Merge pull request #2498 from fireice-uk/dev

release 2.10.7

Author: fireice-uk

README.md

@@ -1,7 +1,7 @@
 ###### fireice-uk's and psychocrypt's
 # XMR-Stak: Cryptonight All-in-One Mining Software
 
-XMR-Stak is a universal open source stratum pool miner. This miner supports CPUs, AMD and NVIDIA GPUs and can be used various crypto currencies: Ryo, Monero, Turtlecoin, Graft, Bittube, Loki, Aeon and many more Cryptonight coins.
+XMR-Stak is a universal open source stratum pool miner. This miner supports x86-64 CPUs, AMD and NVIDIA GPUs and can be used various crypto currencies: Ryo, Monero, Turtlecoin, Graft, Bittube, Loki, Aeon and many more Cryptonight coins.
 
 
 
@@ -52,16 +52,13 @@ Following coins can be mined using this miner:
 - [Graft](https://www.graft.network)
 - [Haven](https://havenprotocol.com)
 - [Lethean](https://lethean.io)
-- [Loki](https://loki.network/)
 - [Masari](https://getmasari.org)
 - [Monero](https://getmonero.org)
 - [Plenteum](https://www.plenteum.com/)
 - [QRL](https://theqrl.org)
 - **[Ryo](https://ryo-currency.com) - Upcoming xmr-stak-gui is sponsored by Ryo Currency**
 - [Torque](https://torque.cash/)
-- [TurtleCoin](https://turtlecoin.lol)
 - [Zelerius](https://zelerius.org/)
-- [X-CASH](https://x-network.io/)
 
 **[Ryo Currency](https://ryo-currency.com)** - is a way for us to implement the ideas that we were unable to in
 Monero. See [here](https://github.com/fireice-uk/cryptonote-speedup-demo/) for details.

doc/usage.md

@@ -3,7 +3,7 @@
 ## Content Overview
 * [Configurations](#configurations)
 * [Usage on Windows](#usage-on-windows)
-* [Usage on Linux](#usage-on-linux)
+* [Usage on Linux & macOS](#usage-on-linux--macos)
 * [Command Line Options](#command-line-options)
 * [Use different backends](#use-different-backends)
 * [HTML and JSON API report configuraton](#html-and-json-api-report-configuraton)

xmrstak/backend/amd/autoAdjust.hpp

@@ -110,6 +110,21 @@ class autoAdjust
 				}
 			}
 
+			// check if cryptonight_monero_v8 is selected for the user or dev pool
+			bool useCryptonight_v8 = (std::find(neededAlgorithms.begin(), neededAlgorithms.end(), cryptonight_monero_v8) != neededAlgorithms.end());
+
+			// true for all cryptonight_heavy derivates since we check the user and dev pool
+			bool useCryptonight_heavy = std::find(neededAlgorithms.begin(), neededAlgorithms.end(), cryptonight_heavy) != neededAlgorithms.end();
+
+			// true for cryptonight_gpu as main user pool algorithm
+			bool useCryptonight_gpu = ::jconf::inst()->GetCurrentCoinSelection().GetDescription(1).GetMiningAlgo() == cryptonight_gpu;
+
+			bool useCryptonight_r = ::jconf::inst()->GetCurrentCoinSelection().GetDescription(1).GetMiningAlgo() == cryptonight_r;
+
+			bool useCryptonight_r_wow = ::jconf::inst()->GetCurrentCoinSelection().GetDescription(1).GetMiningAlgo() == cryptonight_r_wow;
+
+			// 8 threads per block (this is a good value for the most gpus)
+			uint32_t default_workSize = 8;
 			size_t minFreeMem = 128u * byteToMiB;
 			/* 1000 is a magic selected limit, the reason is that more than 2GiB memory
 			 * sowing down the memory performance because of TLB cache misses
@@ -130,6 +145,9 @@ class autoAdjust
 				 * to avoid out of memory errors
 				 */
 				maxThreads = 2024u;
+
+				if(useCryptonight_gpu)
+					default_workSize = 16u;
 			}
 
 			// NVIDIA optimizations
@@ -142,19 +160,6 @@ class autoAdjust
 				minFreeMem = 512u * byteToMiB;
 			}
 
-			// check if cryptonight_monero_v8 is selected for the user or dev pool
-			bool useCryptonight_v8 = (std::find(neededAlgorithms.begin(), neededAlgorithms.end(), cryptonight_monero_v8) != neededAlgorithms.end());
-
-			// true for all cryptonight_heavy derivates since we check the user and dev pool
-			bool useCryptonight_heavy = std::find(neededAlgorithms.begin(), neededAlgorithms.end(), cryptonight_heavy) != neededAlgorithms.end();
-
-			// true for cryptonight_gpu as main user pool algorithm
-			bool useCryptonight_gpu = ::jconf::inst()->GetCurrentCoinSelection().GetDescription(1).GetMiningAlgo() == cryptonight_gpu;
-
-			bool useCryptonight_r = ::jconf::inst()->GetCurrentCoinSelection().GetDescription(1).GetMiningAlgo() == cryptonight_r;
-
-			bool useCryptonight_r_wow = ::jconf::inst()->GetCurrentCoinSelection().GetDescription(1).GetMiningAlgo() == cryptonight_r_wow;
-
 			// set strided index to default
 			ctx.stridedIndex = 1;
 
@@ -203,11 +208,11 @@ class autoAdjust
 			size_t perThread = hashMemSize + 240u;
 			size_t maxIntensity = memPerThread / perThread;
 			size_t possibleIntensity = std::min(maxThreads, maxIntensity);
-			// map intensity to a multiple of the compute unit count, 8 is the number of threads per work group
-			size_t intensity = (possibleIntensity / (8 * ctx.computeUnits)) * ctx.computeUnits * 8;
+			// map intensity to a multiple of the compute unit count, default_workSize is the number of threads per work group
+			size_t intensity = (possibleIntensity / (default_workSize * ctx.computeUnits)) * ctx.computeUnits * default_workSize;
 			// in the case we use two threads per gpu we can be relax and need no multiple of the number of compute units
 			if(numThreads == 2)
-				intensity = (possibleIntensity / 8) * 8;
+				intensity = (possibleIntensity / default_workSize) * default_workSize;
 
 			//If the intensity is 0, then it's because the multiple of the unit count is greater than intensity
 			if(intensity == 0)
@@ -225,9 +230,8 @@ class autoAdjust
 					conf += "  // gpu: " + ctx.name + std::string("  compute units: ") + std::to_string(ctx.computeUnits) + "\n";
 					conf += "  // memory:" + std::to_string(memPerThread / byteToMiB) + "|" +
 							std::to_string(ctx.maxMemPerAlloc / byteToMiB) + "|" + std::to_string(maxAvailableFreeMem / byteToMiB) + " MiB (used per thread|max per alloc|total free)\n";
-					// set 8 threads per block (this is a good value for the most gpus)
 					conf += std::string("  { \"index\" : ") + std::to_string(ctx.deviceIdx) + ",\n" +
-							"    \"intensity\" : " + std::to_string(intensity) + ", \"worksize\" : " + std::to_string(8) + ",\n" +
+							"    \"intensity\" : " + std::to_string(intensity) + ", \"worksize\" : " + std::to_string(default_workSize) + ",\n" +
 							"    \"affine_to_cpu\" : false, \"strided_index\" : " + std::to_string(ctx.stridedIndex) + ", \"mem_chunk\" : 2,\n"
 																													   "    \"unroll\" : " +
 							std::to_string(numUnroll) + ", \"comp_mode\" : true, \"interleave\" : " + std::to_string(ctx.interleave) + "\n" +

xmrstak/backend/nvidia/nvcc_code/cuda_core.cu

@@ -900,7 +900,7 @@ void cryptonight_core_gpu_hash(nvid_ctx* ctx, uint32_t nonce, const xmrstak_algo
 	if(blockSizePhase3 * 2 <= ctx->device_maxThreadsPerBlock)
 	{
 		blockSizePhase3 *= 2;
-		gridSizePhase3 = (blockSizePhase3 + 1) / 2;
+		gridSizePhase3 = (gridSizePhase3 + 1) / 2;
 	}
 	for(int i = 0; i < roundsPhase3; i++)
 	{
@@ -978,7 +978,7 @@ void cryptonight_core_gpu_hash_gpu(nvid_ctx* ctx, uint32_t nonce, const xmrstak_
 	if(blockSizePhase3 * 2 <= ctx->device_maxThreadsPerBlock)
 	{
 		blockSizePhase3 *= 2;
-		gridSizePhase3 = (blockSizePhase3 + 1) / 2;
+		gridSizePhase3 = (gridSizePhase3 + 1) / 2;
 	}
 
 	for(int i = 0; i < roundsPhase3; i++)

xmrstak/jconf.cpp

@@ -132,10 +132,8 @@ xmrstak::coin_selection coins[] = {
 	{"qrl", {POW(cryptonight_monero)}, {POW(cryptonight_gpu)}, nullptr},
 	{"ryo", {POW(cryptonight_gpu)}, {POW(cryptonight_gpu)}, "pool.ryo-currency.com:3333"},
 	{"torque", {POW(cryptonight_v8_half)}, {POW(cryptonight_gpu)}, nullptr},
-	{"turtlecoin", {POW(cryptonight_turtle), 6u, POW(cryptonight_aeon)}, {POW(cryptonight_aeon)}, nullptr},
 	{"plenteum", {POW(cryptonight_turtle)}, {POW(cryptonight_turtle)}, nullptr},
-	{"zelerius", {POW(cryptonight_v8_zelerius), 7, POW(cryptonight_monero_v8)}, {POW(cryptonight_gpu)}, nullptr},
-	{"xcash", {POW(cryptonight_v8_double)}, {POW(cryptonight_gpu)}, nullptr}};
+	{"zelerius", {POW(cryptonight_v8_zelerius), 7, POW(cryptonight_monero_v8)}, {POW(cryptonight_gpu)}, nullptr}};
 
 constexpr size_t coin_algo_size = (sizeof(coins) / sizeof(coins[0]));
 

xmrstak/version.cpp

@@ -20,7 +20,7 @@
 #endif
 
 #define XMR_STAK_NAME "xmr-stak"
-#define XMR_STAK_VERSION "2.10.6"
+#define XMR_STAK_VERSION "2.10.7"
 
 #if defined(_WIN32)
 #define OS_TYPE "win"