url(Json::getString(object, kUrl))
 {
     if (!m_url.isValid()) {
@@ -123,6 +127,7 @@ xmrig::Pool::Pool(const rapidjson::Value &object) :
     m_rigId          = Json::getString(object, kRigId);
     m_fingerprint    = Json::getString(object, kFingerprint);
     m_pollInterval   = Json::getUint64(object, kDaemonPollInterval, kDefaultPollInterval);
+    m_jobTimeout     = Json::getUint64(object, kDaemonJobTimeout, kDefaultJobTimeout);
     m_algorithm      = Json::getString(object, kAlgo);
     m_coin           = Json::getString(object, kCoin);
     m_daemon         = Json::getString(object, kSelfSelect);
@@ -207,6 +212,7 @@ bool xmrig::Pool::isEqual(const Pool &other) const
             && m_url          == other.m_url
             && m_user         == other.m_user
             && m_pollInterval == other.m_pollInterval
+            && m_jobTimeout   == other.m_jobTimeout
             && m_daemon       == other.m_daemon
             && m_proxy        == other.m_proxy
             );
@@ -299,6 +305,7 @@ rapidjson::Value xmrig::Pool::toJSON(rapidjson::Document &doc) const
 
     if (m_mode == MODE_DAEMON) {
         obj.AddMember(StringRef(kDaemonPollInterval), m_pollInterval, allocator);
+        obj.AddMember(StringRef(kDaemonJobTimeout), m_jobTimeout, allocator);
         obj.AddMember(StringRef(kDaemonZMQPort), m_zmqPort, allocator);
     }
     else {

src/base/net/stratum/Pool.h

@@ -59,6 +59,7 @@ public:
     static const char *kCoin;
     static const char *kDaemon;
     static const char *kDaemonPollInterval;
+    static const char* kDaemonJobTimeout;
     static const char *kEnabled;
     static const char *kFingerprint;
     static const char *kKeepalive;
@@ -78,6 +79,7 @@ public:
     constexpr static int kKeepAliveTimeout         = 60;
     constexpr static uint16_t kDefaultPort         = 3333;
     constexpr static uint64_t kDefaultPollInterval = 1000;
+    constexpr static uint64_t kDefaultJobTimeout   = 15000;
 
     Pool() = default;
     Pool(const char *host, uint16_t port, const char *user, const char *password, const char* spendSecretKey, int keepAlive, bool nicehash, bool tls, Mode mode);
@@ -110,6 +112,7 @@ public:
     inline uint16_t port() const                        { return m_url.port(); }
     inline int zmq_port() const                         { return m_zmqPort; }
     inline uint64_t pollInterval() const                { return m_pollInterval; }
+    inline uint64_t jobTimeout() const                  { return m_jobTimeout; }
     inline void setAlgo(const Algorithm &algorithm)     { m_algorithm = algorithm; }
     inline void setUrl(const char *url)                 { m_url = Url(url); }
     inline void setPassword(const String &password)     { m_password = password; }
@@ -156,6 +159,7 @@ private:
     String m_user;
     String m_spendSecretKey;
     uint64_t m_pollInterval         = kDefaultPollInterval;
+    uint64_t m_jobTimeout           = kDefaultJobTimeout;
     Url m_daemon;
     Url m_url;
     int m_zmqPort                   = -1;

src/base/net/tls/TlsContext.cpp

@@ -1,7 +1,7 @@
 /* XMRig
  * Copyright (c) 2018      Lee Clagett <https://github.com/vtnerd>
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -45,6 +45,7 @@ namespace xmrig {
 
 
 // https://wiki.openssl.org/index.php/Diffie-Hellman_parameters
+#if OPENSSL_VERSION_NUMBER < 0x30000000L || defined(LIBRESSL_VERSION_NUMBER)
 static DH *get_dh2048()
 {
     static unsigned char dhp_2048[] = {
@@ -96,6 +97,8 @@ static DH *get_dh2048()
 
     return dh;
 }
+#endif
+
 
 } // namespace xmrig
 
@@ -191,6 +194,7 @@ bool xmrig::TlsContext::setCipherSuites(const char *ciphersuites)
 
 bool xmrig::TlsContext::setDH(const char *dhparam)
 {
+#   if OPENSSL_VERSION_NUMBER < 0x30000000L || defined(LIBRESSL_VERSION_NUMBER)
     DH *dh = nullptr;
 
     if (dhparam != nullptr) {
@@ -225,6 +229,34 @@ bool xmrig::TlsContext::setDH(const char *dhparam)
 
         return false;
     }
+#   else
+    if (dhparam != nullptr) {
+        EVP_PKEY *dh = nullptr;
+        BIO *bio     = BIO_new_file(Env::expand(dhparam), "r");
+
+        if (bio) {
+            dh = PEM_read_bio_Parameters(bio, nullptr);
+            BIO_free(bio);
+        }
+
+        if (!dh) {
+            LOG_ERR("PEM_read_bio_Parameters(\"%s\") failed.", dhparam);
+
+            return false;
+        }
+
+        if (SSL_CTX_set0_tmp_dh_pkey(m_ctx, dh) != 1) {
+            EVP_PKEY_free(dh);
+
+            LOG_ERR("SSL_CTX_set0_tmp_dh_pkey(\"%s\") failed.", dhparam);
+
+            return false;
+        }
+    }
+    else {
+        SSL_CTX_set_dh_auto(m_ctx, 1);
+    }
+#   endif
 
     return true;
 }

src/base/net/tls/TlsContext.h

@@ -1,7 +1,7 @@
 /* XMRig
  * Copyright (c) 2018      Lee Clagett <https://github.com/vtnerd>
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -24,9 +24,6 @@
 #include "base/tools/Object.h"
 
 
-#include <cstdint>
-
-
 using SSL_CTX = struct ssl_ctx_st;
 
 
@@ -60,6 +57,7 @@ private:
 };
 
 
-} /* namespace xmrig */
+} // namespace xmrig
 
-#endif /* XMRIG_TLSCONTEXT_H */
+
+#endif // XMRIG_TLSCONTEXT_H

src/base/net/tls/TlsGen.cpp

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -33,6 +33,7 @@ static const char *kLocalhost = "localhost";
 
 static EVP_PKEY *generate_pkey()
 {
+#   if OPENSSL_VERSION_NUMBER < 0x30000000L || defined(LIBRESSL_VERSION_NUMBER)
     auto pkey = EVP_PKEY_new();
     if (!pkey) {
         return nullptr;
@@ -53,6 +54,9 @@ static EVP_PKEY *generate_pkey()
     BN_free(exponent);
 
     return pkey;
+#   else
+    return EVP_RSA_gen(2048);
+#   endif
 }
 
 

src/base/net/tls/TlsGen.h

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -55,7 +55,7 @@ private:
 };
 
 
-} /* namespace xmrig */
+} // namespace xmrig
 
 
-#endif /* XMRIG_TLSGEN_H */
+#endif // XMRIG_TLSGEN_H

src/base/net/tools/Storage.h

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -42,7 +42,7 @@ public:
     }
 
 
-    inline void *ptr(uintptr_t id)          { return reinterpret_cast<void *>(id); }
+    inline TYPE *ptr(uintptr_t id)          { return reinterpret_cast<TYPE *>(id); }
 
 
     inline TYPE *get(const void *id) const  { return get(reinterpret_cast<uintptr_t>(id)); }
@@ -56,6 +56,9 @@ public:
         return m_data.at(id);
     }
 
+    inline bool isEmpty() const             { return m_data.empty(); }
+    inline size_t size() const              { return m_data.size(); }
+
 
     inline void remove(const void *id)      { delete release(reinterpret_cast<uintptr_t>(id)); }
     inline void remove(uintptr_t id)        { delete release(id); }

src/base/tools/Object.h

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -20,7 +20,9 @@
 #define XMRIG_OBJECT_H
 
 
-#include <chrono>
+#include <cstddef>
+#include <cstdint>
+#include <memory>
 
 
 namespace xmrig {
@@ -41,6 +43,7 @@ namespace xmrig {
     X &operator=(X &&other)      = delete;
 
 
-} /* namespace xmrig */
+} // namespace xmrig
 
-#endif /* XMRIG_OBJECT_H */
+
+#endif // XMRIG_OBJECT_H

src/base/tools/cryptonote/BlockTemplate.cpp

@@ -269,7 +269,7 @@ bool xmrig::BlockTemplate::parse(bool hashes)
         case 0x03: // TX_EXTRA_MERGE_MINING_TAG
             ar_extra(size);
             setOffset(TX_EXTRA_MERGE_MINING_TAG_OFFSET, offset(TX_EXTRA_OFFSET) + ar_extra.index());
-            ar_extra(m_txMergeMiningTag, size + kKeySize);
+            ar_extra(m_txMergeMiningTag, size);
             break;
 
         default:

src/base/tools/cryptonote/Signatures.cpp

@@ -147,7 +147,7 @@ bool check_signature(const uint8_t* prefix_hash, const uint8_t* pub, const uint8
 }
 
 
-bool generate_key_derivation(const uint8_t* key1, const uint8_t* key2, uint8_t* derivation)
+bool generate_key_derivation(const uint8_t* key1, const uint8_t* key2, uint8_t* derivation, uint8_t* view_tag)
 {
     ge_p3 point;
     ge_p2 point2;
@@ -162,6 +162,22 @@ bool generate_key_derivation(const uint8_t* key1, const uint8_t* key2, uint8_t*
     ge_p1p1_to_p2(&point2, &point3);
     ge_tobytes(derivation, &point2);
 
+    if (view_tag) {
+        constexpr uint8_t salt[] = "view_tag";
+        constexpr size_t SALT_SIZE = sizeof(salt) - 1;
+
+        uint8_t buf[SALT_SIZE + 32 + 1];
+        memcpy(buf, salt, SALT_SIZE);
+        memcpy(buf + SALT_SIZE, derivation, 32);
+
+        // Assuming output_index == 0
+        buf[SALT_SIZE + 32] = 0;
+
+        uint8_t view_tag_full[32];
+        xmrig::keccak(buf, sizeof(buf), view_tag_full, sizeof(view_tag_full));
+        *view_tag = view_tag_full[0];
+    }
+
     return true;
 }
 

src/base/tools/cryptonote/Signatures.h

@@ -31,7 +31,7 @@ namespace xmrig {
 void generate_signature(const uint8_t* prefix_hash, const uint8_t* pub, const uint8_t* sec, uint8_t* sig);
 bool check_signature(const uint8_t* prefix_hash, const uint8_t* pub, const uint8_t* sig);
 
-bool generate_key_derivation(const uint8_t* key1, const uint8_t* key2, uint8_t* derivation);
+bool generate_key_derivation(const uint8_t* key1, const uint8_t* key2, uint8_t* derivation, uint8_t* view_tag);
 void derive_secret_key(const uint8_t* derivation, size_t output_index, const uint8_t* base, uint8_t* derived_key);
 bool derive_public_key(const uint8_t* derivation, size_t output_index, const uint8_t* base, uint8_t* derived_key);
 

src/core/config/Config_platform.h

@@ -50,6 +50,7 @@ static const option options[] = {
     { "http-no-restricted",    0, nullptr, IConfig::HttpRestrictedKey     },
     { "daemon",                0, nullptr, IConfig::DaemonKey             },
     { "daemon-poll-interval",  1, nullptr, IConfig::DaemonPollKey         },
+    { "daemon-job-timeout",    1, nullptr, IConfig::DaemonJobTimeoutKey   },
     { "self-select",           1, nullptr, IConfig::SelfSelectKey         },
     { "submit-to-origin",      0, nullptr, IConfig::SubmitToOriginKey     },
     { "daemon-zmq-port",       1, nullptr, IConfig::DaemonZMQPortKey      },

src/core/config/usage.h

@@ -64,7 +64,9 @@ static inline const std::string &usage()
 
 #   ifdef XMRIG_FEATURE_HTTP
     u += "      --daemon                  use daemon RPC instead of pool for solo mining\n";
+    u += "      --daemon-zmq-port         daemon's zmq-pub port number (only use it if daemon has it enabled)\n";
     u += "      --daemon-poll-interval=N  daemon poll interval in milliseconds (default: 1000)\n";
+    u += "      --daemon-job-timeout=N    daemon job timeout in milliseconds (default: 15000)\n";
     u += "      --self-select=URL         self-select block templates from URL\n";
     u += "      --submit-to-origin        also submit solution back to self-select URL\n";
 #   endif

src/crypto/cn/CryptoNight_x86.h

@@ -80,7 +80,7 @@ static inline void do_skein_hash(const uint8_t *input, size_t len, uint8_t *outp
 void (* const extra_hashes[4])(const uint8_t *, size_t, uint8_t *) = {do_blake_hash, do_groestl_hash, do_jh_hash, do_skein_hash};
 
 
-#if defined(__i386__) || defined(_M_IX86)
+#if (defined(__i386__) || defined(_M_IX86)) && !(defined(__clang__) && defined(__clang_major__) && (__clang_major__ >= 15))
 static inline int64_t _mm_cvtsi128_si64(__m128i a)
 {
     return ((uint64_t)(uint32_t)_mm_cvtsi128_si32(a) | ((uint64_t)(uint32_t)_mm_cvtsi128_si32(_mm_srli_si128(a, 4)) << 32));

src/crypto/common/VirtualMemory_hwloc.cpp

@@ -1,8 +1,8 @@
 /* XMRig
  * Copyright (c) 2018      Lee Clagett <https://github.com/vtnerd>
  * Copyright (c) 2018-2019 tevador     <tevador@gmail.com>
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -18,10 +18,8 @@
  *   along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
-
 #include "crypto/common/VirtualMemory.h"
 #include "backend/cpu/Cpu.h"
-#include "backend/cpu/platform/HwlocCpuInfo.h"
 #include "base/io/log/Log.h"
 
 
@@ -34,10 +32,9 @@ uint32_t xmrig::VirtualMemory::bindToNUMANode(int64_t affinity)
         return 0;
     }
 
-    auto cpu       = static_cast<HwlocCpuInfo *>(Cpu::info());
-    hwloc_obj_t pu = hwloc_get_pu_obj_by_os_index(cpu->topology(), static_cast<unsigned>(affinity));
+    auto pu = hwloc_get_pu_obj_by_os_index(Cpu::info()->topology(), static_cast<unsigned>(affinity));
 
-    if (pu == nullptr || !cpu->membind(pu->nodeset)) {
+    if (pu == nullptr || !Cpu::info()->membind(pu->nodeset)) {
         LOG_WARN("CPU #%02" PRId64 " warning: \"can't bind memory\"", affinity);
 
         return 0;

src/crypto/common/VirtualMemory_unix.cpp

@@ -57,6 +57,15 @@
 #   define MAP_HUGE_MASK 0x3f
 #endif
 
+#ifdef XMRIG_OS_FREEBSD
+#   ifndef MAP_ALIGNED_SUPER
+#       define MAP_ALIGNED_SUPER 0
+#   endif
+#   ifndef MAP_PREFAULT_READ
+#       define MAP_PREFAULT_READ 0
+#   endif
+#endif
+
 
 #ifdef XMRIG_SECURE_JIT
 #   define SECURE_PROT_EXEC 0
@@ -65,7 +74,7 @@
 #endif
 
 
-#if defined(XMRIG_OS_LINUX) || (!defined(XMRIG_OS_APPLE) && !defined(__FreeBSD__))
+#if defined(XMRIG_OS_LINUX) || (!defined(XMRIG_OS_APPLE) && !defined(XMRIG_OS_FREEBSD))
 static inline int hugePagesFlag(size_t size)
 {
     return (static_cast<int>(log2(size)) & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
@@ -135,7 +144,7 @@ void *xmrig::VirtualMemory::allocateExecutableMemory(size_t size, bool hugePages
 #   ifdef XMRIG_ARM
     pthread_jit_write_protect_np(false);
 #   endif
-#   elif defined(__FreeBSD__)
+#   elif defined(XMRIG_OS_FREEBSD)
     void *mem = nullptr;
 
     if (hugePages) {
@@ -168,7 +177,7 @@ void *xmrig::VirtualMemory::allocateLargePagesMemory(size_t size)
 {
 #   if defined(XMRIG_OS_APPLE)
     void *mem = mmap(0, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, VM_FLAGS_SUPERPAGE_SIZE_2MB, 0);
-#   elif defined(__FreeBSD__)
+#   elif defined(XMRIG_OS_FREEBSD)
     void *mem = mmap(0, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_ALIGNED_SUPER | MAP_PREFAULT_READ, -1, 0);
 #   else
     void *mem = mmap(0, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_POPULATE | hugePagesFlag(hugePageSize()), 0, 0);

src/crypto/ghostrider/CMakeLists.txt

@@ -1,4 +1,4 @@
-cmake_minimum_required(VERSION 2.8.12)
+cmake_minimum_required(VERSION 3.1)
 project(GhostRider)
 
 set(HEADERS

src/crypto/ghostrider/ghostrider.cpp

@@ -1,6 +1,6 @@
 /* XMRig
- * Copyright 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -16,7 +16,6 @@
  *   along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
-
 #include "ghostrider.h"
 #include "sph_blake.h"
 #include "sph_bmw.h"
@@ -48,9 +47,12 @@
 #include <uv.h>
 
 #ifdef XMRIG_FEATURE_HWLOC
-#include "base/kernel/Platform.h"
-#include "backend/cpu/platform/HwlocCpuInfo.h"
-#include <hwloc.h>
+#   include "base/kernel/Platform.h"
+#   include <hwloc.h>
+
+#   if HWLOC_API_VERSION < 0x20000
+#       define HWLOC_OBJ_L3CACHE HWLOC_OBJ_CACHE
+#   endif
 #endif
 
 #if defined(XMRIG_ARM)
@@ -87,7 +89,7 @@ CORE_HASH(14, whirlpool  );
 
 #undef CORE_HASH
 
-typedef void (*core_hash_func)(const uint8_t* data, size_t size, uint8_t* output);
+using core_hash_func = void (*)(const uint8_t* data, size_t size, uint8_t* output);
 static const core_hash_func core_hash[15] = { h0, h1, h2, h3, h4, h5, h6, h7, h8, h9, h10, h11, h12, h13, h14 };
 
 namespace xmrig
@@ -166,6 +168,8 @@ static struct AlgoTune
 
 struct HelperThread
 {
+    XMRIG_DISABLE_COPY_MOVE_DEFAULT(HelperThread)
+
     HelperThread(hwloc_bitmap_t cpu_set, int priority, bool is8MB) : m_cpuSet(cpu_set), m_priority(priority), m_is8MB(is8MB)
     {
         uv_mutex_init(&m_mutex);
@@ -195,14 +199,17 @@ struct HelperThread
 
     struct TaskBase
     {
-        virtual ~TaskBase() {}
-        virtual void run() = 0;
+        XMRIG_DISABLE_COPY_MOVE(TaskBase)
+
+        TaskBase()          = default;
+        virtual ~TaskBase() = default;
+        virtual void run()  = 0;
     };
 
     template<typename T>
     struct Task : TaskBase
     {
-        inline Task(T&& task) : m_task(std::move(task))
+        explicit inline Task(T&& task) : m_task(std::move(task))
         {
             static_assert(sizeof(Task) <= 128, "Task struct is too large");
         }
@@ -220,7 +227,7 @@ struct HelperThread
     inline void launch_task(T&& task)
     {
         uv_mutex_lock(&m_mutex);
-        new (&m_tasks[m_numTasks++]) Task<T>(std::move(task));
+        new (&m_tasks[m_numTasks++]) Task<T>(std::forward<T>(task));
         uv_cond_signal(&m_cond);
         uv_mutex_unlock(&m_mutex);
     }
@@ -235,7 +242,7 @@ struct HelperThread
     void run()
     {
         if (hwloc_bitmap_weight(m_cpuSet) > 0) {
-            hwloc_topology_t topology = reinterpret_cast<HwlocCpuInfo*>(Cpu::info())->topology();
+            hwloc_topology_t topology = Cpu::info()->topology();
             if (hwloc_set_cpubind(topology, m_cpuSet, HWLOC_CPUBIND_THREAD | HWLOC_CPUBIND_STRICT) < 0) {
                 hwloc_set_cpubind(topology, m_cpuSet, HWLOC_CPUBIND_THREAD);
             }
@@ -289,9 +296,9 @@ void benchmark()
         // Try to avoid CPU core 0 because many system threads use it and can interfere
         uint32_t thread_index1 = (Cpu::info()->threads() > 2) ? 2 : 0;
 
-        hwloc_topology_t topology = reinterpret_cast<HwlocCpuInfo*>(Cpu::info())->topology();
+        hwloc_topology_t topology = Cpu::info()->topology();
         hwloc_obj_t pu = hwloc_get_pu_obj_by_os_index(topology, thread_index1);
-        hwloc_obj_t pu2;
+        hwloc_obj_t pu2 = nullptr;
         hwloc_get_closest_objs(topology, pu, &pu2, 1);
         uint32_t thread_index2 = pu2 ? pu2->os_index : thread_index1;
 
@@ -482,12 +489,17 @@ HelperThread* create_helper_thread(int64_t cpu_index, int priority, const std::v
     }
 
     if (cpu_index >= 0) {
-        hwloc_topology_t topology = reinterpret_cast<HwlocCpuInfo*>(Cpu::info())->topology();
-        hwloc_obj_t root = hwloc_get_root_obj(topology);
+        hwloc_obj_t root = hwloc_get_root_obj(Cpu::info()->topology());
 
         bool is8MB = false;
 
         findByType(root, HWLOC_OBJ_L3CACHE, [cpu_index, &is8MB](hwloc_obj_t obj) {
+#           if HWLOC_API_VERSION < 0x20000
+            if (obj->attr->cache.depth != 3) {
+                return false;
+            }
+#           endif
+
             if (!hwloc_bitmap_isset(obj->cpuset, cpu_index)) {
                 return false;
             }
@@ -511,7 +523,11 @@ HelperThread* create_helper_thread(int64_t cpu_index, int priority, const std::v
             return true;
         });
 
+#       if HWLOC_API_VERSION >= 0x20000
         for (auto obj_type : { HWLOC_OBJ_CORE, HWLOC_OBJ_L1CACHE, HWLOC_OBJ_L2CACHE, HWLOC_OBJ_L3CACHE }) {
+#       else
+        for (auto obj_type : { HWLOC_OBJ_CORE, HWLOC_OBJ_CACHE }) {
+#       endif
             findByType(root, obj_type, [cpu_index, helper_cpu_set, main_threads_set](hwloc_obj_t obj) {
                 const hwloc_cpuset_t& s = obj->cpuset;
                 if (hwloc_bitmap_isset(s, cpu_index)) {
@@ -572,9 +588,13 @@ void hash_octa(const uint8_t* data, size_t size, uint8_t* output, cryptonight_ct
     uint8_t tmp[64 * N];
 
     if (helper && (tune[cn_indices[0]].threads == 2) && (tune[cn_indices[1]].threads == 2) && (tune[cn_indices[2]].threads == 2)) {
-        const size_t n = N / 2;
+        constexpr size_t n = N / 2;
+
+        helper->launch_task([av, data, size, &ctx_memory, ctx, &cn_indices, &core_indices, &tmp, output, tune]() {
+#           ifdef _MSC_VER
+            constexpr size_t n = N / 2;
+#           endif
 
-        helper->launch_task([n, av, data, size, &ctx_memory, ctx, &cn_indices, &core_indices, &tmp, output, tune]() {
             const uint8_t* input = data;
             size_t input_size = size;
 

src/crypto/kawpow/KPHash.h

@@ -7,8 +7,8 @@
  * Copyright 2017-2019 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
  * Copyright 2018      Lee Clagett <https://github.com/vtnerd>
  * Copyright 2018-2019 tevador     <tevador@gmail.com>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2019 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright 2018-2023 SChernykh   <https://github.com/SChernykh>
+ * Copyright 2016-2023 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
  *
  *   This program is free software: you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
@@ -28,7 +28,7 @@
 #define XMRIG_KP_HASH_H
 
 
-#include <stdint.h>
+#include <cstdint>
 
 
 namespace xmrig
@@ -43,16 +43,16 @@ class KPHash
 public:
     static constexpr uint32_t EPOCH_LENGTH  = 7500;
     static constexpr uint32_t PERIOD_LENGTH = 3;
-    static constexpr int CNT_CACHE = 11;
-    static constexpr int CNT_MATH = 18;
-    static constexpr uint32_t REGS = 32;
-    static constexpr uint32_t LANES = 16;
+    static constexpr int CNT_CACHE          = 11;
+    static constexpr int CNT_MATH           = 18;
+    static constexpr uint32_t REGS          = 32;
+    static constexpr uint32_t LANES         = 16;
 
     static void calculate(const KPCache& light_cache, uint32_t block_height, const uint8_t (&header_hash)[32], uint64_t nonce, uint32_t (&output)[8], uint32_t (&mix_hash)[8]);
 };
 
 
-} /* namespace xmrig */
+} // namespace xmrig
 
 
-#endif /* XMRIG_KP_HASH_H */
+#endif // XMRIG_KP_HASH_H

src/crypto/randomx/aes_hash.cpp

@@ -34,6 +34,8 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #include "base/tools/Chrono.h"
 #include "crypto/randomx/randomx.h"
 #include "crypto/randomx/soft_aes.h"
+#include "crypto/randomx/instruction.hpp"
+#include "crypto/randomx/common.hpp"
 #include "crypto/rx/Profiler.h"
 
 #define AES_HASH_1R_STATE0 0xd7983aad, 0xcc82db47, 0x9fa856de, 0x92b52c0d
@@ -165,6 +167,9 @@ void fillAes1Rx4(void *state, size_t outputSize, void *buffer) {
 template void fillAes1Rx4<true>(void *state, size_t outputSize, void *buffer);
 template void fillAes1Rx4<false>(void *state, size_t outputSize, void *buffer);
 
+static constexpr randomx::Instruction inst{ 0xFF, 7, 7, 0xFF, 0xFFFFFFFFU };
+alignas(16) static const randomx::Instruction inst_mask[2] = { inst, inst };
+
 template<int softAes>
 void fillAes4Rx4(void *state, size_t outputSize, void *buffer) {
 	const uint8_t* outptr = (uint8_t*)buffer;
@@ -187,32 +192,42 @@ void fillAes4Rx4(void *state, size_t outputSize, void *buffer) {
 	state2 = rx_load_vec_i128((rx_vec_i128*)state + 2);
 	state3 = rx_load_vec_i128((rx_vec_i128*)state + 3);
 
-	while (outptr < outputEnd) {
-		state0 = aesdec<softAes>(state0, key0);
-		state1 = aesenc<softAes>(state1, key0);
-		state2 = aesdec<softAes>(state2, key4);
-		state3 = aesenc<softAes>(state3, key4);
-
-		state0 = aesdec<softAes>(state0, key1);
-		state1 = aesenc<softAes>(state1, key1);
-		state2 = aesdec<softAes>(state2, key5);
-		state3 = aesenc<softAes>(state3, key5);
-
-		state0 = aesdec<softAes>(state0, key2);
-		state1 = aesenc<softAes>(state1, key2);
-		state2 = aesdec<softAes>(state2, key6);
-		state3 = aesenc<softAes>(state3, key6);
-
-		state0 = aesdec<softAes>(state0, key3);
-		state1 = aesenc<softAes>(state1, key3);
-		state2 = aesdec<softAes>(state2, key7);
-		state3 = aesenc<softAes>(state3, key7);
+#define TRANSFORM do { \
+	state0 = aesdec<softAes>(state0, key0); \
+	state1 = aesenc<softAes>(state1, key0); \
+	state2 = aesdec<softAes>(state2, key4); \
+	state3 = aesenc<softAes>(state3, key4); \
+	state0 = aesdec<softAes>(state0, key1); \
+	state1 = aesenc<softAes>(state1, key1); \
+	state2 = aesdec<softAes>(state2, key5); \
+	state3 = aesenc<softAes>(state3, key5); \
+	state0 = aesdec<softAes>(state0, key2); \
+	state1 = aesenc<softAes>(state1, key2); \
+	state2 = aesdec<softAes>(state2, key6); \
+	state3 = aesenc<softAes>(state3, key6); \
+	state0 = aesdec<softAes>(state0, key3); \
+	state1 = aesenc<softAes>(state1, key3); \
+	state2 = aesdec<softAes>(state2, key7); \
+	state3 = aesenc<softAes>(state3, key7); \
+} while (0)
 
+	for (int i = 0; i < 2; ++i, outptr += 64) {
+		TRANSFORM;
 		rx_store_vec_i128((rx_vec_i128*)outptr + 0, state0);
 		rx_store_vec_i128((rx_vec_i128*)outptr + 1, state1);
 		rx_store_vec_i128((rx_vec_i128*)outptr + 2, state2);
 		rx_store_vec_i128((rx_vec_i128*)outptr + 3, state3);
+	}
 
+	static_assert(sizeof(inst_mask) == sizeof(rx_vec_i128), "Incorrect inst_mask size");
+	const rx_vec_i128 mask = *reinterpret_cast<const rx_vec_i128*>(inst_mask);
+
+	while (outptr < outputEnd) {
+		TRANSFORM;
+		rx_store_vec_i128((rx_vec_i128*)outptr + 0, rx_and_vec_i128(state0, mask));
+		rx_store_vec_i128((rx_vec_i128*)outptr + 1, rx_and_vec_i128(state1, mask));
+		rx_store_vec_i128((rx_vec_i128*)outptr + 2, rx_and_vec_i128(state2, mask));
+		rx_store_vec_i128((rx_vec_i128*)outptr + 3, rx_and_vec_i128(state3, mask));
 		outptr += 64;
 	}
 }

src/crypto/randomx/intrin_portable.h

@@ -126,6 +126,7 @@ FORCE_INLINE rx_vec_f128 rx_set1_vec_f128(uint64_t x) {
 
 #define rx_xor_vec_f128 _mm_xor_pd
 #define rx_and_vec_f128 _mm_and_pd
+#define rx_and_vec_i128 _mm_and_si128
 #define rx_or_vec_f128 _mm_or_pd
 
 #ifdef __AES__
@@ -278,6 +279,10 @@ FORCE_INLINE rx_vec_f128 rx_and_vec_f128(rx_vec_f128 a, rx_vec_f128 b) {
 	return (rx_vec_f128)vec_and(a,b);
 }
 
+FORCE_INLINE rx_vec_i128 rx_and_vec_i128(rx_vec_i128 a, rx_vec_i128 b) {
+	return (rx_vec_i128)vec_and(a, b);
+}
+
 FORCE_INLINE rx_vec_f128 rx_or_vec_f128(rx_vec_f128 a, rx_vec_f128 b) {
 	return (rx_vec_f128)vec_or(a,b);
 }
@@ -444,6 +449,8 @@ FORCE_INLINE rx_vec_f128 rx_and_vec_f128(rx_vec_f128 a, rx_vec_f128 b) {
 	return vreinterpretq_f64_u8(vandq_u8(vreinterpretq_u8_f64(a), vreinterpretq_u8_f64(b)));
 }
 
+#define rx_and_vec_i128 vandq_u8
+
 FORCE_INLINE rx_vec_f128 rx_or_vec_f128(rx_vec_f128 a, rx_vec_f128 b) {
 	return vreinterpretq_f64_u8(vorrq_u8(vreinterpretq_u8_f64(a), vreinterpretq_u8_f64(b)));
 }
@@ -635,6 +642,13 @@ FORCE_INLINE rx_vec_f128 rx_and_vec_f128(rx_vec_f128 a, rx_vec_f128 b) {
 	return x;
 }
 
+FORCE_INLINE rx_vec_i128 rx_and_vec_i128(rx_vec_i128 a, rx_vec_i128 b) {
+	rx_vec_i128 x;
+	x.u64[0] = a.u64[0] & b.u64[0];
+	x.u64[1] = a.u64[1] & b.u64[1];
+	return x;
+}
+
 FORCE_INLINE rx_vec_f128 rx_or_vec_f128(rx_vec_f128 a, rx_vec_f128 b) {
 	rx_vec_f128 x;
 	x.i.u64[0] = a.i.u64[0] | b.i.u64[0];

src/crypto/randomx/jit_compiler_a64.cpp

@@ -144,8 +144,6 @@ void JitCompilerA64::generateProgram(Program& program, ProgramConfiguration& con
 	for (uint32_t i = 0; i < program.getSize(); ++i)
 	{
 		Instruction& instr = program(i);
-		instr.src %= RegistersCount;
-		instr.dst %= RegistersCount;
 		(this->*engine[instr.opcode])(instr, codePos);
 	}
 
@@ -204,8 +202,6 @@ void JitCompilerA64::generateProgramLight(Program& program, ProgramConfiguration
 	for (uint32_t i = 0; i < program.getSize(); ++i)
 	{
 		Instruction& instr = program(i);
-		instr.src %= RegistersCount;
-		instr.dst %= RegistersCount;
 		(this->*engine[instr.opcode])(instr, codePos);
 	}
 

src/crypto/randomx/jit_compiler_x86.cpp

@@ -312,11 +312,19 @@ namespace randomx {
 		freePagedMemory(allocatedCode, allocatedSize);
 	}
 
+	template<size_t N>
+	static FORCE_INLINE void prefetch_data(const void* data) {
+		rx_prefetch_nta(data);
+		prefetch_data<N - 1>(reinterpret_cast<const char*>(data) + 64);
+	}
+
+	template<> FORCE_INLINE void prefetch_data<0>(const void*) {}
+
+	template<typename T> static FORCE_INLINE void prefetch_data(const T& data) { prefetch_data<(sizeof(T) + 63) / 64>(&data); }
+
 	void JitCompilerX86::prepare() {
-		for (size_t i = 0; i < sizeof(engine); i += 64)
-			rx_prefetch_nta((const char*)(&engine) + i);
-		for (size_t i = 0; i < sizeof(RandomX_CurrentConfig); i += 64)
-			rx_prefetch_nta((const char*)(&RandomX_CurrentConfig) + i);
+		prefetch_data(engine);
+		prefetch_data(RandomX_CurrentConfig);
 	}
 
 	void JitCompilerX86::generateProgram(Program& prog, ProgramConfiguration& pcfg, uint32_t flags) {
@@ -748,7 +756,7 @@ namespace randomx {
 	template void JitCompilerX86::genAddressReg<true>(const Instruction& instr, const uint32_t src, uint8_t* code, uint32_t& codePos);
 
 	FORCE_INLINE void JitCompilerX86::genAddressRegDst(const Instruction& instr, uint8_t* code, uint32_t& codePos) {
-		const uint32_t dst = static_cast<uint32_t>(instr.dst % RegistersCount) << 16;
+		const uint32_t dst = static_cast<uint32_t>(instr.dst) << 16;
 		*(uint32_t*)(code + codePos) = 0x24808d41 + dst;
 		codePos += (dst == (RegisterNeedsSib << 16)) ? 4 : 3;
 
@@ -768,8 +776,8 @@ namespace randomx {
 		uint32_t pos = codePos;
 		uint8_t* const p = code + pos;
 
-		const uint32_t dst = instr.dst % RegistersCount;
-		const uint32_t sib = (instr.getModShift() << 6) | ((instr.src % RegistersCount) << 3) | dst;
+		const uint32_t dst = instr.dst;
+		const uint32_t sib = (instr.getModShift() << 6) | (instr.src << 3) | dst;
 
 		uint32_t k = 0x048d4f + (dst << 19);
 		if (dst == RegisterNeedsDisplacement)
@@ -788,8 +796,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint32_t src = instr.src % RegistersCount;
-		const uint32_t dst = instr.dst % RegistersCount;
+		const uint32_t src = instr.src;
+		const uint32_t dst = instr.dst;
 
 		if (src != dst) {
 			genAddressReg<true>(instr, src, p, pos);
@@ -809,8 +817,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 		
-		const uint32_t src = instr.src % RegistersCount;
-		const uint32_t dst = instr.dst % RegistersCount;
+		const uint32_t src = instr.src;
+		const uint32_t dst = instr.dst;
 
 		if (src != dst) {
 			*(uint32_t*)(p + pos) = 0xc02b4d + (dst << 19) + (src << 16);
@@ -830,8 +838,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint32_t src = instr.src % RegistersCount;
-		const uint32_t dst = instr.dst % RegistersCount;
+		const uint32_t src = instr.src;
+		const uint32_t dst = instr.dst;
 
 		if (src != dst) {
 			genAddressReg<true>(instr, src, p, pos);
@@ -851,8 +859,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint32_t src = instr.src % RegistersCount;
-		const uint32_t dst = instr.dst % RegistersCount;
+		const uint32_t src = instr.src;
+		const uint32_t dst = instr.dst;
 
 		if (src != dst) {
 			emit32(0xc0af0f4d + ((dst * 8 + src) << 24), p, pos);
@@ -871,8 +879,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint64_t src = instr.src % RegistersCount;
-		const uint64_t dst = instr.dst % RegistersCount;
+		const uint64_t src = instr.src;
+		const uint64_t dst = instr.dst;
 
 		if (src != dst) {
 			genAddressReg<true>(instr, src, p, pos);
@@ -892,8 +900,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint32_t src = instr.src % RegistersCount;
-		const uint32_t dst = instr.dst % RegistersCount;
+		const uint32_t src = instr.src;
+		const uint32_t dst = instr.dst;
 
 		*(uint32_t*)(p + pos) = 0xc08b49 + (dst << 16);
 		*(uint32_t*)(p + pos + 3) = 0xe0f749 + (src << 16);
@@ -908,8 +916,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint32_t src = instr.src % RegistersCount;
-		const uint32_t dst = instr.dst % RegistersCount;
+		const uint32_t src = instr.src;
+		const uint32_t dst = instr.dst;
 
 		*(uint32_t*)(p + pos) = 0xC4D08B49 + (dst << 16);
 		*(uint32_t*)(p + pos + 4) = 0xC0F6FB42 + (dst << 27) + (src << 24);
@@ -923,8 +931,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint64_t src = instr.src % RegistersCount;
-		const uint64_t dst = instr.dst % RegistersCount;
+		const uint64_t src = instr.src;
+		const uint64_t dst = instr.dst;
 
 		if (src != dst) {
 			genAddressReg<false>(instr, src, p, pos);
@@ -947,8 +955,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint64_t src = instr.src % RegistersCount;
-		const uint64_t dst = instr.dst % RegistersCount;
+		const uint64_t src = instr.src;
+		const uint64_t dst = instr.dst;
 
 		if (src != dst) {
 			genAddressReg<false>(instr, src, p, pos);
@@ -970,8 +978,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint64_t src = instr.src % RegistersCount;
-		const uint64_t dst = instr.dst % RegistersCount;
+		const uint64_t src = instr.src;
+		const uint64_t dst = instr.dst;
 
 		*(uint64_t*)(p + pos) = 0x8b4ce8f749c08b49ull + (dst << 16) + (src << 40);
 		pos += 8;
@@ -985,8 +993,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint64_t src = instr.src % RegistersCount;
-		const uint64_t dst = instr.dst % RegistersCount;
+		const uint64_t src = instr.src;
+		const uint64_t dst = instr.dst;
 
 		if (src != dst) {
 			genAddressReg<false>(instr, src, p, pos);
@@ -1011,7 +1019,7 @@ namespace randomx {
 		
 		uint64_t divisor = instr.getImm32();
 		if (!isZeroOrPowerOf2(divisor)) {
-			const uint32_t dst = instr.dst % RegistersCount;
+			const uint32_t dst = instr.dst;
 
 			const uint64_t reciprocal = randomx_reciprocal_fast(divisor);
 			if (imul_rcp_storage_used < 16) {
@@ -1040,7 +1048,7 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint32_t dst = instr.dst % RegistersCount;
+		const uint32_t dst = instr.dst;
 		*(uint32_t*)(p + pos) = 0xd8f749 + (dst << 16);
 		pos += 3;
 
@@ -1052,8 +1060,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint64_t src = instr.src % RegistersCount;
-		const uint64_t dst = instr.dst % RegistersCount;
+		const uint64_t src = instr.src;
+		const uint64_t dst = instr.dst;
 
 		if (src != dst) {
 			*(uint32_t*)(p + pos) = 0xc0334d + (((dst << 3) + src) << 16);
@@ -1073,8 +1081,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint64_t src = instr.src % RegistersCount;
-		const uint64_t dst = instr.dst % RegistersCount;
+		const uint64_t src = instr.src;
+		const uint64_t dst = instr.dst;
 
 		if (src != dst) {
 			genAddressReg<true>(instr, src, p, pos);
@@ -1094,8 +1102,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint64_t src = instr.src % RegistersCount;
-		const uint64_t dst = instr.dst % RegistersCount;
+		const uint64_t src = instr.src;
+		const uint64_t dst = instr.dst;
 
 		if (src != dst) {
 			*(uint64_t*)(p + pos) = 0xc8d349c88b41ull + (src << 16) + (dst << 40);
@@ -1115,8 +1123,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint64_t src = instr.src % RegistersCount;
-		const uint64_t dst = instr.dst % RegistersCount;
+		const uint64_t src = instr.src;
+		const uint64_t dst = instr.dst;
 
 		if (src != dst) {
 			*(uint64_t*)(p + pos) = 0xc0d349c88b41ull + (src << 16) + (dst << 40);
@@ -1136,8 +1144,8 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint32_t src = instr.src % RegistersCount;
-		const uint32_t dst = instr.dst % RegistersCount;
+		const uint32_t src = instr.src;
+		const uint32_t dst = instr.dst;
 
 		if (src != dst) {
 			*(uint32_t*)(p + pos) = 0xc0874d + (((dst << 3) + src) << 16);
@@ -1153,7 +1161,7 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const uint64_t dst = instr.dst % RegistersCount;
+		const uint64_t dst = instr.dst;
 
 		*(uint64_t*)(p + pos) = 0x01c0c60f66ull + (((dst << 3) + dst) << 24);
 		pos += 5;
@@ -1182,7 +1190,7 @@ namespace randomx {
 
 		prevFPOperation = pos;
 
-		const uint32_t src = instr.src % RegistersCount;
+		const uint32_t src = instr.src;
 		const uint32_t dst = instr.dst % RegisterCountFlt;
 
 		genAddressReg<true>(instr, src, p, pos);
@@ -1214,7 +1222,7 @@ namespace randomx {
 
 		prevFPOperation = pos;
 
-		const uint32_t src = instr.src % RegistersCount;
+		const uint32_t src = instr.src;
 		const uint32_t dst = instr.dst % RegisterCountFlt;
 
 		genAddressReg<true>(instr, src, p, pos);
@@ -1257,7 +1265,7 @@ namespace randomx {
 
 		prevFPOperation = pos;
 
-		const uint32_t src = instr.src % RegistersCount;
+		const uint32_t src = instr.src;
 		const uint64_t dst = instr.dst % RegisterCountFlt;
 
 		genAddressReg<true>(instr, src, p, pos);
@@ -1307,7 +1315,7 @@ namespace randomx {
 		uint32_t pos = codePos;
 		prevCFROUND = pos;
 
-		const uint32_t src = instr.src % RegistersCount;
+		const uint32_t src = instr.src;
 
 		*(uint32_t*)(p + pos) = 0x00C08B49 + (src << 16);
 		const int rotate = (static_cast<int>(instr.getImm32() & 63) - 2) & 63;
@@ -1343,7 +1351,7 @@ namespace randomx {
 		uint32_t pos = codePos;
 		prevCFROUND = pos;
 
-		const uint64_t src = instr.src % RegistersCount;
+		const uint64_t src = instr.src;
 
 		const uint64_t rotate = (static_cast<int>(instr.getImm32() & 63) - 2) & 63;
 		*(uint64_t*)(p + pos) = 0xC0F0FBC3C4ULL | (src << 32) | (rotate << 40);
@@ -1367,7 +1375,7 @@ namespace randomx {
 		uint8_t* const p = code;
 		uint32_t pos = codePos;
 
-		const int reg = instr.dst % RegistersCount;
+		const int reg = instr.dst;
 		int32_t jmp_offset = registerUsage[reg];
 
 		// if it jumps over the previous FP instruction that uses rounding, treat it as if FP instruction happened now
@@ -1426,7 +1434,7 @@ namespace randomx {
 		uint32_t pos = codePos;
 
 		genAddressRegDst(instr, p, pos);
-		emit32(0x0604894c + (static_cast<uint32_t>(instr.src % RegistersCount) << 19), p, pos);
+		emit32(0x0604894c + (static_cast<uint32_t>(instr.src) << 19), p, pos);
 
 		codePos = pos;
 	}