wip

rin/miner/gpu/RinHash-cuda/RinHashCUDA.sln

@@ -0,0 +1,24 @@
+Microsoft Visual Studio Solution File, Format Version 12.00
+# Visual Studio Version 17
+VisualStudioVersion = 17.0.31903.59
+MinimumVisualStudioVersion = 10.0.40219.1
+Project("{8BC9CEB8-8B4A-11D0-8D11-00A0C91BC942}") = "RinHashCUDA", "RinHashCUDA.vcxproj", "{A1B2C3D4-E5F6-7890-ABCD-EF1234567890}"
+EndProject
+Global
+	GlobalSection(SolutionConfigurationPlatforms) = preSolution
+		Debug|x64 = Debug|x64
+		Release|x64 = Release|x64
+	EndGlobalSection
+	GlobalSection(ProjectConfigurationPlatforms) = postSolution
+		{A1B2C3D4-E5F6-7890-ABCD-EF1234567890}.Debug|x64.ActiveCfg = Debug|x64
+		{A1B2C3D4-E5F6-7890-ABCD-EF1234567890}.Debug|x64.Build.0 = Debug|x64
+		{A1B2C3D4-E5F6-7890-ABCD-EF1234567890}.Release|x64.ActiveCfg = Release|x64
+		{A1B2C3D4-E5F6-7890-ABCD-EF1234567890}.Release|x64.Build.0 = Release|x64
+	EndGlobalSection
+	GlobalSection(SolutionProperties) = preSolution
+		HideSolutionNode = FALSE
+	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {12345678-1234-5678-9ABC-DEF123456789}
+	EndGlobalSection
+EndGlobal

rin/miner/gpu/RinHash-cuda/RinHashCUDA.vcxproj

@@ -0,0 +1,114 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <ItemGroup Label="ProjectConfigurations">
+    <ProjectConfiguration Include="Debug|x64">
+      <Configuration>Debug</Configuration>
+      <Platform>x64</Platform>
+    </ProjectConfiguration>
+    <ProjectConfiguration Include="Release|x64">
+      <Configuration>Release</Configuration>
+      <Platform>x64</Platform>
+    </ProjectConfiguration>
+  </ItemGroup>
+  <PropertyGroup Label="Globals">
+    <VCProjectVersion>16.0</VCProjectVersion>
+    <ProjectGuid>{A1B2C3D4-E5F6-7890-ABCD-EF1234567890}</ProjectGuid>
+    <Keyword>Win32Proj</Keyword>
+    <RootNamespace>RinHashCUDA</RootNamespace>
+    <WindowsTargetPlatformVersion>10.0</WindowsTargetPlatformVersion>
+  </PropertyGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.Default.props" />
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>true</UseDebugLibraries>
+    <PlatformToolset>v143</PlatformToolset>
+    <CharacterSet>Unicode</CharacterSet>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'" Label="Configuration">
+    <ConfigurationType>Application</ConfigurationType>
+    <UseDebugLibraries>false</UseDebugLibraries>
+    <PlatformToolset>v143</PlatformToolset>
+    <WholeProgramOptimization>true</WholeProgramOptimization>
+    <CharacterSet>Unicode</CharacterSet>
+  </PropertyGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
+  <ImportGroup Label="ExtensionSettings">
+  </ImportGroup>
+  <ImportGroup Label="Shared">
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <Import Project="$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props" Condition="exists('$(UserRootDir)\Microsoft.Cpp.$(Platform).user.props')" Label="LocalAppDataPlatform" />
+  </ImportGroup>
+  <PropertyGroup Label="UserMacros" />
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <LinkIncremental>true</LinkIncremental>
+    <OutDir>$(SolutionDir)bin\$(Platform)\$(Configuration)\</OutDir>
+    <IntDir>$(SolutionDir)obj\$(Platform)\$(Configuration)\</IntDir>
+  </PropertyGroup>
+  <PropertyGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <LinkIncremental>false</LinkIncremental>
+    <OutDir>$(SolutionDir)bin\$(Platform)\$(Configuration)\</OutDir>
+    <IntDir>$(SolutionDir)obj\$(Platform)\$(Configuration)\</IntDir>
+  </PropertyGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Debug|x64'">
+    <ClCompile>
+      <WarningLevel>Level3</WarningLevel>
+      <SDLCheck>true</SDLCheck>
+      <PreprocessorDefinitions>_DEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <ConformanceMode>true</ConformanceMode>
+      <AdditionalIncludeDirectories>$(CUDA_PATH)\include;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+      <AdditionalLibraryDirectories>$(CUDA_PATH)\lib\x64;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+      <AdditionalDependencies>cudart.lib;cuda.lib;%(AdditionalDependencies)</AdditionalDependencies>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
+    <ClCompile>
+      <WarningLevel>Level3</WarningLevel>
+      <FunctionLevelLinking>true</FunctionLevelLinking>
+      <IntrinsicFunctions>true</IntrinsicFunctions>
+      <SDLCheck>true</SDLCheck>
+      <PreprocessorDefinitions>NDEBUG;_CONSOLE;%(PreprocessorDefinitions)</PreprocessorDefinitions>
+      <ConformanceMode>true</ConformanceMode>
+      <AdditionalIncludeDirectories>$(CUDA_PATH)\include;%(AdditionalIncludeDirectories)</AdditionalIncludeDirectories>
+    </ClCompile>
+    <Link>
+      <SubSystem>Console</SubSystem>
+      <EnableCOMDATFolding>true</EnableCOMDATFolding>
+      <OptimizeReferences>true</OptimizeReferences>
+      <GenerateDebugInformation>true</GenerateDebugInformation>
+      <AdditionalLibraryDirectories>$(CUDA_PATH)\lib\x64;%(AdditionalLibraryDirectories)</AdditionalLibraryDirectories>
+      <AdditionalDependencies>cudart.lib;cuda.lib;%(AdditionalDependencies)</AdditionalDependencies>
+    </Link>
+  </ItemDefinitionGroup>
+  <ItemGroup>
+    <ClCompile Include="rinhash.cu">
+      <FileType>CUDA C/C++</FileType>
+    </ClCompile>
+    <ClCompile Include="sha3-256.cu">
+      <FileType>CUDA C/C++</FileType>
+    </ClCompile>
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="argon2d_device.cuh" />
+    <ClInclude Include="blake3_device.cuh" />
+    <ClInclude Include="blaze3_cpu.cuh" />
+    <ClInclude Include="rinhash_device.cuh" />
+  </ItemGroup>
+  <ItemGroup>
+    <None Include="build-cuda.bat" />
+    <None Include="CMakeLists.txt" />
+    <None Include="Makefile" />
+    <None Include="README.md" />
+  </ItemGroup>
+  <Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
+  <ImportGroup Label="ExtensionTargets">
+    <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 12.5.targets" />
+  </ImportGroup>
+</Project>

rin/miner/gpu/RinHash-cuda/RinHashCUDA.vcxproj.filters

@@ -0,0 +1,56 @@
+<?xml version="1.0" encoding="utf-8"?>
+<Project ToolsVersion="4.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
+  <ItemGroup>
+    <Filter Include="Source Files">
+      <UniqueIdentifier>{4FC737F1-C7A5-4376-A066-2A32D38A0280}</UniqueIdentifier>
+      <Extensions>cpp;c;cc;cxx;c++;cppm;ixx;def;odl;idl;hpj;bat;asm;asmx</Extensions>
+    </Filter>
+    <Filter Include="Header Files">
+      <UniqueIdentifier>{93995380-89BD-4b04-88EB-625FBE52EBFB}</UniqueIdentifier>
+      <Extensions>h;hh;hpp;hxx;h++;hm;inl;inc;ipp;xsd</Extensions>
+    </Filter>
+    <Filter Include="CUDA Files">
+      <UniqueIdentifier>{67DA6AB6-F800-4c08-8B7A-83BB121AAD01}</UniqueIdentifier>
+      <Extensions>cu;cuh</Extensions>
+    </Filter>
+    <Filter Include="Build Files">
+      <UniqueIdentifier>{67DA6AB6-F800-4c08-8B7A-83BB121AAD02}</UniqueIdentifier>
+    </Filter>
+  </ItemGroup>
+  <ItemGroup>
+    <ClCompile Include="rinhash.cu">
+      <Filter>CUDA Files</Filter>
+    </ClCompile>
+    <ClCompile Include="sha3-256.cu">
+      <Filter>CUDA Files</Filter>
+    </ClCompile>
+  </ItemGroup>
+  <ItemGroup>
+    <ClInclude Include="argon2d_device.cuh">
+      <Filter>CUDA Files</Filter>
+    </ClInclude>
+    <ClInclude Include="blake3_device.cuh">
+      <Filter>CUDA Files</Filter>
+    </ClInclude>
+    <ClInclude Include="blaze3_cpu.cuh">
+      <Filter>CUDA Files</Filter>
+    </ClInclude>
+    <ClInclude Include="rinhash_device.cuh">
+      <Filter>CUDA Files</Filter>
+    </ClInclude>
+  </ItemGroup>
+  <ItemGroup>
+    <None Include="build-cuda.bat">
+      <Filter>Build Files</Filter>
+    </None>
+    <None Include="CMakeLists.txt">
+      <Filter>Build Files</Filter>
+    </None>
+    <None Include="Makefile">
+      <Filter>Build Files</Filter>
+    </None>
+    <None Include="README.md">
+      <Filter>Build Files</Filter>
+    </None>
+  </ItemGroup>
+</Project>

rin/miner/gpu/RinHash-cuda/argon2d_device.cuh

@@ -809,7 +809,6 @@ __device__ void device_argon2d_hash(
     block* memory,
     const uint8_t* salt, size_t salt_len
 ) {
-    argon2_instance_t instance;
     // 1. メモリサイズの調整
     uint32_t memory_blocks = m_cost;
     if (memory_blocks < 2 * ARGON2_SYNC_POINTS * lanes) {
@@ -819,16 +818,6 @@ __device__ void device_argon2d_hash(
     uint32_t segment_length = memory_blocks / (lanes * ARGON2_SYNC_POINTS);
     memory_blocks = segment_length * (lanes * ARGON2_SYNC_POINTS);
     uint32_t lane_length = segment_length * ARGON2_SYNC_POINTS;
-    
-    // Initialize instance with the provided memory pointer
-    instance.version = ARGON2_VERSION_13;
-    instance.memory = memory;  // Use the provided memory pointer
-    instance.passes = t_cost;
-    instance.memory_blocks = memory_blocks;
-    instance.segment_length = segment_length;
-    instance.lane_length = lane_length;
-    instance.lanes = lanes;
-    instance.threads = 1;
 
     // 2. 初期ハッシュの計算
     uint8_t blockhash[ARGON2_PREHASH_DIGEST_LENGTH];

rin/miner/gpu/RinHash-cuda/blake3_device.cuh

@@ -201,10 +201,12 @@ __global__ void compute(Chunk *data, int l, int r) {
         // printf("Compressing : %d\n", l);
     }
     else {
+        // Launch child kernels without synchronization (host will handle sync)
         compute<<<n/2,16>>>(data, l, l+n/2);
-        cudaDeviceSynchronize();
         compute<<<n/2,16>>>(data, l+n/2, r);
-        cudaDeviceSynchronize();
+        
+        // Wait for all threads in this block to finish
+        __syncthreads();
 
         data[l].flags |= PARENT;
 

rin/miner/gpu/RinHash-cuda/build-cuda-linux.sh

@@ -0,0 +1,99 @@
+#!/bin/bash
+# RinHash CUDA Build Script for Linux/WSL
+# This script builds the CUDA implementation of RinHash
+
+echo "======================================"
+echo "  RinHash CUDA Miner Build Script"
+echo "======================================"
+
+# Check if NVCC is available
+if ! command -v nvcc &> /dev/null; then
+    echo "ERROR: NVCC not found in PATH"
+    echo "Please install CUDA Toolkit"
+    echo "On Ubuntu/Debian: sudo apt install nvidia-cuda-toolkit"
+    echo "Or download from: https://developer.nvidia.com/cuda-downloads"
+    exit 1
+fi
+
+echo "NVCC found:"
+nvcc --version
+echo ""
+
+# Check if gcc/g++ is available
+if ! command -v gcc &> /dev/null; then
+    echo "ERROR: GCC not found in PATH"
+    echo "Please install build-essential: sudo apt install build-essential"
+    exit 1
+fi
+
+echo "GCC found:"
+gcc --version | head -1
+echo ""
+
+echo "Building RinHash CUDA miner..."
+echo ""
+
+# Create output directory
+mkdir -p bin
+
+# Compile with NVCC (enable device linking for dynamic parallelism)
+nvcc -O3 -std=c++11 \
+     -arch=sm_50 \
+     -gencode arch=compute_50,code=sm_50 \
+     -gencode arch=compute_52,code=sm_52 \
+     -gencode arch=compute_60,code=sm_60 \
+     -gencode arch=compute_61,code=sm_61 \
+     -gencode arch=compute_70,code=sm_70 \
+     -gencode arch=compute_75,code=sm_75 \
+     -gencode arch=compute_80,code=sm_80 \
+     -gencode arch=compute_86,code=sm_86 \
+     -I. \
+     rinhash.cu sha3-256.cu \
+     -o bin/rinhash-cuda-miner \
+     -lcuda -lcudart -lcudadevrt
+
+# Also build test program
+echo "Building test program..."
+nvcc -O3 -std=c++11 \
+     -arch=sm_50 \
+     -gencode arch=compute_50,code=sm_50 \
+     -gencode arch=compute_52,code=sm_52 \
+     -gencode arch=compute_60,code=sm_60 \
+     -gencode arch=compute_61,code=sm_61 \
+     -gencode arch=compute_70,code=sm_70 \
+     -gencode arch=compute_75,code=sm_75 \
+     -gencode arch=compute_80,code=sm_80 \
+     -gencode arch=compute_86,code=sm_86 \
+     -I. \
+     test_miner.cu rinhash.cu sha3-256.cu \
+     -o bin/test_miner \
+     -lcuda -lcudart -lcudadevrt
+
+if [ $? -eq 0 ]; then
+    echo ""
+    echo "======================================"
+    echo "   BUILD SUCCESSFUL!"
+    echo "======================================"
+    echo ""
+    echo "Executables created:"
+    echo "  - bin/rinhash-cuda-miner (main miner)"
+    echo "  - bin/test_miner (test program)"
+    echo ""
+    echo "To test the miner:"
+    echo "  ./bin/test_miner"
+    echo ""
+else
+    echo ""
+    echo "======================================"
+    echo "   BUILD FAILED!"
+    echo "======================================"
+    echo ""
+    echo "Common issues:"
+    echo "1. Missing CUDA runtime libraries"
+    echo "2. Incompatible CUDA version"
+    echo "3. Missing development tools"
+    echo ""
+    exit 1
+fi
+
+echo "Build completed successfully!"

rin/miner/gpu/RinHash-cuda/sha3-256.cu

@@ -111,7 +111,7 @@ __device__ void sha3_256_device(const uint8_t *input, size_t inlen, uint8_t *has
     uint64_t st[25] = {0};   // 内部状態（25ワード＝1600ビット）
 
     for (int i = 0; i < 25; i++) st[i] = 0;
-    size_t offset = 0;
+    // size_t offset = 0; // Removed unused variable
 
 
     // 通常ブロック（rateバイト）処理（今回inlen=32なのでスキップされるはず）

rin/miner/gpu/RinHash-cuda/test_miner.cu

@@ -0,0 +1,85 @@
+#include <cuda_runtime.h>
+#include <stdio.h>
+#include <string.h>
+#include <stdint.h>
+
+// External functions from our CUDA implementation
+extern "C" void RinHash(
+    const uint32_t* version,
+    const uint32_t* prev_block,
+    const uint32_t* merkle_root,
+    const uint32_t* timestamp,
+    const uint32_t* bits,
+    const uint32_t* nonce,
+    uint8_t* output
+);
+
+extern "C" void RinHash_mine(
+    const uint32_t* version,
+    const uint32_t* prev_block,
+    const uint32_t* merkle_root,
+    const uint32_t* timestamp,
+    const uint32_t* bits,
+    uint32_t start_nonce,
+    uint32_t num_nonces,
+    uint32_t* found_nonce,
+    uint8_t* target_hash,
+    uint8_t* best_hash
+);
+
+void print_hex(const char* label, const uint8_t* data, size_t len) {
+    printf("%s: ", label);
+    for (size_t i = 0; i < len; i++) {
+        printf("%02x", data[i]);
+    }
+    printf("\n");
+}
+
+int main(int argc, char* argv[]) {
+    printf("RinHash CUDA Miner Test\n");
+    printf("=======================\n\n");
+
+    // Initialize CUDA
+    cudaError_t cudaStatus = cudaSetDevice(0);
+    if (cudaStatus != cudaSuccess) {
+        fprintf(stderr, "cudaSetDevice failed! Do you have a CUDA-capable GPU?\n");
+        return 1;
+    }
+
+    // Test data - sample block header
+    uint32_t version = 0x20000000;
+    uint32_t prev_block[8] = {
+        0x12345678, 0x9abcdef0, 0x12345678, 0x9abcdef0,
+        0x12345678, 0x9abcdef0, 0x12345678, 0x9abcdef0
+    };
+    uint32_t merkle_root[8] = {
+        0xabcdef12, 0x34567890, 0xabcdef12, 0x34567890,
+        0xabcdef12, 0x34567890, 0xabcdef12, 0x34567890
+    };
+    uint32_t timestamp = 0x5f123456;
+    uint32_t bits = 0x1d00ffff;
+    uint32_t nonce = 0x12345678;
+
+    uint8_t output[32];
+    
+    printf("Testing single hash...\n");
+    RinHash(&version, prev_block, merkle_root, &timestamp, &bits, &nonce, output);
+    print_hex("Hash result", output, 32);
+
+    printf("\nTesting mining (trying 1000 nonces)...\n");
+    uint32_t found_nonce;
+    uint8_t target_hash[32];
+    uint8_t best_hash[32];
+    
+    // Set a target (easier than difficulty)
+    memset(target_hash, 0xff, 32);
+    
+    RinHash_mine(&version, prev_block, merkle_root, &timestamp, &bits, 
+                 0, 1000, &found_nonce, target_hash, best_hash);
+    
+    printf("Found nonce: 0x%08x\n", found_nonce);
+    print_hex("Best hash", best_hash, 32);
+
+    printf("\nTest completed successfully!\n");
+    return 0;
+}