v6.18.1

Added Zen4 to randomx_boost.sh

CHANGELOG.md

@@ -1,3 +1,86 @@
+# 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.
+- [#3120](https://github.com/xmrig/xmrig/pull/3120) RandomX: optimized `CFROUND` elimination.
+- [#3109](https://github.com/xmrig/xmrig/pull/3109) RandomX: added Blake2 AVX2 version.
+- [#3082](https://github.com/xmrig/xmrig/pull/3082) Fixed GCC 12 warnings.
+- [#3075](https://github.com/xmrig/xmrig/pull/3075) Recognize `armv7ve` as valid ARMv7 target.
+- [#3132](https://github.com/xmrig/xmrig/pull/3132) RandomX: added MSR mod for Zen 4.
+- [#3134](https://github.com/xmrig/xmrig/pull/3134) Added Zen4 to `randomx_boost.sh`.
+
+# v6.18.0
+- [#3067](https://github.com/xmrig/xmrig/pull/3067) Monero v15 network upgrade support and more house keeping.
+  - Removed deprecated AstroBWTv1 and v2.
+  - Fixed debug GhostRider build.
+  - Monero v15 network upgrade support.
+  - Fixed ZMQ debug log.
+  - Improved daemon ZMQ mining stability.
+- [#3054](https://github.com/xmrig/xmrig/pull/3054) Fixes for 32-bit ARM.
+- [#3042](https://github.com/xmrig/xmrig/pull/3042) Fixed being unable to resume from `pause-on-battery`.
+- [#3031](https://github.com/xmrig/xmrig/pull/3031) Fixed `--cpu-priority` not working sometimes.
+- [#3020](https://github.com/xmrig/xmrig/pull/3020) Removed old AstroBWT algorithm.
+
+# v6.17.0
+- [#2954](https://github.com/xmrig/xmrig/pull/2954) **Dero HE fork support (`astrobwt/v2` algorithm).**
+  - [#2961](https://github.com/xmrig/xmrig/pull/2961) Dero HE (`astrobwt/v2`) CUDA config generator.
+  - [#2969](https://github.com/xmrig/xmrig/pull/2969) Dero HE (`astrobwt/v2`) OpenCL support.
+- Fixed displayed DMI memory information for empty slots.
+- [#2932](https://github.com/xmrig/xmrig/pull/2932) Fixed GhostRider with hwloc disabled.
+
+# v6.16.4
+- [#2904](https://github.com/xmrig/xmrig/pull/2904) Fixed unaligned memory accesses.
+- [#2908](https://github.com/xmrig/xmrig/pull/2908) Added MSVC/2022 to `version.h`.
+- [#2910](https://github.com/xmrig/xmrig/issues/2910) Fixed donation for GhostRider/RTM.
+
+# v6.16.3
+- [#2778](https://github.com/xmrig/xmrig/pull/2778) Fixed `READY threads X/X` display after algorithm switching.
+- [#2782](https://github.com/xmrig/xmrig/pull/2782) Updated GhostRider documentation.
+- [#2815](https://github.com/xmrig/xmrig/pull/2815) Fixed `cn-heavy` in 32-bit builds.
+- [#2827](https://github.com/xmrig/xmrig/pull/2827) GhostRider: set correct priority for helper threads.
+- [#2837](https://github.com/xmrig/xmrig/pull/2837) RandomX: don't restart mining threads when the seed changes.
+- [#2848](https://github.com/xmrig/xmrig/pull/2848) GhostRider: added support for `client.reconnect` method.
+- [#2856](https://github.com/xmrig/xmrig/pull/2856) Fix for short responses from some Raptoreum pools.
+- [#2873](https://github.com/xmrig/xmrig/pull/2873) Fixed GhostRider benchmark on single-core systems.
+- [#2882](https://github.com/xmrig/xmrig/pull/2882) Fixed ARMv7 compilation.
+- [#2893](https://github.com/xmrig/xmrig/pull/2893) KawPow OpenCL: use separate UV loop for building programs.
+
+# v6.16.2
+- [#2751](https://github.com/xmrig/xmrig/pull/2751) Fixed crash on CPUs supporting VAES and running GCC-compiled xmrig.
+- [#2761](https://github.com/xmrig/xmrig/pull/2761) Fixed broken auto-tuning in GCC Windows build.
+- [#2771](https://github.com/xmrig/xmrig/issues/2771) Fixed environment variables support for GhostRider and KawPow. 
+- [#2769](https://github.com/xmrig/xmrig/pull/2769) Performance fixes:
+  - Fixed several performance bottlenecks introduced in v6.16.1.
+  - Fixed overall GCC-compiled build performance, it's the same speed as MSVC build now.
+  - **Linux builds are up to 10% faster now compared to v6.16.0 GCC build.**
+  - **Windows builds are up to 5% faster now compared to v6.16.0 MSVC build.**
+
+# v6.16.1
+- [#2729](https://github.com/xmrig/xmrig/pull/2729) GhostRider fixes:
+  - Added average hashrate display.
+  - Fixed the number of threads shown at startup.
+  - Fixed `--threads` or `-t` command line option (but `--cpu-max-threads-hint` is recommended to use).
+- [#2738](https://github.com/xmrig/xmrig/pull/2738) GhostRider fixes:
+  - Fixed "difficulty is not a number" error when diff is high on some pools.
+  - Fixed GhostRider compilation when `WITH_KAWPOW=OFF`.
+- [#2740](https://github.com/xmrig/xmrig/pull/2740) Added VAES support for Cryptonight variants **+4% speedup on Zen3**.
+  - VAES instructions are available on Intel Ice Lake/AMD Zen3 and newer CPUs.
+  - +4% speedup on Ryzen 5 5600X.
+
+# v6.16.0
+- [#2712](https://github.com/xmrig/xmrig/pull/2712) **GhostRider algorithm (Raptoreum) support**: read the [RELEASE NOTES](src/crypto/ghostrider/README.md) for quick start guide and performance comparisons.
+- [#2682](https://github.com/xmrig/xmrig/pull/2682) Fixed: use cn-heavy optimization only for Vermeer CPUs.
+- [#2684](https://github.com/xmrig/xmrig/pull/2684) MSR mod: fix for error 183.
+
+# v6.15.3
+- [#2614](https://github.com/xmrig/xmrig/pull/2614) OpenCL fixes for non-AMD platforms.
+- [#2623](https://github.com/xmrig/xmrig/pull/2623) Fixed compiling without kawpow.
+- [#2636](https://github.com/xmrig/xmrig/pull/2636) [#2639](https://github.com/xmrig/xmrig/pull/2639) AstroBWT speedup (up to +35%).
+- [#2646](https://github.com/xmrig/xmrig/pull/2646) Fixed MSVC compilation error.
+
+# v6.15.2
+- [#2606](https://github.com/xmrig/xmrig/pull/2606) Fixed: AstroBWT auto-config ignored `max-threads-hint`.
+- Fixed possible crash on Windows (regression in v6.15.1).
+
 # v6.15.1
 - [#2586](https://github.com/xmrig/xmrig/pull/2586) Fixed Windows 7 compatibility.
 - [#2594](https://github.com/xmrig/xmrig/pull/2594) Added Windows taskbar icon colors.

CMakeLists.txt

@@ -8,8 +8,8 @@ option(WITH_CN_PICO         "Enable CryptoNight-Pico algorithm" ON)
 option(WITH_CN_FEMTO        "Enable CryptoNight-UPX2 algorithm" ON)
 option(WITH_RANDOMX         "Enable RandomX algorithms family" ON)
 option(WITH_ARGON2          "Enable Argon2 algorithms family" ON)
-option(WITH_ASTROBWT        "Enable AstroBWT algorithms family" ON)
 option(WITH_KAWPOW          "Enable KawPow algorithms family" ON)
+option(WITH_GHOSTRIDER      "Enable GhostRider algorithm" ON)
 option(WITH_HTTP            "Enable HTTP protocol support (client/server)" ON)
 option(WITH_DEBUG_LOG       "Enable debug log output" OFF)
 option(WITH_TLS             "Enable OpenSSL support" ON)
@@ -18,6 +18,8 @@ option(WITH_MSR             "Enable MSR mod & 1st-gen Ryzen fix" ON)
 option(WITH_ENV_VARS        "Enable environment variables support in config file" ON)
 option(WITH_EMBEDDED_CONFIG "Enable internal embedded JSON config" OFF)
 option(WITH_OPENCL          "Enable OpenCL backend" ON)
+set(WITH_OPENCL_VERSION 200 CACHE STRING "Target OpenCL version")
+set_property(CACHE WITH_OPENCL_VERSION PROPERTY STRINGS 120 200 210 220)
 option(WITH_CUDA            "Enable CUDA backend" ON)
 option(WITH_NVML            "Enable NVML (NVIDIA Management Library) support (only if CUDA backend enabled)" ON)
 option(WITH_ADL             "Enable ADL (AMD Display Library) or sysfs support (only if OpenCL backend enabled)" ON)
@@ -25,6 +27,8 @@ option(WITH_STRICT_CACHE    "Enable strict checks for OpenCL cache" ON)
 option(WITH_INTERLEAVE_DEBUG_LOG "Enable debug log for threads interleave" OFF)
 option(WITH_PROFILING       "Enable profiling for developers" OFF)
 option(WITH_SSE4_1          "Enable SSE 4.1 for Blake2" ON)
+option(WITH_AVX2            "Enable AVX2 for Blake2" ON)
+option(WITH_VAES            "Enable VAES instructions for Cryptonight" ON)
 option(WITH_BENCHMARK       "Enable builtin RandomX benchmark and stress test" ON)
 option(WITH_SECURE_JIT      "Enable secure access to JIT memory" OFF)
 option(WITH_DMI             "Enable DMI/SMBIOS reader" ON)
@@ -126,6 +130,19 @@ set(SOURCES_CRYPTO
     src/crypto/common/VirtualMemory.cpp
    )
 
+if (CMAKE_C_COMPILER_ID MATCHES GNU)
+    set_source_files_properties(src/crypto/cn/CnHash.cpp PROPERTIES COMPILE_FLAGS "-Ofast -fno-tree-vectorize")
+endif()
+
+if (WITH_VAES)
+    add_definitions(-DXMRIG_VAES)
+    set(HEADERS_CRYPTO "${HEADERS_CRYPTO}" src/crypto/cn/CryptoNight_x86_vaes.h)
+    set(SOURCES_CRYPTO "${SOURCES_CRYPTO}" src/crypto/cn/CryptoNight_x86_vaes.cpp)
+    if (CMAKE_C_COMPILER_ID MATCHES GNU OR CMAKE_C_COMPILER_ID MATCHES Clang)
+        set_source_files_properties(src/crypto/cn/CryptoNight_x86_vaes.cpp PROPERTIES COMPILE_FLAGS "-Ofast -fno-tree-vectorize -mavx2 -mvaes")
+    endif()
+endif()
+
 if (WITH_HWLOC)
     list(APPEND HEADERS_CRYPTO
         src/crypto/common/NUMAMemoryPool.h
@@ -182,8 +199,8 @@ find_package(UV REQUIRED)
 include(cmake/flags.cmake)
 include(cmake/randomx.cmake)
 include(cmake/argon2.cmake)
-include(cmake/astrobwt.cmake)
 include(cmake/kawpow.cmake)
+include(cmake/ghostrider.cmake)
 include(cmake/OpenSSL.cmake)
 include(cmake/asm.cmake)
 
@@ -219,7 +236,7 @@ if (WITH_DEBUG_LOG)
 endif()
 
 add_executable(${CMAKE_PROJECT_NAME} ${HEADERS} ${SOURCES} ${SOURCES_OS} ${HEADERS_CRYPTO} ${SOURCES_CRYPTO} ${SOURCES_SYSLOG} ${TLS_SOURCES} ${XMRIG_ASM_SOURCES})
-target_link_libraries(${CMAKE_PROJECT_NAME} ${XMRIG_ASM_LIBRARY} ${OPENSSL_LIBRARIES} ${UV_LIBRARIES} ${EXTRA_LIBS} ${CPUID_LIB} ${ARGON2_LIBRARY} ${ETHASH_LIBRARY})
+target_link_libraries(${CMAKE_PROJECT_NAME} ${XMRIG_ASM_LIBRARY} ${OPENSSL_LIBRARIES} ${UV_LIBRARIES} ${EXTRA_LIBS} ${CPUID_LIB} ${ARGON2_LIBRARY} ${ETHASH_LIBRARY} ${GHOSTRIDER_LIBRARY})
 
 if (WIN32)
     add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/bin/WinRing0/WinRing0x64.sys" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
@@ -227,6 +244,7 @@ if (WIN32)
     add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/scripts/benchmark_10M.cmd" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
     add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/scripts/pool_mine_example.cmd" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
     add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/scripts/solo_mine_example.cmd" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
+    add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/scripts/rtm_ghostrider_example.cmd" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
 endif()
 
 if (CMAKE_CXX_COMPILER_ID MATCHES Clang AND CMAKE_BUILD_TYPE STREQUAL Release AND NOT CMAKE_GENERATOR STREQUAL Xcode)

README.md

@@ -7,10 +7,10 @@
 [![GitHub stars](https://img.shields.io/github/stars/xmrig/xmrig.svg)](https://github.com/xmrig/xmrig/stargazers)
 [![GitHub forks](https://img.shields.io/github/forks/xmrig/xmrig.svg)](https://github.com/xmrig/xmrig/network)
 
-XMRig is a high performance, open source, cross platform RandomX, KawPow, CryptoNight and AstroBWT unified CPU/GPU miner and [RandomX benchmark](https://xmrig.com/benchmark). Official binaries are available for Windows, Linux, macOS and FreeBSD.
+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/ARMv8)
+- **CPU** (x64/ARMv7/ARMv8)
 - **OpenCL** for AMD GPUs.
 - **CUDA** for NVIDIA GPUs via external [CUDA plugin](https://github.com/xmrig/xmrig-cuda).
 

cmake/astrobwt.cmake

@@ -1,51 +0,0 @@
-if (WITH_ASTROBWT)
-    add_definitions(/DXMRIG_ALGO_ASTROBWT)
-
-    list(APPEND HEADERS_CRYPTO
-        src/crypto/astrobwt/AstroBWT.h
-    )
-
-    list(APPEND SOURCES_CRYPTO
-        src/crypto/astrobwt/AstroBWT.cpp
-    )
-
-    if (XMRIG_ARM)
-        list(APPEND HEADERS_CRYPTO
-            src/crypto/astrobwt/salsa20_ref/ecrypt-config.h
-            src/crypto/astrobwt/salsa20_ref/ecrypt-machine.h
-            src/crypto/astrobwt/salsa20_ref/ecrypt-portable.h
-            src/crypto/astrobwt/salsa20_ref/ecrypt-sync.h
-        )
-
-        list(APPEND SOURCES_CRYPTO
-            src/crypto/astrobwt/salsa20_ref/salsa20.c
-        )
-    else()
-        if (CMAKE_SIZEOF_VOID_P EQUAL 8)
-            add_definitions(/DASTROBWT_AVX2)
-            list(APPEND SOURCES_CRYPTO src/crypto/astrobwt/xmm6int/salsa20_xmm6int-avx2.c)
-
-            if (CMAKE_C_COMPILER_ID MATCHES GNU OR CMAKE_C_COMPILER_ID MATCHES Clang)
-                set_source_files_properties(src/crypto/astrobwt/xmm6int/salsa20_xmm6int-avx2.c PROPERTIES COMPILE_FLAGS -mavx2)
-            endif()
-
-            if (CMAKE_C_COMPILER_ID MATCHES MSVC)
-                enable_language(ASM_MASM)
-                list(APPEND SOURCES_CRYPTO src/crypto/astrobwt/sha3_256_avx2.asm)
-            else()
-                enable_language(ASM)
-                list(APPEND SOURCES_CRYPTO src/crypto/astrobwt/sha3_256_avx2.S)
-            endif()
-        endif()
-
-        list(APPEND HEADERS_CRYPTO
-            src/crypto/astrobwt/Salsa20.hpp
-        )
-
-        list(APPEND SOURCES_CRYPTO
-            src/crypto/astrobwt/Salsa20.cpp
-        )
-    endif()
-else()
-    remove_definitions(/DXMRIG_ALGO_ASTROBWT)
-endif()

cmake/cpu.cmake

@@ -9,16 +9,30 @@ if (NOT CMAKE_SYSTEM_PROCESSOR)
     message(WARNING "CMAKE_SYSTEM_PROCESSOR not defined")
 endif()
 
+include(CheckCXXCompilerFlag)
+
+if (CMAKE_CXX_COMPILER_ID MATCHES MSVC)
+    set(VAES_SUPPORTED ON)
+else()
+    CHECK_CXX_COMPILER_FLAG("-mavx2 -mvaes" VAES_SUPPORTED)
+endif()
+
+if (NOT VAES_SUPPORTED)
+    set(WITH_VAES OFF)
+endif()
+
 if (XMRIG_64_BIT AND CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|AMD64)$")
     add_definitions(-DRAPIDJSON_SSE2)
 else()
     set(WITH_SSE4_1 OFF)
+    set(WITH_AVX2 OFF)
+    set(WITH_VAES OFF)
 endif()
 
 if (NOT ARM_TARGET)
     if (CMAKE_SYSTEM_PROCESSOR MATCHES "^(aarch64|arm64|armv8-a)$")
         set(ARM_TARGET 8)
-    elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "^(armv7|armv7f|armv7s|armv7k|armv7-a|armv7l)$")
+    elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "^(armv7|armv7f|armv7s|armv7k|armv7-a|armv7l|armv7ve)$")
         set(ARM_TARGET 7)
     endif()
 endif()
@@ -29,8 +43,6 @@ if (ARM_TARGET AND ARM_TARGET GREATER 6)
 
     message(STATUS "Use ARM_TARGET=${ARM_TARGET} (${CMAKE_SYSTEM_PROCESSOR})")
 
-    include(CheckCXXCompilerFlag)
-
     if (ARM_TARGET EQUAL 8)
         CHECK_CXX_COMPILER_FLAG(-march=armv8-a+crypto XMRIG_ARM_CRYPTO)
 
@@ -46,3 +58,7 @@ endif()
 if (WITH_SSE4_1)
     add_definitions(-DXMRIG_FEATURE_SSE4_1)
 endif()
+
+if (WITH_AVX2)
+    add_definitions(-DXMRIG_FEATURE_AVX2)
+endif()

cmake/flags.cmake

@@ -26,8 +26,8 @@ if (CMAKE_CXX_COMPILER_ID MATCHES GNU)
         set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${ARM8_CXX_FLAGS}")
         set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${ARM8_CXX_FLAGS} -flax-vector-conversions")
     elseif (ARM_TARGET EQUAL 7)
-        set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mfpu=neon")
-        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mfpu=neon -flax-vector-conversions")
+        set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv7-a -mfpu=neon")
+        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv7-a -mfpu=neon -flax-vector-conversions")
     else()
         set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -maes")
         set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -maes")

cmake/ghostrider.cmake

@@ -0,0 +1,8 @@
+if (WITH_GHOSTRIDER)
+    add_definitions(/DXMRIG_ALGO_GHOSTRIDER)
+    add_subdirectory(src/crypto/ghostrider)
+    set(GHOSTRIDER_LIBRARY ghostrider)
+else()
+    remove_definitions(/DXMRIG_ALGO_GHOSTRIDER)
+    set(GHOSTRIDER_LIBRARY "")
+endif()

cmake/randomx.cmake

@@ -76,7 +76,15 @@ if (WITH_RANDOMX)
         list(APPEND SOURCES_CRYPTO src/crypto/randomx/blake2/blake2b_sse41.c)
 
         if (CMAKE_C_COMPILER_ID MATCHES GNU OR CMAKE_C_COMPILER_ID MATCHES Clang)
-            set_source_files_properties(src/crypto/randomx/blake2/blake2b_sse41.c PROPERTIES COMPILE_FLAGS -msse4.1)
+            set_source_files_properties(src/crypto/randomx/blake2/blake2b_sse41.c PROPERTIES COMPILE_FLAGS "-Ofast -msse4.1")
+        endif()
+    endif()
+
+    if (WITH_AVX2)
+        list(APPEND SOURCES_CRYPTO src/crypto/randomx/blake2/avx2/blake2b_avx2.c)
+
+        if (CMAKE_C_COMPILER_ID MATCHES GNU OR CMAKE_C_COMPILER_ID MATCHES Clang)
+            set_source_files_properties(src/crypto/randomx/blake2/avx2/blake2b_avx2.c PROPERTIES COMPILE_FLAGS "-Ofast -mavx2")
         endif()
     endif()
 

scripts/build.hwloc.sh

@@ -1,6 +1,10 @@
 #!/bin/bash -e
 
-HWLOC_VERSION="2.5.0"
+HWLOC_VERSION_MAJOR="2"
+HWLOC_VERSION_MINOR="7"
+HWLOC_VERSION_PATCH="1"
+
+HWLOC_VERSION="${HWLOC_VERSION_MAJOR}.${HWLOC_VERSION_MINOR}.${HWLOC_VERSION_PATCH}"
 
 mkdir -p deps
 mkdir -p deps/include
@@ -8,7 +12,7 @@ mkdir -p deps/lib
 
 mkdir -p build && cd build
 
-wget https://download.open-mpi.org/release/hwloc/v2.5/hwloc-${HWLOC_VERSION}.tar.gz -O hwloc-${HWLOC_VERSION}.tar.gz
+wget https://download.open-mpi.org/release/hwloc/v${HWLOC_VERSION_MAJOR}.${HWLOC_VERSION_MINOR}/hwloc-${HWLOC_VERSION}.tar.gz -O hwloc-${HWLOC_VERSION}.tar.gz
 tar -xzf hwloc-${HWLOC_VERSION}.tar.gz
 
 cd hwloc-${HWLOC_VERSION}
@@ -16,4 +20,4 @@ cd hwloc-${HWLOC_VERSION}
 make -j$(nproc || sysctl -n hw.ncpu || sysctl -n hw.logicalcpu)
 cp -fr include ../../deps
 cp hwloc/.libs/libhwloc.a ../../deps/lib
-cd ..
+cd ..

scripts/build.libressl.sh

@@ -1,6 +1,6 @@
 #!/bin/bash -e
 
-LIBRESSL_VERSION="3.0.2"
+LIBRESSL_VERSION="3.5.2"
 
 mkdir -p deps
 mkdir -p deps/include
@@ -17,4 +17,4 @@ make -j$(nproc || sysctl -n hw.ncpu || sysctl -n hw.logicalcpu)
 cp -fr include ../../deps
 cp crypto/.libs/libcrypto.a ../../deps/lib
 cp ssl/.libs/libssl.a ../../deps/lib
-cd ..
+cd ..

scripts/build.openssl.sh

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

scripts/build.openssl3.sh

@@ -0,0 +1,20 @@
+#!/bin/bash -e
+
+OPENSSL_VERSION="3.0.3"
+
+mkdir -p deps
+mkdir -p deps/include
+mkdir -p deps/lib
+
+mkdir -p build && cd build
+
+wget https://www.openssl.org/source/openssl-${OPENSSL_VERSION}.tar.gz -O openssl-${OPENSSL_VERSION}.tar.gz
+tar -xzf openssl-${OPENSSL_VERSION}.tar.gz
+
+cd openssl-${OPENSSL_VERSION}
+./config -no-shared -no-asm -no-zlib -no-comp -no-dgram -no-filenames -no-cms
+make -j$(nproc || sysctl -n hw.ncpu || sysctl -n hw.logicalcpu)
+cp -fr include ../../deps
+cp libcrypto.a ../../deps/lib
+cp libssl.a ../../deps/lib
+cd ..

scripts/build.uv.sh

@@ -1,6 +1,6 @@
 #!/bin/bash -e
 
-UV_VERSION="1.42.0"
+UV_VERSION="1.44.1"
 
 mkdir -p deps
 mkdir -p deps/include
@@ -17,4 +17,4 @@ sh autogen.sh
 make -j$(nproc || sysctl -n hw.ncpu || sysctl -n hw.logicalcpu)
 cp -fr include ../../deps
 cp .libs/libuv.a ../../deps/lib
-cd ..
+cd ..

scripts/generate_cl.js

@@ -67,15 +67,6 @@ function rx()
 }
 
 
-function astrobwt()
-{
-    const astrobwt = opencl_minify(addIncludes('astrobwt.cl', [ 'BWT.cl', 'salsa20.cl', 'sha3.cl' ]));
-
-    // fs.writeFileSync('astrobwt_gen.cl', astrobwt);
-    fs.writeFileSync('astrobwt_cl.h', text2h(astrobwt, 'xmrig', 'astrobwt_cl'));
-}
-
-
 function kawpow()
 {
     const kawpow = opencl_minify(addIncludes('kawpow.cl', [ 'defs.h' ]));
@@ -97,11 +88,6 @@ process.chdir(path.resolve('src/backend/opencl/cl/rx'));
 
 rx();
 
-process.chdir(cwd);
-process.chdir(path.resolve('src/backend/opencl/cl/astrobwt'));
-
-astrobwt();
-
 process.chdir(cwd);
 process.chdir(path.resolve('src/backend/opencl/cl/kawpow'));
 

scripts/randomx_boost.sh

@@ -10,14 +10,24 @@ fi
 
 if grep -E 'AMD Ryzen|AMD EPYC' /proc/cpuinfo > /dev/null;
 	then
-	if grep "cpu family[[:space:]]:[[:space:]]25" /proc/cpuinfo > /dev/null;
+	if grep "cpu family[[:space:]]\{1,\}:[[:space:]]25" /proc/cpuinfo > /dev/null;
 		then
-			echo "Detected Zen3 CPU"
-			wrmsr -a 0xc0011020 0x4480000000000
-			wrmsr -a 0xc0011021 0x1c000200000040
-			wrmsr -a 0xc0011022 0xc000000401500000
-			wrmsr -a 0xc001102b 0x2000cc14
-			echo "MSR register values for Zen3 applied"
+			if grep "model[[:space:]]\{1,\}:[[:space:]]97" /proc/cpuinfo > /dev/null;
+				then
+					echo "Detected Zen4 CPU"
+					wrmsr -a 0xc0011020 0x4400000000000
+					wrmsr -a 0xc0011021 0x4000000000040
+					wrmsr -a 0xc0011022 0x8680000401570000
+					wrmsr -a 0xc001102b 0x2040cc10
+					echo "MSR register values for Zen4 applied"
+				else
+					echo "Detected Zen3 CPU"
+					wrmsr -a 0xc0011020 0x4480000000000
+					wrmsr -a 0xc0011021 0x1c000200000040
+					wrmsr -a 0xc0011022 0xc000000401500000
+					wrmsr -a 0xc001102b 0x2000cc14
+					echo "MSR register values for Zen3 applied"
+				fi
 		else
 			echo "Detected Zen1/Zen2 CPU"
 			wrmsr -a 0xc0011020 0

scripts/rtm_ghostrider_example.cmd

@@ -0,0 +1,23 @@
+:: Example batch file for mining Raptoreum at a pool
+::
+:: Format:
+::      xmrig.exe -a gr -o <pool address>:<pool port> -u <pool username/wallet> -p <pool password>
+::
+:: Fields:
+::      pool address            The host name of the pool stratum or its IP address, for example raptoreumemporium.com
+::      pool port               The port of the pool's stratum to connect to, for example 3333. Check your pool's getting started page.
+::      pool username/wallet    For most pools, this is the wallet address you want to mine to. Some pools require a username
+::      pool password           For most pools this can be just 'x'. For pools using usernames, you may need to provide a password as configured on the pool.
+::
+:: List of Raptoreum mining pools:
+::      https://miningpoolstats.stream/raptoreum
+::
+:: Choose pools outside of top 5 to help Raptoreum network be more decentralized!
+:: Smaller pools also often have smaller fees/payout limits.
+
+cd %~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
+:: xmrig.exe -a gr -o rtm.suprnova.cc:4273 --tls -u WALLET_ADDRESS -p x
+pause

src/3rdparty/CL/cl_dx9_media_sharing.h

@@ -44,7 +44,7 @@ extern "C" {
 
 typedef cl_uint             cl_dx9_media_adapter_type_khr;
 typedef cl_uint             cl_dx9_media_adapter_set_khr;
-    
+
 #if defined(_WIN32)
 #include <d3d9.h>
 typedef struct _cl_dx9_surface_info_khr
@@ -105,7 +105,7 @@ typedef CL_API_ENTRY cl_mem (CL_API_CALL *clCreateFromDX9MediaSurfaceKHR_fn)(
     cl_mem_flags                  flags,
     cl_dx9_media_adapter_type_khr adapter_type,
     void *                        surface_info,
-    cl_uint                       plane,                                                                          
+    cl_uint                       plane,
     cl_int *                      errcode_ret) CL_API_SUFFIX__VERSION_1_2;
 
 typedef CL_API_ENTRY cl_int (CL_API_CALL *clEnqueueAcquireDX9MediaSurfacesKHR_fn)(

src/3rdparty/CL/cl_gl_ext.h

@@ -35,7 +35,7 @@ extern "C" {
 
 #include <CL/cl_gl.h>
 
-/* 
+/*
  *  cl_khr_gl_event extension
  */
 #define CL_COMMAND_GL_FENCE_SYNC_OBJECT_KHR     0x200D

src/3rdparty/adl/adl_defines.h

@@ -1471,7 +1471,7 @@ typedef enum _ADLProfilePropertyType
 #define ADL_HDR_FREESYNC_HDR    0x0004      ///< FreeSync HDR supported
 /// @}
 
-/// \defgroup define_FreesyncFlags ADLDDCInfo2 Freesync HDR flags 
+/// \defgroup define_FreesyncFlags ADLDDCInfo2 Freesync HDR flags
 /// @{
 /// defines for iFreesyncFlags in ADLDDCInfo2
 #define ADL_HDR_FREESYNC_BACKLIGHT_SUPPORT           0x0001      ///< Global backlight control supported
@@ -1738,7 +1738,7 @@ enum ADLODNDPMMaskType
      ADL_ODN_DPM_MASK                = 1 << 2,
 };
 
-//ODN features Bits for ADLODNCapabilitiesX2 
+//ODN features Bits for ADLODNCapabilitiesX2
 enum ADLODNFeatureControl
 {
      ADL_ODN_SCLK_DPM                = 1 << 0,
@@ -1764,7 +1764,7 @@ enum ADLODNFeatureControl
 
 //If any new feature is added, PPLIB only needs to add ext feature ID and Item ID(Seeting ID). These IDs should match the drive defined in CWDDEPM.h
 enum ADLODNExtFeatureControl
-{	
+{
 	ADL_ODN_EXT_FEATURE_MEMORY_TIMING_TUNE = 1 << 0,
 	ADL_ODN_EXT_FEATURE_FAN_ZERO_RPM_CONTROL = 1 << 1,
 	ADL_ODN_EXT_FEATURE_AUTO_UV_ENGINE = 1 << 2,   //Auto under voltage
@@ -1794,7 +1794,7 @@ enum ADLODNExtSettingId
 	ADL_ODN_PARAMETER_FAN_CURVE_SPEED_5,
     ADL_ODN_POWERGAUGE,
 	ODN_COUNT
-	
+
 } ;
 
 //OD8 Capability features bits
@@ -1811,7 +1811,7 @@ enum ADLOD8FeatureControl
     ADL_OD8_MEMORY_TIMING_TUNE = 1 << 8,
     ADL_OD8_FAN_ZERO_RPM_CONTROL = 1 << 9 ,
 	ADL_OD8_AUTO_UV_ENGINE = 1 << 10,  //Auto under voltage
-	ADL_OD8_AUTO_OC_ENGINE = 1 << 11,  //Auto overclock engine     
+	ADL_OD8_AUTO_OC_ENGINE = 1 << 11,  //Auto overclock engine
 	ADL_OD8_AUTO_OC_MEMORY = 1 << 12,  //Auto overclock memory
 	ADL_OD8_FAN_CURVE = 1 << 13,   //Fan curve
 	ADL_OD8_WS_AUTO_FAN_ACOUSTIC_LIMIT = 1 << 14, //Workstation Manual Fan controller
@@ -1888,7 +1888,7 @@ typedef enum _ADLSensorType
 	PMLOG_TEMPERATURE_VRSOC = 24,
 	PMLOG_TEMPERATURE_VRMVDD0 = 25,
 	PMLOG_TEMPERATURE_VRMVDD1 = 26,
-	PMLOG_TEMPERATURE_HOTSPOT = 27,    
+	PMLOG_TEMPERATURE_HOTSPOT = 27,
         PMLOG_TEMPERATURE_GFX = 28,
         PMLOG_TEMPERATURE_SOC = 29,
         PMLOG_GFX_POWER = 30,

src/3rdparty/adl/adl_sdk.h

@@ -37,7 +37,7 @@
 #define __stdcall
 #endif /* (LINUX) */
 
-/// Memory Allocation Call back 
+/// Memory Allocation Call back
 typedef void* ( __stdcall *ADL_MAIN_MALLOC_CALLBACK )( int );
 
 

src/3rdparty/adl/adl_structures.h

@@ -1753,7 +1753,7 @@ typedef struct ADLPXConfigCaps
 ///\brief Enum containing PX or HG type
 ///
 /// This enum is used to get PX or hG type
-/// 
+///
 /// \nosubgrouping
 //////////////////////////////////////////////////////////////////////////////////////////
 enum ADLPxType

src/3rdparty/epee/README.md

@@ -1 +1 @@
-epee -  is a small library of helpers, wrappers, tools and and so on, used to make my life easier. 
+epee -  is a small library of helpers, wrappers, tools and and so on, used to make my life easier.

src/3rdparty/epee/span.h

@@ -145,7 +145,7 @@ namespace epee
   span<const std::uint8_t> to_byte_span(const span<const T> src) noexcept
   {
     static_assert(!has_padding<T>(), "source type may have padding");
-    return {reinterpret_cast<const std::uint8_t*>(src.data()), src.size_bytes()}; 
+    return {reinterpret_cast<const std::uint8_t*>(src.data()), src.size_bytes()};
   }
 
   //! \return `span<const std::uint8_t>` which represents the bytes at `&src`.

src/3rdparty/fmt/README.rst

@@ -81,7 +81,7 @@ Examples
 .. code:: c++
 
     #include <fmt/core.h>
-    
+
     int main() {
       fmt::print("Hello, world!\n");
     }
@@ -293,11 +293,11 @@ Projects using this library
   An open-source library for mathematical programming
 
 * `Aseprite <https://github.com/aseprite/aseprite>`_:
-  Animated sprite editor & pixel art tool 
+  Animated sprite editor & pixel art tool
 
 * `AvioBook <https://www.aviobook.aero/en>`_: A comprehensive aircraft
   operations suite
-  
+
 * `Celestia <https://celestia.space/>`_: Real-time 3D visualization of space
 
 * `Ceph <https://ceph.com/>`_: A scalable distributed storage system
@@ -351,7 +351,7 @@ Projects using this library
 
 * `quasardb <https://www.quasardb.net/>`_: A distributed, high-performance,
   associative database
-  
+
 * `Quill <https://github.com/odygrd/quill>`_: Asynchronous low-latency logging library
 
 * `QKW <https://github.com/ravijanjam/qkw>`_: Generalizing aliasing to simplify

src/3rdparty/getopt/getopt.h

@@ -3,9 +3,9 @@
  * DISCLAIMER
  * This file is part of the mingw-w64 runtime package.
  *
- * The mingw-w64 runtime package and its code is distributed in the hope that it 
- * will be useful but WITHOUT ANY WARRANTY.  ALL WARRANTIES, EXPRESSED OR 
- * IMPLIED ARE HEREBY DISCLAIMED.  This includes but is not limited to 
+ * The mingw-w64 runtime package and its code is distributed in the hope that it
+ * will be useful but WITHOUT ANY WARRANTY.  ALL WARRANTIES, EXPRESSED OR
+ * IMPLIED ARE HEREBY DISCLAIMED.  This includes but is not limited to
  * warranties of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
  */
  /*
@@ -109,11 +109,7 @@ char    *optarg;		/* argument associated with option */
 extern char __declspec(dllimport) *__progname;
 #endif
 
-#ifdef __CYGWIN__
 static char EMSG[] = "";
-#else
-#define	EMSG		""
-#endif
 
 static int getopt_internal(int, char * const *, const char *,
 			   const struct option *, int *, int);

src/3rdparty/hwloc/NEWS

@@ -1,5 +1,5 @@
 Copyright © 2009 CNRS
-Copyright © 2009-2021 Inria.  All rights reserved.
+Copyright © 2009-2022 Inria.  All rights reserved.
 Copyright © 2009-2013 Université Bordeaux
 Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
 Copyright © 2020 Hewlett Packard Enterprise.  All rights reserved.
@@ -17,6 +17,88 @@ bug fixes (and other actions) for each version of hwloc since version
 0.9.
 
 
+Version 2.7.1
+-------------
+* Workaround crashes when virtual machines report incoherent x86 CPUID
+  information about numbers of cores and threads.
+  Thanks to Peter Bense for the report.
+* Use setenv() instead of putenv() when trying to force enable oneAPI L0
+  support, to avoid issues with applications that touch the environment,
+  thanks to Josh Hursey for the patch.
+* Add some warnings at the end of configure when GPU libraries are
+  missing on the system or their path is missing in the environment.
+
+
+Version 2.7.0
+-------------
+* Backends
+  + Add support for NUMA nodes and caches with more than 64 PUs across
+    multiple processor groups on Windows 11 and Windows Server 2022.
+  + Group objects are not created for Windows processor groups anymore,
+    except if HWLOC_WINDOWS_PROCESSOR_GROUP_OBJS=1 in the environment.
+  + Expose "Cluster" group objects on Linux kernel 5.16+ for CPUs
+    that share some internal cache or bus. This can be equivalent
+    to the L2 Cache level on some platforms (e.g. x86) or a specific
+    level between L2 and L3 on others (e.g. ARM Kungpeng 920).
+    Thanks to Jonathan Cameron for the help.
+    - HWLOC_DONT_MERGE_CLUSTER_GROUPS=1 may be set in the environment
+      to prevent these groups from being merged with identical caches, etc.
+  + Improve the oneAPI LevelZero backend:
+    - Expose subdevices such as "ze0.1" inside root OS devices ("ze0")
+      when the hardware contains multiple subdevices.
+    - Add many new attributes to describe device type, and the
+      numbers of slices, subslices, execution units and threads.
+    - Expose the memory information as LevelZeroHBM/DDR/MemorySize infos.
+  + Ignore the max frequencies of cores in Linux cpukinds when the
+    base frequencies are available (to avoid exposing hybrid CPUs
+    when Intel Turbo Boost Max 3.0 gives slightly different max
+    frequencies to CPU cores).
+    - May be reverted by setting HWLOC_CPUKINDS_MAXFREQ=1 in the environment.
+* Tools
+  + Add --grey and --palette options to switch lstopo to greyscale or
+    white-background-only graphics, or to tune individual colors.
+* Build
+  + Windows CMake builds now support non-MSVC compilers, detect several
+    features at build time, can build/run tests, etc.
+    Thanks to Michael Hirsch and Alexander Neumann .
+
+
+Version 2.6.0
+-------------
+* Backends
+  + Expose two cpukinds for energy-efficient cores (icestorm) and
+    high-performance cores (firestorm) on Apple M1 on Mac OS X.
+  + Use sysfs CPU "capacity" to rank hybrid cores by efficiency
+    on Linux when available (mostly on recent ARM platforms for now).
+  + Improve HWLOC_MEMBIND_BIND (without the STRICT flag) on Linux kernel
+    >= 5.15: If more than one node is given, the kernel may now use all
+    of them instead of only the first one before falling back to others.
+  + Expose cache os_index when available on Linux, it may be needed
+    when using resctrl to configure cache partitioning, memory bandwidth
+    monitoring, etc.
+  + Add a "XGMIHops" distances matrix in the RSMI backend for AMD GPU
+    interconnected through XGMI links.
+  + Expose AMD GPU memory information (VRAM and GTT) in the RSMI backend.
+  + Add OS devices such as "bxi0" for Atos/Bull BXI HCAs on Linux.
+* Tools
+  + lstopo has a better placement algorithm with respect to I/O
+    objects, see --children-order in the manpage for details.
+  + hwloc-annotate may now change object subtypes and cache or memory
+    sizes.
+* Build
+  + Allow to specify the ROCm installation for building the RSMI backend:
+    - Use a custom installation path if specified with --with-rocm=<dir>.
+    - Use /opt/rocm-<version> if specified with --with-rocm-version=<version>
+      or the ROCM_VERSION environment variable.
+    - Try /opt/rocm if it exists.
+    - See "How do I enable ROCm SMI and select which version to use?"
+      in the FAQ for details.
+  + Add a CMakeLists for Windows under contrib/windows-cmake/ .
+* Documentation
+  + Add FAQ entry "How do I create a custom heterogeneous and
+     asymmetric topology?"
+
+
 Version 2.5.0
 -------------
 * API

src/3rdparty/hwloc/VERSION

@@ -8,8 +8,8 @@
 # Please update HWLOC_VERSION* in contrib/windows/hwloc_config.h too.
 
 major=2
-minor=5
-release=0
+minor=7
+release=1
 
 # 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="Jun 14, 2021"
+date="Mar 20, 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=20:0:5
+libhwloc_so_version=20:3:5
 libnetloc_so_version=0:0:0
 
 # Please also update the <TargetName> lines in contrib/windows/libhwloc.vcxproj

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

@@ -29,7 +29,7 @@
  * THAT IS IN THE PDF/HTML THAT IS ***NOT*** IN hwloc.h!
  *
  * There are entire paragraph-length descriptions, discussions, and
- * pretty prictures to explain subtle corner cases, provide concrete
+ * pretty pictures to explain subtle corner cases, provide concrete
  * examples, etc.
  *
  * Please, go read the documentation.  :-)
@@ -346,7 +346,8 @@ typedef enum hwloc_obj_osdev_type_e {
 				  * For instance the "eth0" interface on Linux. */
   HWLOC_OBJ_OSDEV_OPENFABRICS,	/**< \brief Operating system openfabrics device.
 				  * For instance the "mlx4_0" InfiniBand HCA,
-				  * or "hfi1_0" Omni-Path interface on Linux. */
+				  * "hfi1_0" Omni-Path interface,
+				  * or "bxi0" Atos/Bull BXI HCA on Linux. */
   HWLOC_OBJ_OSDEV_DMA,		/**< \brief Operating system dma engine device.
 				  * For instance the "dma0chan0" DMA channel on Linux. */
   HWLOC_OBJ_OSDEV_COPROC	/**< \brief Operating system co-processor device.
@@ -516,7 +517,7 @@ struct hwloc_obj {
                                           * objects).
                                           *
                                           * If the ::HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED configuration flag is set,
-                                          * some of these CPUs may not be allowed for binding,
+                                          * some of these CPUs may be online but not allowed for binding,
                                           * see hwloc_topology_get_allowed_cpuset().
                                           *
 					  * \note All objects have non-NULL CPU and node sets except Misc and I/O objects.
@@ -548,7 +549,7 @@ struct hwloc_obj {
                                           * nodes more precisely.
                                           *
                                           * If the ::HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED configuration flag is set,
-                                          * some of these nodes may not be allowed for allocation,
+                                          * some of these nodes may be online but not allowed for allocation,
                                           * see hwloc_topology_get_allowed_nodeset().
                                           *
                                           * If there are no NUMA nodes in the machine, all the memory is close to this
@@ -641,7 +642,7 @@ union hwloc_obj_attr_u {
     unsigned char revision;
     float linkspeed; /* in GB/s */
   } pcidev;
-  /** \brief Bridge specific Object Attribues */
+  /** \brief Bridge specific Object Attributes */
   struct hwloc_bridge_attr_s {
     union {
       struct hwloc_pcidev_attr_s pci;
@@ -1088,7 +1089,7 @@ HWLOC_DECLSPEC int hwloc_obj_add_info(hwloc_obj_t obj, const char *name, const c
  *
  * Some operating systems only support binding threads or processes to a single PU.
  * Others allow binding to larger sets such as entire Cores or Packages or
- * even random sets of invididual PUs. In such operating system, the scheduler
+ * even random sets of individual PUs. In such operating system, the scheduler
  * is free to run the task on one of these PU, then migrate it to another PU, etc.
  * It is often useful to call hwloc_bitmap_singlify() on the target CPU set before
  * passing it to the binding function to avoid these expensive migrations.
@@ -1166,7 +1167,7 @@ typedef enum {
    * CPUs are idle, operating systems may execute the thread/process
    * on those other CPUs instead of the designated CPUs, to let them
    * progress anyway.  Strict binding means that the thread/process
-   * will _never_ execute on other cpus than the designated CPUs, even
+   * will _never_ execute on other CPUs than the designated CPUs, even
    * when those are busy with other tasks and other CPUs are idle.
    *
    * \note Depending on the operating system, strict binding may not
@@ -1203,7 +1204,7 @@ typedef enum {
   HWLOC_CPUBIND_NOMEMBIND = (1<<3)
 } hwloc_cpubind_flags_t;
 
-/** \brief Bind current process or thread on cpus given in physical bitmap \p set.
+/** \brief Bind current process or thread on CPUs given in physical bitmap \p set.
  *
  * \return -1 with errno set to ENOSYS if the action is not supported
  * \return -1 with errno set to EXDEV if the binding cannot be enforced
@@ -1212,12 +1213,13 @@ HWLOC_DECLSPEC int hwloc_set_cpubind(hwloc_topology_t topology, hwloc_const_cpus
 
 /** \brief Get current process or thread binding.
  *
- * Writes into \p set the physical cpuset which the process or thread (according to \e
- * flags) was last bound to.
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the list of PUs which the process or
+ * thread (according to \e flags) was last bound to.
  */
 HWLOC_DECLSPEC int hwloc_get_cpubind(hwloc_topology_t topology, hwloc_cpuset_t set, int flags);
 
-/** \brief Bind a process \p pid on cpus given in physical bitmap \p set.
+/** \brief Bind a process \p pid on CPUs given in physical bitmap \p set.
  *
  * \note \p hwloc_pid_t is \p pid_t on Unix platforms,
  * and \p HANDLE on native Windows platforms.
@@ -1231,6 +1233,10 @@ HWLOC_DECLSPEC int hwloc_get_cpubind(hwloc_topology_t topology, hwloc_cpuset_t s
 HWLOC_DECLSPEC int hwloc_set_proc_cpubind(hwloc_topology_t topology, hwloc_pid_t pid, hwloc_const_cpuset_t set, int flags);
 
 /** \brief Get the current physical binding of process \p pid.
+ *
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the list of PUs which the process
+ * was last bound to.
  *
  * \note \p hwloc_pid_t is \p pid_t on Unix platforms,
  * and \p HANDLE on native Windows platforms.
@@ -1244,7 +1250,7 @@ HWLOC_DECLSPEC int hwloc_set_proc_cpubind(hwloc_topology_t topology, hwloc_pid_t
 HWLOC_DECLSPEC int hwloc_get_proc_cpubind(hwloc_topology_t topology, hwloc_pid_t pid, hwloc_cpuset_t set, int flags);
 
 #ifdef hwloc_thread_t
-/** \brief Bind a thread \p thread on cpus given in physical bitmap \p set.
+/** \brief Bind a thread \p thread on CPUs given in physical bitmap \p set.
  *
  * \note \p hwloc_thread_t is \p pthread_t on Unix platforms,
  * and \p HANDLE on native Windows platforms.
@@ -1256,6 +1262,10 @@ HWLOC_DECLSPEC int hwloc_set_thread_cpubind(hwloc_topology_t topology, hwloc_thr
 
 #ifdef hwloc_thread_t
 /** \brief Get the current physical binding of thread \p tid.
+ *
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the list of PUs which the thread
+ * was last bound to.
  *
  * \note \p hwloc_thread_t is \p pthread_t on Unix platforms,
  * and \p HANDLE on native Windows platforms.
@@ -1266,6 +1276,10 @@ HWLOC_DECLSPEC int hwloc_get_thread_cpubind(hwloc_topology_t topology, hwloc_thr
 #endif
 
 /** \brief Get the last physical CPU where the current process or thread ran.
+ *
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the list of PUs which the process or
+ * thread (according to \e flags) last ran on.
  *
  * The operating system may move some tasks from one processor
  * to another at any time according to their binding,
@@ -1281,6 +1295,10 @@ HWLOC_DECLSPEC int hwloc_get_thread_cpubind(hwloc_topology_t topology, hwloc_thr
 HWLOC_DECLSPEC int hwloc_get_last_cpu_location(hwloc_topology_t topology, hwloc_cpuset_t set, int flags);
 
 /** \brief Get the last physical CPU where a process ran.
+ *
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the list of PUs which the process
+ * last ran on.
  *
  * The operating system may move some tasks from one processor
  * to another at any time according to their binding,
@@ -1511,6 +1529,9 @@ HWLOC_DECLSPEC int hwloc_set_membind(hwloc_topology_t topology, hwloc_const_bitm
 /** \brief Query the default memory binding policy and physical locality of the
  * current process or thread.
  *
+ * The bitmap \p set (previously allocated by the caller)
+ * is filled with the process or thread memory binding.
+ *
  * This function has two output parameters: \p set and \p policy.
  * The values returned in these parameters depend on both the \p flags
  * passed in and the current memory binding policies and nodesets in
@@ -1571,6 +1592,9 @@ HWLOC_DECLSPEC int hwloc_set_proc_membind(hwloc_topology_t topology, hwloc_pid_t
 /** \brief Query the default memory binding policy and physical locality of the
  * specified process.
  *
+ * The bitmap \p set (previously allocated by the caller)
+ * is filled with the process memory binding.
+ *
  * This function has two output parameters: \p set and \p policy.
  * The values returned in these parameters depend on both the \p flags
  * passed in and the current memory binding policies and nodesets in
@@ -1624,6 +1648,9 @@ HWLOC_DECLSPEC int hwloc_set_area_membind(hwloc_topology_t topology, const void
 /** \brief Query the CPUs near the physical NUMA node(s) and binding policy of
  * the memory identified by (\p addr, \p len ).
  *
+ * The bitmap \p set (previously allocated by the caller)
+ * is filled with the memory area binding.
+ *
  * This function has two output parameters: \p set and \p policy.
  * The values returned in these parameters depend on both the \p flags
  * passed in and the memory binding policies and nodesets of the pages
@@ -1652,7 +1679,8 @@ HWLOC_DECLSPEC int hwloc_get_area_membind(hwloc_topology_t topology, const void
 
 /** \brief Get the NUMA nodes where memory identified by (\p addr, \p len ) is physically allocated.
  *
- * Fills \p set according to the NUMA nodes where the memory area pages
+ * The bitmap \p set (previously allocated by the caller)
+ * is filled according to the NUMA nodes where the memory area pages
  * are physically allocated. If no page is actually allocated yet,
  * \p set may be empty.
  *
@@ -1698,9 +1726,12 @@ HWLOC_DECLSPEC void *hwloc_alloc_membind(hwloc_topology_t topology, size_t len,
 
 /** \brief Allocate some memory on NUMA memory nodes specified by \p set
  *
- * This is similar to hwloc_alloc_membind_nodeset() except that it is allowed to change
- * the current memory binding policy, thus providing more binding support, at
- * the expense of changing the current state.
+ * First, try to allocate properly with hwloc_alloc_membind().
+ * On failure, the current process or thread memory binding policy
+ * is changed with hwloc_set_membind() before allocating memory.
+ * Thus this function works in more cases, at the expense of changing
+ * the current state (possibly affecting future allocations that
+ * would not specify any policy).
  *
  * If ::HWLOC_MEMBIND_BYNODESET is specified, set is considered a nodeset.
  * Otherwise it's a cpuset.
@@ -1883,8 +1914,9 @@ HWLOC_DECLSPEC int hwloc_topology_set_components(hwloc_topology_t __hwloc_restri
 enum hwloc_topology_flags_e {
  /** \brief Detect the whole system, ignore reservations, include disallowed objects.
    *
-   * Gather all resources, even if some were disabled by the administrator.
+   * Gather all online resources, even if some were disabled by the administrator.
    * For instance, ignore Linux Cgroup/Cpusets and gather all processors and memory nodes.
+   * However offline PUs and NUMA nodes are still ignored.
    *
    * When this flag is not set, PUs and NUMA nodes that are disallowed are not added to the topology.
    * Parent objects (package, core, cache, etc.) are added only if some of their children are allowed.
@@ -2035,10 +2067,12 @@ enum hwloc_topology_flags_e {
  *
  * Set a OR'ed set of ::hwloc_topology_flags_e onto a topology that was not yet loaded.
  *
- * If this function is called multiple times, the last invokation will erase
+ * If this function is called multiple times, the last invocation will erase
  * and replace the set of flags that was previously set.
  *
- * The flags set in a topology may be retrieved with hwloc_topology_get_flags()
+ * By default, no flags are set (\c 0).
+ *
+ * The flags set in a topology may be retrieved with hwloc_topology_get_flags().
  */
 HWLOC_DECLSPEC int hwloc_topology_set_flags (hwloc_topology_t topology, unsigned long flags);
 
@@ -2046,6 +2080,9 @@ HWLOC_DECLSPEC int hwloc_topology_set_flags (hwloc_topology_t topology, unsigned
  *
  * Get the OR'ed set of ::hwloc_topology_flags_e of a topology.
  *
+ * If hwloc_topology_set_flags() was not called earlier,
+ * no flags are set (\c 0 is returned).
+ *
  * \return the flags previously set with hwloc_topology_set_flags().
  */
 HWLOC_DECLSPEC unsigned long hwloc_topology_get_flags (hwloc_topology_t topology);

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

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2020 Inria.  All rights reserved.
+ * Copyright © 2009-2021 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 "2.5.0"
+#define HWLOC_VERSION "2.7.1"
 #define HWLOC_VERSION_MAJOR 2
-#define HWLOC_VERSION_MINOR 5
-#define HWLOC_VERSION_RELEASE 0
+#define HWLOC_VERSION_MINOR 7
+#define HWLOC_VERSION_RELEASE 1
 #define HWLOC_VERSION_GREEK ""
 
 #define __hwloc_restrict

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

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2020 Inria.  All rights reserved.
+ * Copyright © 2020-2021 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -42,18 +42,23 @@ extern "C" {
  * (for instance the "CoreType" and "FrequencyMaxMHz",
  *  see \ref topoattrs_cpukinds).
  *
- * A higher efficiency value means intrinsic greater performance
+ * A higher efficiency value means greater intrinsic performance
  * (and possibly less performance/power efficiency).
- * Kinds with lower efficiency are ranked first:
+ * Kinds with lower efficiency values are ranked first:
  * Passing 0 as \p kind_index to hwloc_cpukinds_get_info() will
- * return information about the less efficient CPU kind.
+ * return information about the CPU kind with lower performance
+ * but higher energy-efficiency.
+ * Higher \p kind_index values would rather return information
+ * about power-hungry high-performance cores.
  *
- * When available, efficiency values are gathered from the operating
- * system (when \p cpukind_efficiency is set in the
- * struct hwloc_topology_discovery_support array, only on Windows 10 for now).
- * Otherwise hwloc tries to compute efficiencies
- * by comparing CPU kinds using frequencies (on ARM),
- * or core types and frequencies (on other architectures).
+ * When available, efficiency values are gathered from the operating system.
+ * If so, \p cpukind_efficiency is set in the struct hwloc_topology_discovery_support array.
+ * This is currently available on Windows 10, Mac OS X (Darwin),
+ * and on some Linux platforms where core "capacity" is exposed in sysfs.
+ *
+ * If the operating system does not expose core efficiencies natively,
+ * hwloc tries to compute efficiencies by comparing CPU kinds using
+ * frequencies (on ARM), or core types and frequencies (on other architectures).
  * The environment variable HWLOC_CPUKINDS_RANKING may be used
  * to change this heuristics, see \ref envvar.
  *

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

@@ -35,7 +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" and "NVLinkBandwidth".
+ * Others distance structures include and "XGMIBandwidth", "XGMIHops"
+ * 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.
@@ -159,7 +160,7 @@ 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" and "NVLinkBandwidth".
+ * Others include "XGMIBandwidth", "XGMIHops" and "NVLinkBandwidth".
  */
 HWLOC_DECLSPEC int
 hwloc_distances_get_by_name(hwloc_topology_t topology, const char *name,

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

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2016 Inria.  All rights reserved.
+ * Copyright © 2009-2021 Inria.  All rights reserved.
  * Copyright © 2009-2011 Université Bordeaux
  * See COPYING in top-level directory.
  */
@@ -44,6 +44,10 @@ extern "C" {
 HWLOC_DECLSPEC int hwloc_linux_set_tid_cpubind(hwloc_topology_t topology, pid_t tid, hwloc_const_cpuset_t set);
 
 /** \brief Get the current binding of thread \p tid
+ *
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the list of PUs which the thread
+ * was last bound to.
  *
  * The behavior is exactly the same as the Linux sched_getaffinity system call,
  * but uses a hwloc cpuset.
@@ -54,6 +58,9 @@ HWLOC_DECLSPEC int hwloc_linux_set_tid_cpubind(hwloc_topology_t topology, pid_t
 HWLOC_DECLSPEC int hwloc_linux_get_tid_cpubind(hwloc_topology_t topology, pid_t tid, hwloc_cpuset_t set);
 
 /** \brief Get the last physical CPU where thread \p tid ran.
+ *
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the PU which the thread last ran on.
  *
  * \note This is equivalent to calling hwloc_get_proc_last_cpu_location() with
  * ::HWLOC_CPUBIND_THREAD as flags.

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

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2019-2020 Inria.  All rights reserved.
+ * Copyright © 2019-2022 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -354,7 +354,7 @@ hwloc_memattr_register(hwloc_topology_t topology,
  * \p flags must be \c 0 for now.
  *
  * \note The initiator \p initiator should be of type ::HWLOC_LOCATION_TYPE_CPUSET
- * when refering to accesses performed by CPU cores.
+ * when referring to accesses performed by CPU cores.
  * ::HWLOC_LOCATION_TYPE_OBJECT is currently unused internally by hwloc,
  * but users may for instance use it to provide custom information about
  * host memory accesses performed by GPUs.
@@ -398,7 +398,7 @@ hwloc_memattr_set_value(hwloc_topology_t topology,
  * values.
  *
  * \note The initiator \p initiator should be of type ::HWLOC_LOCATION_TYPE_CPUSET
- * when refering to accesses performed by CPU cores.
+ * when referring to accesses performed by CPU cores.
  * ::HWLOC_LOCATION_TYPE_OBJECT is currently unused internally by hwloc,
  * but users may for instance use it to provide custom information about
  * host memory accesses performed by GPUs.
@@ -408,7 +408,7 @@ hwloc_memattr_get_targets(hwloc_topology_t topology,
                           hwloc_memattr_id_t attribute,
                           struct hwloc_location *initiator,
                           unsigned long flags,
-                          unsigned *nrp, hwloc_obj_t *targets, hwloc_uint64_t *values);
+                          unsigned *nr, hwloc_obj_t *targets, hwloc_uint64_t *values);
 
 /** \brief Return the initiators that have values for a given attribute for a specific target NUMA node.
  *

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

@@ -497,6 +497,7 @@ hwloc_filter_check_pcidev_subtype_important(unsigned classid)
   return (baseclass == 0x03 /* PCI_BASE_CLASS_DISPLAY */
 	  || baseclass == 0x02 /* PCI_BASE_CLASS_NETWORK */
 	  || baseclass == 0x01 /* PCI_BASE_CLASS_STORAGE */
+	  || baseclass == 0x00 /* Unclassified, for Atos/Bull BXI */
 	  || baseclass == 0x0b /* PCI_BASE_CLASS_PROCESSOR */
 	  || classid == 0x0c04 /* PCI_CLASS_SERIAL_FIBER */
 	  || classid == 0x0c06 /* PCI_CLASS_SERIAL_INFINIBAND */

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

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009, 2011, 2012 CNRS.  All rights reserved.
- * Copyright © 2009-2020 Inria.  All rights reserved.
+ * Copyright © 2009-2021 Inria.  All rights reserved.
  * Copyright © 2009, 2011, 2012, 2015 Université Bordeaux.  All rights reserved.
  * Copyright © 2009-2020 Cisco Systems, Inc.  All rights reserved.
  * $COPYRIGHT$
@@ -290,10 +290,6 @@
 /* Define to '1' if sysctlbyname is present and usable */
 /* #undef HAVE_SYSCTLBYNAME */
 
-/* Define to 1 if the system has the type
-   `SYSTEM_LOGICAL_PROCESSOR_INFORMATION'. */
-#define HAVE_SYSTEM_LOGICAL_PROCESSOR_INFORMATION 1
-
 /* Define to 1 if the system has the type
    `SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX'. */
 #define HAVE_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX 1

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

@@ -504,7 +504,7 @@ hwloc__obj_type_is_icache(hwloc_obj_type_t type)
   }                                    \
 } while(0)
 #else /* HAVE_USELOCALE */
-#if __HWLOC_HAVE_ATTRIBUTE_UNUSED
+#if HWLOC_HAVE_ATTRIBUTE_UNUSED
 #define hwloc_localeswitch_declare int __dummy_nolocale __hwloc_attribute_unused
 #define hwloc_localeswitch_init()
 #else

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

@@ -480,6 +480,7 @@ extern char * hwloc_progname(struct hwloc_topology *topology);
 #define HWLOC_GROUP_KIND_AIX_SDL_UNKNOWN		210	/* subkind is SDL level */
 #define HWLOC_GROUP_KIND_WINDOWS_PROCESSOR_GROUP	220	/* no subkind */
 #define HWLOC_GROUP_KIND_WINDOWS_RELATIONSHIP_UNKNOWN	221	/* no subkind */
+#define HWLOC_GROUP_KIND_LINUX_CLUSTER                  222     /* no subkind */
 /* distance groups */
 #define HWLOC_GROUP_KIND_DISTANCE			900	/* subkind is round of adding these groups during distance based grouping */
 /* finally, hwloc-specific groups required to insert something else, should disappear as soon as possible */

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

@@ -0,0 +1,21 @@
+/*
+ * Copyright © 2009 Université Bordeaux
+ * Copyright © 2020 Inria.  All rights reserved.
+ *
+ * See COPYING in top-level directory.
+ */
+
+#ifndef HWLOC_PRIVATE_WINDOWS_H
+#define HWLOC_PRIVATE_WINDOWS_H
+
+#ifdef __GNUC__
+#define _ANONYMOUS_UNION __extension__
+#define _ANONYMOUS_STRUCT __extension__
+#else
+#define _ANONYMOUS_UNION
+#define _ANONYMOUS_STRUCT
+#endif /* __GNUC__ */
+#define DUMMYUNIONNAME
+#define DUMMYSTRUCTNAME
+
+#endif /* HWLOC_PRIVATE_WINDOWS_H */

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

@@ -42,6 +42,9 @@ hwloc_internal_cpukinds_dup(hwloc_topology_t new, hwloc_topology_t old)
   struct hwloc_internal_cpukind_s *kinds;
   unsigned i;
 
+  if (!old->nr_cpukinds)
+    return 0;
+
   kinds = hwloc_tma_malloc(tma, old->nr_cpukinds * sizeof(*kinds));
   if (!kinds)
     return -1;
@@ -445,7 +448,9 @@ static int hwloc__cpukinds_compare_ranking_values(const void *_a, const void *_b
 {
   const struct hwloc_internal_cpukind_s *a = _a;
   const struct hwloc_internal_cpukind_s *b = _b;
-  return a->ranking_value - b->ranking_value;
+  uint64_t arv = a->ranking_value;
+  uint64_t brv = b->ranking_value;
+  return arv < brv ? -1 : arv > brv ? 1 : 0;
 }
 
 /* this function requires ranking values to be unique */

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

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2020 Inria.  All rights reserved.
+ * Copyright © 2020-2021 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -127,6 +127,8 @@ hwloc_internal_memattrs_dup(struct hwloc_topology *new, struct hwloc_topology *o
   struct hwloc_internal_memattr_s *imattrs;
   hwloc_memattr_id_t id;
 
+  /* old->nr_memattrs is always > 0 thanks to default memattrs */
+
   imattrs = hwloc_tma_malloc(tma, old->nr_memattrs * sizeof(*imattrs));
   if (!imattrs)
     return -1;

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

@@ -810,13 +810,14 @@ hwloc_pcidisc_find_linkspeed(const unsigned char *config,
    * 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
    */
 
   /* lanespeed in Gbit/s */
   if (speed <= 2)
     lanespeed = 2.5f * speed * 0.8f;
   else
-    lanespeed = 8.0f * (1<<(speed-3)) * 128/130; /* assume Gen6 will be 64 GT/s and so on */
+    lanespeed = 8.0f * (1<<(speed-3)) * 128/130; /* assume Gen7 will be 128 GT/s and so on */
 
   /* linkspeed in GB/s */
   *linkspeed = lanespeed * width / 8;

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

@@ -13,6 +13,7 @@
 #include "hwloc.h"
 #include "hwloc/windows.h"
 #include "private/private.h"
+#include "private/windows.h" /* must be before windows.h */
 #include "private/debug.h"
 
 #include <windows.h>
@@ -65,26 +66,6 @@ typedef enum _LOGICAL_PROCESSOR_RELATIONSHIP {
 #  endif /* HAVE_RELATIONPROCESSORPACKAGE */
 #endif /* HAVE_LOGICAL_PROCESSOR_RELATIONSHIP */
 
-#ifndef HAVE_SYSTEM_LOGICAL_PROCESSOR_INFORMATION
-typedef struct _SYSTEM_LOGICAL_PROCESSOR_INFORMATION {
-  ULONG_PTR ProcessorMask;
-  LOGICAL_PROCESSOR_RELATIONSHIP Relationship;
-  _ANONYMOUS_UNION
-  union {
-    struct {
-      BYTE flags;
-    } ProcessorCore;
-    struct {
-      DWORD NodeNumber;
-    } NumaNode;
-    CACHE_DESCRIPTOR Cache;
-    ULONGLONG Reserved[2];
-  } DUMMYUNIONNAME;
-} SYSTEM_LOGICAL_PROCESSOR_INFORMATION, *PSYSTEM_LOGICAL_PROCESSOR_INFORMATION;
-#endif
-
-/* Extended interface, for group support */
-
 #ifndef HAVE_GROUP_AFFINITY
 typedef struct _GROUP_AFFINITY {
   KAFFINITY Mask;
@@ -93,35 +74,40 @@ typedef struct _GROUP_AFFINITY {
 } GROUP_AFFINITY, *PGROUP_AFFINITY;
 #endif
 
-#ifndef HAVE_PROCESSOR_RELATIONSHIP
+/* always use our own structure because the EfficiencyClass field didn't exist before Win10 */
 typedef struct HWLOC_PROCESSOR_RELATIONSHIP {
   BYTE Flags;
-  BYTE EfficiencyClass; /* for RelationProcessorCore, higher means greater performance but less efficiency, only available in Win10+ */
+  BYTE EfficiencyClass; /* for RelationProcessorCore, higher means greater performance but less efficiency */
   BYTE Reserved[20];
   WORD GroupCount;
   GROUP_AFFINITY GroupMask[ANYSIZE_ARRAY];
-} PROCESSOR_RELATIONSHIP, *PPROCESSOR_RELATIONSHIP;
-#endif
+} HWLOC_PROCESSOR_RELATIONSHIP;
 
-#ifndef HAVE_NUMA_NODE_RELATIONSHIP
-typedef struct _NUMA_NODE_RELATIONSHIP {
+/* always use our own structure because the GroupCount and GroupMasks fields didn't exist in some Win10 */
+typedef struct HWLOC_NUMA_NODE_RELATIONSHIP {
   DWORD NodeNumber;
-  BYTE Reserved[20];
-  GROUP_AFFINITY GroupMask;
-} NUMA_NODE_RELATIONSHIP, *PNUMA_NODE_RELATIONSHIP;
-#endif
+  BYTE Reserved[18];
+  WORD GroupCount;
+  _ANONYMOUS_UNION
+  union {
+    GROUP_AFFINITY GroupMask;
+    GROUP_AFFINITY GroupMasks[ANYSIZE_ARRAY];
+  } DUMMYUNIONNAME;
+} HWLOC_NUMA_NODE_RELATIONSHIP;
 
-#ifndef HAVE_CACHE_RELATIONSHIP
-typedef struct _CACHE_RELATIONSHIP {
+typedef struct HWLOC_CACHE_RELATIONSHIP {
   BYTE Level;
   BYTE Associativity;
   WORD LineSize;
   DWORD CacheSize;
   PROCESSOR_CACHE_TYPE Type;
-  BYTE Reserved[20];
-  GROUP_AFFINITY GroupMask;
-} CACHE_RELATIONSHIP, *PCACHE_RELATIONSHIP;
-#endif
+  BYTE Reserved[18];
+  WORD GroupCount;
+  union {
+    GROUP_AFFINITY GroupMask;
+    GROUP_AFFINITY GroupMasks[ANYSIZE_ARRAY];
+  } DUMMYUNIONNAME;
+} HWLOC_CACHE_RELATIONSHIP;
 
 #ifndef HAVE_PROCESSOR_GROUP_INFO
 typedef struct _PROCESSOR_GROUP_INFO {
@@ -141,20 +127,19 @@ typedef struct _GROUP_RELATIONSHIP {
 } GROUP_RELATIONSHIP, *PGROUP_RELATIONSHIP;
 #endif
 
-#ifndef HAVE_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX
-typedef struct _SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX {
+/* always use our own structure because we need our own HWLOC_PROCESSOR/CACHE/NUMA_NODE_RELATIONSHIP */
+typedef struct HWLOC_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX {
   LOGICAL_PROCESSOR_RELATIONSHIP Relationship;
   DWORD Size;
   _ANONYMOUS_UNION
   union {
-    PROCESSOR_RELATIONSHIP Processor;
-    NUMA_NODE_RELATIONSHIP NumaNode;
-    CACHE_RELATIONSHIP Cache;
+    HWLOC_PROCESSOR_RELATIONSHIP Processor;
+    HWLOC_NUMA_NODE_RELATIONSHIP NumaNode;
+    HWLOC_CACHE_RELATIONSHIP Cache;
     GROUP_RELATIONSHIP Group;
     /* Odd: no member to tell the cpu mask of the package... */
   } DUMMYUNIONNAME;
-} SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX, *PSYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX;
-#endif
+} HWLOC_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX;
 
 #ifndef HAVE_PSAPI_WORKING_SET_EX_BLOCK
 typedef union _PSAPI_WORKING_SET_EX_BLOCK {
@@ -200,10 +185,7 @@ static PFN_GETCURRENTPROCESSORNUMBER GetCurrentProcessorNumberProc;
 typedef VOID (WINAPI *PFN_GETCURRENTPROCESSORNUMBEREX)(PPROCESSOR_NUMBER);
 static PFN_GETCURRENTPROCESSORNUMBEREX GetCurrentProcessorNumberExProc;
 
-typedef BOOL (WINAPI *PFN_GETLOGICALPROCESSORINFORMATION)(PSYSTEM_LOGICAL_PROCESSOR_INFORMATION Buffer, PDWORD ReturnLength);
-static PFN_GETLOGICALPROCESSORINFORMATION GetLogicalProcessorInformationProc;
-
-typedef BOOL (WINAPI *PFN_GETLOGICALPROCESSORINFORMATIONEX)(LOGICAL_PROCESSOR_RELATIONSHIP relationship, PSYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX Buffer, PDWORD ReturnLength);
+typedef BOOL (WINAPI *PFN_GETLOGICALPROCESSORINFORMATIONEX)(LOGICAL_PROCESSOR_RELATIONSHIP relationship, HWLOC_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *Buffer, PDWORD ReturnLength);
 static PFN_GETLOGICALPROCESSORINFORMATIONEX GetLogicalProcessorInformationExProc;
 
 typedef BOOL (WINAPI *PFN_SETTHREADGROUPAFFINITY)(HANDLE hThread, const GROUP_AFFINITY *GroupAffinity, PGROUP_AFFINITY PreviousGroupAffinity);
@@ -244,8 +226,6 @@ static void hwloc_win_get_function_ptrs(void)
 	(PFN_GETACTIVEPROCESSORGROUPCOUNT) GetProcAddress(kernel32, "GetActiveProcessorGroupCount");
       GetActiveProcessorCountProc =
 	(PFN_GETACTIVEPROCESSORCOUNT) GetProcAddress(kernel32, "GetActiveProcessorCount");
-      GetLogicalProcessorInformationProc =
-	(PFN_GETLOGICALPROCESSORINFORMATION) GetProcAddress(kernel32, "GetLogicalProcessorInformation");
       GetCurrentProcessorNumberProc =
 	(PFN_GETCURRENTPROCESSORNUMBER) GetProcAddress(kernel32, "GetCurrentProcessorNumber");
       GetCurrentProcessorNumberExProc =
@@ -370,13 +350,13 @@ static hwloc_cpuset_t * processor_group_cpusets = NULL;
 static void
 hwloc_win_get_processor_groups(void)
 {
-  PSYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX procInfoTotal, tmpprocInfoTotal, procInfo;
+  HWLOC_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *procInfoTotal, *tmpprocInfoTotal, *procInfo;
   DWORD length;
   unsigned i;
 
   hwloc_debug("querying windows processor groups\n");
 
-  if (!GetActiveProcessorGroupCountProc || !GetLogicalProcessorInformationExProc)
+  if (!GetLogicalProcessorInformationExProc)
     goto error;
 
   nr_processor_groups = GetActiveProcessorGroupCountProc();
@@ -415,6 +395,8 @@ hwloc_win_get_processor_groups(void)
 
     assert(procInfo->Relationship == RelationGroup);
 
+    hwloc_debug("Found %u active windows processor groups\n",
+                (unsigned) procInfo->Group.ActiveGroupCount);
     for (id = 0; id < procInfo->Group.ActiveGroupCount; id++) {
       KAFFINITY mask;
       hwloc_bitmap_t set;
@@ -424,8 +406,8 @@ hwloc_win_get_processor_groups(void)
         goto error_with_cpusets;
 
       mask = procInfo->Group.GroupInfo[id].ActiveProcessorMask;
-      hwloc_debug("group %u %d cpus mask %lx\n", id,
-                  procInfo->Group.GroupInfo[id].ActiveProcessorCount, mask);
+      hwloc_debug("group %u with %u cpus mask 0x%llx\n", id,
+                  (unsigned) procInfo->Group.GroupInfo[id].ActiveProcessorCount, (unsigned long long) mask);
       /* KAFFINITY is ULONG_PTR */
       hwloc_bitmap_set_ith_ULONG_PTR(set, id, mask);
       /* FIXME: what if running 32bits on a 64bits windows with 64-processor groups?
@@ -1008,6 +990,8 @@ hwloc_look_windows(struct hwloc_backend *backend, struct hwloc_disc_status *dsta
   unsigned hostname_size = sizeof(hostname);
   int has_efficiencyclass = 0;
   struct hwloc_win_efficiency_classes eclasses;
+  char *env = getenv("HWLOC_WINDOWS_PROCESSOR_GROUP_OBJS");
+  int keep_pgroup_objs = (env && atoi(env));
 
   assert(dstatus->phase == HWLOC_DISC_PHASE_CPU);
 
@@ -1038,137 +1022,8 @@ hwloc_look_windows(struct hwloc_backend *backend, struct hwloc_disc_status *dsta
 
   GetSystemInfo(&SystemInfo);
 
-  if (!GetLogicalProcessorInformationExProc && GetLogicalProcessorInformationProc) {
-      PSYSTEM_LOGICAL_PROCESSOR_INFORMATION procInfo, tmpprocInfo;
-      unsigned id;
-      unsigned i;
-      struct hwloc_obj *obj;
-      hwloc_obj_type_t type;
-
-      length = 0;
-      procInfo = NULL;
-
-      while (1) {
-	if (GetLogicalProcessorInformationProc(procInfo, &length))
-	  break;
-	if (GetLastError() != ERROR_INSUFFICIENT_BUFFER)
-	  return -1;
-	tmpprocInfo = realloc(procInfo, length);
-	if (!tmpprocInfo) {
-	  free(procInfo);
-	  goto out;
-	}
-	procInfo = tmpprocInfo;
-      }
-
-      assert(!length || procInfo);
-
-      for (i = 0; i < length / sizeof(*procInfo); i++) {
-
-        /* Ignore unknown caches */
-	if (procInfo->Relationship == RelationCache
-		&& procInfo->Cache.Type != CacheUnified
-		&& procInfo->Cache.Type != CacheData
-		&& procInfo->Cache.Type != CacheInstruction)
-	  continue;
-
-	id = HWLOC_UNKNOWN_INDEX;
-	switch (procInfo[i].Relationship) {
-	  case RelationNumaNode:
-	    type = HWLOC_OBJ_NUMANODE;
-	    id = procInfo[i].NumaNode.NodeNumber;
-	    gotnuma++;
-	    if (id > max_numanode_index)
-	      max_numanode_index = id;
-	    break;
-	  case RelationProcessorPackage:
-	    type = HWLOC_OBJ_PACKAGE;
-	    break;
-	  case RelationCache:
-	    type = (procInfo[i].Cache.Type == CacheInstruction ? HWLOC_OBJ_L1ICACHE : HWLOC_OBJ_L1CACHE) + procInfo[i].Cache.Level - 1;
-	    break;
-	  case RelationProcessorCore:
-	    type = HWLOC_OBJ_CORE;
-	    break;
-	  case RelationGroup:
-	  default:
-	    type = HWLOC_OBJ_GROUP;
-	    break;
-	}
-
-	if (!hwloc_filter_check_keep_object_type(topology, type))
-	  continue;
-
-	obj = hwloc_alloc_setup_object(topology, type, id);
-        obj->cpuset = hwloc_bitmap_alloc();
-	hwloc_debug("%s#%u mask %llx\n", hwloc_obj_type_string(type), id, (unsigned long long) procInfo[i].ProcessorMask);
-	/* ProcessorMask is a ULONG_PTR */
-	hwloc_bitmap_set_ith_ULONG_PTR(obj->cpuset, 0, procInfo[i].ProcessorMask);
-	hwloc_debug_2args_bitmap("%s#%u bitmap %s\n", hwloc_obj_type_string(type), id, obj->cpuset);
-
-	switch (type) {
-	  case HWLOC_OBJ_NUMANODE:
-	    {
-	      ULONGLONG avail;
-	      obj->nodeset = hwloc_bitmap_alloc();
-	      hwloc_bitmap_set(obj->nodeset, id);
-	      if ((GetNumaAvailableMemoryNodeExProc && GetNumaAvailableMemoryNodeExProc(id, &avail))
-		  || (GetNumaAvailableMemoryNodeProc && GetNumaAvailableMemoryNodeProc(id, &avail))) {
-		obj->attr->numanode.local_memory = avail;
-		gotnumamemory++;
-	      }
-	      obj->attr->numanode.page_types_len = 2;
-	      obj->attr->numanode.page_types = malloc(2 * sizeof(*obj->attr->numanode.page_types));
-	      memset(obj->attr->numanode.page_types, 0, 2 * sizeof(*obj->attr->numanode.page_types));
-	      obj->attr->numanode.page_types_len = 1;
-	      obj->attr->numanode.page_types[0].size = SystemInfo.dwPageSize;
-#if HAVE_DECL__SC_LARGE_PAGESIZE
-	      obj->attr->numanode.page_types_len++;
-	      obj->attr->numanode.page_types[1].size = sysconf(_SC_LARGE_PAGESIZE);
-#endif
-	      break;
-	    }
-	  case HWLOC_OBJ_L1CACHE:
-	  case HWLOC_OBJ_L2CACHE:
-	  case HWLOC_OBJ_L3CACHE:
-	  case HWLOC_OBJ_L4CACHE:
-	  case HWLOC_OBJ_L5CACHE:
-	  case HWLOC_OBJ_L1ICACHE:
-	  case HWLOC_OBJ_L2ICACHE:
-	  case HWLOC_OBJ_L3ICACHE:
-	    obj->attr->cache.size = procInfo[i].Cache.Size;
-	    obj->attr->cache.associativity = procInfo[i].Cache.Associativity == CACHE_FULLY_ASSOCIATIVE ? -1 : procInfo[i].Cache.Associativity ;
-	    obj->attr->cache.linesize = procInfo[i].Cache.LineSize;
-	    obj->attr->cache.depth = procInfo[i].Cache.Level;
-	    switch (procInfo->Cache.Type) {
-	      case CacheUnified:
-		obj->attr->cache.type = HWLOC_OBJ_CACHE_UNIFIED;
-		break;
-	      case CacheData:
-		obj->attr->cache.type = HWLOC_OBJ_CACHE_DATA;
-		break;
-	      case CacheInstruction:
-		obj->attr->cache.type = HWLOC_OBJ_CACHE_INSTRUCTION;
-		break;
-	      default:
-		hwloc_free_unlinked_object(obj);
-		continue;
-	    }
-	    break;
-	  case HWLOC_OBJ_GROUP:
-	    obj->attr->group.kind = procInfo[i].Relationship == RelationGroup ? HWLOC_GROUP_KIND_WINDOWS_PROCESSOR_GROUP : HWLOC_GROUP_KIND_WINDOWS_RELATIONSHIP_UNKNOWN;
-	    break;
-	  default:
-	    break;
-	}
-	hwloc__insert_object_by_cpuset(topology, NULL, obj, "windows:GetLogicalProcessorInformation");
-      }
-
-      free(procInfo);
-  }
-
   if (GetLogicalProcessorInformationExProc) {
-      PSYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX procInfoTotal, tmpprocInfoTotal, procInfo;
+      HWLOC_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *procInfoTotal, *tmpprocInfoTotal, *procInfo;
       unsigned id;
       struct hwloc_obj *obj;
       hwloc_obj_type_t type;
@@ -1207,8 +1062,16 @@ hwloc_look_windows(struct hwloc_backend *backend, struct hwloc_disc_status *dsta
 	switch (procInfo->Relationship) {
 	  case RelationNumaNode:
 	    type = HWLOC_OBJ_NUMANODE;
-            num = 1;
-            GroupMask = &procInfo->NumaNode.GroupMask;
+            /* Starting with Windows 11 and Server 2022, the GroupCount field is valid and >=1
+             * and we may read GroupMasks[]. Older releases have GroupCount==0 and we must read GroupMask.
+             */
+            if (procInfo->NumaNode.GroupCount) {
+              num = procInfo->NumaNode.GroupCount;
+              GroupMask = procInfo->NumaNode.GroupMasks;
+            } else {
+              num = 1;
+              GroupMask = &procInfo->NumaNode.GroupMask;
+            }
 	    id = procInfo->NumaNode.NodeNumber;
 	    gotnuma++;
 	    if (id > max_numanode_index)
@@ -1221,18 +1084,20 @@ hwloc_look_windows(struct hwloc_backend *backend, struct hwloc_disc_status *dsta
 	    break;
 	  case RelationCache:
 	    type = (procInfo->Cache.Type == CacheInstruction ? HWLOC_OBJ_L1ICACHE : HWLOC_OBJ_L1CACHE) + procInfo->Cache.Level - 1;
-            num = 1;
-            GroupMask = &procInfo->Cache.GroupMask;
+            /* GroupCount added approximately with NumaNode.GroupCount above */
+            if (procInfo->Cache.GroupCount) {
+              num = procInfo->Cache.GroupCount;
+              GroupMask = procInfo->Cache.GroupMasks;
+            } else {
+              num = 1;
+              GroupMask = &procInfo->Cache.GroupMask;
+            }
 	    break;
 	  case RelationProcessorCore:
 	    type = HWLOC_OBJ_CORE;
             num = procInfo->Processor.GroupCount;
             GroupMask = procInfo->Processor.GroupMask;
-            if (has_efficiencyclass)
-              /* the EfficiencyClass field didn't exist before Windows10 and recent MSVC headers,
-               * so just access it manually instead of trying to detect it.
-               */
-              efficiency_class = * ((&procInfo->Processor.Flags) + 1);
+            efficiency_class = procInfo->Processor.EfficiencyClass;
 	    break;
 	  case RelationGroup:
 	    /* So strange an interface... */
@@ -1257,11 +1122,12 @@ hwloc_look_windows(struct hwloc_backend *backend, struct hwloc_disc_status *dsta
 		groups_pu_set = hwloc_bitmap_alloc();
 	      hwloc_bitmap_or(groups_pu_set, groups_pu_set, set);
 
-	      if (hwloc_filter_check_keep_object_type(topology, HWLOC_OBJ_GROUP)) {
+              /* Ignore processor groups unless requested and filtered-in */
+              if (keep_pgroup_objs && hwloc_filter_check_keep_object_type(topology, HWLOC_OBJ_GROUP)) {
 		obj = hwloc_alloc_setup_object(topology, HWLOC_OBJ_GROUP, id);
 		obj->cpuset = set;
 		obj->attr->group.kind = HWLOC_GROUP_KIND_WINDOWS_PROCESSOR_GROUP;
-		hwloc__insert_object_by_cpuset(topology, NULL, obj, "windows:GetLogicalProcessorInformation:ProcessorGroup");
+		hwloc__insert_object_by_cpuset(topology, NULL, obj, "windows:GetLogicalProcessorInformationEx:ProcessorGroup");
 	      } else
 		hwloc_bitmap_free(set);
 	    }

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

@@ -500,7 +500,8 @@ static void read_amd_cores_topoext(struct procinfo *infos, unsigned long flags,
       nodes_per_proc = ((ecx >> 8) & 7) + 1;
     }
     if ((infos->cpufamilynumber == 0x15 && nodes_per_proc > 2)
-	|| ((infos->cpufamilynumber == 0x17 || infos->cpufamilynumber == 0x18) && nodes_per_proc > 4)) {
+	|| ((infos->cpufamilynumber == 0x17 || infos->cpufamilynumber == 0x18) && nodes_per_proc > 4)
+        || (infos->cpufamilynumber == 0x19 && nodes_per_proc > 1)) {
       hwloc_debug("warning: undefined nodes_per_proc value %u, assuming it means %u\n", nodes_per_proc, nodes_per_proc);
     }
   }
@@ -613,10 +614,13 @@ static void look_proc(struct hwloc_backend *backend, struct procinfo *infos, uns
   eax = 0x01;
   cpuid_or_from_dump(&eax, &ebx, &ecx, &edx, src_cpuiddump);
   infos->apicid = ebx >> 24;
-  if (edx & (1 << 28))
+  if (edx & (1 << 28)) {
     legacy_max_log_proc = 1 << hwloc_flsl(((ebx >> 16) & 0xff) - 1);
-  else
+  } else {
+    hwloc_debug("HTT bit not set in CPUID 0x01.edx, assuming legacy_max_log_proc = 1\n");
     legacy_max_log_proc = 1;
+  }
+
   hwloc_debug("APIC ID 0x%02x legacy_max_log_proc %u\n", infos->apicid, legacy_max_log_proc);
   infos->ids[PKG] = infos->apicid / legacy_max_log_proc;
   legacy_log_proc_id = infos->apicid % legacy_max_log_proc;
@@ -679,12 +683,23 @@ static void look_proc(struct hwloc_backend *backend, struct procinfo *infos, uns
       unsigned max_nbcores;
       unsigned max_nbthreads;
       unsigned threadid __hwloc_attribute_unused;
+      hwloc_debug("Trying to get core/thread IDs from 0x04...\n");
       max_nbcores = ((eax >> 26) & 0x3f) + 1;
-      max_nbthreads = legacy_max_log_proc / max_nbcores;
-      hwloc_debug("thus %u threads\n", max_nbthreads);
-      threadid = legacy_log_proc_id % max_nbthreads;
-      infos->ids[CORE] = legacy_log_proc_id / max_nbthreads;
-      hwloc_debug("this is thread %u of core %u\n", threadid, infos->ids[CORE]);
+      hwloc_debug("found %u cores max\n", max_nbcores);
+      /* some VMs (e.g. issue#525) don't report valid information, check things before dividing by 0. */
+      if (!max_nbcores) {
+        hwloc_debug("cannot detect core/thread IDs from 0x04 without a valid max of cores\n");
+      } else {
+        max_nbthreads = legacy_max_log_proc / max_nbcores;
+        hwloc_debug("found %u threads max\n", max_nbthreads);
+        if (!max_nbthreads) {
+          hwloc_debug("cannot detect core/thread IDs from 0x04 without a valid max of threads\n");
+        } else {
+          threadid = legacy_log_proc_id % max_nbthreads;
+          infos->ids[CORE] = legacy_log_proc_id / max_nbthreads;
+          hwloc_debug("this is thread %u of core %u\n", threadid, infos->ids[CORE]);
+        }
+      }
     }
   }
 
@@ -775,13 +790,19 @@ static void look_proc(struct hwloc_backend *backend, struct procinfo *infos, uns
 
     } else if (cpuid_type == amd) {
       /* AMD quirks */
-      if (infos->cpufamilynumber == 0x17
-	  && cache->level == 3 && cache->nbthreads_sharing == 6) {
-	/* AMD family 0x17 always shares L3 between 8 APIC ids,
-	 * even when only 6 APIC ids are enabled and reported in nbthreads_sharing
-	 * (on 24-core CPUs).
+      if (infos->cpufamilynumber >= 0x17 && cache->level == 3) {
+	/* AMD family 0x19 always shares L3 between 16 APIC ids (8 HT cores).
+         * while Family 0x17 shares between 8 APIC ids (4 HT cores).
+         * But many models have less APIC ids enabled and reported in nbthreads_sharing.
+         * It means we must round-up nbthreads_sharing to the nearest power of 2
+         * before computing cacheid.
 	 */
-	cache->cacheid = infos->apicid / 8;
+        unsigned nbapics_sharing = cache->nbthreads_sharing;
+        if (nbapics_sharing & (nbapics_sharing-1))
+          /* not a power of two, round-up */
+          nbapics_sharing = 1U<<(1+hwloc_ffsl(nbapics_sharing));
+
+	cache->cacheid = infos->apicid / nbapics_sharing;
 
       } else if (infos->cpufamilynumber== 0x10 && infos->cpumodelnumber == 0x9
 	  && cache->level == 3
@@ -807,7 +828,7 @@ static void look_proc(struct hwloc_backend *backend, struct procinfo *infos, uns
       } else if (infos->cpufamilynumber == 0x15
 		 && (infos->cpumodelnumber == 0x1 /* Bulldozer */ || infos->cpumodelnumber == 0x2 /* Piledriver */)
 		 && cache->level == 3 && cache->nbthreads_sharing == 6) {
-	/* AMD Bulldozer and Piledriver 12-core processors have same APIC ids as Magny-Cours below,
+	/* AMD Bulldozer and Piledriver 12-core processors have same APIC ids as Magny-Cours above,
 	 * but we can't merge the checks because the original nbthreads_sharing must be exactly 6 here.
 	 */
 	cache->cacheid = (infos->apicid % legacy_max_log_proc) / cache->nbthreads_sharing /* cacheid within the package */
@@ -1231,6 +1252,18 @@ static void summarize(struct hwloc_backend *backend, struct procinfo *infos, uns
 	    }
 	  }
 	  cache = hwloc_alloc_setup_object(topology, otype, HWLOC_UNKNOWN_INDEX);
+          /* We don't specify the os_index of caches because we want to be
+           * 100% sure they are identical to what the Linux kernel reports
+           * (so that things like resctrl work).
+           * However, vendor/model-specific quirks in the x86 code above
+           * make this difficult.
+           *
+           * Caveat: if the x86 backend is used on Linux to avoid kernel bugs,
+           * IDs won't be available to resctrl users. But resctrl heavily
+           * relies on the kernel x86 discovery being non-buggy anyway.
+           *
+           * TODO: make this optional? or only disable it on Linux?
+           */
 	  cache->attr->cache.depth = level;
 	  cache->attr->cache.size = infos[i].cache[l].size;
 	  cache->attr->cache.linesize = infos[i].cache[l].linesize;

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

@@ -243,7 +243,7 @@ hwloc__xml_import_object_attr(struct hwloc_topology *topology,
   else if (!strcmp(name, "dont_merge")) {
     unsigned long lvalue = strtoul(value, NULL, 10);
     if (obj->type == HWLOC_OBJ_GROUP)
-      obj->attr->group.dont_merge = lvalue;
+      obj->attr->group.dont_merge = (unsigned char) lvalue;
     else if (hwloc__xml_verbose())
       fprintf(stderr, "%s: ignoring dont_merge attribute for non-group object type\n",
 	      state->global->msgprefix);
@@ -2825,6 +2825,7 @@ hwloc__xml_v1export_object_with_memory(hwloc__xml_export_state_t parentstate, hw
     /* child has sibling, we must add a Group around those memory children */
     hwloc_obj_t group = parentstate->global->v1_memory_group;
     parentstate->new_child(parentstate, &gstate, "object");
+    group->parent = obj->parent;
     group->cpuset = obj->cpuset;
     group->complete_cpuset = obj->complete_cpuset;
     group->nodeset = obj->nodeset;

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

@@ -3,6 +3,7 @@
  * Copyright © 2009-2021 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.
  * See COPYING in top-level directory.
  */
 
@@ -52,29 +53,41 @@
 #include <windows.h>
 #endif
 
+
+#ifdef HWLOC_HAVE_LEVELZERO
 /*
  * Define ZES_ENABLE_SYSMAN=1 early so that the LevelZero backend gets Sysman enabled.
+ *
+ * Only if the levelzero was enabled in this build so that we don't enable sysman
+ * for external levelzero users when hwloc doesn't need it. If somebody ever loads
+ * an external levelzero plugin in a hwloc library built without levelzero (unlikely),
+ * he may have to manually set ZES_ENABLE_SYSMAN=1.
+ *
  * Use the constructor if supported and/or the Windows DllMain callback.
  * Do it in the main hwloc library instead of the levelzero component because
  * the latter could be loaded later as a plugin.
  *
  * L0 seems to be using getenv() to check this variable on Windows
  * (at least in the Intel Compute-Runtime of March 2021),
- * so use putenv() to set the variable.
+ * but setenv() doesn't seem to exist on Windows, hence use putenv() to set the variable.
  *
  * For the record, Get/SetEnvironmentVariable() is not exactly the same as getenv/putenv():
  * - getenv() doesn't see what was set with SetEnvironmentVariable()
  * - GetEnvironmentVariable() doesn't see putenv() in cygwin (while it does in MSVC and MinGW).
  * Hence, if L0 ever switches from getenv() to GetEnvironmentVariable(),
  * it will break in cygwin, we'll have to use both putenv() and SetEnvironmentVariable().
- * Hopefully L0 will be provide a way to enable Sysman without env vars before it happens.
+ * Hopefully L0 will provide a way to enable Sysman without env vars before it happens.
  */
-#ifdef HWLOC_HAVE_ATTRIBUTE_CONSTRUCTOR
+#if HWLOC_HAVE_ATTRIBUTE_CONSTRUCTOR
 static void hwloc_constructor(void) __attribute__((constructor));
 static void hwloc_constructor(void)
 {
   if (!getenv("ZES_ENABLE_SYSMAN"))
-    putenv((char *) "ZES_ENABLE_SYSMAN=1");
+#ifdef HWLOC_WIN_SYS
+    putenv("ZES_ENABLE_SYSMAN=1");
+#else
+    setenv("ZES_ENABLE_SYSMAN", "1", 1);
+#endif
 }
 #endif
 #ifdef HWLOC_WIN_SYS
@@ -82,11 +95,14 @@ BOOL WINAPI DllMain(HINSTANCE hinstDLL, DWORD fdwReason, LPVOID lpReserved)
 {
   if (fdwReason == DLL_PROCESS_ATTACH) {
     if (!getenv("ZES_ENABLE_SYSMAN"))
+      /* Windows does not have a setenv, so use putenv. */
       putenv((char *) "ZES_ENABLE_SYSMAN=1");
   }
   return TRUE;
 }
 #endif
+#endif /* HWLOC_HAVE_LEVELZERO */
+
 
 unsigned hwloc_get_api_version(void)
 {
@@ -1901,6 +1917,9 @@ hwloc_topology_alloc_group_object(struct hwloc_topology *topology)
 static void hwloc_propagate_symmetric_subtree(hwloc_topology_t topology, hwloc_obj_t root);
 static void propagate_total_memory(hwloc_obj_t obj);
 static void hwloc_set_group_depth(hwloc_topology_t topology);
+static void hwloc_connect_children(hwloc_obj_t parent);
+static int hwloc_connect_levels(hwloc_topology_t topology);
+static int hwloc_connect_special_levels(hwloc_topology_t topology);
 
 hwloc_obj_t
 hwloc_topology_insert_group_object(struct hwloc_topology *topology, hwloc_obj_t obj)
@@ -2474,13 +2493,26 @@ hwloc_compare_levels_structure(hwloc_topology_t topology, unsigned i)
   return 0;
 }
 
-/* return > 0 if any level was removed, which means reconnect is needed */
-static void
+/* return > 0 if any level was removed.
+ * performs its own reconnect internally if needed
+ */
+static int
 hwloc_filter_levels_keep_structure(hwloc_topology_t topology)
 {
   unsigned i, j;
   int res = 0;
 
+  if (topology->modified) {
+    /* WARNING: hwloc_topology_reconnect() is duplicated partially here
+     * and at the end of this function:
+     * - we need normal levels before merging.
+     * - and we'll need to update special levels after merging.
+     */
+    hwloc_connect_children(topology->levels[0][0]);
+    if (hwloc_connect_levels(topology) < 0)
+      return -1;
+  }
+
   /* start from the bottom since we'll remove intermediate levels */
   for(i=topology->nb_levels-1; i>0; i--) {
     int replacechild = 0, replaceparent = 0;
@@ -2646,6 +2678,22 @@ hwloc_filter_levels_keep_structure(hwloc_topology_t topology)
 	topology->type_depth[type] = HWLOC_TYPE_DEPTH_MULTIPLE;
     }
   }
+
+
+  if (res > 0 || topology-> modified) {
+    /* WARNING: hwloc_topology_reconnect() is duplicated partially here
+     * and at the beginning of this function.
+     * If we merged some levels, some child+parent special children lisst
+     * may have been merged, hence specials level might need reordering,
+     * So reconnect special levels only here at the end
+     * (it's not needed at the beginning of this function).
+     */
+    if (hwloc_connect_special_levels(topology) < 0)
+      return -1;
+    topology->modified = 0;
+  }
+
+  return 0;
 }
 
 static void
@@ -2963,9 +3011,9 @@ hwloc_list_special_objects(hwloc_topology_t topology, hwloc_obj_t obj)
   }
 }
 
-/* Build I/O levels */
+/* Build Memory, I/O and Misc levels */
 static int
-hwloc_connect_io_misc_levels(hwloc_topology_t topology)
+hwloc_connect_special_levels(hwloc_topology_t topology)
 {
   unsigned i;
 
@@ -3176,6 +3224,10 @@ hwloc_connect_levels(hwloc_topology_t topology)
 int
 hwloc_topology_reconnect(struct hwloc_topology *topology, unsigned long flags)
 {
+  /* WARNING: when updating this function, the replicated code must
+   * also be updated inside hwloc_filter_levels_keep_structure()
+   */
+
   if (flags) {
     errno = EINVAL;
     return -1;
@@ -3188,7 +3240,7 @@ hwloc_topology_reconnect(struct hwloc_topology *topology, unsigned long flags)
   if (hwloc_connect_levels(topology) < 0)
     return -1;
 
-  if (hwloc_connect_io_misc_levels(topology) < 0)
+  if (hwloc_connect_special_levels(topology) < 0)
     return -1;
 
   topology->modified = 0;
@@ -3529,15 +3581,12 @@ hwloc_discover(struct hwloc_topology *topology,
   }
   hwloc_debug_print_objects(0, topology->levels[0][0]);
 
-  /* Reconnect things after all these changes.
-   * Often needed because of Groups inserted for I/Os.
-   * And required for KEEP_STRUCTURE below.
-   */
-  if (hwloc_topology_reconnect(topology, 0) < 0)
-    return -1;
-
   hwloc_debug("%s", "\nRemoving levels with HWLOC_TYPE_FILTER_KEEP_STRUCTURE\n");
-  hwloc_filter_levels_keep_structure(topology);
+  if (hwloc_filter_levels_keep_structure(topology) < 0)
+    return -1;
+  /* takes care of reconnecting children/levels internally,
+   * because it needs normal levels.
+   * and it's often needed below because of Groups inserted for I/Os anyway */
   hwloc_debug_print_objects(0, topology->levels[0][0]);
 
   /* accumulate children memory in total_memory fields (only once parent is set) */
@@ -4360,14 +4409,13 @@ hwloc_topology_restrict(struct hwloc_topology *topology, hwloc_const_bitmap_t se
   hwloc_bitmap_free(droppedcpuset);
   hwloc_bitmap_free(droppednodeset);
 
-  if (hwloc_topology_reconnect(topology, 0) < 0)
+  if (hwloc_filter_levels_keep_structure(topology) < 0) /* takes care of reconnecting internally */
     goto out;
 
   /* some objects may have disappeared, we need to update distances objs arrays */
   hwloc_internal_distances_invalidate_cached_objs(topology);
   hwloc_internal_memattrs_need_refresh(topology);
 
-  hwloc_filter_levels_keep_structure(topology);
   hwloc_propagate_symmetric_subtree(topology, topology->levels[0][0]);
   propagate_total_memory(topology->levels[0][0]);
   hwloc_internal_cpukinds_restrict(topology);

src/3rdparty/rapidjson/allocators.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_ALLOCATORS_H_
@@ -31,10 +31,10 @@ RAPIDJSON_NAMESPACE_BEGIN
 
 /*! \class rapidjson::Allocator
     \brief Concept for allocating, resizing and freeing memory block.
-    
+
     Note that Malloc() and Realloc() are non-static but Free() is static.
-    
-    So if an allocator need to support Free(), it needs to put its pointer in 
+
+    So if an allocator need to support Free(), it needs to put its pointer in
     the header of memory block.
 
 \code
@@ -82,7 +82,7 @@ concept Allocator {
 class CrtAllocator {
 public:
     static const bool kNeedFree = true;
-    void* Malloc(size_t size) { 
+    void* Malloc(size_t size) {
         if (size) //  behavior of malloc(0) is implementation defined.
             return RAPIDJSON_MALLOC(size);
         else
@@ -110,7 +110,7 @@ public:
 // MemoryPoolAllocator
 
 //! Default memory allocator used by the parser and DOM.
-/*! This allocator allocate memory blocks from pre-allocated memory chunks. 
+/*! This allocator allocate memory blocks from pre-allocated memory chunks.
 
     It does not free memory blocks. And Realloc() only allocate new memory.
 
@@ -166,7 +166,7 @@ public:
         \param baseAllocator The allocator for allocating memory chunks.
     */
     explicit
-    MemoryPoolAllocator(size_t chunkSize = kDefaultChunkCapacity, BaseAllocator* baseAllocator = 0) : 
+    MemoryPoolAllocator(size_t chunkSize = kDefaultChunkCapacity, BaseAllocator* baseAllocator = 0) :
         chunk_capacity_(chunkSize),
         baseAllocator_(baseAllocator ? baseAllocator : RAPIDJSON_NEW(BaseAllocator)()),
         shared_(static_cast<SharedData*>(baseAllocator_ ? baseAllocator_->Malloc(SIZEOF_SHARED_DATA + SIZEOF_CHUNK_HEADER) : 0))

src/3rdparty/rapidjson/document.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_DOCUMENT_H_
@@ -116,7 +116,7 @@ class GenericDocument;
     But a compiler (IBM XL C/C++ for AIX) have reported to have problem with that so it moved as a namespace scope struct.
     https://code.google.com/p/rapidjson/issues/detail?id=64
 */
-template <typename Encoding, typename Allocator> 
+template <typename Encoding, typename Allocator>
 class GenericMember {
 public:
     GenericValue<Encoding, Allocator> name;     //!< name of member (must be a string)
@@ -518,7 +518,7 @@ namespace internal {
 template <typename ValueType, typename T>
 struct TypeHelper {};
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, bool> {
     static bool Is(const ValueType& v) { return v.IsBool(); }
     static bool Get(const ValueType& v) { return v.GetBool(); }
@@ -526,7 +526,7 @@ struct TypeHelper<ValueType, bool> {
     static ValueType& Set(ValueType& v, bool data, typename ValueType::AllocatorType&) { return v.SetBool(data); }
 };
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, int> {
     static bool Is(const ValueType& v) { return v.IsInt(); }
     static int Get(const ValueType& v) { return v.GetInt(); }
@@ -534,7 +534,7 @@ struct TypeHelper<ValueType, int> {
     static ValueType& Set(ValueType& v, int data, typename ValueType::AllocatorType&) { return v.SetInt(data); }
 };
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, unsigned> {
     static bool Is(const ValueType& v) { return v.IsUint(); }
     static unsigned Get(const ValueType& v) { return v.GetUint(); }
@@ -562,7 +562,7 @@ struct TypeHelper<ValueType, unsigned long> {
 };
 #endif
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, int64_t> {
     static bool Is(const ValueType& v) { return v.IsInt64(); }
     static int64_t Get(const ValueType& v) { return v.GetInt64(); }
@@ -570,7 +570,7 @@ struct TypeHelper<ValueType, int64_t> {
     static ValueType& Set(ValueType& v, int64_t data, typename ValueType::AllocatorType&) { return v.SetInt64(data); }
 };
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, uint64_t> {
     static bool Is(const ValueType& v) { return v.IsUint64(); }
     static uint64_t Get(const ValueType& v) { return v.GetUint64(); }
@@ -578,7 +578,7 @@ struct TypeHelper<ValueType, uint64_t> {
     static ValueType& Set(ValueType& v, uint64_t data, typename ValueType::AllocatorType&) { return v.SetUint64(data); }
 };
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, double> {
     static bool Is(const ValueType& v) { return v.IsDouble(); }
     static double Get(const ValueType& v) { return v.GetDouble(); }
@@ -586,7 +586,7 @@ struct TypeHelper<ValueType, double> {
     static ValueType& Set(ValueType& v, double data, typename ValueType::AllocatorType&) { return v.SetDouble(data); }
 };
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, float> {
     static bool Is(const ValueType& v) { return v.IsFloat(); }
     static float Get(const ValueType& v) { return v.GetFloat(); }
@@ -594,7 +594,7 @@ struct TypeHelper<ValueType, float> {
     static ValueType& Set(ValueType& v, float data, typename ValueType::AllocatorType&) { return v.SetFloat(data); }
 };
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, const typename ValueType::Ch*> {
     typedef const typename ValueType::Ch* StringType;
     static bool Is(const ValueType& v) { return v.IsString(); }
@@ -604,7 +604,7 @@ struct TypeHelper<ValueType, const typename ValueType::Ch*> {
 };
 
 #if RAPIDJSON_HAS_STDSTRING
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, std::basic_string<typename ValueType::Ch> > {
     typedef std::basic_string<typename ValueType::Ch> StringType;
     static bool Is(const ValueType& v) { return v.IsString(); }
@@ -613,7 +613,7 @@ struct TypeHelper<ValueType, std::basic_string<typename ValueType::Ch> > {
 };
 #endif
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, typename ValueType::Array> {
     typedef typename ValueType::Array ArrayType;
     static bool Is(const ValueType& v) { return v.IsArray(); }
@@ -622,14 +622,14 @@ struct TypeHelper<ValueType, typename ValueType::Array> {
     static ValueType& Set(ValueType& v, ArrayType data, typename ValueType::AllocatorType&) { return v = data; }
 };
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, typename ValueType::ConstArray> {
     typedef typename ValueType::ConstArray ArrayType;
     static bool Is(const ValueType& v) { return v.IsArray(); }
     static ArrayType Get(const ValueType& v) { return v.GetArray(); }
 };
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, typename ValueType::Object> {
     typedef typename ValueType::Object ObjectType;
     static bool Is(const ValueType& v) { return v.IsObject(); }
@@ -638,7 +638,7 @@ struct TypeHelper<ValueType, typename ValueType::Object> {
     static ValueType& Set(ValueType& v, ObjectType data, typename ValueType::AllocatorType&) { return v = data; }
 };
 
-template<typename ValueType> 
+template<typename ValueType>
 struct TypeHelper<ValueType, typename ValueType::ConstObject> {
     typedef typename ValueType::ConstObject ObjectType;
     static bool Is(const ValueType& v) { return v.IsObject(); }
@@ -796,7 +796,7 @@ public:
 
     //! Constructor for unsigned value.
     explicit GenericValue(unsigned u) RAPIDJSON_NOEXCEPT : data_() {
-        data_.n.u64 = u; 
+        data_.n.u64 = u;
         data_.f.flags = (u & 0x80000000) ? kNumberUintFlag : (kNumberUintFlag | kIntFlag | kInt64Flag);
     }
 
@@ -1030,14 +1030,14 @@ public:
         switch (GetType()) {
         case kObjectType: // Warning: O(n^2) inner-loop
             if (data_.o.size != rhs.data_.o.size)
-                return false;           
+                return false;
             for (ConstMemberIterator lhsMemberItr = MemberBegin(); lhsMemberItr != MemberEnd(); ++lhsMemberItr) {
                 typename RhsType::ConstMemberIterator rhsMemberItr = rhs.FindMember(lhsMemberItr->name);
                 if (rhsMemberItr == rhs.MemberEnd() || lhsMemberItr->value != rhsMemberItr->value)
                     return false;
             }
             return true;
-            
+
         case kArrayType:
             if (data_.a.size != rhs.data_.a.size)
                 return false;
@@ -1505,7 +1505,7 @@ public:
         \note Linear time complexity.
     */
     void RemoveAllMembers() {
-        RAPIDJSON_ASSERT(IsObject()); 
+        RAPIDJSON_ASSERT(IsObject());
         DoClearMembers();
     }
 
@@ -1638,7 +1638,7 @@ public:
         \note Linear time complexity.
     */
     void Clear() {
-        RAPIDJSON_ASSERT(IsArray()); 
+        RAPIDJSON_ASSERT(IsArray());
         GenericValue* e = GetElementsPointer();
         for (GenericValue* v = e; v != e + data_.a.size; ++v)
             v->~GenericValue();
@@ -1844,7 +1844,7 @@ public:
 
     //! Set this value as a string without copying source string.
     /*! This version has better performance with supplied length, and also support string containing null character.
-        \param s source string pointer. 
+        \param s source string pointer.
         \param length The length of source string, excluding the trailing null terminator.
         \return The value itself for fluent API.
         \post IsString() == true && GetString() == s && GetStringLength() == length
@@ -1861,7 +1861,7 @@ public:
 
     //! Set this value as a string by copying from source string.
     /*! This version has better performance with supplied length, and also support string containing null character.
-        \param s source string. 
+        \param s source string.
         \param length The length of source string, excluding the trailing null terminator.
         \param allocator Allocator for allocating copied buffer. Commonly use GenericDocument::GetAllocator().
         \return The value itself for fluent API.
@@ -1870,7 +1870,7 @@ public:
     GenericValue& SetString(const Ch* s, SizeType length, Allocator& allocator) { return SetString(StringRef(s, length), allocator); }
 
     //! Set this value as a string by copying from source string.
-    /*! \param s source string. 
+    /*! \param s source string.
         \param allocator Allocator for allocating copied buffer. Commonly use GenericDocument::GetAllocator().
         \return The value itself for fluent API.
         \post IsString() == true && GetString() != s && strcmp(GetString(),s) == 0 && GetStringLength() == length
@@ -1955,10 +1955,10 @@ public:
                 if (RAPIDJSON_UNLIKELY(!v->Accept(handler)))
                     return false;
             return handler.EndArray(data_.a.size);
-    
+
         case kStringType:
             return handler.String(GetString(), GetStringLength(), (data_.f.flags & kCopyFlag) != 0);
-    
+
         default:
             RAPIDJSON_ASSERT(GetType() == kNumberType);
             if (IsDouble())         return handler.Double(data_.n.d);
@@ -2470,7 +2470,7 @@ private:
 typedef GenericValue<UTF8<> > Value;
 
 ///////////////////////////////////////////////////////////////////////////////
-// GenericDocument 
+// GenericDocument
 
 //! A document for parsing JSON text as DOM.
 /*!
@@ -2502,12 +2502,12 @@ public:
     }
 
     //! Constructor
-    /*! Creates an empty document which type is Null. 
+    /*! Creates an empty document which type is Null.
         \param allocator        Optional allocator for allocating memory.
         \param stackCapacity    Optional initial capacity of stack in bytes.
         \param stackAllocator   Optional allocator for allocating memory for stack.
     */
-    GenericDocument(Allocator* allocator = 0, size_t stackCapacity = kDefaultStackCapacity, StackAllocator* stackAllocator = 0) : 
+    GenericDocument(Allocator* allocator = 0, size_t stackCapacity = kDefaultStackCapacity, StackAllocator* stackAllocator = 0) :
         allocator_(allocator), ownAllocator_(0), stack_(stackAllocator, stackCapacity), parseResult_()
     {
         if (!allocator_)
@@ -2724,7 +2724,7 @@ public:
     GenericDocument& Parse(const Ch* str, size_t length) {
         return Parse<parseFlags, Encoding>(str, length);
     }
-    
+
     GenericDocument& Parse(const Ch* str, size_t length) {
         return Parse<kParseDefaultFlags>(str, length);
     }
@@ -2744,7 +2744,7 @@ public:
     GenericDocument& Parse(const std::basic_string<Ch>& str) {
         return Parse<kParseDefaultFlags>(str);
     }
-#endif // RAPIDJSON_HAS_STDSTRING    
+#endif // RAPIDJSON_HAS_STDSTRING
 
     //!@}
 
@@ -2809,16 +2809,16 @@ public:
     bool Uint64(uint64_t i) { new (stack_.template Push<ValueType>()) ValueType(i); return true; }
     bool Double(double d) { new (stack_.template Push<ValueType>()) ValueType(d); return true; }
 
-    bool RawNumber(const Ch* str, SizeType length, bool copy) { 
-        if (copy) 
+    bool RawNumber(const Ch* str, SizeType length, bool copy) {
+        if (copy)
             new (stack_.template Push<ValueType>()) ValueType(str, length, GetAllocator());
         else
             new (stack_.template Push<ValueType>()) ValueType(str, length);
         return true;
     }
 
-    bool String(const Ch* str, SizeType length, bool copy) { 
-        if (copy) 
+    bool String(const Ch* str, SizeType length, bool copy) {
+        if (copy)
             new (stack_.template Push<ValueType>()) ValueType(str, length, GetAllocator());
         else
             new (stack_.template Push<ValueType>()) ValueType(str, length);
@@ -2826,7 +2826,7 @@ public:
     }
 
     bool StartObject() { new (stack_.template Push<ValueType>()) ValueType(kObjectType); return true; }
-    
+
     bool Key(const Ch* str, SizeType length, bool copy) { return String(str, length, copy); }
 
     bool EndObject(SizeType memberCount) {
@@ -2836,7 +2836,7 @@ public:
     }
 
     bool StartArray() { new (stack_.template Push<ValueType>()) ValueType(kArrayType); return true; }
-    
+
     bool EndArray(SizeType elementCount) {
         ValueType* elements = stack_.template Pop<ValueType>(elementCount);
         stack_.template Top<ValueType>()->SetArrayRaw(elements, elementCount, GetAllocator());

src/3rdparty/rapidjson/encodedstream.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_ENCODEDSTREAM_H_
@@ -41,7 +41,7 @@ class EncodedInputStream {
 public:
     typedef typename Encoding::Ch Ch;
 
-    EncodedInputStream(InputByteStream& is) : is_(is) { 
+    EncodedInputStream(InputByteStream& is) : is_(is) {
         current_ = Encoding::TakeBOM(is_);
     }
 
@@ -51,7 +51,7 @@ public:
 
     // Not implemented
     void Put(Ch) { RAPIDJSON_ASSERT(false); }
-    void Flush() { RAPIDJSON_ASSERT(false); } 
+    void Flush() { RAPIDJSON_ASSERT(false); }
     Ch* PutBegin() { RAPIDJSON_ASSERT(false); return 0; }
     size_t PutEnd(Ch*) { RAPIDJSON_ASSERT(false); return 0; }
 
@@ -80,7 +80,7 @@ public:
 
     // Not implemented
     void Put(Ch) {}
-    void Flush() {} 
+    void Flush() {}
     Ch* PutBegin() { return 0; }
     size_t PutEnd(Ch*) { return 0; }
 
@@ -102,7 +102,7 @@ class EncodedOutputStream {
 public:
     typedef typename Encoding::Ch Ch;
 
-    EncodedOutputStream(OutputByteStream& os, bool putBOM = true) : os_(os) { 
+    EncodedOutputStream(OutputByteStream& os, bool putBOM = true) : os_(os) {
         if (putBOM)
             Encoding::PutBOM(os_);
     }
@@ -143,7 +143,7 @@ public:
         \param type UTF encoding type if it is not detected from the stream.
     */
     AutoUTFInputStream(InputByteStream& is, UTFType type = kUTF8) : is_(&is), type_(type), hasBOM_(false) {
-        RAPIDJSON_ASSERT(type >= kUTF8 && type <= kUTF32BE);        
+        RAPIDJSON_ASSERT(type >= kUTF8 && type <= kUTF32BE);
         DetectType();
         static const TakeFunc f[] = { RAPIDJSON_ENCODINGS_FUNC(Take) };
         takeFunc_ = f[type_];
@@ -159,7 +159,7 @@ public:
 
     // Not implemented
     void Put(Ch) { RAPIDJSON_ASSERT(false); }
-    void Flush() { RAPIDJSON_ASSERT(false); } 
+    void Flush() { RAPIDJSON_ASSERT(false); }
     Ch* PutBegin() { RAPIDJSON_ASSERT(false); return 0; }
     size_t PutEnd(Ch*) { RAPIDJSON_ASSERT(false); return 0; }
 
@@ -258,7 +258,7 @@ public:
     UTFType GetType() const { return type_; }
 
     void Put(Ch c) { putFunc_(*os_, c); }
-    void Flush() { os_->Flush(); } 
+    void Flush() { os_->Flush(); }
 
     // Not implemented
     Ch Peek() const { RAPIDJSON_ASSERT(false); return 0;}
@@ -271,7 +271,7 @@ private:
     AutoUTFOutputStream(const AutoUTFOutputStream&);
     AutoUTFOutputStream& operator=(const AutoUTFOutputStream&);
 
-    void PutBOM() { 
+    void PutBOM() {
         typedef void (*PutBOMFunc)(OutputByteStream&);
         static const PutBOMFunc f[] = { RAPIDJSON_ENCODINGS_FUNC(PutBOM) };
         f[type_](*os_);

src/3rdparty/rapidjson/encodings.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_ENCODINGS_H_
@@ -100,7 +100,7 @@ struct UTF8 {
 
     template<typename OutputStream>
     static void Encode(OutputStream& os, unsigned codepoint) {
-        if (codepoint <= 0x7F) 
+        if (codepoint <= 0x7F)
             os.Put(static_cast<Ch>(codepoint & 0xFF));
         else if (codepoint <= 0x7FF) {
             os.Put(static_cast<Ch>(0xC0 | ((codepoint >> 6) & 0xFF)));
@@ -122,7 +122,7 @@ struct UTF8 {
 
     template<typename OutputStream>
     static void EncodeUnsafe(OutputStream& os, unsigned codepoint) {
-        if (codepoint <= 0x7F) 
+        if (codepoint <= 0x7F)
             PutUnsafe(os, static_cast<Ch>(codepoint & 0xFF));
         else if (codepoint <= 0x7FF) {
             PutUnsafe(os, static_cast<Ch>(0xC0 | ((codepoint >> 6) & 0xFF)));
@@ -276,7 +276,7 @@ struct UTF16 {
     static void Encode(OutputStream& os, unsigned codepoint) {
         RAPIDJSON_STATIC_ASSERT(sizeof(typename OutputStream::Ch) >= 2);
         if (codepoint <= 0xFFFF) {
-            RAPIDJSON_ASSERT(codepoint < 0xD800 || codepoint > 0xDFFF); // Code point itself cannot be surrogate pair 
+            RAPIDJSON_ASSERT(codepoint < 0xD800 || codepoint > 0xDFFF); // Code point itself cannot be surrogate pair
             os.Put(static_cast<typename OutputStream::Ch>(codepoint));
         }
         else {
@@ -292,7 +292,7 @@ struct UTF16 {
     static void EncodeUnsafe(OutputStream& os, unsigned codepoint) {
         RAPIDJSON_STATIC_ASSERT(sizeof(typename OutputStream::Ch) >= 2);
         if (codepoint <= 0xFFFF) {
-            RAPIDJSON_ASSERT(codepoint < 0xD800 || codepoint > 0xDFFF); // Code point itself cannot be surrogate pair 
+            RAPIDJSON_ASSERT(codepoint < 0xD800 || codepoint > 0xDFFF); // Code point itself cannot be surrogate pair
             PutUnsafe(os, static_cast<typename OutputStream::Ch>(codepoint));
         }
         else {
@@ -406,7 +406,7 @@ struct UTF16BE : UTF16<CharType> {
 ///////////////////////////////////////////////////////////////////////////////
 // UTF32
 
-//! UTF-32 encoding. 
+//! UTF-32 encoding.
 /*! http://en.wikipedia.org/wiki/UTF-32
     \tparam CharType Type for storing 32-bit UTF-32 data. Default is unsigned. C++11 may use char32_t instead.
     \note implements Encoding concept
@@ -498,7 +498,7 @@ struct UTF32BE : UTF32<CharType> {
     static CharType TakeBOM(InputByteStream& is) {
         RAPIDJSON_STATIC_ASSERT(sizeof(typename InputByteStream::Ch) == 1);
         CharType c = Take(is);
-        return static_cast<uint32_t>(c) == 0x0000FEFFu ? Take(is) : c; 
+        return static_cast<uint32_t>(c) == 0x0000FEFFu ? Take(is) : c;
     }
 
     template <typename InputByteStream>
@@ -694,13 +694,13 @@ struct Transcoder<Encoding, Encoding> {
         os.Put(is.Take());  // Just copy one code unit. This semantic is different from primary template class.
         return true;
     }
-    
+
     template<typename InputStream, typename OutputStream>
     static RAPIDJSON_FORCEINLINE bool TranscodeUnsafe(InputStream& is, OutputStream& os) {
         PutUnsafe(os, is.Take());  // Just copy one code unit. This semantic is different from primary template class.
         return true;
     }
-    
+
     template<typename InputStream, typename OutputStream>
     static RAPIDJSON_FORCEINLINE bool Validate(InputStream& is, OutputStream& os) {
         return Encoding::Validate(is, os);  // source/target encoding are the same

src/3rdparty/rapidjson/error/en.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_ERROR_EN_H_
@@ -39,13 +39,13 @@ inline const RAPIDJSON_ERROR_CHARTYPE* GetParseError_En(ParseErrorCode parseErro
 
         case kParseErrorDocumentEmpty:                  return RAPIDJSON_ERROR_STRING("The document is empty.");
         case kParseErrorDocumentRootNotSingular:        return RAPIDJSON_ERROR_STRING("The document root must not be followed by other values.");
-    
+
         case kParseErrorValueInvalid:                   return RAPIDJSON_ERROR_STRING("Invalid value.");
-    
+
         case kParseErrorObjectMissName:                 return RAPIDJSON_ERROR_STRING("Missing a name for object member.");
         case kParseErrorObjectMissColon:                return RAPIDJSON_ERROR_STRING("Missing a colon after a name of object member.");
         case kParseErrorObjectMissCommaOrCurlyBracket:  return RAPIDJSON_ERROR_STRING("Missing a comma or '}' after an object member.");
-    
+
         case kParseErrorArrayMissCommaOrSquareBracket:  return RAPIDJSON_ERROR_STRING("Missing a comma or ']' after an array element.");
 
         case kParseErrorStringUnicodeEscapeInvalidHex:  return RAPIDJSON_ERROR_STRING("Incorrect hex digit after \\u escape in string.");

src/3rdparty/rapidjson/error/error.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_ERROR_ERROR_H_

src/3rdparty/rapidjson/filereadstream.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_FILEREADSTREAM_H_
@@ -41,7 +41,7 @@ public:
         \param buffer user-supplied buffer.
         \param bufferSize size of buffer in bytes. Must >=4 bytes.
     */
-    FileReadStream(std::FILE* fp, char* buffer, size_t bufferSize) : fp_(fp), buffer_(buffer), bufferSize_(bufferSize), bufferLast_(0), current_(buffer_), readCount_(0), count_(0), eof_(false) { 
+    FileReadStream(std::FILE* fp, char* buffer, size_t bufferSize) : fp_(fp), buffer_(buffer), bufferSize_(bufferSize), bufferLast_(0), current_(buffer_), readCount_(0), count_(0), eof_(false) {
         RAPIDJSON_ASSERT(fp_ != 0);
         RAPIDJSON_ASSERT(bufferSize >= 4);
         Read();
@@ -53,7 +53,7 @@ public:
 
     // Not implemented
     void Put(Ch) { RAPIDJSON_ASSERT(false); }
-    void Flush() { RAPIDJSON_ASSERT(false); } 
+    void Flush() { RAPIDJSON_ASSERT(false); }
     Ch* PutBegin() { RAPIDJSON_ASSERT(false); return 0; }
     size_t PutEnd(Ch*) { RAPIDJSON_ASSERT(false); return 0; }
 

src/3rdparty/rapidjson/filewritestream.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_FILEWRITESTREAM_H_
@@ -33,11 +33,11 @@ class FileWriteStream {
 public:
     typedef char Ch;    //!< Character type. Only support char.
 
-    FileWriteStream(std::FILE* fp, char* buffer, size_t bufferSize) : fp_(fp), buffer_(buffer), bufferEnd_(buffer + bufferSize), current_(buffer_) { 
+    FileWriteStream(std::FILE* fp, char* buffer, size_t bufferSize) : fp_(fp), buffer_(buffer), bufferEnd_(buffer + bufferSize), current_(buffer_) {
         RAPIDJSON_ASSERT(fp_ != 0);
     }
 
-    void Put(char c) { 
+    void Put(char c) {
         if (current_ >= bufferEnd_)
             Flush();
 

src/3rdparty/rapidjson/fwd.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_FWD_H_
@@ -101,7 +101,7 @@ class PrettyWriter;
 
 // document.h
 
-template <typename Encoding, typename Allocator> 
+template <typename Encoding, typename Allocator>
 class GenericMember;
 
 template <bool Const, typename Encoding, typename Allocator>
@@ -110,7 +110,7 @@ class GenericMemberIterator;
 template<typename CharType>
 struct GenericStringRef;
 
-template <typename Encoding, typename Allocator> 
+template <typename Encoding, typename Allocator>
 class GenericValue;
 
 typedef GenericValue<UTF8<char>, MemoryPoolAllocator<CrtAllocator> > Value;

src/3rdparty/rapidjson/internal/biginteger.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_BIGINTEGER_H_
@@ -52,7 +52,7 @@ public:
         if (length > 0)
             AppendDecimal64(decimals + i, decimals + i + length);
     }
-    
+
     BigInteger& operator=(const BigInteger &rhs)
     {
         if (this != &rhs) {
@@ -61,9 +61,9 @@ public:
         }
         return *this;
     }
-    
+
     BigInteger& operator=(uint64_t u) {
-        digits_[0] = u;            
+        digits_[0] = u;
         count_ = 1;
         return *this;
     }
@@ -96,7 +96,7 @@ public:
             digits_[i] = MulAdd64(digits_[i], u, k, &hi);
             k = hi;
         }
-        
+
         if (k > 0)
             PushBack(k);
 
@@ -119,7 +119,7 @@ public:
             digits_[i] = (p0 & 0xFFFFFFFF) | (p1 << 32);
             k = p1 >> 32;
         }
-        
+
         if (k > 0)
             PushBack(k);
 

src/3rdparty/rapidjson/internal/dtoa.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 // This is a C++ header-only implementation of Grisu2 algorithm from the publication:

src/3rdparty/rapidjson/internal/ieee754.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_IEEE754_

src/3rdparty/rapidjson/internal/meta.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_INTERNAL_META_H_

src/3rdparty/rapidjson/internal/pow10.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_POW10_
@@ -27,8 +27,8 @@ namespace internal {
 */
 inline double Pow10(int n) {
     static const double e[] = { // 1e-0...1e308: 309 * 8 bytes = 2472 bytes
-        1e+0,  
-        1e+1,  1e+2,  1e+3,  1e+4,  1e+5,  1e+6,  1e+7,  1e+8,  1e+9,  1e+10, 1e+11, 1e+12, 1e+13, 1e+14, 1e+15, 1e+16, 1e+17, 1e+18, 1e+19, 1e+20, 
+        1e+0,
+        1e+1,  1e+2,  1e+3,  1e+4,  1e+5,  1e+6,  1e+7,  1e+8,  1e+9,  1e+10, 1e+11, 1e+12, 1e+13, 1e+14, 1e+15, 1e+16, 1e+17, 1e+18, 1e+19, 1e+20,
         1e+21, 1e+22, 1e+23, 1e+24, 1e+25, 1e+26, 1e+27, 1e+28, 1e+29, 1e+30, 1e+31, 1e+32, 1e+33, 1e+34, 1e+35, 1e+36, 1e+37, 1e+38, 1e+39, 1e+40,
         1e+41, 1e+42, 1e+43, 1e+44, 1e+45, 1e+46, 1e+47, 1e+48, 1e+49, 1e+50, 1e+51, 1e+52, 1e+53, 1e+54, 1e+55, 1e+56, 1e+57, 1e+58, 1e+59, 1e+60,
         1e+61, 1e+62, 1e+63, 1e+64, 1e+65, 1e+66, 1e+67, 1e+68, 1e+69, 1e+70, 1e+71, 1e+72, 1e+73, 1e+74, 1e+75, 1e+76, 1e+77, 1e+78, 1e+79, 1e+80,

src/3rdparty/rapidjson/internal/regex.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_INTERNAL_REGEX_H_
@@ -102,9 +102,9 @@ class GenericRegexSearch;
     - \c \\t Tab (U+0009)
     - \c \\v Vertical tab (U+000B)
 
-    \note This is a Thompson NFA engine, implemented with reference to 
-        Cox, Russ. "Regular Expression Matching Can Be Simple And Fast (but is slow in Java, Perl, PHP, Python, Ruby,...).", 
-        https://swtch.com/~rsc/regexp/regexp1.html 
+    \note This is a Thompson NFA engine, implemented with reference to
+        Cox, Russ. "Regular Expression Matching Can Be Simple And Fast (but is slow in Java, Perl, PHP, Python, Ruby,...).",
+        https://swtch.com/~rsc/regexp/regexp1.html
 */
 template <typename Encoding, typename Allocator = CrtAllocator>
 class GenericRegex {
@@ -113,9 +113,9 @@ public:
     typedef typename Encoding::Ch Ch;
     template <typename, typename> friend class GenericRegexSearch;
 
-    GenericRegex(const Ch* source, Allocator* allocator = 0) : 
-        ownAllocator_(allocator ? 0 : RAPIDJSON_NEW(Allocator)()), allocator_(allocator ? allocator : ownAllocator_), 
-        states_(allocator_, 256), ranges_(allocator_, 256), root_(kRegexInvalidState), stateCount_(), rangeCount_(), 
+    GenericRegex(const Ch* source, Allocator* allocator = 0) :
+        ownAllocator_(allocator ? 0 : RAPIDJSON_NEW(Allocator)()), allocator_(allocator ? allocator : ownAllocator_),
+        states_(allocator_, 256), ranges_(allocator_, 256), root_(kRegexInvalidState), stateCount_(), rangeCount_(),
         anchorBegin_(), anchorEnd_()
     {
         GenericStringStream<Encoding> ss(source);
@@ -147,7 +147,7 @@ private:
     static const unsigned kRangeNegationFlag = 0x80000000;
 
     struct Range {
-        unsigned start; // 
+        unsigned start; //
         unsigned end;
         SizeType next;
     };
@@ -402,7 +402,7 @@ private:
                 }
                 return false;
 
-            default: 
+            default:
                 // syntax error (e.g. unclosed kLeftParenthesis)
                 return false;
         }
@@ -550,7 +550,7 @@ private:
         }
         return false;
     }
-    
+
     SizeType NewRange(unsigned codepoint) {
         Range* r = ranges_.template Push<Range>();
         r->start = r->end = codepoint;
@@ -608,7 +608,7 @@ public:
     typedef typename RegexType::EncodingType Encoding;
     typedef typename Encoding::Ch Ch;
 
-    GenericRegexSearch(const RegexType& regex, Allocator* allocator = 0) : 
+    GenericRegexSearch(const RegexType& regex, Allocator* allocator = 0) :
         regex_(regex), allocator_(allocator), ownAllocator_(0),
         state0_(allocator, 0), state1_(allocator, 0), stateSet_()
     {
@@ -667,7 +667,7 @@ private:
             for (const SizeType* s = current->template Bottom<SizeType>(); s != current->template End<SizeType>(); ++s) {
                 const State& sr = regex_.GetState(*s);
                 if (sr.codepoint == codepoint ||
-                    sr.codepoint == RegexType::kAnyCharacterClass || 
+                    sr.codepoint == RegexType::kAnyCharacterClass ||
                     (sr.codepoint == RegexType::kRangeCharacterClass && MatchRange(sr.rangeStart, codepoint)))
                 {
                     matched = AddState(*next, sr.out) || matched;

src/3rdparty/rapidjson/internal/stack.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_INTERNAL_STACK_H_
@@ -98,7 +98,7 @@ public:
 
     void Clear() { stackTop_ = stack_; }
 
-    void ShrinkToFit() { 
+    void ShrinkToFit() {
         if (Empty()) {
             // If the stack is empty, completely deallocate the memory.
             Allocator::Free(stack_); // NOLINT (+clang-analyzer-unix.Malloc)
@@ -142,7 +142,7 @@ public:
     }
 
     template<typename T>
-    T* Top() { 
+    T* Top() {
         RAPIDJSON_ASSERT(GetSize() >= sizeof(T));
         return reinterpret_cast<T*>(stackTop_ - sizeof(T));
     }

src/3rdparty/rapidjson/internal/strfunc.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_INTERNAL_STRFUNC_H_
@@ -24,7 +24,7 @@ namespace internal {
 //! Custom strlen() which works on different character types.
 /*! \tparam Ch Character type (e.g. char, wchar_t, short)
     \param s Null-terminated input string.
-    \return Number of characters in the string. 
+    \return Number of characters in the string.
     \note This has the same semantics as strlen(), the return value is not number of Unicode codepoints.
 */
 template <typename Ch>

src/3rdparty/rapidjson/internal/strtod.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_STRTOD_
@@ -131,14 +131,14 @@ inline bool StrtodFast(double d, int p, double* result) {
 template<typename Ch>
 inline bool StrtodDiyFp(const Ch* decimals, int dLen, int dExp, double* result) {
     uint64_t significand = 0;
-    int i = 0;   // 2^64 - 1 = 18446744073709551615, 1844674407370955161 = 0x1999999999999999    
+    int i = 0;   // 2^64 - 1 = 18446744073709551615, 1844674407370955161 = 0x1999999999999999
     for (; i < dLen; i++) {
         if (significand  >  RAPIDJSON_UINT64_C2(0x19999999, 0x99999999) ||
             (significand == RAPIDJSON_UINT64_C2(0x19999999, 0x99999999) && decimals[i] > Ch('5')))
             break;
         significand = significand * 10u + static_cast<unsigned>(decimals[i] - Ch('0'));
     }
-    
+
     if (i < dLen && decimals[i] >= Ch('5')) // Rounding
         significand++;
 
@@ -185,7 +185,7 @@ inline bool StrtodDiyFp(const Ch* decimals, int dLen, int dExp, double* result)
     if (precisionSize + kUlpShift >= 64) {
         int scaleExp = (precisionSize + kUlpShift) - 63;
         v.f >>= scaleExp;
-        v.e += scaleExp; 
+        v.e += scaleExp;
         error = (error >> scaleExp) + 1 + kUlp;
         precisionSize -= scaleExp;
     }

src/3rdparty/rapidjson/istreamwrapper.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_ISTREAMWRAPPER_H_
@@ -44,7 +44,7 @@ RAPIDJSON_NAMESPACE_BEGIN
 
     \tparam StreamType Class derived from \c std::basic_istream.
 */
-   
+
 template <typename StreamType>
 class BasicIStreamWrapper {
 public:
@@ -54,7 +54,7 @@ public:
     /*!
         \param stream stream opened for read.
     */
-    BasicIStreamWrapper(StreamType &stream) : stream_(stream), buffer_(peekBuffer_), bufferSize_(4), bufferLast_(0), current_(buffer_), readCount_(0), count_(0), eof_(false) { 
+    BasicIStreamWrapper(StreamType &stream) : stream_(stream), buffer_(peekBuffer_), bufferSize_(4), bufferLast_(0), current_(buffer_), readCount_(0), count_(0), eof_(false) {
         Read();
     }
 
@@ -64,7 +64,7 @@ public:
         \param buffer user-supplied buffer.
         \param bufferSize size of buffer in bytes. Must >=4 bytes.
     */
-    BasicIStreamWrapper(StreamType &stream, char* buffer, size_t bufferSize) : stream_(stream), buffer_(buffer), bufferSize_(bufferSize), bufferLast_(0), current_(buffer_), readCount_(0), count_(0), eof_(false) { 
+    BasicIStreamWrapper(StreamType &stream, char* buffer, size_t bufferSize) : stream_(stream), buffer_(buffer), bufferSize_(bufferSize), bufferLast_(0), current_(buffer_), readCount_(0), count_(0), eof_(false) {
         RAPIDJSON_ASSERT(bufferSize >= 4);
         Read();
     }
@@ -75,7 +75,7 @@ public:
 
     // Not implemented
     void Put(Ch) { RAPIDJSON_ASSERT(false); }
-    void Flush() { RAPIDJSON_ASSERT(false); } 
+    void Flush() { RAPIDJSON_ASSERT(false); }
     Ch* PutBegin() { RAPIDJSON_ASSERT(false); return 0; }
     size_t PutEnd(Ch*) { RAPIDJSON_ASSERT(false); return 0; }
 

src/3rdparty/rapidjson/license.txt

@@ -1,5 +1,5 @@
-Tencent is pleased to support the open source community by making RapidJSON available. 
- 
+Tencent is pleased to support the open source community by making RapidJSON available.
+
 Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.  All rights reserved.
 
 If you have downloaded a copy of the RapidJSON binary from Tencent, please note that the RapidJSON binary is licensed under the MIT License.
@@ -11,13 +11,13 @@ Other dependencies and licenses:
 Open Source Software Licensed Under the BSD License:
 --------------------------------------------------------------------
 
-The msinttypes r29 
-Copyright (c) 2006-2013 Alexander Chemeris 
+The msinttypes r29
+Copyright (c) 2006-2013 Alexander Chemeris
 All rights reserved.
 
 Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
 
-* Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer. 
+* Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
 * Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
 * Neither the name of  copyright holder nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
 
@@ -26,7 +26,7 @@ THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND ANY EXPR
 Open Source Software Licensed Under the JSON License:
 --------------------------------------------------------------------
 
-json.org 
+json.org
 Copyright (c) 2002 JSON.org
 All Rights Reserved.
 
@@ -34,7 +34,7 @@ JSON_checker
 Copyright (c) 2002 JSON.org
 All Rights Reserved.
 
-	
+
 Terms of the JSON License:
 ---------------------------------------------------
 

src/3rdparty/rapidjson/memorybuffer.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_MEMORYBUFFER_H_
@@ -27,7 +27,7 @@ RAPIDJSON_NAMESPACE_BEGIN
     It is similar to FileWriteBuffer but the destination is an in-memory buffer instead of a file.
 
     Differences between MemoryBuffer and StringBuffer:
-    1. StringBuffer has Encoding but MemoryBuffer is only a byte buffer. 
+    1. StringBuffer has Encoding but MemoryBuffer is only a byte buffer.
     2. StringBuffer::GetString() returns a null-terminated string. MemoryBuffer::GetBuffer() returns a buffer without terminator.
 
     \tparam Allocator type for allocating memory buffer.

src/3rdparty/rapidjson/memorystream.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_MEMORYSTREAM_H_

src/3rdparty/rapidjson/msinttypes/inttypes.h

@@ -1,37 +1,37 @@
 // ISO C9x  compliant inttypes.h for Microsoft Visual Studio
-// Based on ISO/IEC 9899:TC2 Committee draft (May 6, 2005) WG14/N1124 
-// 
+// Based on ISO/IEC 9899:TC2 Committee draft (May 6, 2005) WG14/N1124
+//
 //  Copyright (c) 2006-2013 Alexander Chemeris
-// 
+//
 // Redistribution and use in source and binary forms, with or without
 // modification, are permitted provided that the following conditions are met:
-// 
+//
 //   1. Redistributions of source code must retain the above copyright notice,
 //      this list of conditions and the following disclaimer.
-// 
+//
 //   2. Redistributions in binary form must reproduce the above copyright
 //      notice, this list of conditions and the following disclaimer in the
 //      documentation and/or other materials provided with the distribution.
-// 
+//
 //   3. Neither the name of the product nor the names of its contributors may
 //      be used to endorse or promote products derived from this software
 //      without specific prior written permission.
-// 
+//
 // THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
 // WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 // MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
 // EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
 // PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
-// OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, 
+// OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
 // WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
 // OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
 // ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-// 
+//
 ///////////////////////////////////////////////////////////////////////////////
 
-// The above software in this distribution may have been modified by 
-// THL A29 Limited ("Tencent Modifications"). 
+// The above software in this distribution may have been modified by
+// THL A29 Limited ("Tencent Modifications").
 // All Tencent Modifications are Copyright (C) 2015 THL A29 Limited.
 
 #ifndef _MSC_VER // [

src/3rdparty/rapidjson/msinttypes/stdint.h

@@ -1,37 +1,37 @@
 // ISO C9x  compliant stdint.h for Microsoft Visual Studio
-// Based on ISO/IEC 9899:TC2 Committee draft (May 6, 2005) WG14/N1124 
-// 
+// Based on ISO/IEC 9899:TC2 Committee draft (May 6, 2005) WG14/N1124
+//
 //  Copyright (c) 2006-2013 Alexander Chemeris
-// 
+//
 // Redistribution and use in source and binary forms, with or without
 // modification, are permitted provided that the following conditions are met:
-// 
+//
 //   1. Redistributions of source code must retain the above copyright notice,
 //      this list of conditions and the following disclaimer.
-// 
+//
 //   2. Redistributions in binary form must reproduce the above copyright
 //      notice, this list of conditions and the following disclaimer in the
 //      documentation and/or other materials provided with the distribution.
-// 
+//
 //   3. Neither the name of the product nor the names of its contributors may
 //      be used to endorse or promote products derived from this software
 //      without specific prior written permission.
-// 
+//
 // THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
 // WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
 // MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO
 // EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
 // PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
-// OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, 
+// OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
 // WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
 // OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
 // ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-// 
+//
 ///////////////////////////////////////////////////////////////////////////////
 
-// The above software in this distribution may have been modified by 
-// THL A29 Limited ("Tencent Modifications"). 
+// The above software in this distribution may have been modified by
+// THL A29 Limited ("Tencent Modifications").
 // All Tencent Modifications are Copyright (C) 2015 THL A29 Limited.
 
 #ifndef _MSC_VER // [

src/3rdparty/rapidjson/ostreamwrapper.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_OSTREAMWRAPPER_H_
@@ -40,7 +40,7 @@ RAPIDJSON_NAMESPACE_BEGIN
 
     \tparam StreamType Class derived from \c std::basic_ostream.
 */
-   
+
 template <typename StreamType>
 class BasicOStreamWrapper {
 public:

src/3rdparty/rapidjson/pointer.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_POINTER_H_
@@ -49,16 +49,16 @@ enum PointerParseErrorCode {
 
 //! Represents a JSON Pointer. Use Pointer for UTF8 encoding and default allocator.
 /*!
-    This class implements RFC 6901 "JavaScript Object Notation (JSON) Pointer" 
+    This class implements RFC 6901 "JavaScript Object Notation (JSON) Pointer"
     (https://tools.ietf.org/html/rfc6901).
 
     A JSON pointer is for identifying a specific value in a JSON document
     (GenericDocument). It can simplify coding of DOM tree manipulation, because it
     can access multiple-level depth of DOM tree with single API call.
 
-    After it parses a string representation (e.g. "/foo/0" or URI fragment 
+    After it parses a string representation (e.g. "/foo/0" or URI fragment
     representation (e.g. "#/foo/0") into its internal representation (tokens),
-    it can be used to resolve a specific value in multiple documents, or sub-tree 
+    it can be used to resolve a specific value in multiple documents, or sub-tree
     of documents.
 
     Contrary to GenericValue, Pointer can be copy constructed and copy assigned.
@@ -69,10 +69,10 @@ enum PointerParseErrorCode {
     supplied tokens eliminates these.
 
     GenericPointer depends on GenericDocument and GenericValue.
-    
+
     \tparam ValueType The value type of the DOM tree. E.g. GenericValue<UTF8<> >
     \tparam Allocator The allocator type for allocating memory for internal representation.
-    
+
     \note GenericPointer uses same encoding of ValueType.
     However, Allocator of GenericPointer is independent of Allocator of Value.
 */
@@ -86,7 +86,7 @@ public:
 
     //! A token is the basic units of internal representation.
     /*!
-        A JSON pointer string representation "/foo/123" is parsed to two tokens: 
+        A JSON pointer string representation "/foo/123" is parsed to two tokens:
         "foo" and 123. 123 will be represented in both numeric form and string form.
         They are resolved according to the actual value type (object or array).
 
@@ -94,7 +94,7 @@ public:
         (greater than limits of SizeType), they are only treated as string form
         (i.e. the token's index will be equal to kPointerInvalidIndex).
 
-        This struct is public so that user can create a Pointer without parsing and 
+        This struct is public so that user can create a Pointer without parsing and
         allocation, using a special constructor.
     */
     struct Token {
@@ -373,7 +373,7 @@ public:
 
         for (size_t i = 0; i < tokenCount_; i++) {
             if (tokens_[i].index != rhs.tokens_[i].index ||
-                tokens_[i].length != rhs.tokens_[i].length || 
+                tokens_[i].length != rhs.tokens_[i].length ||
                 (tokens_[i].length != 0 && std::memcmp(tokens_[i].name, rhs.tokens_[i].name, sizeof(Ch)* tokens_[i].length) != 0))
             {
                 return false;
@@ -451,9 +451,9 @@ public:
         If the value is not exist, it creates all parent values and a JSON Null value.
         So it always succeed and return the newly created or existing value.
 
-        Remind that it may change types of parents according to tokens, so it 
-        potentially removes previously stored values. For example, if a document 
-        was an array, and "/foo" is used to create a value, then the document 
+        Remind that it may change types of parents according to tokens, so it
+        potentially removes previously stored values. For example, if a document
+        was an array, and "/foo" is used to create a value, then the document
         will be changed to an object, and all existing array elements are lost.
 
         \param root Root value of a DOM subtree to be resolved. It can be any value other than document root.
@@ -639,7 +639,7 @@ public:
         \param root Root value of a DOM sub-tree to be resolved. It can be any value other than document root.
         \return Pointer to the value if it can be resolved. Otherwise null.
     */
-    const ValueType* Get(const ValueType& root, size_t* unresolvedTokenIndex = 0) const { 
+    const ValueType* Get(const ValueType& root, size_t* unresolvedTokenIndex = 0) const {
         return Get(const_cast<ValueType&>(root), unresolvedTokenIndex);
     }
 
@@ -701,7 +701,7 @@ public:
     ValueType& GetWithDefault(GenericDocument<EncodingType, typename ValueType::AllocatorType, stackAllocator>& document, const Ch* defaultValue) const {
         return GetWithDefault(document, defaultValue, document.GetAllocator());
     }
-    
+
 #if RAPIDJSON_HAS_STDSTRING
     //! Query a value in a document with default std::basic_string.
     template <typename stackAllocator>
@@ -938,7 +938,7 @@ private:
 
         // Count number of '/' as tokenCount
         tokenCount_ = 0;
-        for (const Ch* s = source; s != source + length; s++) 
+        for (const Ch* s = source; s != source + length; s++)
             if (*s == '/')
                 tokenCount_++;
 
@@ -995,7 +995,7 @@ private:
                 }
 
                 i++;
-                
+
                 // Escaping "~0" -> '~', "~1" -> '/'
                 if (c == '~') {
                     if (i < length) {
@@ -1084,7 +1084,7 @@ private:
                     os.Put('~');
                     os.Put('1');
                 }
-                else if (uriFragment && NeedPercentEncode(c)) { 
+                else if (uriFragment && NeedPercentEncode(c)) {
                     // Transcode to UTF8 sequence
                     GenericStringStream<typename ValueType::EncodingType> source(&t->name[j]);
                     PercentEncodeStream<OutputStream> target(os);
@@ -1102,7 +1102,7 @@ private:
     //! A helper stream for decoding a percent-encoded sequence into code unit.
     /*!
         This stream decodes %XY triplet into code unit (0-255).
-        If it encounters invalid characters, it sets output code unit as 0 and 
+        If it encounters invalid characters, it sets output code unit as 0 and
         mark invalid, and to be checked by IsValid().
     */
     class PercentDecodeStream {

src/3rdparty/rapidjson/prettywriter.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_PRETTYWRITER_H_
@@ -55,11 +55,11 @@ public:
         \param allocator User supplied allocator. If it is null, it will create a private one.
         \param levelDepth Initial capacity of stack.
     */
-    explicit PrettyWriter(OutputStream& os, StackAllocator* allocator = 0, size_t levelDepth = Base::kDefaultLevelDepth) : 
+    explicit PrettyWriter(OutputStream& os, StackAllocator* allocator = 0, size_t levelDepth = Base::kDefaultLevelDepth) :
         Base(os, allocator, levelDepth), indentChar_(' '), indentCharCount_(4), formatOptions_(kFormatDefault) {}
 
 
-    explicit PrettyWriter(StackAllocator* allocator = 0, size_t levelDepth = Base::kDefaultLevelDepth) : 
+    explicit PrettyWriter(StackAllocator* allocator = 0, size_t levelDepth = Base::kDefaultLevelDepth) :
         Base(allocator, levelDepth), indentChar_(' '), indentCharCount_(4), formatOptions_(kFormatDefault) {}
 
 #if RAPIDJSON_HAS_CXX11_RVALUE_REFS
@@ -133,13 +133,13 @@ public:
         return Key(str.data(), SizeType(str.size()));
     }
 #endif
-	
+
     bool EndObject(SizeType memberCount = 0) {
         (void)memberCount;
         RAPIDJSON_ASSERT(Base::level_stack_.GetSize() >= sizeof(typename Base::Level)); // not inside an Object
         RAPIDJSON_ASSERT(!Base::level_stack_.template Top<typename Base::Level>()->inArray); // currently inside an Array, not Object
         RAPIDJSON_ASSERT(0 == Base::level_stack_.template Top<typename Base::Level>()->valueCount % 2); // Object has a Key without a Value
-       
+
         bool empty = Base::level_stack_.template Pop<typename Base::Level>(1)->valueCount == 0;
 
         if (!empty) {

src/3rdparty/rapidjson/rapidjson.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_RAPIDJSON_H_
@@ -17,7 +17,7 @@
 
 /*!\file rapidjson.h
     \brief common definitions and configuration
-    
+
     \see RAPIDJSON_CONFIG
  */
 
@@ -277,7 +277,7 @@
 #  elif defined(RAPIDJSON_DOXYGEN_RUNNING)
 #    define RAPIDJSON_ENDIAN
 #  else
-#    error Unknown machine endianness detected. User needs to define RAPIDJSON_ENDIAN.   
+#    error Unknown machine endianness detected. User needs to define RAPIDJSON_ENDIAN.
 #  endif
 #endif // RAPIDJSON_ENDIAN
 
@@ -462,7 +462,7 @@ RAPIDJSON_NAMESPACE_END
 #if defined(__GNUC__) || defined(__clang__)
 #define RAPIDJSON_STATIC_ASSERT_UNUSED_ATTRIBUTE __attribute__((unused))
 #else
-#define RAPIDJSON_STATIC_ASSERT_UNUSED_ATTRIBUTE 
+#define RAPIDJSON_STATIC_ASSERT_UNUSED_ATTRIBUTE
 #endif
 #ifndef __clang__
 //!@endcond
@@ -513,7 +513,7 @@ RAPIDJSON_NAMESPACE_END
 
 //!@cond RAPIDJSON_HIDDEN_FROM_DOXYGEN
 
-#define RAPIDJSON_MULTILINEMACRO_BEGIN do {  
+#define RAPIDJSON_MULTILINEMACRO_BEGIN do {
 #define RAPIDJSON_MULTILINEMACRO_END \
 } while((void)0, 0)
 
@@ -731,7 +731,7 @@ enum Type {
     kFalseType = 1,     //!< false
     kTrueType = 2,      //!< true
     kObjectType = 3,    //!< object
-    kArrayType = 4,     //!< array 
+    kArrayType = 4,     //!< array
     kStringType = 5,    //!< string
     kNumberType = 6     //!< number
 };

src/3rdparty/rapidjson/readme.md

@@ -203,8 +203,8 @@ in compliance with the License. You may obtain a copy of the License at
 
 http://opensource.org/licenses/MIT
 
-Unless required by applicable law or agreed to in writing, software distributed 
-under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+Unless required by applicable law or agreed to in writing, software distributed
+under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+CONDITIONS OF ANY KIND, either express or implied. See the License for the
 specific language governing permissions and limitations under the License.
 ```

src/3rdparty/rapidjson/schema.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available->
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip-> All rights reserved->
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource->org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied-> See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied-> See the License for the
 // specific language governing permissions and limitations under the License->
 
 #ifndef RAPIDJSON_SCHEMA_H_
@@ -256,10 +256,10 @@ public:
     bool Uint(unsigned u) { Number n; n.u.u = u; n.d = static_cast<double>(u); return WriteNumber(n); }
     bool Int64(int64_t i) { Number n; n.u.i = i; n.d = static_cast<double>(i); return WriteNumber(n); }
     bool Uint64(uint64_t u) { Number n; n.u.u = u; n.d = static_cast<double>(u); return WriteNumber(n); }
-    bool Double(double d) { 
-        Number n; 
+    bool Double(double d) {
+        Number n;
         if (d < 0) n.u.i = static_cast<int64_t>(d);
-        else       n.u.u = static_cast<uint64_t>(d); 
+        else       n.u.u = static_cast<uint64_t>(d);
         n.d = d;
         return WriteNumber(n);
     }
@@ -276,7 +276,7 @@ public:
 
     bool StartObject() { return true; }
     bool Key(const Ch* str, SizeType len, bool copy) { return String(str, len, copy); }
-    bool EndObject(SizeType memberCount) { 
+    bool EndObject(SizeType memberCount) {
         uint64_t h = Hash(0, kObjectType);
         uint64_t* kv = stack_.template Pop<uint64_t>(memberCount * 2);
         for (SizeType i = 0; i < memberCount; i++)
@@ -284,9 +284,9 @@ public:
         *stack_.template Push<uint64_t>() = h;
         return true;
     }
-    
+
     bool StartArray() { return true; }
-    bool EndArray(SizeType elementCount) { 
+    bool EndArray(SizeType elementCount) {
         uint64_t h = Hash(0, kArrayType);
         uint64_t* e = stack_.template Pop<uint64_t>(elementCount);
         for (SizeType i = 0; i < elementCount; i++)
@@ -313,9 +313,9 @@ private:
     };
 
     bool WriteType(Type type) { return WriteBuffer(type, 0, 0); }
-    
+
     bool WriteNumber(const Number& n) { return WriteBuffer(kNumberType, &n, sizeof(n)); }
-    
+
     bool WriteBuffer(Type type, const void* data, size_t len) {
         // FNV-1a from http://isthe.com/chongo/tech/comp/fnv/
         uint64_t h = Hash(RAPIDJSON_UINT64_C2(0x84222325, 0xcbf29ce4), type);
@@ -1987,7 +1987,7 @@ template <
     typename OutputHandler = BaseReaderHandler<typename SchemaDocumentType::SchemaType::EncodingType>,
     typename StateAllocator = CrtAllocator>
 class GenericSchemaValidator :
-    public internal::ISchemaStateFactory<typename SchemaDocumentType::SchemaType>, 
+    public internal::ISchemaStateFactory<typename SchemaDocumentType::SchemaType>,
     public internal::ISchemaValidator,
     public internal::IValidationErrorHandler<typename SchemaDocumentType::SchemaType> {
 public:
@@ -2008,7 +2008,7 @@ public:
     */
     GenericSchemaValidator(
         const SchemaDocumentType& schemaDocument,
-        StateAllocator* allocator = 0, 
+        StateAllocator* allocator = 0,
         size_t schemaStackCapacity = kDefaultSchemaStackCapacity,
         size_t documentStackCapacity = kDefaultDocumentStackCapacity)
         :
@@ -2040,7 +2040,7 @@ public:
     GenericSchemaValidator(
         const SchemaDocumentType& schemaDocument,
         OutputHandler& outputHandler,
-        StateAllocator* allocator = 0, 
+        StateAllocator* allocator = 0,
         size_t schemaStackCapacity = kDefaultSchemaStackCapacity,
         size_t documentStackCapacity = kDefaultDocumentStackCapacity)
         :
@@ -2390,7 +2390,7 @@ RAPIDJSON_MULTILINEMACRO_END
         RAPIDJSON_SCHEMA_HANDLE_PARALLEL_(StartObject, ());
         return valid_ = !outputHandler_ || outputHandler_->StartObject();
     }
-    
+
     bool Key(const Ch* str, SizeType len, bool copy) {
         if (!valid_) return false;
         AppendToken(str, len);
@@ -2398,7 +2398,7 @@ RAPIDJSON_MULTILINEMACRO_END
         RAPIDJSON_SCHEMA_HANDLE_PARALLEL_(Key, (str, len, copy));
         return valid_ = !outputHandler_ || outputHandler_->Key(str, len, copy);
     }
-    
+
     bool EndObject(SizeType memberCount) {
         if (!valid_) return false;
         RAPIDJSON_SCHEMA_HANDLE_PARALLEL_(EndObject, (memberCount));
@@ -2411,7 +2411,7 @@ RAPIDJSON_MULTILINEMACRO_END
         RAPIDJSON_SCHEMA_HANDLE_PARALLEL_(StartArray, ());
         return valid_ = !outputHandler_ || outputHandler_->StartArray();
     }
-    
+
     bool EndArray(SizeType elementCount) {
         if (!valid_) return false;
         RAPIDJSON_SCHEMA_HANDLE_PARALLEL_(EndArray, (elementCount));
@@ -2468,7 +2468,7 @@ private:
     typedef GenericValue<UTF8<>, StateAllocator> HashCodeArray;
     typedef internal::Hasher<EncodingType, StateAllocator> HasherType;
 
-    GenericSchemaValidator( 
+    GenericSchemaValidator(
         const SchemaDocumentType& schemaDocument,
         const SchemaType& root,
         const char* basePath, size_t basePathSize,
@@ -2554,7 +2554,7 @@ private:
 #endif
         void* hasher = CurrentContext().hasher;
         uint64_t h = hasher && CurrentContext().arrayUniqueness ? static_cast<HasherType*>(hasher)->GetHashCode() : 0;
-        
+
         PopSchema();
 
         if (!schemaStack_.Empty()) {
@@ -2603,7 +2603,7 @@ private:
     }
 
     RAPIDJSON_FORCEINLINE void PushSchema(const SchemaType& schema) { new (schemaStack_.template Push<Context>()) Context(*this, *this, &schema); }
-    
+
     RAPIDJSON_FORCEINLINE void PopSchema() {
         Context* c = schemaStack_.template Pop<Context>(1);
         if (HashCodeArray* a = static_cast<HashCodeArray*>(c->arrayElementHashCodes)) {

src/3rdparty/rapidjson/stringbuffer.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_STRINGBUFFER_H_

src/3rdparty/rapidjson/writer.h

@@ -1,5 +1,5 @@
 // Tencent is pleased to support the open source community by making RapidJSON available.
-// 
+//
 // Copyright (C) 2015 THL A29 Limited, a Tencent company, and Milo Yip.
 //
 // Licensed under the MIT License (the "License"); you may not use this file except
@@ -7,9 +7,9 @@
 //
 // http://opensource.org/licenses/MIT
 //
-// Unless required by applicable law or agreed to in writing, software distributed 
-// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 
-// CONDITIONS OF ANY KIND, either express or implied. See the License for the 
+// Unless required by applicable law or agreed to in writing, software distributed
+// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+// CONDITIONS OF ANY KIND, either express or implied. See the License for the
 // specific language governing permissions and limitations under the License.
 
 #ifndef RAPIDJSON_WRITER_H_
@@ -52,7 +52,7 @@ RAPIDJSON_NAMESPACE_BEGIN
 ///////////////////////////////////////////////////////////////////////////////
 // WriteFlag
 
-/*! \def RAPIDJSON_WRITE_DEFAULT_FLAGS 
+/*! \def RAPIDJSON_WRITE_DEFAULT_FLAGS
     \ingroup RAPIDJSON_CONFIG
     \brief User-defined kWriteDefaultFlags definition.
 
@@ -76,7 +76,7 @@ enum WriteFlag {
 
     User may programmatically calls the functions of a writer to generate JSON text.
 
-    On the other side, a writer can also be passed to objects that generates events, 
+    On the other side, a writer can also be passed to objects that generates events,
 
     for example Reader::Parse() and Document::Accept().
 
@@ -99,7 +99,7 @@ public:
         \param levelDepth Initial capacity of stack.
     */
     explicit
-    Writer(OutputStream& os, StackAllocator* stackAllocator = 0, size_t levelDepth = kDefaultLevelDepth) : 
+    Writer(OutputStream& os, StackAllocator* stackAllocator = 0, size_t levelDepth = kDefaultLevelDepth) :
         os_(&os), level_stack_(stackAllocator, levelDepth * sizeof(Level)), maxDecimalPlaces_(kDefaultMaxDecimalPlaces), hasRoot_(false) {}
 
     explicit
@@ -153,7 +153,7 @@ public:
     /*!
         This setting truncates the output with specified number of decimal places.
 
-        For example, 
+        For example,
 
         \code
         writer.SetMaxDecimalPlaces(3);
@@ -258,7 +258,7 @@ public:
     //! Simpler but slower overload.
     bool String(const Ch* const& str) { return String(str, internal::StrLen(str)); }
     bool Key(const Ch* const& str) { return Key(str, internal::StrLen(str)); }
-    
+
     //@}
 
     //! Write a raw JSON value.
@@ -426,7 +426,7 @@ protected:
                     PutUnsafe(*os_, hexDigits[(trail >> 12) & 15]);
                     PutUnsafe(*os_, hexDigits[(trail >>  8) & 15]);
                     PutUnsafe(*os_, hexDigits[(trail >>  4) & 15]);
-                    PutUnsafe(*os_, hexDigits[(trail      ) & 15]);                    
+                    PutUnsafe(*os_, hexDigits[(trail      ) & 15]);
                 }
             }
             else if ((sizeof(Ch) == 1 || static_cast<unsigned>(c) < 256) && RAPIDJSON_UNLIKELY(escape[static_cast<unsigned char>(c)]))  {
@@ -440,7 +440,7 @@ protected:
                     PutUnsafe(*os_, hexDigits[static_cast<unsigned char>(c) & 0xF]);
                 }
             }
-            else if (RAPIDJSON_UNLIKELY(!(writeFlags & kWriteValidateEncodingFlag ? 
+            else if (RAPIDJSON_UNLIKELY(!(writeFlags & kWriteValidateEncodingFlag ?
                 Transcoder<SourceEncoding, TargetEncoding>::Validate(is, *os_) :
                 Transcoder<SourceEncoding, TargetEncoding>::TranscodeUnsafe(is, *os_))))
                 return false;
@@ -463,7 +463,7 @@ protected:
         GenericStringStream<SourceEncoding> is(json);
         while (RAPIDJSON_LIKELY(is.Tell() < length)) {
             RAPIDJSON_ASSERT(is.Peek() != '\0');
-            if (RAPIDJSON_UNLIKELY(!(writeFlags & kWriteValidateEncodingFlag ? 
+            if (RAPIDJSON_UNLIKELY(!(writeFlags & kWriteValidateEncodingFlag ?
                 Transcoder<SourceEncoding, TargetEncoding>::Validate(is, *os_) :
                 Transcoder<SourceEncoding, TargetEncoding>::TranscodeUnsafe(is, *os_))))
                 return false;
@@ -476,7 +476,7 @@ protected:
         if (RAPIDJSON_LIKELY(level_stack_.GetSize() != 0)) { // this value is not at root
             Level* level = level_stack_.template Top<Level>();
             if (level->valueCount > 0) {
-                if (level->inArray) 
+                if (level->inArray)
                     os_->Put(','); // add comma if it is not the first element in array
                 else  // in object
                     os_->Put((level->valueCount % 2 == 0) ? ',' : ':');
@@ -564,7 +564,7 @@ inline bool Writer<StringBuffer>::WriteDouble(double d) {
         PutUnsafe(*os_, 'i'); PutUnsafe(*os_, 'n'); PutUnsafe(*os_, 'i'); PutUnsafe(*os_, 't'); PutUnsafe(*os_, 'y');
         return true;
     }
-    
+
     char *buffer = os_->Push(25);
     char* end = internal::dtoa(d, buffer, maxDecimalPlaces_);
     os_->Pop(static_cast<size_t>(25 - (end - buffer)));

src/Summary.cpp

@@ -1,12 +1,6 @@
 /* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2019 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2021 XMRig       <support@xmrig.com>
+ * Copyright (c) 2018-2022 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2022 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
@@ -22,7 +16,6 @@
  *   along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
-
 #include <cinttypes>
 #include <cstdio>
 #include <uv.h>
@@ -158,7 +151,7 @@ static void print_memory(const Config *config)
                        "", memory.id().data(), memory.size() / oneGiB, memory.type(), memory.speed() / 1000000ULL, memory.product().data());
         }
         else if (printEmpty) {
-            Log::print(WHITE_BOLD("   %-13s") "%s: " BLACK_BOLD("<empty>"), "", memory.slot().data());
+            Log::print(WHITE_BOLD("   %-13s") "%s: " BLACK_BOLD("<empty>"), "", memory.id().data());
         }
     }
 

src/Summary.h

@@ -1,12 +1,6 @@
 /* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2022 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2022 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

src/backend/common/Hashrate.cpp

@@ -53,6 +53,9 @@ xmrig::Hashrate::Hashrate(size_t threads) :
         m_timestamps[i] = new uint64_t[kBucketSize]();
         m_top[i]        = 0;
     }
+
+    m_earliestTimestamp = std::numeric_limits<uint64_t>::max();
+    m_totalCount = 0;
 }
 
 
@@ -66,6 +69,14 @@ xmrig::Hashrate::~Hashrate()
     delete [] m_counts;
     delete [] m_timestamps;
     delete [] m_top;
+
+}
+
+
+double xmrig::Hashrate::average() const
+{
+    const uint64_t ts = Chrono::steadyMSecs();
+    return (ts > m_earliestTimestamp) ? (m_totalCount * 1e3 / (ts - m_earliestTimestamp)) : 0.0;
 }
 
 
@@ -167,4 +178,11 @@ void xmrig::Hashrate::addData(size_t index, uint64_t count, uint64_t timestamp)
     m_timestamps[index][top] = timestamp;
 
     m_top[index] = (top + 1) & kBucketMask;
+
+    if (index == 0) {
+        if (m_earliestTimestamp == std::numeric_limits<uint64_t>::max()) {
+            m_earliestTimestamp = timestamp;
+        }
+        m_totalCount = count;
+    }
 }

src/backend/common/Hashrate.h

@@ -53,6 +53,8 @@ public:
     inline void add(size_t threadId, uint64_t count, uint64_t timestamp)    { addData(threadId + 1U, count, timestamp); }
     inline void add(uint64_t count, uint64_t timestamp)                     { addData(0U, count, timestamp); }
 
+    double average() const;
+
     static const char *format(double h, char *buf, size_t size);
     static rapidjson::Value normalize(double d);
 
@@ -72,6 +74,9 @@ private:
     uint32_t* m_top;
     uint64_t** m_counts;
     uint64_t** m_timestamps;
+
+    uint64_t m_earliestTimestamp;
+    uint64_t m_totalCount;
 };
 
 

src/backend/common/Worker.h

@@ -31,6 +31,8 @@ class Worker : public IWorker
 public:
     Worker(size_t id, int64_t affinity, int priority);
 
+    size_t threads() const override                         { return 1; }
+
 protected:
     inline int64_t affinity() const                         { return m_affinity; }
     inline size_t id() const override                       { return m_id; }

src/backend/common/WorkerJob.h

@@ -30,6 +30,7 @@
 
 
 #include "base/net/stratum/Job.h"
+#include "base/tools/Alignment.h"
 #include "crypto/common/Nonce.h"
 
 
@@ -77,7 +78,7 @@ public:
         }
         else {
             for (size_t i = 0; i < N; ++i) {
-                *nonce(i) += roundSize;
+                writeUnaligned(nonce(i), readUnaligned(nonce(i)) + roundSize);
             }
         }
 
@@ -108,7 +109,7 @@ private:
     }
 
 
-    alignas(16) uint8_t m_blobs[2][Job::kMaxBlobSize * N]{};
+    alignas(8) uint8_t m_blobs[2][Job::kMaxBlobSize * N]{};
     Job m_jobs[2];
     uint32_t m_rounds[2] = { 0, 0 };
     uint64_t m_nonce_mask[2] = { 0, 0 };
@@ -136,11 +137,11 @@ inline bool xmrig::WorkerJob<1>::nextRound(uint32_t rounds, uint32_t roundSize)
             return false;
         }
         if (nonceSize() == sizeof(uint64_t)) {
-            m_jobs[index()].nonce()[1] = n[1];
+            writeUnaligned(m_jobs[index()].nonce() + 1, readUnaligned(n + 1));
         }
     }
     else {
-        *n += roundSize;
+        writeUnaligned(n, readUnaligned(n) + roundSize);
     }
 
     return true;

src/backend/common/Workers.cpp

@@ -239,6 +239,9 @@ xmrig::IWorker *xmrig::Workers<CpuLaunchData>::create(Thread<CpuLaunchData> *han
 
     case 5:
         return new CpuWorker<5>(handle->id(), handle->config());
+
+    case 8:
+        return new CpuWorker<8>(handle->id(), handle->config());
     }
 
     return nullptr;

src/backend/common/interfaces/IWorker.h

@@ -46,6 +46,7 @@ public:
     virtual const VirtualMemory *memory() const                                                     = 0;
     virtual size_t id() const                                                                       = 0;
     virtual size_t intensity() const                                                                = 0;
+    virtual size_t threads() const                                                                  = 0;
     virtual void hashrateData(uint64_t &hashCount, uint64_t &timeStamp, uint64_t &rawHashes) const  = 0;
     virtual void jobEarlyNotification(const Job &job)                                               = 0;
     virtual void start()                                                                            = 0;

src/backend/cpu/CpuBackend.cpp

@@ -76,18 +76,20 @@ public:
     {
         m_workersMemory.clear();
         m_hugePages.reset();
-        m_memory    = memory;
-        m_started   = 0;
-        m_errors    = 0;
-        m_threads   = threads.size();
-        m_ways      = 0;
-        m_ts        = Chrono::steadyMSecs();
+        m_memory       = memory;
+        m_started      = 0;
+        m_totalStarted = 0;
+        m_errors       = 0;
+        m_threads      = threads.size();
+        m_ways         = 0;
+        m_ts           = Chrono::steadyMSecs();
     }
 
     inline bool started(IWorker *worker, bool ready)
     {
         if (ready) {
             m_started++;
+            m_totalStarted += worker->threads();
 
             if (m_workersMemory.insert(worker->memory()).second) {
                 m_hugePages += worker->memory()->hugePages();
@@ -112,7 +114,7 @@ public:
         LOG_INFO("%s" GREEN_BOLD(" READY") " threads %s%zu/%zu (%zu)" CLEAR " huge pages %s%1.0f%% %zu/%zu" CLEAR " memory " CYAN_BOLD("%zu KB") BLACK_BOLD(" (%" PRIu64 " ms)"),
                  Tags::cpu(),
                  m_errors == 0 ? CYAN_BOLD_S : YELLOW_BOLD_S,
-                 m_started, m_threads, m_ways,
+                 m_totalStarted, std::max(m_totalStarted, m_threads), m_ways,
                  (m_hugePages.isFullyAllocated() ? GREEN_BOLD_S : (m_hugePages.allocated == 0 ? RED_BOLD_S : YELLOW_BOLD_S)),
                  m_hugePages.percent(),
                  m_hugePages.allocated, m_hugePages.total,
@@ -127,6 +129,7 @@ private:
     size_t m_errors       = 0;
     size_t m_memory       = 0;
     size_t m_started      = 0;
+    size_t m_totalStarted = 0;
     size_t m_threads      = 0;
     size_t m_ways         = 0;
     uint64_t m_ts         = 0;
@@ -433,10 +436,6 @@ rapidjson::Value xmrig::CpuBackend::toJSON(rapidjson::Document &doc) const
     out.AddMember("argon2-impl", argon2::Impl::name().toJSON(), allocator);
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    out.AddMember("astrobwt-max-size", cpu.astrobwtMaxSize(), allocator);
-#   endif
-
     out.AddMember("hugepages", d_ptr->hugePages(2, doc), allocator);
     out.AddMember("memory",    static_cast<uint64_t>(d_ptr->algo.isValid() ? (d_ptr->ways() * d_ptr->algo.l3()) : 0), allocator);
 

src/backend/cpu/CpuConfig.cpp

@@ -45,11 +45,6 @@ const char *CpuConfig::kAsm                 = "asm";
 const char *CpuConfig::kArgon2Impl          = "argon2-impl";
 #endif
 
-#ifdef XMRIG_ALGO_ASTROBWT
-const char *CpuConfig::kAstroBWTMaxSize     = "astrobwt-max-size";
-const char *CpuConfig::kAstroBWTAVX2        = "astrobwt-avx2";
-#endif
-
 
 extern template class Threads<CpuThreads>;
 
@@ -89,11 +84,6 @@ rapidjson::Value xmrig::CpuConfig::toJSON(rapidjson::Document &doc) const
     obj.AddMember(StringRef(kArgon2Impl), m_argon2Impl.toJSON(), allocator);
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    obj.AddMember(StringRef(kAstroBWTMaxSize),  m_astrobwtMaxSize, allocator);
-    obj.AddMember(StringRef(kAstroBWTAVX2),     m_astrobwtAVX2, allocator);
-#   endif
-
     m_threads.toJSON(obj, doc);
 
     return obj;
@@ -122,8 +112,15 @@ std::vector<xmrig::CpuLaunchData> xmrig::CpuConfig::get(const Miner *miner, cons
     const size_t count = threads.count();
     out.reserve(count);
 
+    std::vector<int64_t> affinities;
+    affinities.reserve(count);
+
+    for (const auto& thread : threads.data()) {
+        affinities.emplace_back(thread.affinity());
+    }
+
     for (const auto &thread : threads.data()) {
-        out.emplace_back(miner, algorithm, *this, thread, count);
+        out.emplace_back(miner, algorithm, *this, thread, count, affinities);
     }
 
     return out;
@@ -151,24 +148,6 @@ void xmrig::CpuConfig::read(const rapidjson::Value &value)
         m_argon2Impl = Json::getString(value, kArgon2Impl);
 #       endif
 
-#       ifdef XMRIG_ALGO_ASTROBWT
-        const auto& astroBWTMaxSize = Json::getValue(value, kAstroBWTMaxSize);
-        if (astroBWTMaxSize.IsNull() || !astroBWTMaxSize.IsInt()) {
-            m_shouldSave = true;
-        }
-        else {
-            m_astrobwtMaxSize = std::min(std::max(astroBWTMaxSize.GetInt(), 400), 1200);
-        }
-
-        const auto& astroBWTAVX2 = Json::getValue(value, kAstroBWTAVX2);
-        if (astroBWTAVX2.IsNull() || !astroBWTAVX2.IsBool()) {
-            m_shouldSave = true;
-        }
-        else {
-            m_astrobwtAVX2 = astroBWTAVX2.GetBool();
-        }
-#       endif
-
         m_threads.read(value);
 
         generate();
@@ -199,7 +178,7 @@ void xmrig::CpuConfig::generate()
     count += xmrig::generate<Algorithm::CN_FEMTO>(m_threads, m_limit);
     count += xmrig::generate<Algorithm::RANDOM_X>(m_threads, m_limit);
     count += xmrig::generate<Algorithm::ARGON2>(m_threads, m_limit);
-    count += xmrig::generate<Algorithm::ASTROBWT>(m_threads, m_limit);
+    count += xmrig::generate<Algorithm::GHOSTRIDER>(m_threads, m_limit);
 
     m_shouldSave |= count > 0;
 }

src/backend/cpu/CpuConfig.h

@@ -56,11 +56,6 @@ public:
     static const char *kArgon2Impl;
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    static const char *kAstroBWTMaxSize;
-    static const char *kAstroBWTAVX2;
-#   endif
-
     CpuConfig() = default;
 
     bool isHwAES() const;
@@ -69,7 +64,6 @@ public:
     std::vector<CpuLaunchData> get(const Miner *miner, const Algorithm &algorithm) const;
     void read(const rapidjson::Value &value);
 
-    inline bool astrobwtAVX2() const                    { return m_astrobwtAVX2; }
     inline bool isEnabled() const                       { return m_enabled; }
     inline bool isHugePages() const                     { return m_hugePageSize > 0; }
     inline bool isHugePagesJit() const                  { return m_hugePagesJit; }
@@ -78,7 +72,6 @@ public:
     inline const Assembly &assembly() const             { return m_assembly; }
     inline const String &argon2Impl() const             { return m_argon2Impl; }
     inline const Threads<CpuThreads> &threads() const   { return m_threads; }
-    inline int astrobwtMaxSize() const                  { return m_astrobwtMaxSize; }
     inline int priority() const                         { return m_priority; }
     inline size_t hugePageSize() const                  { return m_hugePageSize * 1024U; }
     inline uint32_t limit() const                       { return m_limit; }
@@ -96,12 +89,10 @@ private:
 
     AesMode m_aes           = AES_AUTO;
     Assembly m_assembly;
-    bool m_astrobwtAVX2     = false;
     bool m_enabled          = true;
     bool m_hugePagesJit     = false;
     bool m_shouldSave       = false;
     bool m_yield            = true;
-    int m_astrobwtMaxSize   = 550;
     int m_memoryPool        = 0;
     int m_priority          = -1;
     size_t m_hugePageSize   = kDefaultHugePageSizeKb;

src/backend/cpu/CpuConfig_gen.h

@@ -153,14 +153,15 @@ size_t inline generate<Algorithm::ARGON2>(Threads<CpuThreads> &threads, uint32_t
 #endif
 
 
-#ifdef XMRIG_ALGO_ASTROBWT
+#ifdef XMRIG_ALGO_GHOSTRIDER
 template<>
-size_t inline generate<Algorithm::ASTROBWT>(Threads<CpuThreads>& threads, uint32_t limit)
+size_t inline generate<Algorithm::GHOSTRIDER>(Threads<CpuThreads>& threads, uint32_t limit)
 {
-    return generate(Algorithm::kASTROBWT, threads, Algorithm::ASTROBWT_DERO, limit);
+    return generate(Algorithm::kGHOSTRIDER, threads, Algorithm::GHOSTRIDER_RTM, limit);
 }
 #endif
 
+
 } /* namespace xmrig */
 
 

src/backend/cpu/CpuLaunchData.cpp

@@ -32,19 +32,18 @@
 #include <algorithm>
 
 
-xmrig::CpuLaunchData::CpuLaunchData(const Miner *miner, const Algorithm &algorithm, const CpuConfig &config, const CpuThread &thread, size_t threads) :
+xmrig::CpuLaunchData::CpuLaunchData(const Miner *miner, const Algorithm &algorithm, const CpuConfig &config, const CpuThread &thread, size_t threads, const std::vector<int64_t>& affinities) :
     algorithm(algorithm),
     assembly(config.assembly()),
-    astrobwtAVX2(config.astrobwtAVX2()),
     hugePages(config.isHugePages()),
     hwAES(config.isHwAES()),
     yield(config.isYield()),
-    astrobwtMaxSize(config.astrobwtMaxSize()),    
     priority(config.priority()),
     affinity(thread.affinity()),
     miner(miner),
     threads(threads),
-    intensity(std::min<uint32_t>(thread.intensity(), algorithm.maxIntensity()))
+    intensity(std::max<uint32_t>(std::min<uint32_t>(thread.intensity(), algorithm.maxIntensity()), algorithm.minIntensity())),
+    affinities(affinities)
 {
 }
 

src/backend/cpu/CpuLaunchData.h

@@ -44,7 +44,7 @@ class Miner;
 class CpuLaunchData
 {
 public:
-    CpuLaunchData(const Miner *miner, const Algorithm &algorithm, const CpuConfig &config, const CpuThread &thread, size_t threads);
+    CpuLaunchData(const Miner *miner, const Algorithm &algorithm, const CpuConfig &config, const CpuThread &thread, size_t threads, const std::vector<int64_t>& affinities);
 
     bool isEqual(const CpuLaunchData &other) const;
     CnHash::AlgoVariant av() const;
@@ -58,16 +58,15 @@ public:
 
     const Algorithm algorithm;
     const Assembly assembly;
-    const bool astrobwtAVX2;
     const bool hugePages;
     const bool hwAES;
     const bool yield;
-    const int astrobwtMaxSize;
     const int priority;
     const int64_t affinity;
     const Miner *miner;
     const size_t threads;
     const uint32_t intensity;
+    const std::vector<int64_t> affinities;
 };
 
 

src/backend/cpu/CpuThread.h

@@ -41,7 +41,7 @@ public:
     CpuThread(const rapidjson::Value &value);
 
     inline bool isEqual(const CpuThread &other) const       { return other.m_affinity == m_affinity && other.m_intensity == m_intensity; }
-    inline bool isValid() const                             { return m_intensity <= 5; }
+    inline bool isValid() const                             { return m_intensity <= 8; }
     inline int64_t affinity() const                         { return m_affinity; }
     inline uint32_t intensity() const                       { return m_intensity == 0 ? 1 : m_intensity; }
 

src/backend/cpu/CpuWorker.cpp

@@ -23,6 +23,7 @@
 
 #include "backend/cpu/Cpu.h"
 #include "backend/cpu/CpuWorker.h"
+#include "base/tools/Alignment.h"
 #include "base/tools/Chrono.h"
 #include "core/config/Config.h"
 #include "core/Miner.h"
@@ -34,6 +35,7 @@
 #include "crypto/rx/Rx.h"
 #include "crypto/rx/RxDataset.h"
 #include "crypto/rx/RxVm.h"
+#include "crypto/ghostrider/ghostrider.h"
 #include "net/JobResults.h"
 
 
@@ -42,11 +44,6 @@
 #endif
 
 
-#ifdef XMRIG_ALGO_ASTROBWT
-#   include "crypto/astrobwt/AstroBWT.h"
-#endif
-
-
 #ifdef XMRIG_FEATURE_BENCHMARK
 #   include "backend/common/benchmark/BenchState.h"
 #endif
@@ -71,18 +68,20 @@ xmrig::CpuWorker<N>::CpuWorker(size_t id, const CpuLaunchData &data) :
     Worker(id, data.affinity, data.priority),
     m_algorithm(data.algorithm),
     m_assembly(data.assembly),
-    m_astrobwtAVX2(data.astrobwtAVX2),
     m_hwAES(data.hwAES),
     m_yield(data.yield),
     m_av(data.av()),
-    m_astrobwtMaxSize(data.astrobwtMaxSize * 1000),
     m_miner(data.miner),
     m_threads(data.threads),
     m_ctx()
 {
 #   ifdef XMRIG_ALGO_CN_HEAVY
     // cn-heavy optimization for Zen3 CPUs
-    if ((N == 1) && (m_av == CnHash::AV_SINGLE) && (m_algorithm.family() == Algorithm::CN_HEAVY) && (m_assembly != Assembly::NONE) && (Cpu::info()->arch() == ICpuInfo::ARCH_ZEN3)) {
+    const auto arch = Cpu::info()->arch();
+    const uint32_t model = Cpu::info()->model();
+    const bool is_vermeer = (arch == ICpuInfo::ARCH_ZEN3) && (model == 0x21);
+    const bool is_raphael = (arch == ICpuInfo::ARCH_ZEN4) && (model == 0x61);
+    if ((N == 1) && (m_av == CnHash::AV_SINGLE) && (m_algorithm.family() == Algorithm::CN_HEAVY) && (m_assembly != Assembly::NONE) && (is_vermeer || is_raphael)) {
         std::lock_guard<std::mutex> lock(cn_heavyZen3MemoryMutex);
         if (!cn_heavyZen3Memory) {
             // Round up number of threads to the multiple of 8
@@ -96,6 +95,10 @@ xmrig::CpuWorker<N>::CpuWorker(size_t id, const CpuLaunchData &data) :
     {
         m_memory = new VirtualMemory(m_algorithm.l3() * N, data.hugePages, false, true, node());
     }
+
+#   ifdef XMRIG_ALGO_GHOSTRIDER
+    m_ghHelper = ghostrider::create_helper_thread(affinity(), data.priority, data.affinities);
+#   endif
 }
 
 
@@ -114,6 +117,10 @@ xmrig::CpuWorker<N>::~CpuWorker()
     {
         delete m_memory;
     }
+
+#   ifdef XMRIG_ALGO_GHOSTRIDER
+    ghostrider::destroy_helper_thread(m_ghHelper);
+#   endif
 }
 
 
@@ -124,7 +131,7 @@ void xmrig::CpuWorker<N>::allocateRandomX_VM()
     RxDataset *dataset = Rx::dataset(m_job.currentJob(), node());
 
     while (dataset == nullptr) {
-        std::this_thread::sleep_for(std::chrono::milliseconds(200));
+        std::this_thread::sleep_for(std::chrono::milliseconds(20));
 
         if (Nonce::sequence(Nonce::CPU) == 0) {
             return;
@@ -153,6 +160,12 @@ bool xmrig::CpuWorker<N>::selfTest()
 
     allocateCnCtx();
 
+#   ifdef XMRIG_ALGO_GHOSTRIDER
+    if (m_algorithm.family() == Algorithm::GHOSTRIDER) {
+        return (N == 8) && verify(Algorithm::GHOSTRIDER_RTM, test_output_gr);
+    }
+#   endif
+
     if (m_algorithm.family() == Algorithm::CN) {
         const bool rc = verify(Algorithm::CN_0,      test_output_v0)   &&
                         verify(Algorithm::CN_1,      test_output_v1)   &&
@@ -206,12 +219,6 @@ bool xmrig::CpuWorker<N>::selfTest()
     }
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    if (m_algorithm.family() == Algorithm::ASTROBWT) {
-        return verify(Algorithm::ASTROBWT_DERO, astrobwt_dero_test_out);
-    }
-#   endif
-
     return false;
 }
 
@@ -230,7 +237,7 @@ void xmrig::CpuWorker<N>::start()
     while (Nonce::sequence(Nonce::CPU) > 0) {
         if (Nonce::isPaused()) {
             do {
-                std::this_thread::sleep_for(std::chrono::milliseconds(200));
+                std::this_thread::sleep_for(std::chrono::milliseconds(20));
             }
             while (Nonce::isPaused() && Nonce::sequence(Nonce::CPU) > 0);
 
@@ -255,7 +262,7 @@ void xmrig::CpuWorker<N>::start()
 
             uint32_t current_job_nonces[N];
             for (size_t i = 0; i < N; ++i) {
-                current_job_nonces[i] = *m_job.nonce(i);
+                current_job_nonces[i] = readUnaligned(m_job.nonce(i));
             }
 
 #           ifdef XMRIG_FEATURE_BENCHMARK
@@ -299,16 +306,22 @@ void xmrig::CpuWorker<N>::start()
             else
 #           endif
             {
-#               ifdef XMRIG_ALGO_ASTROBWT
-                if (job.algorithm().family() == Algorithm::ASTROBWT) {
-                    if (!astrobwt::astrobwt_dero(m_job.blob(), job.size(), m_ctx[0]->memory, m_hash, m_astrobwtMaxSize, m_astrobwtAVX2)) {
+                switch (job.algorithm().family()) {
+
+#               ifdef XMRIG_ALGO_GHOSTRIDER
+                case Algorithm::GHOSTRIDER:
+                    if (N == 8) {
+                        ghostrider::hash_octa(m_job.blob(), job.size(), m_hash, m_ctx, m_ghHelper);
+                    }
+                    else {
                         valid = false;
                     }
-                }
-                else
+                    break;
 #               endif
-                {
+
+                default:
                     fn(job.algorithm())(m_job.blob(), job.size(), m_hash, m_ctx, job.height());
+                    break;
                 }
 
                 if (!nextRound()) {
@@ -367,6 +380,37 @@ bool xmrig::CpuWorker<N>::nextRound()
 template<size_t N>
 bool xmrig::CpuWorker<N>::verify(const Algorithm &algorithm, const uint8_t *referenceValue)
 {
+#   ifdef XMRIG_ALGO_GHOSTRIDER
+    if (algorithm == Algorithm::GHOSTRIDER_RTM) {
+        uint8_t blob[N * 80] = {};
+        for (size_t i = 0; i < N; ++i) {
+            blob[i * 80 + 0] = static_cast<uint8_t>(i);
+            blob[i * 80 + 4] = 0x10;
+            blob[i * 80 + 5] = 0x02;
+        }
+
+        uint8_t hash1[N * 32] = {};
+        ghostrider::hash_octa(blob, 80, hash1, m_ctx, 0, false);
+
+        for (size_t i = 0; i < N; ++i) {
+            blob[i * 80 + 0] = static_cast<uint8_t>(i);
+            blob[i * 80 + 4] = 0x43;
+            blob[i * 80 + 5] = 0x05;
+        }
+
+        uint8_t hash2[N * 32] = {};
+        ghostrider::hash_octa(blob, 80, hash2, m_ctx, 0, false);
+
+        for (size_t i = 0; i < N * 32; ++i) {
+            if ((hash1[i] ^ hash2[i]) != referenceValue[i]) {
+                return false;
+            }
+        }
+
+        return true;
+    }
+#   endif
+
     cn_hash_fun func = fn(algorithm);
     if (!func) {
         return false;
@@ -483,6 +527,7 @@ template class CpuWorker<2>;
 template class CpuWorker<3>;
 template class CpuWorker<4>;
 template class CpuWorker<5>;
+template class CpuWorker<8>;
 
 } // namespace xmrig
 

src/backend/cpu/CpuWorker.h

@@ -38,6 +38,11 @@ namespace xmrig {
 class RxVm;
 
 
+#ifdef XMRIG_ALGO_GHOSTRIDER
+namespace ghostrider { struct HelperThread; }
+#endif
+
+
 template<size_t N>
 class CpuWorker : public Worker
 {
@@ -47,6 +52,15 @@ public:
     CpuWorker(size_t id, const CpuLaunchData &data);
     ~CpuWorker() override;
 
+    size_t threads() const override
+    {
+#       ifdef XMRIG_ALGO_GHOSTRIDER
+        return ((m_algorithm.family() == Algorithm::GHOSTRIDER) && m_ghHelper) ? 2 : 1;
+#       else
+        return 1;
+#       endif
+    }
+
 protected:
     bool selfTest() override;
     void hashrateData(uint64_t &hashCount, uint64_t &timeStamp, uint64_t &rawHashes) const override;
@@ -69,14 +83,12 @@ private:
     void allocateCnCtx();
     void consumeJob();
 
-    alignas(16) uint8_t m_hash[N * 32]{ 0 };
+    alignas(8) uint8_t m_hash[N * 32]{ 0 };
     const Algorithm m_algorithm;
     const Assembly m_assembly;
-    const bool m_astrobwtAVX2;
     const bool m_hwAES;
     const bool m_yield;
     const CnHash::AlgoVariant m_av;
-    const int m_astrobwtMaxSize;
     const Miner *m_miner;
     const size_t m_threads;
     cryptonight_ctx *m_ctx[N];
@@ -87,6 +99,10 @@ private:
     randomx_vm *m_vm        = nullptr;
 #   endif
 
+#   ifdef XMRIG_ALGO_GHOSTRIDER
+    ghostrider::HelperThread* m_ghHelper = nullptr;
+#   endif
+
 #   ifdef XMRIG_FEATURE_BENCHMARK
     uint32_t m_benchSize    = 0;
 #   endif
@@ -102,6 +118,7 @@ extern template class CpuWorker<2>;
 extern template class CpuWorker<3>;
 extern template class CpuWorker<4>;
 extern template class CpuWorker<5>;
+extern template class CpuWorker<8>;
 
 
 } // namespace xmrig

src/backend/cpu/interfaces/ICpuInfo.h

@@ -45,22 +45,25 @@ public:
         ARCH_ZEN,
         ARCH_ZEN_PLUS,
         ARCH_ZEN2,
-        ARCH_ZEN3
+        ARCH_ZEN3,
+        ARCH_ZEN4
     };
 
     enum MsrMod : uint32_t {
         MSR_MOD_NONE,
         MSR_MOD_RYZEN_17H,
         MSR_MOD_RYZEN_19H,
+        MSR_MOD_RYZEN_19H_ZEN4,
         MSR_MOD_INTEL,
         MSR_MOD_CUSTOM,
         MSR_MOD_MAX
     };
 
-#   define MSR_NAMES_LIST "none", "ryzen_17h", "ryzen_19h", "intel", "custom"
+#   define MSR_NAMES_LIST "none", "ryzen_17h", "ryzen_19h", "ryzen_19h_zen4", "intel", "custom"
 
     enum Flag : uint32_t {
         FLAG_AES,
+        FLAG_VAES,
         FLAG_AVX,
         FLAG_AVX2,
         FLAG_AVX512F,
@@ -90,6 +93,7 @@ public:
     virtual Assembly::Id assembly() const                                           = 0;
     virtual bool has(Flag feature) const                                            = 0;
     virtual bool hasAES() const                                                     = 0;
+    virtual bool hasVAES() const                                                    = 0;
     virtual bool hasAVX() const                                                     = 0;
     virtual bool hasAVX2() const                                                    = 0;
     virtual bool hasBMI2() const                                                    = 0;
@@ -111,6 +115,7 @@ public:
     virtual size_t packages() const                                                 = 0;
     virtual size_t threads() const                                                  = 0;
     virtual Vendor vendor() const                                                   = 0;
+    virtual uint32_t model() const                                                  = 0;
 };
 
 

src/backend/cpu/platform/BasicCpuInfo.cpp

@@ -30,6 +30,12 @@
 #endif
 
 
+#include "crypto/cn/CryptoNight_monero.h"
+#ifdef XMRIG_VAES
+#   include "crypto/cn/CryptoNight_x86_vaes.h"
+#endif
+
+
 #include "backend/cpu/platform/BasicCpuInfo.h"
 #include "3rdparty/rapidjson/document.h"
 #include "crypto/common/Assembly.h"
@@ -52,13 +58,13 @@
 namespace xmrig {
 
 
-constexpr size_t kCpuFlagsSize                                  = 14;
-static const std::array<const char *, kCpuFlagsSize> flagNames  = { "aes", "avx", "avx2", "avx512f", "bmi2", "osxsave", "pdpe1gb", "sse2", "ssse3", "sse4.1", "xop", "popcnt", "cat_l3", "vm" };
+constexpr size_t kCpuFlagsSize                                  = 15;
+static const std::array<const char *, kCpuFlagsSize> flagNames  = { "aes", "vaes", "avx", "avx2", "avx512f", "bmi2", "osxsave", "pdpe1gb", "sse2", "ssse3", "sse4.1", "xop", "popcnt", "cat_l3", "vm" };
 static_assert(kCpuFlagsSize == ICpuInfo::FLAG_MAX, "kCpuFlagsSize and FLAG_MAX mismatch");
 
 
 #ifdef XMRIG_FEATURE_MSR
-constexpr size_t kMsrArraySize                                  = 5;
+constexpr size_t kMsrArraySize                                  = 6;
 static const std::array<const char *, kMsrArraySize> msrNames   = { MSR_NAMES_LIST };
 static_assert(kMsrArraySize == ICpuInfo::MSR_MOD_MAX, "kMsrArraySize and MSR_MOD_MAX mismatch");
 #endif
@@ -140,6 +146,7 @@ static inline bool has_osxsave()    { return has_feature(PROCESSOR_INFO,
 static inline bool has_aes_ni()     { return has_feature(PROCESSOR_INFO,        ECX_Reg, 1 << 25); }
 static inline bool has_avx()        { return has_feature(PROCESSOR_INFO,        ECX_Reg, 1 << 28) && has_osxsave() && has_xcr_avx(); }
 static inline bool has_avx2()       { return has_feature(EXTENDED_FEATURES,     EBX_Reg, 1 << 5) && has_osxsave() && has_xcr_avx(); }
+static inline bool has_vaes()       { return has_feature(EXTENDED_FEATURES,     ECX_Reg, 1 << 9) && has_osxsave() && has_xcr_avx(); }
 static inline bool has_avx512f()    { return has_feature(EXTENDED_FEATURES,     EBX_Reg, 1 << 16) && has_osxsave() && has_xcr_avx512(); }
 static inline bool has_bmi2()       { return has_feature(EXTENDED_FEATURES,     EBX_Reg, 1 << 8); }
 static inline bool has_pdpe1gb()    { return has_feature(PROCESSOR_EXT_INFO,    EDX_Reg, 1 << 26); }
@@ -178,6 +185,7 @@ xmrig::BasicCpuInfo::BasicCpuInfo() :
     m_flags.set(FLAG_AES,     has_aes_ni());
     m_flags.set(FLAG_AVX,     has_avx());
     m_flags.set(FLAG_AVX2,    has_avx2());
+    m_flags.set(FLAG_VAES,    has_vaes());
     m_flags.set(FLAG_AVX512F, has_avx512f());
     m_flags.set(FLAG_BMI2,    has_bmi2());
     m_flags.set(FLAG_OSXSAVE, has_osxsave());
@@ -242,8 +250,14 @@ xmrig::BasicCpuInfo::BasicCpuInfo() :
                     break;
 
                 case 0x19:
-                    m_arch = ARCH_ZEN3;
-                    m_msrMod = MSR_MOD_RYZEN_19H;
+                    if (m_model == 0x61) {
+                        m_arch = ARCH_ZEN4;
+                        m_msrMod = MSR_MOD_RYZEN_19H_ZEN4;
+                    }
+                    else {
+                        m_arch = ARCH_ZEN3;
+                        m_msrMod = MSR_MOD_RYZEN_19H;
+                    }
                     break;
 
                 default:
@@ -292,6 +306,9 @@ xmrig::BasicCpuInfo::BasicCpuInfo() :
         }
     }
 #   endif
+
+    cn_sse41_enabled = has(FLAG_SSE41);
+    cn_vaes_enabled = has(FLAG_VAES);
 }
 
 
@@ -351,13 +368,9 @@ xmrig::CpuThreads xmrig::BasicCpuInfo::threads(const Algorithm &algorithm, uint3
     }
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    if (f == Algorithm::ASTROBWT) {
-        CpuThreads threads;
-        for (size_t i = 0; i < count; ++i) {
-            threads.add(i, 0);
-        }
-        return threads;
+#   ifdef XMRIG_ALGO_GHOSTRIDER
+    if (f == Algorithm::GHOSTRIDER) {
+        return CpuThreads(std::max<size_t>(count / 2, 1), 8);
     }
 #   endif
 

src/backend/cpu/platform/BasicCpuInfo.h

@@ -44,6 +44,7 @@ protected:
     inline Assembly::Id assembly() const override               { return m_assembly; }
     inline bool has(Flag flag) const override                   { return m_flags.test(flag); }
     inline bool hasAES() const override                         { return has(FLAG_AES); }
+    inline bool hasVAES() const override                        { return has(FLAG_VAES); }
     inline bool hasAVX() const override                         { return has(FLAG_AVX); }
     inline bool hasAVX2() const override                        { return has(FLAG_AVX2); }
     inline bool hasBMI2() const override                        { return has(FLAG_BMI2); }
@@ -62,6 +63,14 @@ protected:
     inline size_t packages() const override                     { return 1; }
     inline size_t threads() const override                      { return m_threads; }
     inline Vendor vendor() const override                       { return m_vendor; }
+    inline uint32_t model() const override
+    {
+#   ifndef XMRIG_ARM
+        return m_model;
+#   else
+        return 0;
+#   endif
+    }
 
 protected:
     Arch m_arch             = ARCH_UNKNOWN;

src/backend/cpu/platform/BasicCpuInfo_arm.cpp

@@ -33,7 +33,7 @@
 #       include <stdint.h>
 #       include <machine/armreg.h>
 #       ifndef ID_AA64ISAR0_AES_VAL
-#           define ID_AA64ISAR0_AES_VAL ID_AA64ISAR0_AES        
+#           define ID_AA64ISAR0_AES_VAL ID_AA64ISAR0_AES
 #       endif
 #   endif
 #endif
@@ -99,8 +99,14 @@ const char *xmrig::BasicCpuInfo::backend() const
 }
 
 
-xmrig::CpuThreads xmrig::BasicCpuInfo::threads(const Algorithm &, uint32_t) const
+xmrig::CpuThreads xmrig::BasicCpuInfo::threads(const Algorithm &algorithm, uint32_t) const
 {
+#   ifdef XMRIG_ALGO_GHOSTRIDER
+    if (algorithm.family() == Algorithm::GHOSTRIDER) {
+        return CpuThreads(threads(), 8);
+    }
+#   endif
+
     return CpuThreads(threads());
 }
 

src/backend/cpu/platform/HwlocCpuInfo.cpp

@@ -216,12 +216,6 @@ bool xmrig::HwlocCpuInfo::membind(hwloc_const_bitmap_t nodeset)
 
 xmrig::CpuThreads xmrig::HwlocCpuInfo::threads(const Algorithm &algorithm, uint32_t limit) const
 {
-#   ifdef XMRIG_ALGO_ASTROBWT
-    if (algorithm == Algorithm::ASTROBWT_DERO) {
-        return allThreads(algorithm, limit);
-    }
-#   endif
-
 #   ifndef XMRIG_ARM
     if (L2() == 0 && L3() == 0) {
         return BasicCpuInfo::threads(algorithm, limit);
@@ -275,8 +269,10 @@ xmrig::CpuThreads xmrig::HwlocCpuInfo::allThreads(const Algorithm &algorithm, ui
     CpuThreads threads;
     threads.reserve(m_threads);
 
+    const uint32_t intensity = (algorithm.family() == Algorithm::GHOSTRIDER) ? 8 : 0;
+
     for (const int32_t pu : m_units) {
-        threads.add(pu, 0);
+        threads.add(pu, intensity);
     }
 
     if (threads.isEmpty()) {
@@ -302,12 +298,24 @@ 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); });
 
+#   ifdef XMRIG_ALGO_GHOSTRIDER
+    if ((algorithm == Algorithm::GHOSTRIDER_RTM) && (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());
+
+        // This shouldn't happen, but check it anyway
+        if (cores.empty()) {
+            findByType(cache, HWLOC_OBJ_CORE, [&cores](hwloc_obj_t found) { cores.emplace_back(found); });
+        }
+    }
+#   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;
-    const size_t scratchpad = algorithm.l3();
+    size_t scratchpad       = algorithm.l3();
     uint32_t intensity      = algorithm.maxIntensity() == 1 ? 0 : 1;
 
     if (cache->attr->cache.depth == 3) {
@@ -350,6 +358,15 @@ void xmrig::HwlocCpuInfo::processTopLevelCache(hwloc_obj_t cache, const Algorith
         cacheHashes = std::min(cacheHashes, limit);
     }
 
+#   ifdef XMRIG_ALGO_GHOSTRIDER
+    if (algorithm == Algorithm::GHOSTRIDER_RTM) {
+        // GhostRider implementation runs 8 hashes at a time
+        intensity = 8;
+        // Always 1 thread per core (it uses additional helper thread when possible)
+        cacheHashes = std::min(cacheHashes, cores.size());
+    }
+#   endif
+
     if (cacheHashes >= PUs) {
         for (hwloc_obj_t core : cores) {
             const std::vector<hwloc_obj_t> units = findByType(core, HWLOC_OBJ_PU);