Merge f0f6d1666c into e1ae367084

Detect AMD engineering samples in randomx_boost.sh

CMakeLists.txt

@@ -32,6 +32,7 @@ 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)
+option(WITH_BUNDLED_FMT     "Force use of bundled fmt library" ON)
 
 option(BUILD_STATIC         "Build static binary" OFF)
 option(ARM_V8               "Force ARMv8 (64 bit) architecture, use with caution if automatic detection fails, but you sure it may work" OFF)
@@ -198,6 +199,7 @@ add_definitions(-D__STDC_FORMAT_MACROS -DUNICODE -D_FILE_OFFSET_BITS=64)
 find_package(UV REQUIRED)
 
 include(cmake/flags.cmake)
+include(cmake/fmt.cmake)
 include(cmake/randomx.cmake)
 include(cmake/argon2.cmake)
 include(cmake/kawpow.cmake)
@@ -229,7 +231,7 @@ include(src/hw/api/api.cmake)
 include(src/hw/dmi/dmi.cmake)
 
 include_directories(src)
-include_directories(src/3rdparty)
+include_directories(src/3rdparty/CL)
 include_directories(${UV_INCLUDE_DIR})
 
 if (WITH_DEBUG_LOG)
@@ -237,7 +239,7 @@ 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} ${GHOSTRIDER_LIBRARY})
+target_link_libraries(${CMAKE_PROJECT_NAME} ${XMRIG_ASM_LIBRARY} ${OPENSSL_LIBRARIES} ${UV_LIBRARIES} ${EXTRA_LIBS} ${CPUID_LIB} ${ARGON2_LIBRARY} ${ETHASH_LIBRARY} ${GHOSTRIDER_LIBRARY} ${FMT_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}>)

cmake/fmt.cmake

@@ -0,0 +1,13 @@
+# SPDX-FileCopyrightText: © 2023 Jean-Pierre De Jesus DIAZ <me@jeandudey.tech>
+# SPDX-License-Identifier: GPL-3.0-or-later
+
+
+if(WITH_BUNDLED_FMT)
+    add_library(fmt INTERFACE)
+    target_sources(fmt INTERFACE ${CMAKE_CURRENT_SOURCE_DIR}/src/3rdparty/fmt/format.cc)
+    target_include_directories(fmt INTERFACE ${CMAKE_CURRENT_SOURCE_DIR}/src/3rdparty/fmt)
+else()
+    set(FMT_LIBRARY fmt)
+    find_package(fmt REQUIRED)
+    set(FMT_LIBRARY fmt::fmt)
+endif()

scripts/randomx_boost.sh

@@ -8,7 +8,7 @@ else
 	modprobe msr allow_writes=on
 fi
 
-if grep -E 'AMD Ryzen|AMD EPYC' /proc/cpuinfo > /dev/null;
+if grep -E 'AMD Ryzen|AMD EPYC|AuthenticAMD' /proc/cpuinfo > /dev/null;
 	then
 	if grep "cpu family[[:space:]]\{1,\}:[[:space:]]25" /proc/cpuinfo > /dev/null;
 		then
@@ -28,6 +28,14 @@ if grep -E 'AMD Ryzen|AMD EPYC' /proc/cpuinfo > /dev/null;
 					wrmsr -a 0xc001102b 0x2000cc10
 					echo "MSR register values for Zen3 applied"
 				fi
+		elif grep "cpu family[[:space:]]\{1,\}:[[:space:]]26" /proc/cpuinfo > /dev/null;
+			then
+				echo "Detected Zen5 CPU"
+				wrmsr -a 0xc0011020 0x4400000000000
+				wrmsr -a 0xc0011021 0x4000000000040
+				wrmsr -a 0xc0011022 0x8680000401570000
+				wrmsr -a 0xc001102b 0x2040cc10
+				echo "MSR register values for Zen5 applied"
 		else
 			echo "Detected Zen1/Zen2 CPU"
 			wrmsr -a 0xc0011020 0

src/3rdparty/cl.h

@@ -29,7 +29,7 @@
 #if defined(__APPLE__)
 #   include <OpenCL/cl.h>
 #else
-#   include "3rdparty/CL/cl.h"
+#   include <CL/cl.h>
 #endif
 
 

src/3rdparty/fmt/fmt/format.cc

@@ -5,7 +5,7 @@
 //
 // For the license information refer to format.h.
 
-#include "3rdparty/fmt/format-inl.h"
+#include "fmt/format-inl.h"
 
 FMT_BEGIN_NAMESPACE
 namespace detail {

src/backend/cpu/CpuWorker.cpp

@@ -359,7 +359,9 @@ void xmrig::CpuWorker<N>::start()
             }
         }
 
-        consumeJob();
+        if (!Nonce::isPaused()) {
+            consumeJob();
+        }
     }
 }
 

src/backend/cpu/platform/HwlocCpuInfo.cpp

@@ -326,7 +326,8 @@ void xmrig::HwlocCpuInfo::processTopLevelCache(hwloc_obj_t cache, const Algorith
         }
     }
 
-    if (scratchpad == 2 * oneMiB) {
+    // This code is supposed to run only on Intel CPUs
+    if ((vendor() == VENDOR_INTEL) && (scratchpad == 2 * oneMiB)) {
         if (L2 && (cores.size() * oneMiB) == L2 && L2_associativity == 16 && L3 >= L2) {
             L3    = L2;
             extra = L2;

src/backend/cpu/platform/lscpu_arm.cpp

@@ -18,11 +18,11 @@
  */
 
 #include "base/tools/String.h"
-#include "3rdparty/fmt/core.h"
 
 
 #include <cstdio>
 #include <cctype>
+#include <fmt/core.h>
 
 
 namespace xmrig {

src/backend/cuda/CudaWorker.cpp

@@ -158,7 +158,7 @@ void xmrig::CudaWorker::start()
             std::this_thread::yield();
         }
 
-        if (!consumeJob()) {
+        if (isReady() && !consumeJob()) {
             return;
         }
     }

src/backend/opencl/OclWorker.cpp

@@ -190,7 +190,7 @@ void xmrig::OclWorker::start()
             std::this_thread::yield();
         }
 
-        if (!consumeJob()) {
+        if (isReady() && !consumeJob()) {
             return;
         }
     }

src/backend/opencl/wrappers/AdlLib_linux.cpp

@@ -20,7 +20,6 @@
 
 
 #include "backend/opencl/wrappers/AdlLib.h"
-#include "3rdparty/fmt/core.h"
 #include "backend/opencl/wrappers/OclDevice.h"
 
 
@@ -31,6 +30,7 @@
 #include <string>
 #include <sys/stat.h>
 #include <sys/types.h>
+#include <fmt/core.h>
 
 
 namespace xmrig {

src/base/base.cmake

@@ -88,7 +88,6 @@ set(HEADERS_BASE
    )
 
 set(SOURCES_BASE
-    src/3rdparty/fmt/format.cc
     src/base/crypto/Algorithm.cpp
     src/base/crypto/Coin.cpp
     src/base/crypto/keccak.cpp

src/base/kernel/Process.cpp

@@ -22,10 +22,10 @@
 
 
 #include "base/kernel/Process.h"
-#include "3rdparty/fmt/core.h"
 #include "base/tools/Chrono.h"
 #include "version.h"
 
+#include <fmt/core.h>
 
 #ifdef XMRIG_OS_WIN
 #   ifdef _MSC_VER

src/base/net/stratum/BaseClient.cpp

@@ -17,7 +17,6 @@
  */
 
 #include "base/net/stratum/BaseClient.h"
-#include "3rdparty/fmt/core.h"
 #include "3rdparty/rapidjson/document.h"
 #include "base/io/Env.h"
 #include "base/io/log/Log.h"
@@ -25,6 +24,8 @@
 #include "base/kernel/interfaces/IClientListener.h"
 #include "base/net/stratum/SubmitResult.h"
 
+#include <fmt/core.h>
+
 
 namespace xmrig {
 

src/base/net/stratum/benchmark/BenchClient.cpp

@@ -17,7 +17,6 @@
  */
 
 #include "base/net/stratum/benchmark/BenchClient.h"
-#include "3rdparty/fmt/core.h"
 #include "3rdparty/rapidjson/document.h"
 #include "backend/common/benchmark/BenchState.h"
 #include "backend/common/interfaces/IBackend.h"
@@ -39,6 +38,8 @@
 #   include "hw/dmi/DmiReader.h"
 #endif
 
+#include <fmt/core.h>
+
 
 xmrig::BenchClient::BenchClient(const std::shared_ptr<BenchConfig> &benchmark, IClientListener* listener) :
     m_listener(listener),

src/base/net/stratum/benchmark/BenchConfig.cpp

@@ -17,12 +17,12 @@
  */
 
 #include "base/net/stratum/benchmark/BenchConfig.h"
-#include "3rdparty/fmt/core.h"
 #include "3rdparty/rapidjson/document.h"
 #include "base/io/json/Json.h"
 
 
 #include <string>
+#include <fmt/core.h>
 
 
 #ifdef _MSC_VER

src/core/Miner.cpp

@@ -576,6 +576,11 @@ void xmrig::Miner::setJob(const Job &job, bool donate)
 
 #   ifdef XMRIG_ALGO_RANDOMX
     const bool ready = d_ptr->initRX();
+
+    // Always reset nonce on RandomX dataset change
+    if (!ready) {
+        d_ptr->reset = true;
+    }
 #   else
     constexpr const bool ready = true;
 #   endif

src/crypto/common/LinuxMemory.cpp

@@ -17,12 +17,12 @@
  */
 
 #include "crypto/common/LinuxMemory.h"
-#include "3rdparty/fmt/core.h"
 #include "crypto/common/VirtualMemory.h"
 
 
 #include <algorithm>
 #include <fstream>
+#include <fmt/core.h>
 #include <mutex>
 #include <string>
 

src/crypto/ghostrider/README.md

@@ -16,7 +16,7 @@ xmrig -a gr -o rtm.suprnova.cc:4273 --tls -u WALLET_ADDRESS -p x
 
 You can use **rtm_ghostrider_example.cmd** as a template and put pool URL and your wallet address there. The general XMRig documentation is available [here](https://xmrig.com/docs/miner).
 
-**Using `--threads` or `-t` option is NOT recommended because it turns off advanced built-in config.** If you want to tweak the nubmer of threads used for GhostRider, it's recommended to start using config.json instead of command line. The best suitable command line option for this is `--cpu-max-threads-hint=N` where N can be between 0 and 100.
+**Using `--threads` or `-t` option is NOT recommended because it turns off advanced built-in config.** If you want to tweak the number of threads used for GhostRider, it's recommended to start using config.json instead of command line. The best suitable command line option for this is `--cpu-max-threads-hint=N` where N can be between 0 and 100.
 
 ## Performance
 

src/crypto/randomx/jit_compiler_x86.cpp

@@ -267,8 +267,8 @@ namespace randomx {
 						initDatasetAVX2 = false;
 						break;
 					case xmrig::ICpuInfo::ARCH_ZEN5:
-						// TODO: test it
-						initDatasetAVX2 = false;
+						// AVX2 init is 49% faster on Zen5
+						initDatasetAVX2 = true;
 						break;
 					}
 				}

src/crypto/rx/RxConfig.cpp

@@ -60,8 +60,6 @@ static const std::array<MsrItems, kMsrArraySize> msrPresets = {
     MsrItems{{ 0xC0011020, 0ULL }, { 0xC0011021, 0x40ULL, ~0x20ULL }, { 0xC0011022, 0x1510000ULL }, { 0xC001102b, 0x2000cc16ULL }},
     MsrItems{{ 0xC0011020, 0x0004480000000000ULL }, { 0xC0011021, 0x001c000200000040ULL, ~0x20ULL }, { 0xC0011022, 0xc000000401570000ULL }, { 0xC001102b, 0x2000cc10ULL }},
     MsrItems{{ 0xC0011020, 0x0004400000000000ULL }, { 0xC0011021, 0x0004000000000040ULL, ~0x20ULL }, { 0xC0011022, 0x8680000401570000ULL }, { 0xC001102b, 0x2040cc10ULL }},
-
-    // TODO: Tune it for Zen5 when it's available
     MsrItems{{ 0xC0011020, 0x0004400000000000ULL }, { 0xC0011021, 0x0004000000000040ULL, ~0x20ULL }, { 0xC0011022, 0x8680000401570000ULL }, { 0xC001102b, 0x2040cc10ULL }},
 
     MsrItems{{ 0x1a4, 0xf }},

src/hw/dmi/DmiMemory.cpp

@@ -20,7 +20,6 @@
 
 
 #include "hw/dmi/DmiMemory.h"
-#include "3rdparty/fmt/format.h"
 #include "3rdparty/rapidjson/document.h"
 #include "hw/dmi/DmiTools.h"
 
@@ -28,6 +27,7 @@
 #include <algorithm>
 #include <array>
 #include <regex>
+#include <fmt/format.h>
 
 
 namespace xmrig {

src/hw/dmi/DmiReader.cpp

@@ -19,10 +19,11 @@
  */
 
 #include "hw/dmi/DmiReader.h"
-#include "3rdparty/fmt/core.h"
 #include "3rdparty/rapidjson/document.h"
 #include "hw/dmi/DmiTools.h"
 
+#include <fmt/core.h>
+
 
 namespace xmrig {
 

src/hw/msr/Msr_linux.cpp

@@ -18,7 +18,6 @@
 
 
 #include "hw/msr/Msr.h"
-#include "3rdparty/fmt/core.h"
 #include "backend/cpu/Cpu.h"
 #include "base/io/log/Log.h"
 
@@ -29,6 +28,7 @@
 #include <cstdio>
 #include <dirent.h>
 #include <fcntl.h>
+#include <fmt/core.h>
 #include <fstream>
 #include <sys/stat.h>
 #include <sys/types.h>

src/version.h

@@ -22,7 +22,7 @@
 #define APP_ID        "xmrig"
 #define APP_NAME      "XMRig"
 #define APP_DESC      "XMRig miner"
-#define APP_VERSION   "6.22.0"
+#define APP_VERSION   "6.22.1-dev"
 #define APP_DOMAIN    "xmrig.com"
 #define APP_SITE      "www.xmrig.com"
 #define APP_COPYRIGHT "Copyright (C) 2016-2024 xmrig.com"
@@ -30,7 +30,7 @@
 
 #define APP_VER_MAJOR  6
 #define APP_VER_MINOR  22
-#define APP_VER_PATCH  0
+#define APP_VER_PATCH  1
 
 #ifdef _MSC_VER
 #   if (_MSC_VER >= 1930)