Merge pull request fireice-uk#1610 from fireice-uk/dev

release 2.4.4

CMakeLists.txt

@@ -141,15 +141,14 @@ if(CUDA_ENABLE)
                 # set flags to create device code for the given architectures
                 set(CLANG_BUILD_FLAGS "${CLANG_BUILD_FLAGS} --cuda-gpu-arch=sm_${CUDA_ARCH_ELEM}")
             endforeach()
-
         elseif(CUDA_COMPILER STREQUAL "nvcc")
             # add c++11 for cuda
             if(NOT CMAKE_CXX_FLAGS MATCHES "-std=c\\+\\+11")
                 set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -std=c++11")
             endif()
 
             # avoid that nvcc in CUDA 8 complains about sm_20 pending removal
-	    if(CUDA_VERSION VERSION_EQUAL 8.0)
+            if(CUDA_VERSION VERSION_EQUAL 8.0)
                 set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS} -Wno-deprecated-gpu-targets")
             endif()
 
@@ -180,14 +179,14 @@ if(CUDA_ENABLE)
             if(CUDA_KEEP_FILES)
                 set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS}" --keep --keep-dir "${PROJECT_BINARY_DIR}")
             endif(CUDA_KEEP_FILES)
-        
+
             if(CUDA_VERSION VERSION_LESS 8.0)
                 # for CUDA 7.5 fix compile error: https://github.com/fireice-uk/xmr-stak/issues/34
                 set(CUDA_NVCC_FLAGS "${CUDA_NVCC_FLAGS}" "-D_MWAITXINTRIN_H_INCLUDED")
             endif()
 
             if(CMAKE_CXX_COMPILER_ID MATCHES "MSVC" AND
-                (CUDA_VERSION VERSION_EQUAL 9.0 OR CUDA_VERSION VERSION_EQUAL 9.1)
+                (CUDA_VERSION VERSION_EQUAL 9.0 OR CUDA_VERSION VERSION_EQUAL 9.1 OR CUDA_VERSION VERSION_EQUAL 9.2)
             )
                 # workaround find_package(CUDA) is using the wrong path to the CXX host compiler
                 # overwrite the CUDA host compiler variable with the used CXX MSVC
@@ -232,7 +231,7 @@ if(OpenCL_ENABLE)
             "AMD APP/include")
 
     find_library(OpenCL_LIBRARY
-        NAMES 
+        NAMES
             OpenCL
             OpenCL.lib
         NO_DEFAULT_PATH
@@ -284,7 +283,7 @@ endif()
 # Find microhttpd
 ################################################################################
 
-option(MICROHTTPD_ENABLE "Enable or disable the requirement of microhttp (http deamon)" ON)
+option(MICROHTTPD_ENABLE "Enable or disable the requirement of microhttp (http daemon)" ON)
 if(MICROHTTPD_ENABLE)
     find_path(MTHD_INCLUDE_DIR
         NAMES
@@ -307,7 +306,7 @@ if(MICROHTTPD_ENABLE)
         PATH_SUFFIXES
             lib)
     if(MHTD STREQUAL "MHTD-NOTFOUND")
-        message(FATAL_ERROR "microhttpd NOT found: use `-DMICROHTTPD_ENABLE=OFF` to build without http deamon support")
+        message(FATAL_ERROR "microhttpd NOT found: use `-DMICROHTTPD_ENABLE=OFF` to build without http daemon support")
     else()
         set(LIBS ${LIBS} ${MHTD})
         include_directories(AFTER ${MTHD_INCLUDE_DIR})
@@ -399,10 +398,10 @@ execute_process(
 )
 
 if(NOT GIT_COMMIT_HASH STREQUAL "")
-	add_definitions("-DGIT_COMMIT_HASH=${GIT_COMMIT_HASH}")
+    add_definitions("-DGIT_COMMIT_HASH=${GIT_COMMIT_HASH}")
 endif()
 if(NOT GIT_BRANCH STREQUAL "")
-	add_definitions("-DGIT_BRANCH=${GIT_BRANCH}")
+    add_definitions("-DGIT_BRANCH=${GIT_BRANCH}")
 endif()
 
 # generate backend string
@@ -426,7 +425,6 @@ else()
     # activate sse2 and aes-ni
     set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -msse2 -maes")
     set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -msse2 -maes")
-
 endif()
 
 # add -Wall for debug builds with gcc
@@ -478,7 +476,7 @@ target_link_libraries(xmr-stak-backend xmr-stak-c ${CMAKE_DL_LIBS})
 
 # compile CUDA backend
 if(CUDA_FOUND)
-    file(GLOB CUDASRCFILES 
+    file(GLOB CUDASRCFILES
         "xmrstak/backend/nvidia/nvcc_code/*.cu"
         "xmrstak/backend/nvidia/*.cpp")
 
@@ -506,7 +504,7 @@ endif()
 
 # compile AMD backend
 if(OpenCL_FOUND)
-    file(GLOB OPENCLSRCFILES  
+    file(GLOB OPENCLSRCFILES
         "xmrstak/backend/amd/amd_gpu/*.cpp"
         "xmrstak/backend/amd/*.cpp")
     add_library(xmrstak_opencl_backend
@@ -536,7 +534,6 @@ target_link_libraries(xmr-stak ${LIBS} xmr-stak-c xmr-stak-backend)
 # Install
 ################################################################################
 
-
 # do not install the binary if the project and install are equal
 if( NOT CMAKE_INSTALL_PREFIX STREQUAL PROJECT_BINARY_DIR )
     install(TARGETS xmr-stak

README.md

@@ -1,7 +1,7 @@
 ###### fireice-uk's and psychocrypt's
 # XMR-Stak - Monero/Aeon All-in-One Mining Software
 
-**XMR-Stak is ready for the POW change of Monero-v7, Aeon-v7 and Sumukoin-v3**
+**XMR-Stak is ready for the POW change of Monero-v7, Aeon-v7, stellite-v4 and Sumukoin-v3**
 
 XMR-Stak is a universal Stratum pool miner. This miner supports CPUs, AMD and NVIDIA gpus and can be used to mine the crypto currency Monero and Aeon.
 
@@ -48,8 +48,11 @@ Besides [Monero](https://getmonero.org), following coins can be mined using this
 - [Graft](https://www.graft.network)
 - [Haven](https://havenprotocol.com)
 - [Intense](https://intensecoin.com)
+- [IPBC](https://ipbc.io)
 - [Karbo](https://karbo.io)
+- [Masari](https://getmasari.org)
 - [Sumokoin](https://www.sumokoin.org)
+- [TurtleCoin](https://turtlecoin.lol)
 
 If your prefered coin is not listed, you can chose one of the following algorithms:
 

THIRD-PARTY-LICENSES

@@ -5,7 +5,7 @@ This application bundles the following third-party software in accordance with t
 Package: Original NVidia mining code
 Authors: tsiv and KlausT
 License: GNU GPLv3
-Notes: Improvements are (c) of Xmr-Stak team
+Notes: Improvements are (c) of Xmr-Stak team and are covered by GNU GPLv3
 
 -------------------------------------------------------------------------
 
@@ -27,3 +27,10 @@ Authors: okdshin
 License: MIT License
 
 -------------------------------------------------------------------------
+
+Package: cpputil
+Authors: Will Zhang
+Source: https://github.com/willzhang4a58/cpputil
+License: MIT License
+
+-------------------------------------------------------------------------

doc/FAQ.md

@@ -44,18 +44,18 @@ Download and install this [runtime package](https://go.microsoft.com/fwlink/?Lin
 
 ## Error: MEMORY ALLOC FAILED: mmap failed
 
-On Linux you will need to configure large page support and increase your ulimit -l. 
+On Linux you will need to configure large page support and increase your ulimit -l.
 
 To set large page support, add the following lines to /etc/sysctl.conf:
-    
+
     vm.nr_hugepages=128
 
 To increase the ulimit, add following lines to /etc/security/limits.conf:
 
     * soft memlock 262144
     * hard memlock 262144
 
-You WILL need to log out and log back in for these settings to take affect on your user (no need to reboot, just relogin in your session).
+You WILL need to log out and log back in for these settings to take effect on your user (no need to reboot, just relogin in your session).
 
 You can also do it Windows-style and simply run-as-root, but this is NOT recommended for security reasons.
 

doc/compile_FreeBSD.md

@@ -6,7 +6,7 @@
 
 From the root shell, run the following commands:
 
-    pkg install git libmicrohttpd hwloc cmake 
+    pkg install git libmicrohttpd hwloc cmake
 
 Type 'y' and hit enter to proceed with installing the packages.
 

doc/compile_Linux.md

@@ -4,7 +4,8 @@
 
 ### AMD APP SDK 3.0 (only needed to use AMD GPUs)
 
-- download and install the latest version from [http://developer.amd.com/amd-accelerated-parallel-processing-app-sdk/](http://developer.amd.com/amd-accelerated-parallel-processing-app-sdk/)
+- download and install the latest version from https://www.dropbox.com/sh/mpg882ekirnsfa7/AADWz5X-TgVdsmWt0QwMgTWLa/AMD-APP-SDKInstaller-v3.0.130.136-GA-linux64.tar.bz2?dl=0
+  (do not wonder why it is a link to a dropbox but AMD has removed the SDK downloads, see https://community.amd.com/thread/228059)
 
 ### Cuda 8.0+ (only needed to use NVIDIA GPUs)
 
@@ -64,7 +65,7 @@
     cd xmr-stak/build
     cmake ..
     make install
-    
+
     # TinyCore Linux 8.x
     # TinyCore is 32-bit only, but there is an x86-64 port, known as "Pure 64,"
     # hosted on the TinyCore home page, and it works well.
@@ -94,7 +95,7 @@
     make install
 ```
 
-- g++ version 5.1 or higher is required for full C++11 support. 
+- g++ version 5.1 or higher is required for full C++11 support.
 If you want to compile the binary without installing libraries / compiler or just compile binary for some other distribution, please check the [build_xmr-stak_docker.sh script](scripts/build_xmr-stak_docker/build_xmr-stak_docker.sh).
 
 - Some newer gcc versions are not supported by CUDA (e.g. Ubuntu 17.10). It will require installing gcc 5 but you can avoid changing defaults.

doc/compile_Windows.md

@@ -13,7 +13,7 @@
 - During install choose following components:
   - `Desktop development with C++` (left side)
   - `VC++ 2015.3 v140 toolset for desktop` (right side - **NOT** needed for CUDA 9 or AMD GPU)
-  - Since release of VS2017 15.5 (12/04/17), require `VC++ 2017 version 15.4 v14.11 toolset` (under tab `Individual Components`, section `Compilers, build tools, and runtimes`), as CUDA 9.1 is not compatible with compiler 14.12.X
+  - Since release of VS2017 15.5 (12/04/17), require `VC++ 2017 version 15.4 v14.11 toolset` (under tab `Individual Components`, section `Compilers, build tools, and runtimes`), as CUDA 9.x is not compatible with compiler 14.12.X
 
 ### CMake for Win64
 
@@ -32,7 +32,8 @@
 
 ### AMD APP SDK 3.0 (only needed for AMD GPUs)
 
-- Download and install the latest version from http://developer.amd.com/amd-accelerated-parallel-processing-app-sdk/
+- Download and install the latest version from https://www.dropbox.com/s/gq8vqhelq0m6gj4/AMD-APP-SDKInstaller-v3.0.130.135-GA-windows-F-x64.exe
+  (do not wonder why it is a link to a dropbox but AMD has removed the SDK downloads, see https://community.amd.com/thread/222855)
 
 ### Dependencies OpenSSL/Hwloc and Microhttpd
 - For CUDA 8*:
@@ -82,17 +83,17 @@
 - Go to extracted source code directory (e.g. `cd C:\Users\USERNAME\xmr-stak-<version>`)
 - Execute the following commands (NOTE: path to Visual Studio Community 2017 can be different)
   ```
-  # Execute next line only if compiling for Cuda 9.1 and using Visual Studio 2017 >= 15.5 (released 12/04/17)
-  "C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\VC\Auxiliary\Build\vcvarsall.bat" x64 -vcvars_ver=14.11  
-  
+  # Execute next line only if compiling for Cuda 9.x and using Visual Studio 2017 >= 15.5 (released 12/04/17)
+  "C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\VC\Auxiliary\Build\vcvarsall.bat" x64 -vcvars_ver=14.11
+
   "C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\Tools\VsMSBuildCmd.bat"
   ```
 - Sometimes Windows will change the directory to `C:\Users\USERNAME\source\` instead of `C:\Users\USERNAME\xmr-stak-<version>\`. If that's the case execute `cd C:\Users\USERNAME\xmr-stak-<version>` followed by:
   ```
   mkdir build
-  
+
   cd build
-  
+
   set CMAKE_PREFIX_PATH=C:\xmr-stak-dep\hwloc;C:\xmr-stak-dep\libmicrohttpd;C:\xmr-stak-dep\openssl
   ```
 
@@ -104,9 +105,9 @@
 - Then execute
   ```
   cmake --build . --config Release --target install
-  
+
   cd bin\Release
-  
+
   copy C:\xmr-stak-dep\openssl\bin\* .
   ```
 - Miner is by default compiled for NVIDIA GPUs (if CUDA is installed), AMD GPUs (if the AMD APP SDK is installed) and CPUs.

doc/tuning.md

@@ -82,10 +82,10 @@ If you are unsure of either GPU or platform index value, you can use `clinfo` to
 ```
 "gpu_threads_conf" :
 [
-    { "index" : 0, "intensity" : 1000, "worksize" : 8, "affine_to_cpu" : false, 
+    { "index" : 0, "intensity" : 1000, "worksize" : 8, "affine_to_cpu" : false,
       "strided_index" : true, "mem_chunk" : 2, "comp_mode" : true
     },
-    { "index" : 1, "intensity" : 1000, "worksize" : 8, "affine_to_cpu" : false, 
+    { "index" : 1, "intensity" : 1000, "worksize" : 8, "affine_to_cpu" : false,
       "strided_index" : true, "mem_chunk" : 2, "comp_mode" : true
     },
 ],

xmrstak/backend/amd/amd_gpu/gpu.cpp

@@ -26,7 +26,7 @@
 #include <algorithm>
 #include <regex>
 #include <cassert>
-#include <algorithm> 
+#include <algorithm>
 
 #include <fstream>
 #include <sstream>
@@ -397,7 +397,7 @@ size_t InitOpenCLGpu(cl_context opencl_ctx, GpuContext* ctx, const char* source_
 		 * used data:
 		 *   - source code
 		 *   - device name
-		 *   - compile paramater
+		 *   - compile parameter
 		 */
 		std::string src_str(source_code);
 		src_str += options;
@@ -476,14 +476,14 @@ size_t InitOpenCLGpu(cl_context opencl_ctx, GpuContext* ctx, const char* source_
 			}
 			while(status == CL_BUILD_IN_PROGRESS);
 
-			std::vector<size_t> binary_sizes(num_devices);
-			clGetProgramInfo (ctx->Program[ii], CL_PROGRAM_BINARY_SIZES, sizeof(size_t) * binary_sizes.size(), binary_sizes.data(), NULL);
-
-			std::vector<char*> all_programs(num_devices);
-			std::vector<std::vector<char>> program_storage;
-
 			if(xmrstak::params::inst().AMDCache)
 			{
+				std::vector<size_t> binary_sizes(num_devices);
+				clGetProgramInfo (ctx->Program[ii], CL_PROGRAM_BINARY_SIZES, sizeof(size_t) * binary_sizes.size(), binary_sizes.data(), NULL);
+
+				std::vector<char*> all_programs(num_devices);
+				std::vector<std::vector<char>> program_storage;
+
 				int p_id = 0;
 				size_t mem_size = 0;
 				// create memory  structure to query all OpenCL program binaries
@@ -935,7 +935,7 @@ size_t InitOpenCL(GpuContext* ctx, size_t num_gpus, size_t platform_idx)
 
 size_t XMRSetJob(GpuContext* ctx, uint8_t* input, size_t input_len, uint64_t target, xmrstak_algo miner_algo)
 {
-	// switch to the kernel storage 
+	// switch to the kernel storage
 	int kernel_storage = miner_algo == ::jconf::inst()->GetCurrentCoinSelection().GetDescription(1).GetMiningAlgo() ? 0 : 1;
 
 	cl_int ret;
@@ -1004,12 +1004,12 @@ size_t XMRSetJob(GpuContext* ctx, uint8_t* input, size_t input_len, uint64_t tar
 		return(ERR_OCL_API);
 	}
 
-	if(miner_algo == cryptonight_monero || miner_algo == cryptonight_aeon )
+	if(miner_algo == cryptonight_monero || miner_algo == cryptonight_aeon || miner_algo == cryptonight_ipbc || miner_algo == cryptonight_stellite)
 	{
 		// Input
 		if ((ret = clSetKernelArg(ctx->Kernels[kernel_storage][1], 3, sizeof(cl_mem), &ctx->InputBuffer)) != CL_SUCCESS)
 		{
-			printer::inst()->print_msg(L1, "Error %s when calling clSetKernelArg for kernel 1, arugment 4(input buffer).", err_to_str(ret));
+			printer::inst()->print_msg(L1, "Error %s when calling clSetKernelArg for kernel 1, argument 4(input buffer).", err_to_str(ret));
 			return ERR_OCL_API;
 		}
 	}
@@ -1102,7 +1102,7 @@ size_t XMRRunJob(GpuContext* ctx, cl_uint* HashOutput, xmrstak_algo miner_algo)
 {
 	// switch to the kernel storage
 	int kernel_storage = miner_algo == ::jconf::inst()->GetCurrentCoinSelection().GetDescription(1).GetMiningAlgo() ? 0 : 1;
-	
+
 	cl_int ret;
 	cl_uint zero = 0;
 	size_t BranchNonces[4];