Merge ead82cdba9 into e32731b60b

Detect AMD engineering samples in randomx_boost.sh

scripts/build.hwloc.sh

@@ -1,8 +1,8 @@
 #!/bin/sh -e
 
 HWLOC_VERSION_MAJOR="2"
-HWLOC_VERSION_MINOR="10"
-HWLOC_VERSION_PATCH="0"
+HWLOC_VERSION_MINOR="11"
+HWLOC_VERSION_PATCH="2"
 
 HWLOC_VERSION="${HWLOC_VERSION_MAJOR}.${HWLOC_VERSION_MINOR}.${HWLOC_VERSION_PATCH}"
 

scripts/build.openssl3.sh

@@ -1,6 +1,6 @@
 #!/bin/sh -e
 
-OPENSSL_VERSION="3.0.14"
+OPENSSL_VERSION="3.0.15"
 
 mkdir -p deps
 mkdir -p deps/include

scripts/build.uv.sh

@@ -1,6 +1,6 @@
 #!/bin/sh -e
 
-UV_VERSION="1.48.0"
+UV_VERSION="1.49.2"
 
 mkdir -p deps
 mkdir -p deps/include

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/backend/cpu/CpuBackend.cpp

@@ -180,11 +180,11 @@ public:
         }
     #   endif
 
-        mutex.lock();
+        {
+            std::lock_guard<std::mutex> lock(mutex);
 
-        pages += status.hugePages();
-
-        mutex.unlock();
+            pages += status.hugePages();
+        }
 
         rapidjson::Value hugepages;
 
@@ -380,14 +380,14 @@ void xmrig::CpuBackend::setJob(const Job &job)
 
 void xmrig::CpuBackend::start(IWorker *worker, bool ready)
 {
-    mutex.lock();
+    {
+        std::lock_guard<std::mutex> lock(mutex);
 
-    if (d_ptr->status.started(worker, ready)) {
-        d_ptr->status.print();
+        if (d_ptr->status.started(worker, ready)) {
+            d_ptr->status.print();
+        }
     }
 
-    mutex.unlock();
-
     if (ready) {
         worker->start();
     }

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/cuda/CudaBackend.cpp

@@ -452,16 +452,17 @@ void xmrig::CudaBackend::setJob(const Job &job)
 
 void xmrig::CudaBackend::start(IWorker *worker, bool ready)
 {
-    mutex.lock();
+    {
+        std::lock_guard<std::mutex> lock(mutex);
 
-    if (d_ptr->status.started(ready)) {
-        d_ptr->status.print();
+        if (d_ptr->status.started(ready)) {
+            d_ptr->status.print();
+
+            CudaWorker::ready = true;
+        }
 
-        CudaWorker::ready = true;
     }
 
-    mutex.unlock();
-
     if (ready) {
         worker->start();
     }

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/OclBackend.cpp

@@ -438,16 +438,16 @@ void xmrig::OclBackend::setJob(const Job &job)
 
 void xmrig::OclBackend::start(IWorker *worker, bool ready)
 {
-    mutex.lock();
+    {
+        std::lock_guard<std::mutex> lock(mutex);
 
-    if (d_ptr->status.started(ready)) {
-        d_ptr->status.print();
+        if (d_ptr->status.started(ready)) {
+            d_ptr->status.print();
 
-        OclWorker::ready = true;
+            OclWorker::ready = true;
+        }
     }
 
-    mutex.unlock();
-
     if (ready) {
         worker->start();
     }

src/backend/opencl/OclWorker.cpp

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

src/core/Miner.cpp

@@ -556,7 +556,14 @@ void xmrig::Miner::setJob(const Job &job, bool donate)
 
     d_ptr->algorithm = job.algorithm();
 
-    mutex.lock();
+#   ifdef XMRIG_ALGO_RANDOMX
+    bool ready = false;
+#   else
+    constexpr const bool ready = true;
+#   endif
+
+    {
+    std::lock_guard<std::mutex> lock(mutex);
 
     const uint8_t index = donate ? 1 : 0;
 
@@ -575,9 +582,12 @@ void xmrig::Miner::setJob(const Job &job, bool donate)
     }
 
 #   ifdef XMRIG_ALGO_RANDOMX
-    const bool ready = d_ptr->initRX();
-#   else
-    constexpr const bool ready = true;
+    ready = d_ptr->initRX();
+
+    // Always reset nonce on RandomX dataset change
+    if (!ready) {
+        d_ptr->reset = true;
+    }
 #   endif
 
 #   ifdef XMRIG_ALGO_GHOSTRIDER
@@ -586,7 +596,7 @@ void xmrig::Miner::setJob(const Job &job, bool donate)
     }
 #   endif
 
-    mutex.unlock();
+    }
 
     d_ptr->active = true;
     d_ptr->m_taskbar.setActive(true);

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/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)