From 74096418243136dfabb36bf00d634a9e6b81f4bb Mon Sep 17 00:00:00 2001 From: Jeremy Bottleson Date: Wed, 13 Nov 2024 17:41:27 -0800 Subject: [PATCH 1/3] Initial checkin of the P-ISA functional modeler and supporting common files --- functional_modeler/.clang-format | 78 + functional_modeler/.pre-commit-config.yaml | 47 + functional_modeler/CMakeLists.txt | 74 + functional_modeler/CPPLINT.cfg | 11 + functional_modeler/cmake/dependencies.cmake | 59 + functional_modeler/common/CMakeLists.txt | 15 + functional_modeler/common/config.h.in | 4 + functional_modeler/common/graph/graph.h | 599 ++++ .../common/p_isa/isa_instruction.h | 14 + functional_modeler/common/p_isa/p_isa.h | 27 + .../common/p_isa/p_isa_hardware_models.h | 138 + .../common/p_isa/p_isa_instruction.cpp | 227 ++ .../common/p_isa/p_isa_instruction.h | 364 +++ .../common/p_isa/p_isa_instructions.h | 395 +++ .../p_isa/p_isa_performance_modeler.cpp | 605 ++++ .../common/p_isa/p_isa_performance_modeler.h | 121 + .../common/p_isa/parser/p_isa_parser.cpp | 193 ++ .../common/p_isa/parser/p_isa_parser.h | 41 + functional_modeler/common/string.h | 16 + functional_modeler/common/timer/timer.h | 489 +++ functional_modeler/docs/doxyfile.in | 2844 +++++++++++++++++ .../docs/srcs/p_isa_instruction_set.md | 27 + .../functional_modeler/CMakeLists.txt | 16 + .../functional_modeler/README.md | 136 + .../data_handlers/hec_dataformats_handler.h | 279 ++ .../data_handlers/json_data_handler.h | 383 +++ .../functional_models/multiregister.h | 255 ++ .../p_isa_functional_model.h | 920 ++++++ .../functional_models/p_isa_memory_model.h | 111 + .../functional_models/utility_functions.h | 30 + .../functional_modeler/main.cpp | 679 ++++ .../pisa_runtime/p_isa_instruction_trace.h | 90 + .../pisa_runtime/pisaprogramruntime.h | 341 ++ 33 files changed, 9628 insertions(+) create mode 100644 functional_modeler/.clang-format create mode 100644 functional_modeler/.pre-commit-config.yaml create mode 100644 functional_modeler/CMakeLists.txt create mode 100644 functional_modeler/CPPLINT.cfg create mode 100644 functional_modeler/cmake/dependencies.cmake create mode 100644 functional_modeler/common/CMakeLists.txt create mode 100644 functional_modeler/common/config.h.in create mode 100644 functional_modeler/common/graph/graph.h create mode 100644 functional_modeler/common/p_isa/isa_instruction.h create mode 100644 functional_modeler/common/p_isa/p_isa.h create mode 100644 functional_modeler/common/p_isa/p_isa_hardware_models.h create mode 100644 functional_modeler/common/p_isa/p_isa_instruction.cpp create mode 100644 functional_modeler/common/p_isa/p_isa_instruction.h create mode 100644 functional_modeler/common/p_isa/p_isa_instructions.h create mode 100644 functional_modeler/common/p_isa/p_isa_performance_modeler.cpp create mode 100644 functional_modeler/common/p_isa/p_isa_performance_modeler.h create mode 100644 functional_modeler/common/p_isa/parser/p_isa_parser.cpp create mode 100644 functional_modeler/common/p_isa/parser/p_isa_parser.h create mode 100644 functional_modeler/common/string.h create mode 100644 functional_modeler/common/timer/timer.h create mode 100644 functional_modeler/docs/doxyfile.in create mode 100644 functional_modeler/docs/srcs/p_isa_instruction_set.md create mode 100644 functional_modeler/functional_modeler/CMakeLists.txt create mode 100644 functional_modeler/functional_modeler/README.md create mode 100644 functional_modeler/functional_modeler/data_handlers/hec_dataformats_handler.h create mode 100644 functional_modeler/functional_modeler/data_handlers/json_data_handler.h create mode 100644 functional_modeler/functional_modeler/functional_models/multiregister.h create mode 100644 functional_modeler/functional_modeler/functional_models/p_isa_functional_model.h create mode 100644 functional_modeler/functional_modeler/functional_models/p_isa_memory_model.h create mode 100644 functional_modeler/functional_modeler/functional_models/utility_functions.h create mode 100644 functional_modeler/functional_modeler/main.cpp create mode 100644 functional_modeler/functional_modeler/pisa_runtime/p_isa_instruction_trace.h create mode 100644 functional_modeler/functional_modeler/pisa_runtime/pisaprogramruntime.h diff --git a/functional_modeler/.clang-format b/functional_modeler/.clang-format new file mode 100644 index 0000000..b549eb3 --- /dev/null +++ b/functional_modeler/.clang-format @@ -0,0 +1,78 @@ +--- +--- +Language: Cpp +BasedOnStyle: Microsoft +AccessModifierOffset: -4 +AlignAfterOpenBracket: Align +AlignConsecutiveAssignments: true +AlignConsecutiveMacros: true +AlignOperands: true +AlignTrailingComments: false +AllowAllArgumentsOnNextLine: true +AllowAllConstructorInitializersOnNextLine: true +AllowAllParametersOfDeclarationOnNextLine: true +AllowShortCaseLabelsOnASingleLine: false +AllowShortFunctionsOnASingleLine: Inline +AllowShortIfStatementsOnASingleLine: false +AllowShortLoopsOnASingleLine: false +AlwaysBreakAfterDefinitionReturnType: None +AlwaysBreakAfterReturnType: None +AlwaysBreakTemplateDeclarations: true +BinPackArguments: true +BinPackParameters: true +BraceWrapping: + AfterCaseLabel: true + AfterClass: true + AfterControlStatement: true + AfterEnum: true + AfterFunction: true + AfterNamespace: false + AfterObjCDeclaration: true + AfterStruct: true + AfterUnion: true + BeforeCatch: true + BeforeElse: true + IndentBraces: false +BreakBeforeBinaryOperators: NonAssignment +BreakBeforeBraces: Custom +BreakBeforeTernaryOperators: false +BreakConstructorInitializers: AfterColon +ColumnLimit: 0 +CompactNamespaces: false +ConstructorInitializerAllOnOneLineOrOnePerLine: false +ConstructorInitializerIndentWidth: 4 +ContinuationIndentWidth: 4 +Cpp11BracedListStyle: false +DerivePointerAlignment: false +FixNamespaceComments: true +IndentCaseLabels: false +IndentPPDirectives: None +IndentWidth: 4 +NamespaceIndentation: None +PenaltyBreakBeforeFirstCallParameter: 19 +PenaltyBreakComment: 300 +PenaltyBreakFirstLessLess: 120 +PenaltyBreakString: 1000 +PenaltyBreakTemplateDeclaration: 10 +PenaltyExcessCharacter: 1000000 +PenaltyReturnTypeOnItsOwnLine: 1000 +PointerAlignment: Right +SortIncludes: true +SortUsingDeclarations: true +SpaceAfterCStyleCast: false +SpaceAfterLogicalNot: false +SpaceBeforeAssignmentOperators: true +SpaceBeforeCpp11BracedList: false +SpaceBeforeCtorInitializerColon: true +SpaceBeforeInheritanceColon: true +SpaceBeforeParens: ControlStatements +SpaceBeforeRangeBasedForLoopColon: true +SpaceInEmptyParentheses: false +SpacesBeforeTrailingComments: 1 +SpacesInAngles: false +SpacesInContainerLiterals: true +SpacesInCStyleCastParentheses: false +SpacesInParentheses: false +SpacesInSquareBrackets: false +ReflowComments: false +UseTab: Never diff --git a/functional_modeler/.pre-commit-config.yaml b/functional_modeler/.pre-commit-config.yaml new file mode 100644 index 0000000..cd53ff2 --- /dev/null +++ b/functional_modeler/.pre-commit-config.yaml @@ -0,0 +1,47 @@ +repos: + - repo: https://github.com/pre-commit/pre-commit-hooks + rev: v2.5.0 + hooks: + - id: trailing-whitespace + - id: end-of-file-fixer + - id: check-merge-conflict + - id: mixed-line-ending + - id: check-byte-order-marker + - repo: https://github.com/crate-ci/typos + rev: v1.20.9 # Updated 2024/04 + hooks: + - id: typos + - repo: https://github.com/Lucas-C/pre-commit-hooks + rev: v1.5.1 # Updated 2023/07 + hooks: + - id: insert-license + name: insert-license-shell + files: \.(sh|py)$ + args: + - --license-filepath + # defaults to: LICENSE.txt + - HEADER + - id: insert-license + name: insert-license-cpp + files: \.(c|cc|cxx|cpp|h|hpp|hxx|inl|h.in)$ + args: + - --license-filepath + # defaults to: LICENSE.txt + - HEADER + - --comment-style + - // # defaults to: # + - repo: local + hooks: + - id: clang-format-14 + name: clang-format-14 + entry: clang-format-14 + language: system + files: \.(c|cc|cxx|cpp|h|hpp|hxx|inl)$ + args: ["-i", "--style=file"] + - id: cpplint + name: cpplint + entry: cpplint + language: system + files: \.(c|cc|cxx|cpp|h|hpp|hxx)$ + args: + - --recursive diff --git a/functional_modeler/CMakeLists.txt b/functional_modeler/CMakeLists.txt new file mode 100644 index 0000000..61b6b2b --- /dev/null +++ b/functional_modeler/CMakeLists.txt @@ -0,0 +1,74 @@ +################################ +# P-ISA Tools Main Entrypoint +################################ + +cmake_minimum_required(VERSION 3.22) + +# General Setup +if(CMAKE_BUILD_TYPE) + set(RELEASE_TYPES + Debug + Release + RelWithDebInfo + MinSizeRel) + list(FIND RELEASE_TYPES ${CMAKE_BUILD_TYPE} INDEX_FOUND) + if(${INDEX_FOUND} EQUAL -1) + message( + FATAL_ERROR + "CMAKE_BUILD_TYPE must be one of Debug, Release, RelWithDebInfo, or MinSizeRel" + ) + endif() +else() + set(CMAKE_BUILD_TYPE "Debug" CACHE STRING "Choose the type of Build" FORCE) +endif() + +option(ENABLE_DATA_FORMATS "Enable support for the data formats library" OFF) +message(ENABLE_DATA_FORMATS="${ENABLE_DATA_FORMATS}") + +option(ENABLE_FUNCTIONAL_MODELER "Enable building of functional modeler" ON) +message(ENABLE_FUNCTIONAL_MODELER="${ENABLE_FUNCTIONAL_MODELER}") + +option(ENABLE_PROGRAM_MAPPER "Enable building of program mapper" OFF) +message(ENABLE_PROGRAM_MAPPER="${ENABLE_PROGRAM_MAPPER}") + +option(ENABLE_P_ISA_UTILITIES "Enable building of p-isa utilities" OFF) +message(ENABLE_P_ISA_UTILITIES="${ENABLE_P_ISA_UTILITIES}") + +configure_file(common/config.h.in "${CMAKE_BINARY_DIR}/p_isa_tools_config/config.h") + +project(p_isa_tools LANGUAGES CXX) + +set(CMAKE_CXX_STANDARD 17) +set(CMAKE_CXX_STANDARD_REQUIRED ON) + +# Define standard installation directories (GNU) +include(GNUInstallDirs) + +# Set default output directories +set(CMAKE_ARCHIVE_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}/${CMAKE_INSTALL_LIBDIR}") +set(CMAKE_LIBRARY_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}/${CMAKE_INSTALL_LIBDIR}") +set(CMAKE_RUNTIME_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}/${CMAKE_INSTALL_BINDIR}") + +# Find OpenMP on system +find_package(OpenMP REQUIRED) + +# External fetch and build dependencies +include(cmake/dependencies.cmake) + +# Policy is explicit header locations +set(INCLUDE_DIRS ${PROJECT_SOURCE_DIR} ${CMAKE_BINARY_DIR}/p_isa_tools_config/) + +# Include *.h files in sources so they appear in IDEs +file(GLOB_RECURSE IDE_HEADERS program_mapper/*.h functional_modeler/*.h dependencies/*.h common/*.h) + +# Build sub-directories +add_subdirectory(common) +if(ENABLE_FUNCTIONAL_MODELER) +add_subdirectory(functional_modeler) +endif() +if(ENABLE_PROGRAM_MAPPER) +add_subdirectory(program_mapper) +endif() +if(ENABLE_P_ISA_UTILITIES) +add_subdirectory(p_isa_utilities) +endif() diff --git a/functional_modeler/CPPLINT.cfg b/functional_modeler/CPPLINT.cfg new file mode 100644 index 0000000..597aa8a --- /dev/null +++ b/functional_modeler/CPPLINT.cfg @@ -0,0 +1,11 @@ +# Copyright (C) 2020 Intel Corporation +# SPDX-License-Identifier: Apache-2.0 + +# Some of these filters can be removed once existing code permits +filter=-whitespace +filter=-readability/todo +filter=-runtime/references +filter=-runtime/explicit +filter=-build/c++11 +filter=-build/namespaces +filter=-build/include diff --git a/functional_modeler/cmake/dependencies.cmake b/functional_modeler/cmake/dependencies.cmake new file mode 100644 index 0000000..47f8fbc --- /dev/null +++ b/functional_modeler/cmake/dependencies.cmake @@ -0,0 +1,59 @@ + +include(FetchContent) +FetchContent_Declare( + json_for_modern_cpp + # v3.11.2 released Aug 2023 + URL https://github.com/nlohmann/json/releases/download/v3.11.2/json.tar.xz + URL_HASH SHA256=8c4b26bf4b422252e13f332bc5e388ec0ab5c3443d24399acb675e68278d341f +) + +FetchContent_MakeAvailable(json_for_modern_cpp) + +FetchContent_Declare( + argmap + # TODO at the mo, grabs the latest this should change once versioned + URL https://raw.githubusercontent.com/helibproject/argmap/main/argmap.h + DOWNLOAD_NO_EXTRACT TRUE +) + +FetchContent_GetProperties(argmap) +if (NOT argmap_POPULATED) + FetchContent_Populate(argmap) + include_directories(${argmap_SOURCE_DIR}) +endif() + +FetchContent_Declare( + snap + # commit from Feb 2023 + GIT_REPOSITORY https://github.com/snap-stanford/snap.git + GIT_TAG 6924a035aabd1ce0a547b94e995e142f29eb5040 +) + +FetchContent_GetProperties(snap) +if (NOT snap_POPULATED) + FetchContent_Populate(snap) + message(STATUS "Building SNAP, this may take a while ...") + execute_process(COMMAND make -j + WORKING_DIRECTORY ${snap_SOURCE_DIR} + OUTPUT_QUIET + ERROR_QUIET + OUTPUT_FILE ${FETCHCONTENT_BASE_DIR}/snap.stdout + ERROR_FILE ${FETCHCONTENT_BASE_DIR}/snap.stderr + ) + add_library(snap OBJECT IMPORTED GLOBAL) + set_target_properties(snap PROPERTIES IMPORTED_OBJECTS ${snap_SOURCE_DIR}/snap-core/Snap.o) + include_directories(${snap_SOURCE_DIR}/snap-core ${snap_SOURCE_DIR}/glib-core) + message(STATUS "Finished building SNAP") +endif() + +if(ENABLE_DATA_FORMATS) + find_package(HERACLES_DATA_FORMATS CONFIG) + if(NOT HERACLES_DATA_FORMATS_FOUND) + FetchContent_Declare( + heracles_data_formats + GIT_REPOSITORY git@github.com:IntelLabs/HERACLES-data-formats.git + GIT_TAG main + ) + FetchContent_MakeAvailable(heracles_data_formats) + endif() +endif() diff --git a/functional_modeler/common/CMakeLists.txt b/functional_modeler/common/CMakeLists.txt new file mode 100644 index 0000000..ed0f519 --- /dev/null +++ b/functional_modeler/common/CMakeLists.txt @@ -0,0 +1,15 @@ +################## +# HERACLES Utils +################## + +project(common) + +set(SRCS + p_isa/p_isa_instruction.cpp + p_isa/parser/p_isa_parser.cpp + p_isa/p_isa_performance_modeler.h + p_isa/p_isa_performance_modeler.cpp +) + +add_library(common OBJECT ${SRCS}) +target_include_directories(common PRIVATE ${INCLUDE_DIRS}) diff --git a/functional_modeler/common/config.h.in b/functional_modeler/common/config.h.in new file mode 100644 index 0000000..dac9b91 --- /dev/null +++ b/functional_modeler/common/config.h.in @@ -0,0 +1,4 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#cmakedefine01 ENABLE_DATA_FORMATS diff --git a/functional_modeler/common/graph/graph.h b/functional_modeler/common/graph/graph.h new file mode 100644 index 0000000..cf42543 --- /dev/null +++ b/functional_modeler/common/graph/graph.h @@ -0,0 +1,599 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#pragma once + +#include +#include + +#include + +#include + +namespace graph { + +enum NODE_TYPE +{ + OPERATION, + REGISTER_ADDRESS, + IMMEDIATE +}; + +enum LABEL_OPTION +{ + NAME, + OUT_STRING, + ID, + NONE +}; + +template +class Node +{ +public: + Node() = default; + Node(const std::string &_label, int _ID, NODE_TYPE _type, INSTRUCTION *instr = nullptr) : + ID(_ID), + type(_type), + label(_label), + output_string(label), + instruction(instr) + { + } + + void Save(TSOut &SOut) const {} + + int ID; + int count; + NODE_TYPE type; + std::string memory_classification; + std::string label; + std::string output_string; + INSTRUCTION *instruction; + + //Perf tracking + bool scheduled = false; + int start_time = -1; + int end_time = -1; + int last_access_time = -1; +}; + +class Edge +{ +public: + void Save(TSOut &SOut) const {} + bool operator<(const Edge &b) const + { + return name < b.name; + } + + std::string name; + int value; +}; + +template +using NetworkNode = typename TNodeEDatNet, Edge>::TNodeI; +template +using Network = typename TNodeEDatNet, Edge>::PNet; + +// Wrapper to help with stream operator +template +struct with_delimiter +{ + with_delimiter(const std::vector &elements, const std::string &delim) : + elements_(elements), delimiter_(delim) {} + const std::vector &elements_; + const std::string delimiter_; +}; + +template +inline std::ostream &operator<<(std::ostream &out, const with_delimiter &nodes) +{ + for (const auto &node : nodes.elements_) + { + out << node.GetDat().label << nodes.delimiter_; + } + return out; +} + +template +class Graph +{ +public: + static Graph createGraph(std::vector instructions); + + Graph() = default; + Graph(Graph &graph) : + + network(graph.cloneGraph(graph.network)) + { + } + + Graph clone() const + { + Graph graph; + graph.network = cloneGraph(network); + return graph; + } + + void printGraphInfo() const + { + TSnap::PrintInfo(network); + } + + NetworkNode getNode(int node_id); + std::vector> getNodes() const; + std::vector> getOutputNodes() const; + std::vector> getInputNodes(bool include_registers = true, bool include_immediates = true, bool include_operations = true) const; + void removeAllExceptOutputNodes() { getOutputNodesInPlace(network); } + void removeAllExceptInputNodes() { getInputNodesInPlace(network); } + void removeNode(NetworkNode &node); + void removeNodeMaintainConnections(NetworkNode &node); + size_t getNodeCount() { return network->GetNodes(); } + std::vector>> getGraphInputLayers(); + Graph getInstructionGraph() + { + auto instruction_graph = this->clone(); + auto all_nodes = instruction_graph.getNodes(); + for (auto node : all_nodes) + { + if (node.GetDat().type != graph::OPERATION) + { + instruction_graph.removeNodeMaintainConnections(node); + } + } + return instruction_graph; + } + Graph getDataGraph() + { + auto instruction_graph = this->clone(); + auto all_nodes = instruction_graph.getNodes(); + for (auto node : all_nodes) + { + if (node.GetDat().type == graph::OPERATION) + { + instruction_graph.removeNodeMaintainConnections(node); + } + } + return instruction_graph; + } + + //Graph manipulation functions + void renderGraphToPNGDot(const std::string &filename, LABEL_OPTION label) const; + void writeDotFile(const std::string &filename, LABEL_OPTION label) const; + Graph getNodeDependencyGraph(int start_node_id, bool trace_ancestors, bool trace_dependents) const; + +private: + Network cloneGraph(const Network &input) const; + void getOutputNodesInPlace(Network &graph_output_nodes); + Network getOutputNodesInternal(const Network &graph) const; + void getInputNodesInPlace(Network &graph); + + void reverseEdgeDirections(Network &graph); + + Network GetBfsTree(const Network &graph, int start_node_id, bool in_direction, bool out_direction) const; + + TIntStrH getDataNodeNames(Network graph) const; + TIntStrH getInstructionResults(Network graph) const; + + std::map> node_ID_Map; + Network network; +}; + +template +Graph Graph::createGraph(std::vector instructions) +{ + Graph graph; + graph.network = TNodeEDatNet, Edge>::New(); + + int node_id = 0; + for (const auto &instruction : instructions) + { + int operation_ID = 0; + Node test(instruction->Name() + "_" + std::to_string(node_id), node_id, OPERATION, instruction); + graph.network->AddNode(node_id, test); + operation_ID = node_id; + graph.node_ID_Map[instruction->Name()] = std::vector({ node_id }); + node_id++; + + auto op_node = graph.network->GetNDat(operation_ID); + std::ostringstream oss; + oss << instruction->Name() << "("; + for (int x = 0; x < instruction->numInputOperands(); x++) + { + auto retrievedID = graph.node_ID_Map.find(instruction->getInputOperand(x).location()); + int input_ID = 0; + if (retrievedID == graph.node_ID_Map.end()) + { + Node input(instruction->getInputOperand(x).location(), node_id, + instruction->getInputOperand(x).immediate() ? IMMEDIATE : REGISTER_ADDRESS); + graph.network->AddNode(node_id, input); + input_ID = node_id; + graph.node_ID_Map[instruction->getInputOperand(x).location()] = std::vector({ input_ID }); + node_id++; + } + else + { + input_ID = retrievedID->second.back(); + } + + graph.network->AddEdge(input_ID, operation_ID); + + auto node = graph.network->GetNDat(input_ID); + oss << node.output_string; + if (x < instruction->numInputOperands() - 1) + { + oss << ","; + } + } + oss << ")"; + op_node.output_string = oss.str(); + for (int x = 0; x < instruction->numOutputOperands(); x++) + { + auto retrievedID = graph.node_ID_Map.find(instruction->getOutputOperand(x).location()); + int output_ID = 0; + if (retrievedID == graph.node_ID_Map.end()) + { + Node input(instruction->getOutputOperand(x).location(), node_id, REGISTER_ADDRESS); + graph.network->AddNode(node_id, input); + output_ID = node_id; + graph.node_ID_Map[instruction->getOutputOperand(x).location()] = std::vector({ output_ID }); + node_id++; + } + else + { + Node input(instruction->getOutputOperand(x).location(), node_id, REGISTER_ADDRESS); + graph.network->AddNode(node_id, input); + output_ID = node_id; + retrievedID->second.push_back(node_id); + //node_ID_Map[instruction->getOutputOperand(x).location()]=std::vector({output_ID}); + node_id++; + } + + graph.network->AddEdge(operation_ID, output_ID); + } + } + + TIntStrH outputs; + return graph; +} + +template +NetworkNode Graph::getNode(int node_id) +{ + try + { + for (auto node = network->BegNI(); node < network->EndNI(); node++) + { + if (node.GetId() == node_id) + return node; + } + throw std::runtime_error("Requested Node ID does not exist"); + } + catch (...) + { + throw; + } +} + +template +std::vector> Graph::getNodes() const +{ + std::vector> nodes; + for (auto node = network->BegNI(); node < network->EndNI(); node++) + nodes.push_back(node); + + return nodes; +} + +template +std::vector> Graph::getOutputNodes() const +{ + std::vector> nodes; + for (auto node = network->BegNI(); node < network->EndNI(); node++) + { + if (node.GetOutDeg() == 0) + { + nodes.push_back(node); + } + } + + return nodes; +} + +template +std::vector> Graph::getInputNodes(bool include_registers, bool include_immediates, bool include_operations) const +{ + std::vector> nodes; + for (auto node = network->BegNI(); node < network->EndNI(); node++) + { + if (node.GetInDeg() == 0 && ((node.GetDat().type == IMMEDIATE && include_immediates == true) || (node.GetDat().type == REGISTER_ADDRESS && include_registers == true) || (node.GetDat().type == OPERATION && include_operations == true))) + { + nodes.push_back(node); + } + } + + return nodes; +} + +template +void Graph::removeNode(NetworkNode &node) +{ + network->DelNode(node.GetId()); +} + +template +void Graph::removeNodeMaintainConnections(NetworkNode &node) +{ + std::vector prev_nodes; + std::vector after_nodes; + + for (int e = 0; e < node.GetInDeg(); e++) + { + const int prev = node.GetInNId(e); + prev_nodes.push_back(prev); + } + + for (int e = 0; e < node.GetOutDeg(); e++) + { + const int after = node.GetOutNId(e); + after_nodes.push_back(after); + } + + network->DelNode(node.GetId()); + + for (auto pnode : prev_nodes) + { + for (auto anode : after_nodes) + { + network->AddEdge(pnode, anode); + } + } + return; +} + +template +std::vector>> Graph::getGraphInputLayers() +{ + std::vector>> input_layers; + auto instruction_graph_consumable = this->clone(); + //Layer peel + while (instruction_graph_consumable.getNodeCount() > 0) + { + auto inputs = instruction_graph_consumable.getInputNodes(); + // //input_layers.push_back(inputs); + std::vector> layer; + for (auto &node : inputs) + { + + layer.push_back(this->getNode(node.GetId())); + // //std::cout << *node.GetDat().instruction << std::endl; + instruction_graph_consumable.removeNode(node); + // //std::cout << *node.GetDat().instruction << std::endl; + } + input_layers.push_back(layer); + } + return input_layers; +} + +template +Network Graph::cloneGraph(const Network &input) const +{ + Network output_graph = Network::New(); + for (auto node = input->BegNI(); node != input->EndNI(); node++) + { + output_graph->AddNode(node); + } + for (auto edge = input->BegEI(); edge != input->EndEI(); edge++) + { + output_graph->AddEdge(edge); + } + return output_graph; +} + +template +void Graph::getOutputNodesInPlace(Network &graph_output_nodes) +{ + std::vector non_zero_deg_out_nodes; + for (auto node = graph_output_nodes->BegNI(); node != graph_output_nodes->EndNI(); node++) + { + if (node.GetOutDeg() > 0) + { + non_zero_deg_out_nodes.push_back(node.GetId()); + } + } + for (const auto &node : non_zero_deg_out_nodes) + graph_output_nodes->DelNode(node); + + return; +} + +template +Network Graph::getOutputNodesInternal(const Network &graph) const +{ + auto graph_output_nodes = cloneGraph(graph); + getOutputNodesInPlace(graph_output_nodes); + return graph_output_nodes; +} + +template +void Graph::getInputNodesInPlace(Network &graph) +{ + throw std::logic_error("getInputNodesInPlace not implemented."); +} + +template +void Graph::renderGraphToPNGDot(const std::string &filename, LABEL_OPTION label) const +{ + TIntStrH name; + switch (label) + { + case LABEL_OPTION::NAME: + name = getDataNodeNames(network); + break; + case LABEL_OPTION::OUT_STRING: + name = getInstructionResults(network); + break; + default: + throw std::logic_error("Unknown label"); + } + + TSnap::DrawGViz>(network, gvlDot, filename.c_str(), "", name); +} + +template +void Graph::writeDotFile(const std::string &filename, LABEL_OPTION label) const +{ + TIntStrH name; + switch (label) + { + case LABEL_OPTION::NAME: + name = getDataNodeNames(network); + break; + case LABEL_OPTION::OUT_STRING: + name = getInstructionResults(network); + break; + default: + throw std::logic_error("Unknown label"); + } + + TSnap::SaveGViz>(network, filename.c_str(), "", name); +} + +template +Graph Graph::getNodeDependencyGraph(int start_node_id, bool trace_ancestors, bool trace_dependents) const +{ + Graph dependency_graph; + dependency_graph.network = GetBfsTree(network, start_node_id, trace_ancestors, trace_dependents); + return dependency_graph; +} + +template +void Graph::reverseEdgeDirections(Network &graph) +{ + throw std::logic_error("reverseEdgeDirections not implemented."); +} + +template +Network Graph::GetBfsTree(const Network &graph, int start_node_id, bool in_direction, bool out_direction) const +{ + TBreathFS> BFS(graph); + BFS.DoBfs(start_node_id, out_direction, in_direction, -1, TInt::Mx); + Network tree = Network::New(); + BFS.NIdDistH.SortByDat(); + + for (int i = 0; i < BFS.NIdDistH.Len(); i++) + { + const int NId = BFS.NIdDistH.GetKey(i); + const int Dist = BFS.NIdDistH[i]; + auto NI = graph->GetNI(NId); + if (!tree->IsNode(NId)) + { + auto dataNode = graph->GetNI(NId); + tree->AddNode(dataNode); + } + } + + for (int i = 0; i < BFS.NIdDistH.Len(); i++) + { + const int NId = BFS.NIdDistH.GetKey(i); + const int Dist = BFS.NIdDistH[i]; + auto NI = graph->GetNI(NId); + + if (in_direction) + { + for (int e = 0; e < NI.GetInDeg(); e++) + { + const int Prev = NI.GetInNId(e); + // std::cout << "prev: " << Prev; + // std::cout << " NId: " << NI.GetId() << std::endl; + if (tree->IsNode(Prev) /*&& BFS.NIdDistH.GetDat(Prev)==Dist-1*/) + { + tree->AddEdge(Prev, NId); + } + } + } + + if (out_direction) + { + for (int e = 0; e < NI.GetOutDeg(); e++) + { + const int Prev = NI.GetOutNId(e); + if (tree->IsNode(Prev) /*&& BFS.NIdDistH.GetDat(Prev)==Dist-1*/) + { + tree->AddEdge(Prev, NId); + } + } + } + } + + return tree; +} + +template +TIntStrH Graph::getDataNodeNames(Network graph) const +{ + TIntStrH name; + for (auto node = graph->BegNI(); node != graph->EndNI(); node++) + { + name.AddDat(node.GetId()) = TStr(node.GetDat().label.c_str()); + std::string color = "white"; + if (node.GetInDeg() == 0) + { + color = "skyblue3"; + } + if (node.GetOutDeg() == 0) + { + color = "seagreen1"; + } + + std::string output_color_and_label = std::string(node.GetDat().label + '"' + ", style=filled, fillcolor=" + '"' + color); + name.AddDat(node.GetId(), output_color_and_label.c_str()); + } + return name; +} + +template +TIntStrH Graph::getInstructionResults(Network graph) const +{ + TIntStrH name; + for (auto node = graph->BegNI(); node != graph->EndNI(); node++) + { + std::ostringstream label_stream; + label_stream << node.GetDat().label << "= "; + + auto *instruction = node.GetDat().instruction; + if (instruction != nullptr) + { + //label_stream << instruction->outLabel(); + } + const std::string label = label_stream.str(); + name.AddDat(node.GetId()) = TStr(label.c_str()); + } + return name; +} + +/** + * @brief printGraphInformation Prints out some high level summary information for an HE graph. + * @param graph + */ +template +void printGraphInformation(Graph &graph, const std::string &desc) +{ + try + { + std::cout << desc << std::endl; + graph.printGraphInfo(); + auto inputs = graph.getInputNodes(); + auto outputs = graph.getOutputNodes(); + std::cout << "inputs:" << inputs.size() << '\n' + << with_delimiter(inputs, " , ") << '\n' + << "outputs:" << outputs.size() << '\n' + << with_delimiter(outputs, " , ") << std::endl; + } + catch (...) + { + throw; + } +} +} // namespace graph diff --git a/functional_modeler/common/p_isa/isa_instruction.h b/functional_modeler/common/p_isa/isa_instruction.h new file mode 100644 index 0000000..c1d3a74 --- /dev/null +++ b/functional_modeler/common/p_isa/isa_instruction.h @@ -0,0 +1,14 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#pragma once + +/** + * @brief The ISAInstruction class used to represent an generic ISA instruction + * + */ +class ISAInstruction +{ +public: + ISAInstruction() = default; +}; diff --git a/functional_modeler/common/p_isa/p_isa.h b/functional_modeler/common/p_isa/p_isa.h new file mode 100644 index 0000000..f940e8d --- /dev/null +++ b/functional_modeler/common/p_isa/p_isa.h @@ -0,0 +1,27 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#pragma once + +#include "p_isa_instructions.h" +#include + +namespace pisa { + +///** InstructionMap provides a mapping from OP name to implementation of that instruction. +// * +// **/ + +static const std::map InstructionMap = { + { instruction::Add::baseName, new instruction::Add() }, + { instruction::Sub::baseName, new instruction::Sub() }, + { instruction::Mul::baseName, new instruction::Mul() }, + { instruction::Mac::baseName, new instruction::Mac() }, + { instruction::Maci::baseName, new instruction::Maci() }, + { instruction::Intt::baseName, new instruction::Intt() }, + { instruction::Ntt::baseName, new instruction::Ntt() }, + { instruction::Muli::baseName, new instruction::Muli() }, + { instruction::Copy::baseName, new instruction::Copy() } +}; + +} // namespace pisa diff --git a/functional_modeler/common/p_isa/p_isa_hardware_models.h b/functional_modeler/common/p_isa/p_isa_hardware_models.h new file mode 100644 index 0000000..2c07f5b --- /dev/null +++ b/functional_modeler/common/p_isa/p_isa_hardware_models.h @@ -0,0 +1,138 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#pragma once + +#include +#include +#include + +namespace pisa::PerformanceModels { + +struct InstructionPerfCharacteristics +{ + InstructionPerfCharacteristics() = default; + InstructionPerfCharacteristics(int _throughput, int _latency) : + throughput(_throughput), + latency(_latency) + { + } + + int throughput = 1; + int latency = 1; +}; + +class PISAHardwareModel +{ +public: + std::map ISAInstructionPerformanceMap; + // Memory behavior performance map + std::map ISAInstructionMemoryMap; + std::map MemorySizesMap; +}; + +class ExampleHardware : public PISAHardwareModel +{ +public: + ExampleHardware() + { + ISAInstructionPerformanceMap = { + { pisa::instruction::Add::baseName, InstructionPerfCharacteristics(8192, 8192) }, + { pisa::instruction::Sub::baseName, InstructionPerfCharacteristics(8192, 8192) }, + { pisa::instruction::Mul::baseName, InstructionPerfCharacteristics(8192, 8192) }, + { pisa::instruction::Mac::baseName, InstructionPerfCharacteristics(8192, 8192) }, + { pisa::instruction::Maci::baseName, InstructionPerfCharacteristics(8192, 8192) }, + { pisa::instruction::Intt::baseName, InstructionPerfCharacteristics(8192 * 6, 8192 * 6) }, + { pisa::instruction::Ntt::baseName, InstructionPerfCharacteristics(8192 * 6, 8192 * 6) }, + { pisa::instruction::Muli::baseName, InstructionPerfCharacteristics(8192, 8192) } + }; + + // Memory behavior performance map + ISAInstructionMemoryMap = { + { "MEMORY", InstructionPerfCharacteristics(1, 40) }, + { "MEMORY_CACHE", InstructionPerfCharacteristics(5, 44) }, + { "CACHE", InstructionPerfCharacteristics(4, 4) }, + { "REGISTER", InstructionPerfCharacteristics(1, 1) }, + + }; + + MemorySizesMap = { + { "MEMORY", uint64_t(1572000) }, + { "CACHE", uint64_t(1572000) }, + { "REGISTER", uint64_t(1572000) }, + + }; + } +}; + +class Model1 : public PISAHardwareModel +{ +public: + Model1() + { + ISAInstructionPerformanceMap = { + { pisa::instruction::Add::baseName, InstructionPerfCharacteristics(1, 6) }, + { pisa::instruction::Sub::baseName, InstructionPerfCharacteristics(1, 6) }, + { pisa::instruction::Mul::baseName, InstructionPerfCharacteristics(1, 6) }, + { pisa::instruction::Mac::baseName, InstructionPerfCharacteristics(1, 6) }, + { pisa::instruction::Maci::baseName, InstructionPerfCharacteristics(1, 6) }, + { pisa::instruction::Intt::baseName, InstructionPerfCharacteristics(1, 33) }, + { pisa::instruction::Ntt::baseName, InstructionPerfCharacteristics(1, 33) }, + { pisa::instruction::Muli::baseName, InstructionPerfCharacteristics(1, 6) } + }; + + // Memory behavior performance map + ISAInstructionMemoryMap = { + { "MEMORY", InstructionPerfCharacteristics(1, 40) }, + { "MEMORY_CACHE", InstructionPerfCharacteristics(5, 44) }, + { "CACHE", InstructionPerfCharacteristics(4, 4) }, + { "REGISTER", InstructionPerfCharacteristics(1, 1) }, + + }; + + MemorySizesMap = { + { "MEMORY", uint64_t(1572000) }, + { "CACHE", uint64_t(1572000) }, + { "REGISTER", uint64_t(1572000) }, + + }; + } +}; + +class Model2 : public PISAHardwareModel +{ +public: + Model2() + { + ISAInstructionPerformanceMap = { + { pisa::instruction::Add::baseName, InstructionPerfCharacteristics(1, 6) }, + { pisa::instruction::Sub::baseName, InstructionPerfCharacteristics(1, 6) }, + { pisa::instruction::Mul::baseName, InstructionPerfCharacteristics(1, 6) }, + { pisa::instruction::Mac::baseName, InstructionPerfCharacteristics(1, 6) }, + { pisa::instruction::Maci::baseName, InstructionPerfCharacteristics(1, 6) }, + { pisa::instruction::Intt::baseName, InstructionPerfCharacteristics(1, 33) }, + { pisa::instruction::Ntt::baseName, InstructionPerfCharacteristics(1, 33) }, + { pisa::instruction::Muli::baseName, InstructionPerfCharacteristics(1, 6) } + }; + + // Memory behavior performance map + ISAInstructionMemoryMap = { + { "MEMORY", InstructionPerfCharacteristics(1, 40) }, + { "MEMORY_CACHE", InstructionPerfCharacteristics(5, 44) }, + { "CACHE", InstructionPerfCharacteristics(4, 4) }, + { "REGISTER", InstructionPerfCharacteristics(1, 1) }, + + }; + + MemorySizesMap = { + { "MEMORY", uint64_t(1572000) }, + { "CACHE", uint64_t(2048) }, + { "REGISTER", uint64_t(256) }, + + }; + } +}; + +static std::map hardwareModels = { { "example", ExampleHardware() }, { "model1", Model1() }, { "model2", Model2() } }; + +} // namespace pisa::PerformanceModels diff --git a/functional_modeler/common/p_isa/p_isa_instruction.cpp b/functional_modeler/common/p_isa/p_isa_instruction.cpp new file mode 100644 index 0000000..6bff8f4 --- /dev/null +++ b/functional_modeler/common/p_isa/p_isa_instruction.cpp @@ -0,0 +1,227 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#include "p_isa_instruction.h" + +namespace pisa { +PISAInstruction::PISAInstruction(std::string name) : + m_operation_name(name) +{ +} + +PISAInstruction::PISAInstruction(std::string name, InstructionDesc desc) : + m_operation_name(name), + m_description(desc) +{ +} + +Operand &PISAInstruction::getInputOperand(int n) +{ + m_input_operands[n].setOutputBank(m_output_block); + return m_input_operands[n]; +} + +Operand &PISAInstruction::getOutputOperand(int n) +{ + m_output_operands[n].setOutputBank(m_output_block); + return m_output_operands[n]; +} + +void PISAInstruction::setInputOperand(const Operand &op, int n) +{ + m_input_operands[n] = op; +} + +void PISAInstruction::setOutputOperand(const Operand &op, int n) +{ + m_output_operands[n] = op; +} + +void PISAInstruction::addInputOperand(const Operand &op) +{ + m_input_operands.push_back(op); +} + +void PISAInstruction::addOutputOperand(const Operand &op) +{ + m_output_operands.push_back(op); +} + +int PISAInstruction::PMD() const +{ + return m_pmd_log2; +} + +void PISAInstruction::setPMD(int newPmd_log2) +{ + m_pmd_log2 = newPmd_log2; +} + +const std::string &PISAInstruction::Name() const +{ + return m_operation_name; +} + +void PISAInstruction::setName(const std::string &newOperation_name) +{ + m_operation_name = newOperation_name; +} + +int PISAInstruction::residual() const +{ + return m_residual; +} + +void PISAInstruction::setResidual(int newResidual) +{ + m_residual = newResidual; +} + +int PISAInstruction::numOutputOperands() const +{ + return m_output_operands.size(); +} + +int PISAInstruction::numInputOperands() const +{ + return m_input_operands.size(); +} + +int PISAInstruction::stage() const +{ + return m_stage; +} + +void PISAInstruction::setStage(int newStage) +{ + m_stage = newStage; +} + +int PISAInstruction::block() const +{ + return m_block; +} + +void PISAInstruction::setBlock(int newBlock) +{ + m_block = newBlock; +} + +// temporary +int PISAInstruction::galois_element() const +{ + return m_galois_element; +} + +void PISAInstruction::setGalois_element(int newGalois_element) +{ + m_galois_element = newGalois_element; +} + +std::string PISAInstruction::operationName() +{ + return std::string("base"); +} + +const InstructionDesc PISAInstruction::getDescription() const +{ + return m_description; +} + +PISAInstruction *PISAInstruction::create() +{ + return new PISAInstruction("none"); +} + +const WParam &PISAInstruction::wParam() const +{ + return m_w_param; +} + +void PISAInstruction::setWParam(const WParam &newW_param) +{ + m_w_param = newW_param; +} + +bool PISAInstruction::outputBlock() const +{ + return m_output_block; +} + +void PISAInstruction::setOutputBlock(bool newOutput_block) +{ + m_output_block = newOutput_block; +} + +int PISAInstruction::groupId() const +{ + return m_group_id; +} + +void PISAInstruction::setGroupId(int newGroup_id) +{ + m_group_id = newGroup_id; +} + +int WParam::residual() const +{ + return m_residual; +} + +void WParam::setResidual(int newResidual) +{ + m_residual = newResidual; +} + +int WParam::stage() const +{ + return m_stage; +} + +void WParam::setStage(int newStage) +{ + m_stage = newStage; +} + +int WParam::block() const +{ + return m_block; +} + +void WParam::setBlock(int newBlock) +{ + m_block = newBlock; +} + +bool Operand::immediate() const +{ + return m_immediate; +} + +void Operand::setImmediate(bool newImmediate) +{ + m_immediate = newImmediate; +} + +const std::string &Operand::locationRoot() const +{ + return m_location_root; +} + +void Operand::setLocationRoot(const std::string &newLocation_root) +{ + m_location_root = newLocation_root; + m_location = m_location_root + m_location_index; +} + +bool Operand::outputBank() const +{ + return m_output_bank; +} + +void Operand::setOutputBank(bool newOutput_bank) +{ + m_output_bank = newOutput_bank; +} + +} // namespace pisa diff --git a/functional_modeler/common/p_isa/p_isa_instruction.h b/functional_modeler/common/p_isa/p_isa_instruction.h new file mode 100644 index 0000000..e11d400 --- /dev/null +++ b/functional_modeler/common/p_isa/p_isa_instruction.h @@ -0,0 +1,364 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#pragma once + +#include +#include +#include +#include +#include +#include +#include + +#include "isa_instruction.h" + +namespace pisa { +/** + * @brief The PARAM_TYPE enum used to indicate the type of a parameter during instruction parsing + */ +enum PARAM_TYPE +{ + OP_NAME, + INPUT_OPERAND, + OUTPUT_OPERAND, + INPUT_OUTPUT_OPERAND, + POLYMOD_DEG_LOG2, + RESIDUAL, + W_PACKED_PARAM, + IMMEDIATE, + GROUP_ID, + STAGE, + BLOCK, + // temporary + GALOIS_ELEMENT, + ADDITIONAL_PARAMS +}; + +enum class INSTRUCTIONS +{ +}; + +/** + * @brief The InstructionDesc struct stores a vector of param type objects used to describe the type of parameter in each location of an instruction + */ +struct InstructionDesc +{ + InstructionDesc() = default; + InstructionDesc(const std::initializer_list &_params) : + params(_params) {} + + std::vector params; +}; + +/** + * @brief The WParam class + * w___ + */ +class WParam +{ +public: + WParam() = default; + + WParam(const std::string &w_param) + { + std::stringstream splitter(w_param); + std::string token; + //Remove preamble + std::getline(splitter, token, '_'); + + //Get the residual + std::getline(splitter, token, '_'); + m_residual = stoi(token); + + //Get stage + std::getline(splitter, token, '_'); + m_stage = stoi(token); + + //block + std::getline(splitter, token); + m_block = stoi(token); + } + + friend std::ostream &operator<<(std::ostream &stream, WParam op) + { + stream << "w_" << op.residual() << "_" << op.stage() << "_" << op.block(); + return stream; + } + + int residual() const; + void setResidual(int newResidual); + + int stage() const; + void setStage(int newStage); + + int block() const; + void setBlock(int newBlock); + +private: + int m_residual; + int m_stage; + int m_block; +}; + +/** + * @brief The Operand class represents an operand for a PISA instruction. + */ +class Operand +{ +public: + Operand() : + m_location("unassigned"), + m_bank(-1) + { + } + + Operand(const std::string &_location, bool _immediate) : + m_location(_location), + m_immediate(_immediate) + { + } + + Operand(const std::string &name, int bank) : + m_bank(bank), + m_immediate(false) + { + setLocation(name); + } + + Operand(const std::string &location_and_bank) + { + std::string location; + std::string bank; + + std::istringstream splitter(location_and_bank); + splitter >> std::skipws >> location; + splitter >> bank; + + setLocation(location); + if (bank.size() > 2) + { + bank = bank.substr(1, bank.size() - 2); + m_bank = std::stoi(bank); + } + m_immediate = false; + } + + const std::string &location() const + { + return m_location; + } + + void setLocation(const std::string &newLocation) + { + const auto &[root, index] = splitLocation(newLocation); + m_location_root = root; + m_location_index = index; + m_location = root + index; + } + + int bank() const + { + return m_bank; + } + + void setBank(int newBank) + { + m_bank = newBank; + } + + friend std::ostream &operator<<(std::ostream &stream, const Operand &op) + { + stream << op.location(); + if (op.immediate() == false && op.outputBank()) + stream << " (" << op.bank() << ")"; + + return stream; + } + + bool immediate() const; + void setImmediate(bool newImmediate); + + const std::string &locationRoot() const; + void setLocationRoot(const std::string &newLocation_root); + + bool outputBank() const; + void setOutputBank(bool newOutput_bank); + +private: + /** + * @brief splitLocation + * @param location + * Attempts to split the register name into a root and address portion. Does this by reversing V0 logic that always appends poly and rns terms + * to end of input/register names(but varies depending on if 1 or n outputs) + */ + static std::pair splitLocation(const std::string &location) + { + std::string reg_name = location; + int count = std::count(location.begin(), location.end(), '_'); + if (count == 0) + return std::pair{ location, "" }; + + int size = reg_name.size(); + for (int x = 0; x < count; x++) + { + size = reg_name.rfind('_', size) - 1; + } + size = size + 1; + + return std::pair{ location.substr(0, size), + location.substr(size, location.size()) }; + } + + std::string m_location_root; + std::string m_location_index; + std::string m_location; + int m_bank; + bool m_immediate; + bool m_output_bank = true; +}; + +/** + * @brief The PISAInstruction class represents an instruction in the P-ISA instruction set. + * It is designed to be able to store all ISA instructions, not all elements are used for every instruction. + * The exact elements used by each instruction is stored in InstructionDesc. + */ + +class PISAInstruction : public ISAInstruction +{ + +public: + PISAInstruction(std::string name); + PISAInstruction(std::string name, InstructionDesc desc); + + Operand &getInputOperand(int n); + + Operand &getOutputOperand(int n); + + void setInputOperand(const Operand &op, int n); + + void setOutputOperand(const Operand &op, int n); + + void addInputOperand(const Operand &op); + + void addOutputOperand(const Operand &op); + + int PMD() const; + void setPMD(int newPmd_log2); + + const std::string &Name() const; + void setName(const std::string &newOperation_name); + + int residual() const; + void setResidual(int newResidual); + + friend std::ostream &operator<<(std::ostream &stream, PISAInstruction instr) + { + int input_count = 0; + int output_count = 0; + int element = 0; + for (pisa::PARAM_TYPE x : instr.getDescription().params) + { + if (element != 0) + stream << ", "; + + switch (x) + { + case pisa::GROUP_ID: + stream << instr.groupId() << " "; + break; + case pisa::STAGE: + stream << instr.stage() << " "; + break; + case pisa::BLOCK: + stream << instr.block() << " "; + break; + case pisa::OP_NAME: + stream << instr.Name() << " "; + break; + case pisa::INPUT_OPERAND: + stream << instr.getInputOperand(input_count); + input_count++; + break; + case pisa::OUTPUT_OPERAND: + stream << instr.getOutputOperand(output_count); + output_count++; + break; + case pisa::INPUT_OUTPUT_OPERAND: + stream << instr.getOutputOperand(output_count); + input_count++; + output_count++; + break; + case pisa::POLYMOD_DEG_LOG2: + stream << instr.PMD(); + break; + case pisa::RESIDUAL: + stream << instr.residual(); + break; + case pisa::W_PACKED_PARAM: + stream << instr.wParam(); + break; + case pisa::IMMEDIATE: + stream << instr.getInputOperand(input_count); + input_count++; + break; + // temporary + case pisa::GALOIS_ELEMENT: + stream << instr.galois_element(); + input_count++; + break; + case pisa::ADDITIONAL_PARAMS: + break; + } + element++; + } + + return stream; + } + + int numOutputOperands() const; + int numInputOperands() const; + + int stage() const; + void setStage(int newStage); + + int block() const; + void setBlock(int newBlock); + + const WParam &wParam() const; + void setWParam(const WParam &newW_param); + // temporary + int galois_element() const; + void setGalois_element(int newGalois_element); + + static std::string operationName(); + + const InstructionDesc getDescription() const; + virtual PISAInstruction *create(); + + bool outputBlock() const; + void setOutputBlock(bool newOutput_block); + + int groupId() const; + void setGroupId(int newGroup_id); + +protected: + int m_pmd_log2; + std::string m_operation_name; + std::vector m_input_operands; + std::vector m_output_operands; + std::vector m_additional_params; + WParam m_w_param; + int m_residual; + int m_group_id; + int m_stage; + + int m_galois_element; + + int m_block; + //Specifies if block parameter should be output as part of operand + bool m_output_block; + InstructionDesc m_description; +}; + +} // namespace pisa diff --git a/functional_modeler/common/p_isa/p_isa_instructions.h b/functional_modeler/common/p_isa/p_isa_instructions.h new file mode 100644 index 0000000..306acd6 --- /dev/null +++ b/functional_modeler/common/p_isa/p_isa_instructions.h @@ -0,0 +1,395 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#pragma once + +#include "p_isa_instruction.h" +#include + +/** + * @brief This namespace encapulates p-ISA instruction(s). + * + */ +namespace pisa::instruction { + +/** + * + * {POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, RESIDUAL} + * **/ +static const pisa::InstructionDesc description_Add = { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, RESIDUAL }; +/** + * @class Add + * \brief + * The Add class represents an Add instruction in P_ISA. + * It receives as input 2 source registers which are added modulus some environment state value Q and result is written to dst. + * + * | Argument | Type | Description | + * | :---------------- | :------ | :--------| + * | POLYMOD_DEG_LOG2 | Int | Not used | + * | OP_NAME | string | add | + * | OUTPUT_OPERAND [out] | string | dst = label of output register | + * | INPUT_OPERAND | string | src1 = label of input register | + * | INPUT_OPERAND | string | src2 = label of input register | + * | RESIDUAL | int | mod_q = index of modulus value to use | + * @details High level functional description: + * dst = (src1+src2) % modulus_chain[mod_q] + */ +class Add : public PISAInstruction +{ +public: + Add() : + PISAInstruction(baseName, description_Add) {} + + Add(int poly_mod, Operand output_op, Operand input_op0, Operand input_op1, int residual) : + Add() + { + setPMD(poly_mod); + addOutputOperand(output_op); + addInputOperand(input_op0); + addInputOperand(input_op1); + setResidual(residual); + } + + inline static const std::string baseName = "add"; + PISAInstruction *create() override { return new Add(); } +}; + +/** + * + * {POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, RESIDUAL} + * **/ +static const pisa::InstructionDesc description_Sub = { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, RESIDUAL }; + +/** + * @class Sub + * @brief The Sub class represents a Sub instruction in P_ISA. + * It receives as input 2 source registers which are subtracted modulus some environment state value Q and result is written to dst. + * + * | Argument | Type | Description | + * | :---------------- | :------ | :--------| + * | POLYMOD_DEG_LOG2 | Int | Not used | + * | OP_NAME | string | sub | + * | OUTPUT_OPERAND [out] | string | dst = label of output register | + * | INPUT_OPERAND | string | src1 = label of input register | + * | INPUT_OPERAND | string | src2 = label of input register | + * | RESIDUAL | int | mod_q = index of modulus value to use | + * + * @details High level functional description: + * dst = (src1-src2) % modulus_chain[mod_q] + */ +class Sub : public PISAInstruction +{ +public: + Sub() : + PISAInstruction(baseName, description_Sub) {} + Sub(int poly_mod, Operand output_op, Operand input_op0, Operand input_op1, int residual) : + Sub() + { + setPMD(poly_mod); + addOutputOperand(output_op); + addInputOperand(input_op0); + addInputOperand(input_op1); + setResidual(residual); + return; + } + + inline static const std::string baseName = "sub"; + PISAInstruction *create() override { return new Sub(); } +}; + +/** + * + * { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, RESIDUAL } + * **/ +static const pisa::InstructionDesc description_Mul = { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, RESIDUAL }; +/** + * @class Mul + * @brief The Mul class represents an multiply instruction in P_ISA. + * It receives as input 2 source registers which are multiplied modulus some environment state value Q and result is written to dst. + * + * | Argument | Type | Description | + * | :---------------- | :------ | :--------| + * | POLYMOD_DEG_LOG2 | Int | Not used | + * | OP_NAME | string | mul | + * | OUTPUT_OPERAND [out] | string | dst = label of output register | + * | INPUT_OPERAND | string | src1 = label of input register | + * | INPUT_OPERAND | string | src2 = label of input register | + * | RESIDUAL | int | mod_q = index of modulus value to use | + * @details High level functional description: + * dst = (src1*src2) % modulus_chain[mod_q] + */ +class Mul : public PISAInstruction +{ +public: + Mul() : + PISAInstruction(baseName, description_Mul) {} + + Mul(int poly_mod, Operand output_op, Operand input_op0, Operand input_op1, int residual) : + Mul() + { + setPMD(poly_mod); + addOutputOperand(output_op); + addInputOperand(input_op0); + addInputOperand(input_op1); + setResidual(residual); + return; + } + + inline static const std::string baseName = "mul"; + PISAInstruction *create() override { return new Mul(); } +}; +/** + * + * { POLYMOD_DEG_LOG2, OP_NAME, INPUT_OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, RESIDUAL } + * **/ +static const pisa::InstructionDesc description_Mac = { POLYMOD_DEG_LOG2, OP_NAME, INPUT_OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, RESIDUAL }; +/** + * @brief The Mac class represents an multiply accumulate instruction in P_ISA. + * It receives as input 2 source registers which are multiplied and then added to the value in the output register modulus some environment state value Q. + * | Argument | Type | Description | + * | :---------------- | :------ | :--------| + * | POLYMOD_DEG_LOG2 | Int | Not used | + * | OP_NAME | string | mac | + * | INPUT_OUTPUT_OPERAND [in/out] | string | dst = label of register to accumulate result value to| + * | INPUT_OPERAND | string | src1 = label of input register | + * | INPUT_OPERAND | string | src2 = label of input register | + * | RESIDUAL | int | mod_q = index of modulus value to use | + * @details High level functional description: + * dst = (dst + (src1*src2) % modulus_chain[mod_q]) % modulus_chain[mod_q] + */ +class Mac : public PISAInstruction +{ +public: + Mac() : + PISAInstruction(baseName, description_Mac) {} + Mac(int poly_mod, Operand input_output_op, Operand input_op0, Operand input_op1, int residual) : + Mac() + { + setPMD(poly_mod); + addOutputOperand(input_output_op); + addInputOperand(input_output_op); + addInputOperand(input_op0); + addInputOperand(input_op1); + setResidual(residual); + return; + } + + inline static const std::string baseName = "mac"; + PISAInstruction *create() override { return new Mac(); } +}; + +/** + * + * { POLYMOD_DEG_LOG2, OP_NAME, INPUT_OUTPUT_OPERAND, INPUT_OPERAND, IMMEDIATE, RESIDUAL } + * **/ +static const pisa::InstructionDesc description_Maci = { POLYMOD_DEG_LOG2, OP_NAME, INPUT_OUTPUT_OPERAND, INPUT_OPERAND, IMMEDIATE, RESIDUAL }; +/** + * @brief The Maci class represents a multiply accumulate immediate instruction in P_ISA. + * It receives as input 1 source register and 1 immediate which are multiplied and then added to the value in the output register modulus some environment state value Q. + * | Argument | Type | Description | + * | :---------------- | :------ | :--------| + * | POLYMOD_DEG_LOG2 | Int | Not used | + * | OP_NAME | string | maci | + * | INPUT_OUTPUT_OPERAND [in/out] | string | dst = label of input and output register | + * | INPUT_OPERAND | string | src1 = label of input register | + * | IMMEDIATE | string | imm = label of input immediate | + * | RESIDUAL | int | mod_q = index of modulus value to use | + * @details High level functional description: + * dst = (dst + (src1*imm) % modulus_chain[mod_q]) % modulus_chain[mod_q] + */ +class Maci : public PISAInstruction +{ +public: + Maci() : + PISAInstruction(baseName, description_Maci) {} + Maci(int poly_mod, Operand input_output_op, Operand input_op0, Operand input_op1, int residual) : + Maci() + { + setPMD(poly_mod); + addOutputOperand(input_output_op); + addInputOperand(input_output_op); + addInputOperand(input_op0); + input_op1.setImmediate(true); + addInputOperand(input_op1); + setResidual(residual); + return; + } + + inline static const std::string baseName = "maci"; + PISAInstruction *create() override { return new Maci(); } +}; + +/** + * + * { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, W_PACKED_PARAM, RESIDUAL, GALOIS_ELEMENT } + * **/ +static const pisa::InstructionDesc description_Intt = { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, W_PACKED_PARAM, RESIDUAL, GALOIS_ELEMENT }; +/** + * @brief The Intt class represents a intt instruction in P_ISA. Each intt instruction performs a partial intt operation on a given ciphertext. To fully perform an inverse + * intt a series of operations + * | Argument | Type | Description | + * | :---------------- | :------ | :--------| + * | POLYMOD_DEG_LOG2 | Int | Used for bit reversal and address calculations | + * | OP_NAME | string | intt | + * | OUTPUT_OPERAND [out] | string | dst1 = label of output register | + * | OUTPUT_OPERAND [out] | string | dst2 = label of output register | + * | INPUT_OPERAND | string | src1 = label of input register | + * | INPUT_OPERAND | string | src2 = label of input register | + * | W_PACKED_PARAM | string | encodes as a string the following values residual_stage_block used for intt calculations | + * | RESIDUAL | int | mod_q = index of modulus value to use | + * | GALOIS_ELEMENT | int | ge = used to determine which set of inverse twiddle factors to use for the current intt operation | + * + * @details High level functional description: + * #TBD needs to inverse ntt? + */ +class Intt : public PISAInstruction +{ +public: + Intt() : + PISAInstruction(baseName, description_Intt) + { + m_galois_element = 1; + } + + inline static const std::string baseName = "intt"; + PISAInstruction *create() override { return new Intt(); } + // galois element default param will be removed or labeled in future update + Intt(int poly_mod, Operand output_op0, Operand output_op1, Operand input_op0, Operand input_op1, WParam w_param, int residual, int galois_element = 1) : + Intt() + { + setPMD(poly_mod); + addOutputOperand(output_op0); + addOutputOperand(output_op1); + addInputOperand(input_op0); + addInputOperand(input_op1); + setWParam(w_param); + setResidual(residual); + // temporary + setGalois_element(galois_element); + return; + } +}; + +/** + * + * { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, W_PACKED_PARAM, RESIDUAL } + * **/ +static const pisa::InstructionDesc description_Ntt = { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, OUTPUT_OPERAND, INPUT_OPERAND, INPUT_OPERAND, W_PACKED_PARAM, RESIDUAL }; +/** + * @brief The Ntt class represents an ntt instruction in P_ISA. + * | Argument | Type | Description | + * | :---------------- | :------ | :--------| + * | POLYMOD_DEG_LOG2 | Int | Used for bit reversal and address calculations | + * | OP_NAME | string | ntt | + * | OUTPUT_OPERAND [out] | string | dst1 = label of output register | + * | OUTPUT_OPERAND [out] | string | dst2 = label of output register | + * | INPUT_OPERAND | string | src1 = label of input register | + * | INPUT_OPERAND | string | src2 = label of input register | + * | W_PACKED_PARAM | string | encodes as a string the following values residual_stage_block used for intt calculations | + * | RESIDUAL | int | mod_q = index of modulus value to use | + * + * @details High level functional description: + * #TBD needs to ntt? + */ +class Ntt : public PISAInstruction +{ +public: + Ntt() : + PISAInstruction(baseName, description_Ntt) {} + Ntt(int poly_mod, Operand output_op0, Operand output_op1, Operand input_op0, Operand input_op1, WParam w_param, int residual) : + Ntt() + { + setPMD(poly_mod); + addOutputOperand(output_op0); + addOutputOperand(output_op1); + addInputOperand(input_op0); + addInputOperand(input_op1); + setWParam(w_param); + setResidual(residual); + return; + } + + inline static const std::string baseName = "ntt"; + PISAInstruction *create() override { return new Ntt(); } +}; + +/** + * + * { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, INPUT_OPERAND, IMMEDIATE, RESIDUAL } + * **/ +static const pisa::InstructionDesc description_Muli = { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, INPUT_OPERAND, IMMEDIATE, RESIDUAL }; +/** + * @brief The Muli class represents an multiply immediate instruction in P_ISA. + * It receives as input 1 source register and scalar 1 immediate value which are multiplied and then added to the value in the output register modulus some environment state value Q. + * Modulus is implemented as montgomery form modulus + * | Argument | Type | Description | + * | :---------------- | :------ | :--------| + * | POLYMOD_DEG_LOG2 | Int | Not used | + * | OP_NAME | string | muli | + * | OUTPUT_OPERAND [out] | string | dst = label of output register | + * | INPUT_OPERAND | string | src1 = label of input register | + * | IMMEDIATE | string | imm = label of input immediate | + * | RESIDUAL | int | mod_q = index of modulus value to use | + * @details High level functional description: + * dst = (src1*imm1 ) % modulus_chain[modulus_q] + */ +class Muli : public PISAInstruction +{ +public: + Muli() : + PISAInstruction(baseName, description_Muli) {} + Muli(int poly_mod, Operand output_op, Operand input_op0, Operand input_op1, int residual) : + Muli() + { + setPMD(poly_mod); + addOutputOperand(output_op); + addInputOperand(input_op0); + input_op1.setImmediate(true); + addInputOperand(input_op1); + setResidual(residual); + return; + } + + inline static const std::string baseName = "muli"; + PISAInstruction *create() override { return new Muli(); } +}; + +/** + * + * { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, INPUT_OPERAND } + * **/ +static const pisa::InstructionDesc description_Copy = { POLYMOD_DEG_LOG2, OP_NAME, OUTPUT_OPERAND, INPUT_OPERAND }; +/** + * @brief The copy class represents an copy instruction in P_ISA. + * This instruction copies the value stored at the input register to the output register. + * | Argument | Type | Description | + * | :---------------- | :------ | :--------| + * | POLYMOD_DEG_LOG2 | Int | Not used | + * | OP_NAME | string | copy | + * | OUTPUT_OPERAND [out] | string | dst = label of output register | + * | INPUT_OPERAND | string | src1 = label of input register | + * @details High level functional description: + * dst = src1; + */ +class Copy : public PISAInstruction +{ +public: + Copy() : + PISAInstruction(baseName, description_Copy) + { + m_residual = 0; + } + Copy(int poly_mod, Operand output_op, Operand input_op0) : + Copy() + { + setPMD(poly_mod); + addOutputOperand(output_op); + addInputOperand(input_op0); + return; + } + + inline static const std::string baseName = "copy"; + PISAInstruction *create() override { return new Copy(); } +}; + +} // namespace pisa::instruction diff --git a/functional_modeler/common/p_isa/p_isa_performance_modeler.cpp b/functional_modeler/common/p_isa/p_isa_performance_modeler.cpp new file mode 100644 index 0000000..1cce6f6 --- /dev/null +++ b/functional_modeler/common/p_isa/p_isa_performance_modeler.cpp @@ -0,0 +1,605 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#include "p_isa_performance_modeler.h" + +using namespace pisa::performance; + +PISAPerformanceModeler::PISAPerformanceModeler() +{ +} + +void PISAPerformanceModeler::addGraphAnalysis(PerformanceReport &report) +{ + auto p_isa_graph_combined = graph::Graph::createGraph(m_instructions); + auto p_isa_graph_instructions = graph::Graph::createGraph(m_instructions); + createInstructionGraph(p_isa_graph_instructions); + auto input = p_isa_graph_combined.getInputNodes(); + report.total_inputs = input.size(); + auto output = p_isa_graph_combined.getOutputNodes(); + report.total_outputs = output.size(); + + int depth = 0; + report.graph_min_width = 999999; + report.graph_max_width = 0; + + while (p_isa_graph_instructions.getNodeCount() > 0) + { + depth++; + auto input_nodes = p_isa_graph_instructions.getInputNodes(true, true, true); + report.graph_min_width = std::min(report.graph_min_width, (int64_t)input_nodes.size()); + report.graph_max_width = std::max(report.graph_max_width, (int64_t)input_nodes.size()); + report.graph_average_width += input_nodes.size(); + for (auto &input : input_nodes) + { + p_isa_graph_instructions.removeNodeMaintainConnections(input); + } + } + report.graph_depth = depth; + if (depth > 0) + { + report.graph_average_width = report.graph_average_width / report.graph_depth; + } + return; +} + +void PISAPerformanceModeler::createMemoryGraph(graph::Graph &graph) +{ + auto all_nodes = graph.getNodes(); + for (auto node : all_nodes) + { + if (node.GetDat().type == graph::OPERATION) + { + graph.removeNodeMaintainConnections(node); + } + } +} + +void PISAPerformanceModeler::createInstructionGraph(graph::Graph &graph) +{ + auto all_nodes = graph.getNodes(); + for (auto node : all_nodes) + { + if (node.GetDat().type != graph::OPERATION) + { + graph.removeNodeMaintainConnections(node); + } + } +} + +void PISAPerformanceModeler::updateInstructionsToUniqueIntermediateRegisters() +{ + auto p_isa_graph_main = graph::Graph::createGraph(m_instructions); + auto p_isa_graph = p_isa_graph_main.clone(); + auto all_nodes = p_isa_graph.getNodes(); + + //std::cout << "Classify memory nodes" << std::endl; + // Classify memory types + for (auto &instr_node : all_nodes) + { + if (instr_node.GetDat().type != graph::OPERATION && instr_node.GetInDeg() != 0 && instr_node.GetOutDeg() != 0) + { + // Check for restricted instructions to not rename operations + bool restricted = false; + for (int x = 0; x < instr_node.GetInDeg(); x++) + { + auto node_id = instr_node.GetInNId(x); + auto node = p_isa_graph.getNode(node_id); + if (node.GetDat().instruction->Name() == "mac") + restricted = true; + } + + for (int x = 0; x < instr_node.GetOutDeg(); x++) + { + auto node_id = instr_node.GetOutNId(x); + auto node = p_isa_graph.getNode(node_id); + if (node.GetDat().instruction->Name() == "mac") + restricted = true; + } + + if (restricted == false) + { + std::string new_node_name = "uid" + std::to_string(instr_node.GetDat().ID) + instr_node.GetDat().label; + for (int x = 0; x < instr_node.GetInDeg(); x++) + { + auto node_id = instr_node.GetInNId(x); + auto node = p_isa_graph.getNode(node_id); + for (int y = 0; y < node.GetDat().instruction->numOutputOperands(); y++) + { + if (instr_node.GetDat().label == node.GetDat().instruction->getOutputOperand(y).location()) + { + node.GetDat().instruction->getOutputOperand(y).setLocation(new_node_name); + } + } + } + for (int x = 0; x < instr_node.GetOutDeg(); x++) + { + auto node_id = instr_node.GetOutNId(x); + auto node = p_isa_graph.getNode(node_id); + for (int y = 0; y < node.GetDat().instruction->numInputOperands(); y++) + { + if (instr_node.GetDat().label == node.GetDat().instruction->getInputOperand(y).location()) + { + node.GetDat().instruction->getInputOperand(y).setLocation(new_node_name); + } + } + } + } + } + } +} + +void PISAPerformanceModeler::updateInstructionsToUniqueIntermediateRegistersNew() +{ + auto p_isa_graph_main = graph::Graph::createGraph(m_instructions); + auto p_isa_graph = p_isa_graph_main.clone(); + auto all_nodes = p_isa_graph.getNodes(); + + // First generate set of all nodes with shared mem addresses + std::map>> memory_node_histogram; + for (auto &instr_node : all_nodes) + { + if (instr_node.GetDat().type != graph::OPERATION) + { + memory_node_histogram[instr_node.GetDat().label].push_back(instr_node); + } + } + + //Print out histogram + for (auto name : memory_node_histogram) + { + std::cout << "Location:" << name.first << " : " << name.second.size() << std::endl; + } + + int uid_index = 0; + for (auto &name : memory_node_histogram) + { + if (name.second.size() > 1) + { + bool needs_rename = true; + bool started_rename = false; + while (name.second.size() > 0 && needs_rename) + { + auto &first_node = name.second.front(); + //name.second.pop_back(); + int min_dependency_size = 999999999; + int max_dependency_size = 0; + int max_id = -1; + for (auto hdnode : name.second) + { + auto depend_graph = p_isa_graph.getNodeDependencyGraph(hdnode.GetId(), false, true); + std::vector> dependent_nodes; + //dependent_nodes.push_back(first_node); + + auto dependency_nodes = depend_graph.getNodes(); + std::cout << "Size of dependency graph: " << dependency_nodes.size() << std::endl; + if (dependency_nodes.size() < min_dependency_size) + { + min_dependency_size = dependency_nodes.size(); + max_id = hdnode.GetId(); + } + } + + auto depend_graph = p_isa_graph.getNodeDependencyGraph(max_id, false, true); + std::vector> dependent_nodes; + //dependent_nodes.push_back(first_node); + + auto dependency_nodes = depend_graph.getNodes(); + std::cout << "Size of dependency graph: " << dependency_nodes.size() << std::endl; + + for (auto &depend_node : dependency_nodes) + { + if (depend_node.GetDat().label == first_node.GetDat().label) + { + dependent_nodes.push_back(depend_node); + } + } + + std::cout << "Found difference in nodes for: " << name.first << std::endl; + std::cout << "Dependent nodes: " << dependent_nodes.size() << " Histogram nodes: " << name.second.size() << std::endl; + if (dependent_nodes.size() != name.second.size() || started_rename) + { + started_rename = true; + // Create new histogram list + std::vector> new_histogram; + + for (auto &node : name.second) + { + bool is_dependent = false; + for (auto hnode : dependent_nodes) + { + if (node.GetId() == hnode.GetId()) + { + is_dependent = true; + std::cout << "Node is a dependent : " << node.GetId() << " : " << hnode.GetId() << std::endl; + } + } + if (is_dependent == false) + { + new_histogram.push_back(node); + } + } + std::cout << "New histogram size: " << new_histogram.size() << std::endl; + memory_node_histogram[name.first] = new_histogram; + + //Update label + for (auto &unode : dependent_nodes) + { + std::string core_name = unode.GetDat().label; + std::cout << "Core name:" << core_name << std::endl; + std::string updated_name = "uid" + std::to_string(uid_index) + unode.GetDat().label; + //Update instr input/output to new label + for (int x = 0; x < unode.GetInDeg(); x++) + { + auto node_id = unode.GetInNId(x); + auto node = p_isa_graph.getNode(node_id); + for (int y = 0; y < node.GetDat().instruction->numOutputOperands(); y++) + { + if (node.GetDat().instruction->getOutputOperand(y).location().length() >= core_name.size()) + { + std::string core_name_comp = node.GetDat().instruction->getOutputOperand(y).location().substr(node.GetDat().instruction->getOutputOperand(y).location().length() - core_name.size(), + core_name.size()); + std::cout << "core name comp " << core_name_comp << std::endl; + if (core_name == core_name_comp) + { + node.GetDat().instruction->getOutputOperand(y).setLocation(updated_name); + } + } + } + // for(int y = 0; y < node.GetDat().instruction->numInputOperands(); y++) { + // if(unode.GetDat().label == node.GetDat().instruction->getInputOperand(y).location()) { + // node.GetDat().instruction->getInputOperand(y).setLocation(updated_name); + // } + // } + } + for (int x = 0; x < unode.GetOutDeg(); x++) + { + auto node_id = unode.GetOutNId(x); + auto node = p_isa_graph.getNode(node_id); + for (int y = 0; y < node.GetDat().instruction->numInputOperands(); y++) + { + if (node.GetDat().instruction->getInputOperand(y).location().length() >= core_name.size()) + { + std::string core_name_comp = node.GetDat().instruction->getInputOperand(y).location().substr(node.GetDat().instruction->getInputOperand(y).location().length() - core_name.size(), + core_name.size()); + + std::cout << "core name comp " << core_name_comp << std::endl; + if (core_name == core_name_comp) + { + node.GetDat().instruction->getInputOperand(y).setLocation(updated_name); + } + } + } + // for(int y = 0; y < node.GetDat().instruction->numOutputOperands(); y++) { + // if(unode.GetDat().label == node.GetDat().instruction->getOutputOperand(y).location()) { + // node.GetDat().instruction->getOutputOperand(y).setLocation(updated_name); + // } + // } + } + + //Update reg label + auto pnode = p_isa_graph.getNode(unode.GetId()); + std::cout << "Updated: " << pnode.GetDat().label << " to " << ("uid" + std::to_string(uid_index) + pnode.GetDat().label) << std::endl; + pnode.GetDat().label = updated_name; + } + uid_index++; + } + else + { + needs_rename = false; + } + } + } + } + + auto output = p_isa_graph.getOutputNodes(); + + std::cout << "Output nodes after modification: " << std::endl; + for (auto &x : output) + { + std::cout << x.GetDat().label << std::endl; + } + + p_isa_graph.renderGraphToPNGDot("new_dependent.png", graph::NAME); + + return; +} + +void PISAPerformanceModeler::generateAndPrintPerformanceReport(pisa::PerformanceModels::PISAHardwareModel model) +{ + + //#TODO: This is currently not functional and under development. + // Instruction register name rewriting rules. Attempts to identify distinct sets of registers which share a name but are used + // independently by different sections of the execution graph so that they can be rewritten to allow for safe parallel + // execution without name conflicts. + if (false) + { + updateInstructionsToUniqueIntermediateRegistersNew(); + } + + std::cout << "Total_Instruction_count: " << m_instructions.size() << std::endl; + + for (auto x : m_instruction_instance_count) + { + std::cout << "op_" << x.first << "_Instances: " << x.second << std::endl; + } + std::cout << std::endl; + + int64_t min_cycle_time = 99999999999999; + int64_t max_cycle_time = 0; + int64_t avg_cycle_time = 0; + PerformanceReport best_found; + std::srand(std::time(0)); + ScheduleConfig config; + for (int x = 0; x < 1; x++) + { + auto report_standard = generateInstructionAndMemoryPerformanceGraphReport(config, model); + if (report_standard.total_cycles_used < min_cycle_time) + { + best_found = report_standard; + } + min_cycle_time = std::min(min_cycle_time, report_standard.total_cycles_used); + max_cycle_time = std::max(max_cycle_time, report_standard.total_cycles_used); + avg_cycle_time += report_standard.total_cycles_used; + } + + best_found.instruction_count = m_instructions.size(); + addGraphAnalysis(best_found); + best_found.report_name = "Combined"; + std::cout << "Min cycles:" << min_cycle_time << std::endl; + std::cout << "Max cycles:" << max_cycle_time << std::endl; + std::cout << "Avg cycles:" << avg_cycle_time / 1.0 << std::endl; + best_found.print(std::cout); + + //best_found.outputExecutionTimeline(std::cout); + if (false) + { + auto file = std::ofstream("instructions.txt"); + best_found.outputInstructions(file); + for (auto instr : m_instructions) + { + instr->setOutputBlock(false); + file << *instr << std::endl; + } + file.close(); + } +} + +void PISAPerformanceModeler::generatePerformanceReport(pisa::PerformanceModels::PISAHardwareModel hardware_model) +{ + PerformanceReport report; + for (auto instr : m_instructions) + { + report.total_cycles_used += hardware_model.ISAInstructionPerformanceMap[instr->Name()].throughput; + } + + std::cout << "Total cycles used: " << report.total_cycles_used << std::endl; +} + +PerformanceReport PISAPerformanceModeler::generateInstructionAndMemoryPerformanceGraphReport(ScheduleConfig config, pisa::PerformanceModels::PISAHardwareModel hardware_model) +{ + try + { + PerformanceReport report; + + auto p_isa_graph_main = graph::Graph::createGraph(m_instructions); + auto p_isa_graph = p_isa_graph_main.clone(); + auto all_nodes = p_isa_graph.getNodes(); + + //std::cout << "Classify memory nodes" << std::endl; + // Classify memory types + for (auto &mem_node : all_nodes) + { + if (mem_node.GetDat().type != graph::OPERATION) + { + if (mem_node.GetInDeg() == 0 || mem_node.GetOutDeg() == 0) + { + mem_node.GetDat().memory_classification = "MEMORY_CACHE"; + } + else + { + mem_node.GetDat().memory_classification = "REGISTER"; + } + } + } + + if (config.analysis_type == ANALYSIS_TYPE::instruction) + { + createInstructionGraph(p_isa_graph); + } + else if (config.analysis_type == ANALYSIS_TYPE::memory) + { + createMemoryGraph(p_isa_graph); + } + //p_isa_graph.printGraphInfo(); + + auto input_nodes = p_isa_graph.getInputNodes(true, true, true); + + bool use_separate_queues = false; + //Instructions + { + uint64_t instruction_queue_clock = 0; + uint64_t memory_queue_clock = 0; + uint64_t system_clock = 0; + + uint64_t current_finish_time = 0; + uint64_t memory_access_counter = 0; + + while (p_isa_graph.getNodeCount() > 0) + { + + //Remove any nodes that are complete from input + { + + //auto input_nodes = p_isa_graph.getInputNodes(true, true, true); + //std::cout << "Input nodes size: " << input_nodes.size() << std::endl; + auto input = input_nodes.begin(); + while (input != input_nodes.end()) + { + if (input->GetDat().scheduled && input->GetDat().end_time <= system_clock) + { + //std::cout << "Attempting node removal" << std::endl; + p_isa_graph.removeNodeMaintainConnections(*input); + input = input_nodes.erase(input); + // std::cout << "Removal finished" << std::endl; + } + //std::cout << input. + if (input != input_nodes.end()) + input++; + } + //std::cout << "Finished node remove" << std::endl; + } + + //Schedule a new node for execution if possible + { + // bool instruction_scheduled = false; + //std::cout << "Refreshing input nodes:" << input_nodes.size() << std::endl; + if (input_nodes.size() < 2) + { + //std::cout << "Nodes zero, refreshing" << std::endl; + input_nodes = p_isa_graph.getInputNodes(true, true, true); + } + else if (config.quick_schedule) + { + //std::cout << "No fast schedule, refreshing" << std::endl; + input_nodes = p_isa_graph.getInputNodes(true, true, true); + } + + //Shuffle order if using random schedule + if (config.schedule_mode == SCHEDULE_MODE::random) + std::random_shuffle(input_nodes.begin(), input_nodes.end()); + + bool instr_scheduled = false; + bool mem_scheduled = false; + //use_separate_queues + for (auto &input : input_nodes) + { + if (input.GetDat().scheduled == false) + { + + if (input.GetDat().type == graph::OPERATION) + { + + if (instruction_queue_clock <= system_clock) + { + auto instr_perf = hardware_model.ISAInstructionPerformanceMap[input.GetDat().instruction->Name()]; + input.GetDat().start_time = system_clock; + input.GetDat().end_time = system_clock + instr_perf.latency; + input.GetDat().scheduled = true; + + instruction_queue_clock += instr_perf.throughput; + system_clock += instr_perf.throughput - 1; + for (int x = 1; x < instr_perf.throughput; x++) + { + report.schedule_timeline_operation.push_back(std::pair("NOP", nullptr)); + } + + for (int x = 0; x < input.GetOutDeg(); x++) + { + auto output_node = p_isa_graph.getNode(input.GetOutNId(x)); + output_node.GetDat().last_access_time = memory_access_counter; + } + instr_scheduled = true; + } + } + else + { + if (memory_queue_clock <= system_clock) + { + input.GetDat().start_time = system_clock; + pisa::PerformanceModels::InstructionPerfCharacteristics mem_perf; + if (true) + { + mem_perf = getMemoryPerformance(input, memory_access_counter, hardware_model); + } + else + { + mem_perf = hardware_model.ISAInstructionMemoryMap[input.GetDat().memory_classification]; + } + + memory_access_counter++; + + input.GetDat().end_time = system_clock + mem_perf.latency; + input.GetDat().scheduled = true; + memory_queue_clock += mem_perf.throughput; + system_clock += mem_perf.throughput - 1; + for (int x = 1; x < mem_perf.throughput; x++) + { + report.schedule_timeline_mem_queue.push_back(std::pair("NOP", nullptr)); + } + mem_scheduled = true; + } + } + if (input.GetDat().scheduled == true) + { + report.total_cycles_used = current_finish_time; + current_finish_time = input.GetDat().end_time; + //instruction_scheduled = true; + report.schedule_timeline_operation.push_back(std::pair(input.GetDat().label, input.GetDat().instruction)); + } + if (instr_scheduled && mem_scheduled) + break; + } + } + if (instr_scheduled == false) + { + report.schedule_timeline_operation.push_back(std::pair("NOP", nullptr)); + report.total_nops_issued++; + } + if (mem_scheduled == false) + { + report.schedule_timeline_mem_queue.push_back(std::pair("NOP", nullptr)); + } + system_clock++; + } + } + } + + return report; + } + catch (...) + { + std::cout << "Crash during perf analysis" << std::endl; + throw; + } +} + +void PISAPerformanceModeler::generatePerformanceReportGraph() +{ + PerformanceReport report; +} + +pisa::PerformanceModels::InstructionPerfCharacteristics PISAPerformanceModeler::getMemoryPerformance(graph::NetworkNode &mem, int current_clock, pisa::PerformanceModels::PISAHardwareModel hardware_model) +{ + pisa::PerformanceModels::InstructionPerfCharacteristics perf; + + if (mem.GetDat().memory_classification == "MEMORY_CACHE") + { + perf = hardware_model.ISAInstructionMemoryMap["MEMORY_CACHE"]; + } + else if (current_clock - mem.GetDat().last_access_time < hardware_model.MemorySizesMap["REGISTER"]) + { + perf = hardware_model.ISAInstructionMemoryMap["REGISTER"]; + } + else if (current_clock - mem.GetDat().last_access_time < hardware_model.MemorySizesMap["CACHE"]) + { + perf = hardware_model.ISAInstructionMemoryMap["CACHE"]; + } + else + { + perf = hardware_model.ISAInstructionMemoryMap["MEMORY_CACHE"]; + } + + mem.GetDat().last_access_time = current_clock; + + return perf; +} + +void PISAPerformanceModeler::setInstructionStream(std::vector instructions) +{ + for (auto instr : instructions) + { + m_instruction_instance_count[instr->Name()]++; + this->m_instructions.push_back(instr); + } +} diff --git a/functional_modeler/common/p_isa/p_isa_performance_modeler.h b/functional_modeler/common/p_isa/p_isa_performance_modeler.h new file mode 100644 index 0000000..4fd0dac --- /dev/null +++ b/functional_modeler/common/p_isa/p_isa_performance_modeler.h @@ -0,0 +1,121 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#pragma once + +#include +#include +#include +#include + +#include +#include +#include + +namespace pisa::performance { + +struct PerformanceReport +{ + + std::string report_name; + int64_t instruction_count = 0; + int64_t total_cycles_used = 0; + int64_t total_nops_issued = 0; + int64_t total_input_memory_read = 0; + int64_t total_output_memory_written = 0; + // Graph analysis + int64_t total_inputs = 0; + int64_t total_outputs = 0; + int64_t graph_depth = 0; + int64_t graph_average_width = 0; + int64_t graph_min_width = 0; + int64_t graph_max_width = 0; + // + std::vector> schedule_timeline_operation; + std::vector> schedule_timeline_mem_queue; + void print(std::ostream &output) + { + + output << report_name << "_Total_cycles: " << total_cycles_used << std::endl; + output << report_name << "_Total_NOPS: " << total_nops_issued << std::endl; + output << report_name << "_instructions_per_cycle: " << static_cast(instruction_count) / static_cast(total_cycles_used) << std::endl; + output << report_name << "_Total_inputs: " << total_inputs << std::endl; + output << report_name << "_Total_outputs: " << total_outputs << std::endl; + output << report_name << "_Total_depth: " << graph_depth << std::endl; + output << report_name << "_Total_avg_width: " << graph_average_width << std::endl; + output << report_name << "_Total_min_width: " << graph_min_width << std::endl; + output << report_name << "_Total_max_width: " << graph_max_width << std::endl; + return; + } + void outputExecutionTimeline(std::ostream &output) + { + int timeline = 0; + for (auto op : schedule_timeline_operation) + { + output << timeline << ":" << op.first << std::endl; + timeline++; + } + } + void outputInstructions(std::ostream &output) + { + for (auto op : schedule_timeline_operation) + { + if (op.first != "NOP" && op.second != nullptr) + { + op.second->setOutputBlock(false); + output << *op.second << std::endl; + } + } + } +}; + +enum class SCHEDULE_MODE +{ + in_order, + random, + lookahead_5, + next_best +}; + +enum class ANALYSIS_TYPE +{ + standard, + instruction, + memory +}; + +struct ScheduleConfig +{ + SCHEDULE_MODE schedule_mode = SCHEDULE_MODE::in_order; + ANALYSIS_TYPE analysis_type = ANALYSIS_TYPE::standard; + bool quick_schedule = true; +}; + +class PISAPerformanceModeler +{ +public: + PISAPerformanceModeler(); + + void addGraphAnalysis(PerformanceReport &report); + void createMemoryGraph(graph::Graph &graph); + void createInstructionGraph(graph::Graph &graph); + + //Update all instructions to use memory node address offsets + void updateInstructionsToUniqueIntermediateRegisters(); + void updateInstructionsToUniqueIntermediateRegistersNew(); + void generateAndPrintPerformanceReport(PerformanceModels::PISAHardwareModel model = pisa::PerformanceModels::ExampleHardware()); + void generatePerformanceReport(pisa::PerformanceModels::PISAHardwareModel hardware_model); + + PerformanceReport generateInstructionAndMemoryPerformanceGraphReport(ScheduleConfig config, pisa::PerformanceModels::PISAHardwareModel hardware_model); + void generatePerformanceReportGraph(); + pisa::PerformanceModels::InstructionPerfCharacteristics getMemoryPerformance(graph::NetworkNode &mem, int current_clock, pisa::PerformanceModels::PISAHardwareModel hardware_model); + void setInstructionStream(std::vector instructions); + +private: + pisa::PerformanceModels::PISAHardwareModel m_hardware_model; + + std::map m_instruction_instance_count; + std::vector m_instructions; +}; + +} // namespace pisa::performance diff --git a/functional_modeler/common/p_isa/parser/p_isa_parser.cpp b/functional_modeler/common/p_isa/parser/p_isa_parser.cpp new file mode 100644 index 0000000..a133ed6 --- /dev/null +++ b/functional_modeler/common/p_isa/parser/p_isa_parser.cpp @@ -0,0 +1,193 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#include +#include +#include +#include + +#include + +#include "p_isa_parser.h" + +std::vector pisa::PISAParser::parse(const std::string &filename) +{ + try + { + std::vector instructions; + std::ifstream file(filename); + if (!file.is_open()) + { + throw std::runtime_error("File not found: " + filename); + } + + std::string current_line; + while (std::getline(file, current_line)) + { + std::vector components; + std::istringstream current_line_ss(current_line); + + std::string component; + while (std::getline(current_line_ss, component, ',')) + { + components.push_back(std::move(component)); + } + instructions.push_back(parseInstruction(components)); + } + return instructions; + } + catch (const std::runtime_error &err) + { + std::cout << "Runtime error during parse, err: " << err.what() << std::endl; + throw err; + } + catch (...) + { + std::cout << "Unknown exception caught in " << __FUNCTION__ << " in file " << __FILE__ << std::endl; + throw; + } +} + +pisa::PISAInstruction *pisa::PISAParser::parseInstruction(const std::vector &components) +{ + try + { + std::string operation = whiteSpaceRemoved(components[OP_CODE_LOCATION]); + auto instruction_instance = InstructionMap.at(operation); + PISAInstruction *new_instruction = instruction_instance->create(); + for (int x = 0; x < components.size(); x++) + { + parseComponent(components[x], new_instruction->getDescription().params[x], new_instruction); + } + + return new_instruction; + } + catch (const std::out_of_range &err) + { + std::cerr << "No Instruction Desc found for operation in InstructionMap map. Operation: " + << components[OP_CODE_LOCATION] + << std::endl; + } + catch (...) + { + std::cerr << "Invalid instruction detected during parsing."; + throw; + } + throw; +} + +void pisa::PISAParser::parseComponent(const std::string &component, PARAM_TYPE type, PISAInstruction *instr) +{ + switch (type) + { + case pisa::GROUP_ID: + parse_GROUP_ID(component, instr); + break; + case pisa::STAGE: + parse_STAGE(component, instr); + break; + case pisa::BLOCK: + parse_BLOCK(component, instr); + break; + case pisa::IMMEDIATE: + parse_IMMEDIATE(component, instr); + break; + case pisa::W_PACKED_PARAM: + parse_W_PARAM(component, instr); + break; + case pisa::INPUT_OUTPUT_OPERAND: + parse_INPUT_OUTPUT_OPERAND(component, instr); + break; + case pisa::OP_NAME: + parse_OP_NAME(component, instr); + break; + case pisa::INPUT_OPERAND: + parse_INPUT_OPERAND(component, instr); + break; + case pisa::OUTPUT_OPERAND: + parse_OUTPUT_OPERAND(component, instr); + break; + case pisa::POLYMOD_DEG_LOG2: + parse_POLYMOD_DEG_LOG2(component, instr); + break; + case pisa::RESIDUAL: + parse_RESIDUAL(component, instr); + break; + case pisa::GALOIS_ELEMENT: + parse_GALOIS_ELEMENT(component, instr); + break; + case pisa::ADDITIONAL_PARAMS: + parse_ADDITIONAL_PARAMS(component, instr); + break; + default: + throw std::logic_error("Unhandled component during parsing"); + } +} + +void pisa::PISAParser::parse_OP_NAME(const std::string &component, PISAInstruction *instr) +{ + instr->setName(whiteSpaceRemoved(component)); +} + +void pisa::PISAParser::parse_INPUT_OPERAND(const std::string &component, PISAInstruction *instr) +{ + instr->addInputOperand(Operand(component)); +} + +void pisa::PISAParser::parse_IMMEDIATE(const std::string &component, PISAInstruction *instr) +{ + auto trimmed = whiteSpaceRemoved(component); + instr->addInputOperand(Operand(trimmed, true)); +} + +void pisa::PISAParser::parse_OUTPUT_OPERAND(const std::string &component, PISAInstruction *instr) +{ + instr->addOutputOperand(Operand(component)); +} + +void pisa::PISAParser::parse_INPUT_OUTPUT_OPERAND(const std::string &component, PISAInstruction *instr) +{ + instr->addInputOperand(Operand(component)); + instr->addOutputOperand(Operand(component)); +} + +void pisa::PISAParser::parse_POLYMOD_DEG_LOG2(const std::string &component, PISAInstruction *instr) +{ + instr->setPMD(std::stoi(component)); +} + +void pisa::PISAParser::parse_RESIDUAL(const std::string &component, PISAInstruction *instr) +{ + instr->setResidual(std::stoi(component)); +} + +// TODO: to be investigated a bit more +void pisa::PISAParser::parse_GALOIS_ELEMENT(const std::string &component, PISAInstruction *instr) +{ + instr->setGalois_element(std::stoi(component)); +} + +void pisa::PISAParser::parse_GROUP_ID(const std::string &component, PISAInstruction *instr) +{ + instr->setGroupId(std::stoi(component)); +} + +void pisa::PISAParser::parse_STAGE(const std::string &component, PISAInstruction *instr) +{ + instr->setStage(std::stoi(component)); +} + +void pisa::PISAParser::parse_BLOCK(const std::string &component, PISAInstruction *instr) +{ + instr->setBlock(std::stoi(component)); +} + +void pisa::PISAParser::parse_ADDITIONAL_PARAMS(const std::string &component, PISAInstruction *instr) +{ + throw std::logic_error("parse_ADDITIONAL_PARAMS not implemented."); +} + +void pisa::PISAParser::parse_W_PARAM(const std::string &component, PISAInstruction *instr) +{ + instr->setWParam(WParam(component)); +} diff --git a/functional_modeler/common/p_isa/parser/p_isa_parser.h b/functional_modeler/common/p_isa/parser/p_isa_parser.h new file mode 100644 index 0000000..9aa5ab6 --- /dev/null +++ b/functional_modeler/common/p_isa/parser/p_isa_parser.h @@ -0,0 +1,41 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#pragma once + +#include +#include + +#include + +namespace pisa { + +class PISAParser +{ +public: + PISAParser() = delete; + static std::vector parse(const std::string &filename); + +private: + static constexpr int OP_CODE_LOCATION = 1; + + static PISAInstruction *parseInstruction(const std::vector &components); + + static void parseInstruction(const std::string &, pisa::PARAM_TYPE, pisa::PISAInstruction *instr); + + static void parseComponent(const std::string &component, pisa::PARAM_TYPE type, pisa::PISAInstruction *instr); + static void parse_OP_NAME(const std::string &component, pisa::PISAInstruction *instr); + static void parse_INPUT_OPERAND(const std::string &component, pisa::PISAInstruction *instr); + static void parse_IMMEDIATE(const std::string &component, pisa::PISAInstruction *instr); + static void parse_OUTPUT_OPERAND(const std::string &component, pisa::PISAInstruction *instr); + static void parse_INPUT_OUTPUT_OPERAND(const std::string &component, pisa::PISAInstruction *instr); + static void parse_POLYMOD_DEG_LOG2(const std::string &component, pisa::PISAInstruction *instr); + static void parse_RESIDUAL(const std::string &component, pisa::PISAInstruction *instr); + static void parse_ADDITIONAL_PARAMS(const std::string &component, pisa::PISAInstruction *instr); + static void parse_W_PARAM(const std::string &component, pisa::PISAInstruction *instr); + static void parse_GALOIS_ELEMENT(const std::string &component, pisa::PISAInstruction *instr); + static void parse_GROUP_ID(const std::string &component, pisa::PISAInstruction *instr); + static void parse_STAGE(const std::string &component, pisa::PISAInstruction *instr); + static void parse_BLOCK(const std::string &component, pisa::PISAInstruction *instr); +}; +} // namespace pisa diff --git a/functional_modeler/common/string.h b/functional_modeler/common/string.h new file mode 100644 index 0000000..914080c --- /dev/null +++ b/functional_modeler/common/string.h @@ -0,0 +1,16 @@ + +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#pragma once + +#include +#include + +inline std::string whiteSpaceRemoved(const std::string &str) +{ + auto str_copy = str; + auto trimmed = std::remove(str_copy.begin(), str_copy.end(), ' '); + str_copy.erase(trimmed, str_copy.end()); + return str_copy; +} diff --git a/functional_modeler/common/timer/timer.h b/functional_modeler/common/timer/timer.h new file mode 100644 index 0000000..dab5f8d --- /dev/null +++ b/functional_modeler/common/timer/timer.h @@ -0,0 +1,489 @@ +// Copyright (C) 2024 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +// Copyright (C) 2021 Intel Corporation +// SPDX-License-Identifier: Apache-2.0 + +#pragma once + +#include +#include +#include +#include +#include + +namespace pisa { +namespace common { + +/** + * @brief SimpleTimer + * @details + * This class provides operations to track time. + * + * This timer is as precise as EventTimer. Difference between these classes + * is in the features and flexibility offered. + * + * To measure execution time of a portion of code, sandwich the code between + * calls to `start()` and `stop()`. + */ +class SimpleTimer +{ +public: + /** + * @brief Constructor for the SimpleTimer Class + * @param high_precision - flag to use high precision for time + * @param start_active - flag to start timer instantly + */ + SimpleTimer(bool high_precision = false, bool start_active = false) + { + m_active = false; + m_high_precision_mode = high_precision; + if (start_active == true) + { + start(); + } + } + + /** + * @brief start timer instantly + */ + void start() + { + if (m_high_precision_mode) + m_high_start_time = std::chrono::high_resolution_clock::now(); + else + m_start_time = std::chrono::system_clock::now(); + + m_active = true; + } + + /** + * @brief Stop timer instanstly + * @details Use `elapsedSeconds()`, `elapsedMilliseconds()` and `elapsedMicroseconds()` + * methods to retrieve the time elapsed between the last call to `start()` and + * this call. + */ + void stop() + { + if (m_high_precision_mode) + m_high_end_time = std::chrono::high_resolution_clock::now(); + else + m_end_time = std::chrono::system_clock::now(); + + m_active = false; + } + + /** + * @brief indicate the timer is active or not + * @return boolean - status of the timer + */ + bool isActive() { return m_active; } + + /** + * @brief number of ellapse time that timer is holding + * @param micro - indicates returning in ms or micro-second + * @return number of elappsed millli-second or micro-second + */ + double elapsedMilliseconds(bool micro = false) + { + std::chrono::time_point endTime; + std::chrono::time_point highEndTime; + + if (m_active) + { + if (m_high_precision_mode) + highEndTime = std::chrono::high_resolution_clock::now(); + else + endTime = std::chrono::system_clock::now(); + } + else + { + if (m_high_precision_mode) + highEndTime = m_high_end_time; + else + endTime = m_end_time; + } + + if (micro == false) + { + if (m_high_precision_mode) + return std::chrono::duration(highEndTime - m_high_start_time).count(); + else + return std::chrono::duration(endTime - m_start_time).count(); + } + else + { + if (m_high_precision_mode) + return std::chrono::duration(highEndTime - m_high_start_time).count(); + else + return std::chrono::duration(endTime - m_start_time).count(); + } + } + + /** + * @brief number of elapse time that timer is holding + * @return number of elapsed second + */ + double elapsedSeconds() { return elapsedMilliseconds() / 1000.0; } + + /** + * @brief number of elapse time that timer is holding + * @return number of elappsed micro second + */ + double elapsedMicroSeconds() { return elapsedMilliseconds(true); } + +private: + // Standard + std::chrono::time_point m_start_time; + std::chrono::time_point m_end_time; + + // High + std::chrono::time_point m_high_start_time; + std::chrono::time_point m_high_end_time; + + bool m_active; + bool m_high_precision_mode; +}; + +/** + * @brief Type of objects returned by an EventTimer. + * @details Methods of this class are templated to allow transparent + * conversion to different time scales based on the time interval + * template argument specified as a std::ratio. + */ +class TimingReportEvent +{ +public: + template + friend class EventTimer; + + /** + * Default time interval used for all interval-templated operations. + * Defaults to seconds. + */ + using DefaultTimeInterval = std::ratio<1, 1>; // all times in seconds by default: report will convert to other units if needed + + // set a timing to 0 to ignore in reports + + /** + * @brief Construct a new TimingReportEvent object. + * @param[in] _id Optional ID to associate with this event. + * @param[in] _description Optional text description to add to this event. + */ + TimingReportEvent(std::uint32_t _id = 0, const std::string &_description = std::string()) : + id(_id), + description(_description), + m_cpu_time_start(0.0), + m_cpu_time_end(0.0), + m_wall_time_start(0.0), + m_wall_time_end(0.0), + m_iterations(1), + m_ratio_numerator(1), + m_ratio_denominator(1) + { + } + + typedef std::shared_ptr Ptr; + /** + * @brief Construct a new smart pointer to a TimingReportEvent object. + * @param[in] id Optional ID to associate with this event. + * @param[in] description Optional text description to add to this event. + */ + static TimingReportEvent::Ptr create(std::uint32_t id = 0, const std::string &description = std::string()) + { + return TimingReportEvent::Ptr(new TimingReportEvent(id, description)); + } + + /** + * @brief ID of this event. + */ + std::uint32_t id; + /** + * @brief Description of this event. + */ + std::string description; + + template // TimeInterval = std::nano, std::micro, std::milli, std::ratio<1, 1>, etc. + /** + * @brief Retrieves the absolute CPU timing at which this event started. + * @return System dependent absolute CPU timing at which this event started. + * @details This value is generally meaningless on its own. The total CPU + * time for this event is actually computed as the difference between + * timeEndCPU() and timeStartCPU() in the same TimeInterval i.e. + * + * @code + * double elapsed_time = timeEndCPU() - timeStartCPU(); + * @endcode + * @sa elapsedCPUTime() + */ + double timeStartCPU() const + { + return m_cpu_time_start * convertTimeInterval(); + } + template // TimeInterval = std::nano, std::micro, std::milli, std::ratio<1, 1>, etc. + /** + * @brief Retrieves the absolute CPU timing at which this event ended. + * @return System dependent absolute CPU timing at which this event ended. + * @details This value is generally meaningless on its own. The total CPU + * time for this event is actually computed as the difference between + * timeEndCPU() and timeStartCPU() in the same TimeInterval i.e. + * + * @code + * double elapsed_time = timeEndCPU() - timeStartCPU(); + * @endcode + * @sa elapsedCPUTime() + */ + double timeEndCPU() const + { + return m_cpu_time_end * convertTimeInterval(); + } + template // TimeInterval = std::nano, std::micro, std::milli, std::ratio<1, 1>, etc. + /** + * @brief Retrieves the absolute wall timing at which this event started. + * @return System dependent absolute wall timing at which this event started. + * @details This value is generally meaningless on its own. The total wall + * time for this event is actually computed as the difference between + * timeEndWall() and timeStartWall() in the same TimeInterval i.e. + * + * @code + * double elapsed_time = timeEndWall() - timeStartWall(); + * @endcode + * @sa elapsedWallTime() + */ + double timeStartWall() const + { + return m_wall_time_start * convertTimeInterval(); + } + template // TimeInterval = std::nano, std::micro, std::milli, std::ratio<1, 1>, etc. + /** + * @brief Retrieves the absolute wall timing at which this event ended. + * @return System dependent absolute wall timing at which this event ended. + * @details This value is generally meaningless on its own. The total wall + * time for this event is actually computed as the difference between + * timeEndWall() and timeStartWall() in the same TimeInterval i.e. + * + * @code + * double elapsed_time = timeEndWall() - timeStartWall(); + * @endcode + * @sa elapsedWallTime() + */ + double timeEndWall() const + { + return m_wall_time_end * convertTimeInterval(); + } + + /** + * @brief Number of iterations that occurred in this event. + * @details This value is for information purposes only and can be used + * to express a bulk of events that may be bundled in this event report. + */ + std::uint64_t iterations() const { return m_iterations; } + + template // TimeInterval = std::nano, std::micro, std::milli, std::ratio<1, 1>, etc. + /** + * @brief Retrieves the elapsed CPU time for this event. + * @return The elapsed CPU time for this event in the specified TimeInterval scale. + * @details If no threads are idle (waiting on mutexes or sleeping) during the event + * timed, the following is true: + * + * @code + * elapsedCPUTime() = elapsedWallTime() * number_of_threads + * @endcode + * + * The above is in ideal conditions, but in practice, this is an approximation. + * + * The following indicates idle threads or high levels of contention among threads: + * + * @code + * elapsedCPUTime() < < elapsedWallTime() * number_of_threads + * @endcode + */ + double elapsedCPUTime() const + { + return (m_cpu_time_end - m_cpu_time_start) * convertTimeInterval(); + } + template // TimeInterval = std::nano, std::micro, std::milli, std::ratio<1, 1>, etc. + /** + * @brief Retrieves the elapsed wall time for this event. + * @return The elapsed wall time for this event in the specified TimeInterval scale. + */ + double elapsedWallTime() const + { + return (m_wall_time_end - m_wall_time_start) * convertTimeInterval(); + } + +protected: + template // TimeInterval = std::nano, std::micro, std::milli, std::ratio<1, 1>, etc. + /** + * @brief Sets the timing values for this timing event. + * @param[in] cpu_time_start CPU start time in the specified time interval unit. + * @param[in] cpu_time_end CPU end time in the specified time interval unit. + * @param[in] wall_time_start Wall start time in the specified time interval unit. + * @param[in] wall_time_end Wall end time in the specified time interval unit. + * @param[in] iterations Number of iterations contained this event. + */ + void setTimings(double cpu_time_start, double cpu_time_end, + double wall_time_start, double wall_time_end, + std::uint64_t iterations) + { + m_ratio_numerator = TimeInterval::num; + m_ratio_denominator = TimeInterval::den; + m_cpu_time_start = (cpu_time_start > cpu_time_end ? cpu_time_end : cpu_time_start); + m_cpu_time_end = (cpu_time_start > cpu_time_end ? cpu_time_start : cpu_time_end); + m_wall_time_start = (wall_time_start > wall_time_end ? wall_time_end : wall_time_start); + m_wall_time_end = (wall_time_start > wall_time_end ? wall_time_start : wall_time_end); + m_iterations = iterations; + } + +private: + template + double convertTimeInterval() const + { + return (static_cast(m_ratio_numerator) * TimeInterval::den) / (m_ratio_denominator * TimeInterval::num); + } + + double m_cpu_time_start; + double m_cpu_time_end; + double m_wall_time_start; + double m_wall_time_end; + std::uint64_t m_iterations; + std::intmax_t m_ratio_numerator; + std::intmax_t m_ratio_denominator; +}; + +template +/** + * @brief Timer class that allows advanced time tracking of events and + * time interval manipulation. + * + * If template parameter `high_precision` is true, then this timer will + * attempt to use the highest precision clock available in the system + * to measure wall time, otherwise, the system clock will be used. + * + * This timer is as precise as SimpleTimer. Difference between these classes + * is in the features and flexibility offered. If only basic timing is + * needed, SimpleTimer will offer a quick solution. If extra features + * such as CPU time, flexible time scales, then, this class is better. + * + * To measure execution time of a portion of code, sandwich the code between + * calls to `start()` and `stop()`. + */ +class EventTimer +{ +public: + /** + * @brief Constructs a new EventTimer object. + * @param[in] start_active If `true`, the timer is constructed and started. + * Otherwise, the timer is idle and waiting to be started. + */ + EventTimer(bool start_active = false) + { + m_active = false; + m_cpu_start_time = std::clock(); + m_start_time = ClockType::now(); + // compute the 0 time + m_cpu_init_time = std::clock(); + m_init_time = ClockType::now(); + + if (start_active) + start(); + } + + /** + * @brief Starts measuring time from this call and until stopped. + */ + void start() + { + m_active = true; + m_cpu_start_time = std::clock(); + m_start_time = ClockType::now(); + } + + template // TimeInterval = std::nano, std::micro, std::milli, std::ratio<1, 1>, etc. + /** + * @brief Stops measuring time. + * @param[in] iterations Number of iterations measured in this event. + * @return A TimingReportEvent with the measurement details. + * @details + * The returned event report will reflect the timings between the latest call + * to `start()` and this call. + * @sa TimingReportEvent::iterations() + */ + TimingReportEvent::Ptr stop(std::uint64_t iterations = 1) + { + return stop(0, iterations, nullptr); + } + template // TimeInterval = std::nano, std::micro, std::milli, std::ratio<1, 1>, etc. + /** + * @brief Stops measuring time. + * @param[in] id Optional ID to associate with this event. + * @param[in] iterations Number of iterations measured in this event. + * @param[in] description Optional text description to add to this event. + * @return A TimingReportEvent with the measurement details. + * @details + * The returned event report will reflect the timings between the latest call + * to `start()` and this call. + * @sa TimingReportEvent::iterations() + */ + TimingReportEvent::Ptr stop(std::uint32_t id, + std::uint64_t iterations, + const char *description) + { + double cpu_end_time = getCPUElapsedTime(); + double wall_end_time = getWallElapsedTime(); + m_active = false; + + TimingReportEvent::Ptr retval = TimingReportEvent::create(id, + description ? std::string(description) : std::string()); + retval->setTimings( + getCPUElapsedTime(m_cpu_start_time), cpu_end_time, + getWallElapsedTime(m_start_time), wall_end_time, + iterations); + + return retval; + } + + /** + * @brief Retrieves whether the timer is active. + * @returns `true` if a call to `start()` has been made without a matching call + * to `stop()`, i.e. the timer is active. + * @returns `false` otherwise. + */ + bool isActive() const { return m_active; } + +private: + typedef typename std::conditional::type ClockType; + + template + double getCPUElapsedTime() const + { + return getCPUElapsedTime(std::clock()); + } + template + double getCPUElapsedTime(std::clock_t cpu_end_time) const + { + return (cpu_end_time - m_cpu_init_time) * static_cast(TimeInterval::den) / (static_cast(CLOCKS_PER_SEC) * static_cast(TimeInterval::num)); + } + template + double getWallElapsedTime() const + { + return getWallElapsedTime(ClockType::now()); + } + template + double getWallElapsedTime(const std::chrono::time_point &end_time) const + { + return std::chrono::duration(end_time - m_init_time).count(); + } + + std::chrono::time_point m_init_time; + std::clock_t m_cpu_init_time; + std::chrono::time_point m_start_time; + std::clock_t m_cpu_start_time; + + bool m_active; +}; + +} // namespace common +} // namespace pisa diff --git a/functional_modeler/docs/doxyfile.in b/functional_modeler/docs/doxyfile.in new file mode 100644 index 0000000..7f4f266 --- /dev/null +++ b/functional_modeler/docs/doxyfile.in @@ -0,0 +1,2844 @@ +# Doxyfile 1.12.0 + +# This file describes the settings to be used by the documentation system +# Doxygen (www.doxygen.org) for a project. +# +# All text after a double hash (##) is considered a comment and is placed in +# front of the TAG it is preceding. +# +# All text after a single hash (#) is considered a comment and will be ignored. +# The format is: +# TAG = value [value, ...] +# For lists, items can also be appended using: +# TAG += value [value, ...] +# Values that contain spaces should be placed between quotes (\" \"). +# +# Note: +# +# Use Doxygen to compare the used configuration file with the template +# configuration file: +# doxygen -x [configFile] +# Use Doxygen to compare the used configuration file with the template +# configuration file without replacing the environment variables or CMake type +# replacement variables: +# doxygen -x_noenv [configFile] + +#--------------------------------------------------------------------------- +# Project related configuration options +#--------------------------------------------------------------------------- + +# This tag specifies the encoding used for all characters in the configuration +# file that follow. The default is UTF-8 which is also the encoding used for all +# text before the first occurrence of this tag. Doxygen uses libiconv (or the +# iconv built into libc) for the transcoding. See +# https://www.gnu.org/software/libiconv/ for the list of possible encodings. +# The default value is: UTF-8. + +DOXYFILE_ENCODING = UTF-8 + +# The PROJECT_NAME tag is a single word (or a sequence of words surrounded by +# double-quotes, unless you are using Doxywizard) that should identify the +# project for which the documentation is generated. This name is used in the +# title of most generated pages and in a few other places. +# The default value is: My Project. + +PROJECT_NAME = HERACLES-P-ISA + +# The PROJECT_NUMBER tag can be used to enter a project or revision number. This +# could be handy for archiving the generated documentation or if some version +# control system is used. + +PROJECT_NUMBER = + +# Using the PROJECT_BRIEF tag one can provide an optional one line description +# for a project that appears at the top of each page and should give viewer a +# quick idea about the purpose of the project. Keep the description short. + +PROJECT_BRIEF = + +# With the PROJECT_LOGO tag one can specify a logo or an icon that is included +# in the documentation. The maximum height of the logo should not exceed 55 +# pixels and the maximum width should not exceed 200 pixels. Doxygen will copy +# the logo to the output directory. + +PROJECT_LOGO = + +# With the PROJECT_ICON tag one can specify an icon that is included in the tabs +# when the HTML document is shown. Doxygen will copy the logo to the output +# directory. + +PROJECT_ICON = + +# The OUTPUT_DIRECTORY tag is used to specify the (relative or absolute) path +# into which the generated documentation will be written. If a relative path is +# entered, it will be relative to the location where Doxygen was started. If +# left blank the current directory will be used. + +OUTPUT_DIRECTORY = generated_docs + +# If the CREATE_SUBDIRS tag is set to YES then Doxygen will create up to 4096 +# sub-directories (in 2 levels) under the output directory of each output format +# and will distribute the generated files over these directories. Enabling this +# option can be useful when feeding Doxygen a huge amount of source files, where +# putting all generated files in the same directory would otherwise causes +# performance problems for the file system. Adapt CREATE_SUBDIRS_LEVEL to +# control the number of sub-directories. +# The default value is: NO. + +CREATE_SUBDIRS = NO + +# Controls the number of sub-directories that will be created when +# CREATE_SUBDIRS tag is set to YES. Level 0 represents 16 directories, and every +# level increment doubles the number of directories, resulting in 4096 +# directories at level 8 which is the default and also the maximum value. The +# sub-directories are organized in 2 levels, the first level always has a fixed +# number of 16 directories. +# Minimum value: 0, maximum value: 8, default value: 8. +# This tag requires that the tag CREATE_SUBDIRS is set to YES. + +CREATE_SUBDIRS_LEVEL = 8 + +# If the ALLOW_UNICODE_NAMES tag is set to YES, Doxygen will allow non-ASCII +# characters to appear in the names of generated files. If set to NO, non-ASCII +# characters will be escaped, for example _xE3_x81_x84 will be used for Unicode +# U+3044. +# The default value is: NO. + +ALLOW_UNICODE_NAMES = NO + +# The OUTPUT_LANGUAGE tag is used to specify the language in which all +# documentation generated by Doxygen is written. Doxygen will use this +# information to generate all constant output in the proper language. +# Possible values are: Afrikaans, Arabic, Armenian, Brazilian, Bulgarian, +# Catalan, Chinese, Chinese-Traditional, Croatian, Czech, Danish, Dutch, English +# (United States), Esperanto, Farsi (Persian), Finnish, French, German, Greek, +# Hindi, Hungarian, Indonesian, Italian, Japanese, Japanese-en (Japanese with +# English messages), Korean, Korean-en (Korean with English messages), Latvian, +# Lithuanian, Macedonian, Norwegian, Persian (Farsi), Polish, Portuguese, +# Romanian, Russian, Serbian, Serbian-Cyrillic, Slovak, Slovene, Spanish, +# Swedish, Turkish, Ukrainian and Vietnamese. +# The default value is: English. + +OUTPUT_LANGUAGE = English + +# If the BRIEF_MEMBER_DESC tag is set to YES, Doxygen will include brief member +# descriptions after the members that are listed in the file and class +# documentation (similar to Javadoc). Set to NO to disable this. +# The default value is: YES. + +BRIEF_MEMBER_DESC = YES + +# If the REPEAT_BRIEF tag is set to YES, Doxygen will prepend the brief +# description of a member or function before the detailed description +# +# Note: If both HIDE_UNDOC_MEMBERS and BRIEF_MEMBER_DESC are set to NO, the +# brief descriptions will be completely suppressed. +# The default value is: YES. + +REPEAT_BRIEF = YES + +# This tag implements a quasi-intelligent brief description abbreviator that is +# used to form the text in various listings. Each string in this list, if found +# as the leading text of the brief description, will be stripped from the text +# and the result, after processing the whole list, is used as the annotated +# text. Otherwise, the brief description is used as-is. If left blank, the +# following values are used ($name is automatically replaced with the name of +# the entity):The $name class, The $name widget, The $name file, is, provides, +# specifies, contains, represents, a, an and the. + +ABBREVIATE_BRIEF = "The $name class" \ + "The $name widget" \ + "The $name file" \ + is \ + provides \ + specifies \ + contains \ + represents \ + a \ + an \ + the + +# If the ALWAYS_DETAILED_SEC and REPEAT_BRIEF tags are both set to YES then +# Doxygen will generate a detailed section even if there is only a brief +# description. +# The default value is: NO. + +ALWAYS_DETAILED_SEC = NO + +# If the INLINE_INHERITED_MEMB tag is set to YES, Doxygen will show all +# inherited members of a class in the documentation of that class as if those +# members were ordinary class members. Constructors, destructors and assignment +# operators of the base classes will not be shown. +# The default value is: NO. + +INLINE_INHERITED_MEMB = NO + +# If the FULL_PATH_NAMES tag is set to YES, Doxygen will prepend the full path +# before files name in the file list and in the header files. If set to NO the +# shortest path that makes the file name unique will be used +# The default value is: YES. + +FULL_PATH_NAMES = NO + +# The STRIP_FROM_PATH tag can be used to strip a user-defined part of the path. +# Stripping is only done if one of the specified strings matches the left-hand +# part of the path. The tag can be used to show relative paths in the file list. +# If left blank the directory from which Doxygen is run is used as the path to +# strip. +# +# Note that you can specify absolute paths here, but also relative paths, which +# will be relative from the directory where Doxygen is started. +# This tag requires that the tag FULL_PATH_NAMES is set to YES. + +STRIP_FROM_PATH = + +# The STRIP_FROM_INC_PATH tag can be used to strip a user-defined part of the +# path mentioned in the documentation of a class, which tells the reader which +# header file to include in order to use a class. If left blank only the name of +# the header file containing the class definition is used. Otherwise one should +# specify the list of include paths that are normally passed to the compiler +# using the -I flag. + +STRIP_FROM_INC_PATH = + +# If the SHORT_NAMES tag is set to YES, Doxygen will generate much shorter (but +# less readable) file names. This can be useful is your file systems doesn't +# support long names like on DOS, Mac, or CD-ROM. +# The default value is: NO. + +SHORT_NAMES = NO + +# If the JAVADOC_AUTOBRIEF tag is set to YES then Doxygen will interpret the +# first line (until the first dot) of a Javadoc-style comment as the brief +# description. If set to NO, the Javadoc-style will behave just like regular Qt- +# style comments (thus requiring an explicit @brief command for a brief +# description.) +# The default value is: NO. + +JAVADOC_AUTOBRIEF = NO + +# If the JAVADOC_BANNER tag is set to YES then Doxygen will interpret a line +# such as +# /*************** +# as being the beginning of a Javadoc-style comment "banner". If set to NO, the +# Javadoc-style will behave just like regular comments and it will not be +# interpreted by Doxygen. +# The default value is: NO. + +JAVADOC_BANNER = NO + +# If the QT_AUTOBRIEF tag is set to YES then Doxygen will interpret the first +# line (until the first dot) of a Qt-style comment as the brief description. If +# set to NO, the Qt-style will behave just like regular Qt-style comments (thus +# requiring an explicit \brief command for a brief description.) +# The default value is: NO. + +QT_AUTOBRIEF = NO + +# The MULTILINE_CPP_IS_BRIEF tag can be set to YES to make Doxygen treat a +# multi-line C++ special comment block (i.e. a block of //! or /// comments) as +# a brief description. This used to be the default behavior. The new default is +# to treat a multi-line C++ comment block as a detailed description. Set this +# tag to YES if you prefer the old behavior instead. +# +# Note that setting this tag to YES also means that rational rose comments are +# not recognized any more. +# The default value is: NO. + +MULTILINE_CPP_IS_BRIEF = NO + +# By default Python docstrings are displayed as preformatted text and Doxygen's +# special commands cannot be used. By setting PYTHON_DOCSTRING to NO the +# Doxygen's special commands can be used and the contents of the docstring +# documentation blocks is shown as Doxygen documentation. +# The default value is: YES. + +PYTHON_DOCSTRING = NO + +# If the INHERIT_DOCS tag is set to YES then an undocumented member inherits the +# documentation from any documented member that it re-implements. +# The default value is: YES. + +INHERIT_DOCS = YES + +# If the SEPARATE_MEMBER_PAGES tag is set to YES then Doxygen will produce a new +# page for each member. If set to NO, the documentation of a member will be part +# of the file/class/namespace that contains it. +# The default value is: NO. + +SEPARATE_MEMBER_PAGES = NO + +# The TAB_SIZE tag can be used to set the number of spaces in a tab. Doxygen +# uses this value to replace tabs by spaces in code fragments. +# Minimum value: 1, maximum value: 16, default value: 4. + +TAB_SIZE = 4 + +# This tag can be used to specify a number of aliases that act as commands in +# the documentation. An alias has the form: +# name=value +# For example adding +# "sideeffect=@par Side Effects:^^" +# will allow you to put the command \sideeffect (or @sideeffect) in the +# documentation, which will result in a user-defined paragraph with heading +# "Side Effects:". Note that you cannot put \n's in the value part of an alias +# to insert newlines (in the resulting output). You can put ^^ in the value part +# of an alias to insert a newline as if a physical newline was in the original +# file. When you need a literal { or } or , in the value part of an alias you +# have to escape them by means of a backslash (\), this can lead to conflicts +# with the commands \{ and \} for these it is advised to use the version @{ and +# @} or use a double escape (\\{ and \\}) + +ALIASES = + +# Set the OPTIMIZE_OUTPUT_FOR_C tag to YES if your project consists of C sources +# only. Doxygen will then generate output that is more tailored for C. For +# instance, some of the names that are used will be different. The list of all +# members will be omitted, etc. +# The default value is: NO. + +OPTIMIZE_OUTPUT_FOR_C = NO + +# Set the OPTIMIZE_OUTPUT_JAVA tag to YES if your project consists of Java or +# Python sources only. Doxygen will then generate output that is more tailored +# for that language. For instance, namespaces will be presented as packages, +# qualified scopes will look different, etc. +# The default value is: NO. + +OPTIMIZE_OUTPUT_JAVA = NO + +# Set the OPTIMIZE_FOR_FORTRAN tag to YES if your project consists of Fortran +# sources. Doxygen will then generate output that is tailored for Fortran. +# The default value is: NO. + +OPTIMIZE_FOR_FORTRAN = NO + +# Set the OPTIMIZE_OUTPUT_VHDL tag to YES if your project consists of VHDL +# sources. Doxygen will then generate output that is tailored for VHDL. +# The default value is: NO. + +OPTIMIZE_OUTPUT_VHDL = NO + +# Set the OPTIMIZE_OUTPUT_SLICE tag to YES if your project consists of Slice +# sources only. Doxygen will then generate output that is more tailored for that +# language. For instance, namespaces will be presented as modules, types will be +# separated into more groups, etc. +# The default value is: NO. + +OPTIMIZE_OUTPUT_SLICE = NO + +# Doxygen selects the parser to use depending on the extension of the files it +# parses. With this tag you can assign which parser to use for a given +# extension. Doxygen has a built-in mapping, but you can override or extend it +# using this tag. The format is ext=language, where ext is a file extension, and +# language is one of the parsers supported by Doxygen: IDL, Java, JavaScript, +# Csharp (C#), C, C++, Lex, D, PHP, md (Markdown), Objective-C, Python, Slice, +# VHDL, Fortran (fixed format Fortran: FortranFixed, free formatted Fortran: +# FortranFree, unknown formatted Fortran: Fortran. In the later case the parser +# tries to guess whether the code is fixed or free formatted code, this is the +# default for Fortran type files). For instance to make Doxygen treat .inc files +# as Fortran files (default is PHP), and .f files as C (default is Fortran), +# use: inc=Fortran f=C. +# +# Note: For files without extension you can use no_extension as a placeholder. +# +# Note that for custom extensions you also need to set FILE_PATTERNS otherwise +# the files are not read by Doxygen. When specifying no_extension you should add +# * to the FILE_PATTERNS. +# +# Note see also the list of default file extension mappings. + +EXTENSION_MAPPING = + +# If the MARKDOWN_SUPPORT tag is enabled then Doxygen pre-processes all comments +# according to the Markdown format, which allows for more readable +# documentation. See https://daringfireball.net/projects/markdown/ for details. +# The output of markdown processing is further processed by Doxygen, so you can +# mix Doxygen, HTML, and XML commands with Markdown formatting. Disable only in +# case of backward compatibilities issues. +# The default value is: YES. + +MARKDOWN_SUPPORT = YES + +# When the TOC_INCLUDE_HEADINGS tag is set to a non-zero value, all headings up +# to that level are automatically included in the table of contents, even if +# they do not have an id attribute. +# Note: This feature currently applies only to Markdown headings. +# Minimum value: 0, maximum value: 99, default value: 6. +# This tag requires that the tag MARKDOWN_SUPPORT is set to YES. + +TOC_INCLUDE_HEADINGS = 3 + +# The MARKDOWN_ID_STYLE tag can be used to specify the algorithm used to +# generate identifiers for the Markdown headings. Note: Every identifier is +# unique. +# Possible values are: DOXYGEN use a fixed 'autotoc_md' string followed by a +# sequence number starting at 0 and GITHUB use the lower case version of title +# with any whitespace replaced by '-' and punctuation characters removed. +# The default value is: DOXYGEN. +# This tag requires that the tag MARKDOWN_SUPPORT is set to YES. + +MARKDOWN_ID_STYLE = DOXYGEN + +# When enabled Doxygen tries to link words that correspond to documented +# classes, or namespaces to their corresponding documentation. Such a link can +# be prevented in individual cases by putting a % sign in front of the word or +# globally by setting AUTOLINK_SUPPORT to NO. +# The default value is: YES. + +AUTOLINK_SUPPORT = YES + +# If you use STL classes (i.e. std::string, std::vector, etc.) but do not want +# to include (a tag file for) the STL sources as input, then you should set this +# tag to YES in order to let Doxygen match functions declarations and +# definitions whose arguments contain STL classes (e.g. func(std::string); +# versus func(std::string) {}). This also makes the inheritance and +# collaboration diagrams that involve STL classes more complete and accurate. +# The default value is: NO. + +BUILTIN_STL_SUPPORT = YES + +# If you use Microsoft's C++/CLI language, you should set this option to YES to +# enable parsing support. +# The default value is: NO. + +CPP_CLI_SUPPORT = NO + +# Set the SIP_SUPPORT tag to YES if your project consists of sip (see: +# https://www.riverbankcomputing.com/software) sources only. Doxygen will parse +# them like normal C++ but will assume all classes use public instead of private +# inheritance when no explicit protection keyword is present. +# The default value is: NO. + +SIP_SUPPORT = NO + +# For Microsoft's IDL there are propget and propput attributes to indicate +# getter and setter methods for a property. Setting this option to YES will make +# Doxygen to replace the get and set methods by a property in the documentation. +# This will only work if the methods are indeed getting or setting a simple +# type. If this is not the case, or you want to show the methods anyway, you +# should set this option to NO. +# The default value is: YES. + +IDL_PROPERTY_SUPPORT = YES + +# If member grouping is used in the documentation and the DISTRIBUTE_GROUP_DOC +# tag is set to YES then Doxygen will reuse the documentation of the first +# member in the group (if any) for the other members of the group. By default +# all members of a group must be documented explicitly. +# The default value is: NO. + +DISTRIBUTE_GROUP_DOC = NO + +# If one adds a struct or class to a group and this option is enabled, then also +# any nested class or struct is added to the same group. By default this option +# is disabled and one has to add nested compounds explicitly via \ingroup. +# The default value is: NO. + +GROUP_NESTED_COMPOUNDS = YES + +# Set the SUBGROUPING tag to YES to allow class member groups of the same type +# (for instance a group of public functions) to be put as a subgroup of that +# type (e.g. under the Public Functions section). Set it to NO to prevent +# subgrouping. Alternatively, this can be done per class using the +# \nosubgrouping command. +# The default value is: YES. + +SUBGROUPING = YES + +# When the INLINE_GROUPED_CLASSES tag is set to YES, classes, structs and unions +# are shown inside the group in which they are included (e.g. using \ingroup) +# instead of on a separate page (for HTML and Man pages) or section (for LaTeX +# and RTF). +# +# Note that this feature does not work in combination with +# SEPARATE_MEMBER_PAGES. +# The default value is: NO. + +INLINE_GROUPED_CLASSES = YES + +# When the INLINE_SIMPLE_STRUCTS tag is set to YES, structs, classes, and unions +# with only public data fields or simple typedef fields will be shown inline in +# the documentation of the scope in which they are defined (i.e. file, +# namespace, or group documentation), provided this scope is documented. If set +# to NO, structs, classes, and unions are shown on a separate page (for HTML and +# Man pages) or section (for LaTeX and RTF). +# The default value is: NO. + +INLINE_SIMPLE_STRUCTS = YES + +# When TYPEDEF_HIDES_STRUCT tag is enabled, a typedef of a struct, union, or +# enum is documented as struct, union, or enum with the name of the typedef. So +# typedef struct TypeS {} TypeT, will appear in the documentation as a struct +# with name TypeT. When disabled the typedef will appear as a member of a file, +# namespace, or class. And the struct will be named TypeS. This can typically be +# useful for C code in case the coding convention dictates that all compound +# types are typedef'ed and only the typedef is referenced, never the tag name. +# The default value is: NO. + +TYPEDEF_HIDES_STRUCT = NO + +# The size of the symbol lookup cache can be set using LOOKUP_CACHE_SIZE. This +# cache is used to resolve symbols given their name and scope. Since this can be +# an expensive process and often the same symbol appears multiple times in the +# code, Doxygen keeps a cache of pre-resolved symbols. If the cache is too small +# Doxygen will become slower. If the cache is too large, memory is wasted. The +# cache size is given by this formula: 2^(16+LOOKUP_CACHE_SIZE). The valid range +# is 0..9, the default is 0, corresponding to a cache size of 2^16=65536 +# symbols. At the end of a run Doxygen will report the cache usage and suggest +# the optimal cache size from a speed point of view. +# Minimum value: 0, maximum value: 9, default value: 0. + +LOOKUP_CACHE_SIZE = 0 + +# The NUM_PROC_THREADS specifies the number of threads Doxygen is allowed to use +# during processing. When set to 0 Doxygen will based this on the number of +# cores available in the system. You can set it explicitly to a value larger +# than 0 to get more control over the balance between CPU load and processing +# speed. At this moment only the input processing can be done using multiple +# threads. Since this is still an experimental feature the default is set to 1, +# which effectively disables parallel processing. Please report any issues you +# encounter. Generating dot graphs in parallel is controlled by the +# DOT_NUM_THREADS setting. +# Minimum value: 0, maximum value: 32, default value: 1. + +NUM_PROC_THREADS = 1 + +# If the TIMESTAMP tag is set different from NO then each generated page will +# contain the date or date and time when the page was generated. Setting this to +# NO can help when comparing the output of multiple runs. +# Possible values are: YES, NO, DATETIME and DATE. +# The default value is: NO. + +TIMESTAMP = NO + +#--------------------------------------------------------------------------- +# Build related configuration options +#--------------------------------------------------------------------------- + +# If the EXTRACT_ALL tag is set to YES, Doxygen will assume all entities in +# documentation are documented, even if no documentation was available. Private +# class members and static file members will be hidden unless the +# EXTRACT_PRIVATE respectively EXTRACT_STATIC tags are set to YES. +# Note: This will also disable the warnings about undocumented members that are +# normally produced when WARNINGS is set to YES. +# The default value is: NO. + +EXTRACT_ALL = YES + +# If the EXTRACT_PRIVATE tag is set to YES, all private members of a class will +# be included in the documentation. +# The default value is: NO. + +EXTRACT_PRIVATE = YES + +# If the EXTRACT_PRIV_VIRTUAL tag is set to YES, documented private virtual +# methods of a class will be included in the documentation. +# The default value is: NO. + +EXTRACT_PRIV_VIRTUAL = YES + +# If the EXTRACT_PACKAGE tag is set to YES, all members with package or internal +# scope will be included in the documentation. +# The default value is: NO. + +EXTRACT_PACKAGE = YES + +# If the EXTRACT_STATIC tag is set to YES, all static members of a file will be +# included in the documentation. +# The default value is: NO. + +EXTRACT_STATIC = YES + +# If the EXTRACT_LOCAL_CLASSES tag is set to YES, classes (and structs) defined +# locally in source files will be included in the documentation. If set to NO, +# only classes defined in header files are included. Does not have any effect +# for Java sources. +# The default value is: YES. + +EXTRACT_LOCAL_CLASSES = YES + +# This flag is only useful for Objective-C code. If set to YES, local methods, +# which are defined in the implementation section but not in the interface are +# included in the documentation. If set to NO, only methods in the interface are +# included. +# The default value is: NO. + +EXTRACT_LOCAL_METHODS = YES + +# If this flag is set to YES, the members of anonymous namespaces will be +# extracted and appear in the documentation as a namespace called +# 'anonymous_namespace{file}', where file will be replaced with the base name of +# the file that contains the anonymous namespace. By default anonymous namespace +# are hidden. +# The default value is: NO. + +EXTRACT_ANON_NSPACES = YES + +# If this flag is set to YES, the name of an unnamed parameter in a declaration +# will be determined by the corresponding definition. By default unnamed +# parameters remain unnamed in the output. +# The default value is: YES. + +RESOLVE_UNNAMED_PARAMS = YES + +# If the HIDE_UNDOC_MEMBERS tag is set to YES, Doxygen will hide all +# undocumented members inside documented classes or files. If set to NO these +# members will be included in the various overviews, but no documentation +# section is generated. This option has no effect if EXTRACT_ALL is enabled. +# The default value is: NO. + +HIDE_UNDOC_MEMBERS = NO + +# If the HIDE_UNDOC_CLASSES tag is set to YES, Doxygen will hide all +# undocumented classes that are normally visible in the class hierarchy. If set +# to NO, these classes will be included in the various overviews. This option +# will also hide undocumented C++ concepts if enabled. This option has no effect +# if EXTRACT_ALL is enabled. +# The default value is: NO. + +HIDE_UNDOC_CLASSES = NO + +# If the HIDE_FRIEND_COMPOUNDS tag is set to YES, Doxygen will hide all friend +# declarations. If set to NO, these declarations will be included in the +# documentation. +# The default value is: NO. + +HIDE_FRIEND_COMPOUNDS = NO + +# If the HIDE_IN_BODY_DOCS tag is set to YES, Doxygen will hide any +# documentation blocks found inside the body of a function. If set to NO, these +# blocks will be appended to the function's detailed documentation block. +# The default value is: NO. + +HIDE_IN_BODY_DOCS = NO + +# The INTERNAL_DOCS tag determines if documentation that is typed after a +# \internal command is included. If the tag is set to NO then the documentation +# will be excluded. Set it to YES to include the internal documentation. +# The default value is: NO. + +INTERNAL_DOCS = NO + +# With the correct setting of option CASE_SENSE_NAMES Doxygen will better be +# able to match the capabilities of the underlying filesystem. In case the +# filesystem is case sensitive (i.e. it supports files in the same directory +# whose names only differ in casing), the option must be set to YES to properly +# deal with such files in case they appear in the input. For filesystems that +# are not case sensitive the option should be set to NO to properly deal with +# output files written for symbols that only differ in casing, such as for two +# classes, one named CLASS and the other named Class, and to also support +# references to files without having to specify the exact matching casing. On +# Windows (including Cygwin) and macOS, users should typically set this option +# to NO, whereas on Linux or other Unix flavors it should typically be set to +# YES. +# Possible values are: SYSTEM, NO and YES. +# The default value is: SYSTEM. + +CASE_SENSE_NAMES = YES + +# If the HIDE_SCOPE_NAMES tag is set to NO then Doxygen will show members with +# their full class and namespace scopes in the documentation. If set to YES, the +# scope will be hidden. +# The default value is: NO. + +HIDE_SCOPE_NAMES = NO + +# If the HIDE_COMPOUND_REFERENCE tag is set to NO (default) then Doxygen will +# append additional text to a page's title, such as Class Reference. If set to +# YES the compound reference will be hidden. +# The default value is: NO. + +HIDE_COMPOUND_REFERENCE= NO + +# If the SHOW_HEADERFILE tag is set to YES then the documentation for a class +# will show which file needs to be included to use the class. +# The default value is: YES. + +SHOW_HEADERFILE = YES + +# If the SHOW_INCLUDE_FILES tag is set to YES then Doxygen will put a list of +# the files that are included by a file in the documentation of that file. +# The default value is: YES. + +SHOW_INCLUDE_FILES = YES + +# If the SHOW_GROUPED_MEMB_INC tag is set to YES then Doxygen will add for each +# grouped member an include statement to the documentation, telling the reader +# which file to include in order to use the member. +# The default value is: NO. + +SHOW_GROUPED_MEMB_INC = NO + +# If the FORCE_LOCAL_INCLUDES tag is set to YES then Doxygen will list include +# files with double quotes in the documentation rather than with sharp brackets. +# The default value is: NO. + +FORCE_LOCAL_INCLUDES = NO + +# If the INLINE_INFO tag is set to YES then a tag [inline] is inserted in the +# documentation for inline members. +# The default value is: YES. + +INLINE_INFO = YES + +# If the SORT_MEMBER_DOCS tag is set to YES then Doxygen will sort the +# (detailed) documentation of file and class members alphabetically by member +# name. If set to NO, the members will appear in declaration order. +# The default value is: YES. + +SORT_MEMBER_DOCS = YES + +# If the SORT_BRIEF_DOCS tag is set to YES then Doxygen will sort the brief +# descriptions of file, namespace and class members alphabetically by member +# name. If set to NO, the members will appear in declaration order. Note that +# this will also influence the order of the classes in the class list. +# The default value is: NO. + +SORT_BRIEF_DOCS = NO + +# If the SORT_MEMBERS_CTORS_1ST tag is set to YES then Doxygen will sort the +# (brief and detailed) documentation of class members so that constructors and +# destructors are listed first. If set to NO the constructors will appear in the +# respective orders defined by SORT_BRIEF_DOCS and SORT_MEMBER_DOCS. +# Note: If SORT_BRIEF_DOCS is set to NO this option is ignored for sorting brief +# member documentation. +# Note: If SORT_MEMBER_DOCS is set to NO this option is ignored for sorting +# detailed member documentation. +# The default value is: NO. + +SORT_MEMBERS_CTORS_1ST = YES + +# If the SORT_GROUP_NAMES tag is set to YES then Doxygen will sort the hierarchy +# of group names into alphabetical order. If set to NO the group names will +# appear in their defined order. +# The default value is: NO. + +SORT_GROUP_NAMES = YES + +# If the SORT_BY_SCOPE_NAME tag is set to YES, the class list will be sorted by +# fully-qualified names, including namespaces. If set to NO, the class list will +# be sorted only by class name, not including the namespace part. +# Note: This option is not very useful if HIDE_SCOPE_NAMES is set to YES. +# Note: This option applies only to the class list, not to the alphabetical +# list. +# The default value is: NO. + +SORT_BY_SCOPE_NAME = YES + +# If the STRICT_PROTO_MATCHING option is enabled and Doxygen fails to do proper +# type resolution of all parameters of a function it will reject a match between +# the prototype and the implementation of a member function even if there is +# only one candidate or it is obvious which candidate to choose by doing a +# simple string match. By disabling STRICT_PROTO_MATCHING Doxygen will still +# accept a match between prototype and implementation in such cases. +# The default value is: NO. + +STRICT_PROTO_MATCHING = NO + +# The GENERATE_TODOLIST tag can be used to enable (YES) or disable (NO) the todo +# list. This list is created by putting \todo commands in the documentation. +# The default value is: YES. + +GENERATE_TODOLIST = YES + +# The GENERATE_TESTLIST tag can be used to enable (YES) or disable (NO) the test +# list. This list is created by putting \test commands in the documentation. +# The default value is: YES. + +GENERATE_TESTLIST = NO + +# The GENERATE_BUGLIST tag can be used to enable (YES) or disable (NO) the bug +# list. This list is created by putting \bug commands in the documentation. +# The default value is: YES. + +GENERATE_BUGLIST = NO + +# The GENERATE_DEPRECATEDLIST tag can be used to enable (YES) or disable (NO) +# the deprecated list. This list is created by putting \deprecated commands in +# the documentation. +# The default value is: YES. + +GENERATE_DEPRECATEDLIST= NO + +# The ENABLED_SECTIONS tag can be used to enable conditional documentation +# sections, marked by \if ... \endif and \cond +# ... \endcond blocks. + +ENABLED_SECTIONS = + +# The MAX_INITIALIZER_LINES tag determines the maximum number of lines that the +# initial value of a variable or macro / define can have for it to appear in the +# documentation. If the initializer consists of more lines than specified here +# it will be hidden. Use a value of 0 to hide initializers completely. The +# appearance of the value of individual variables and macros / defines can be +# controlled using \showinitializer or \hideinitializer command in the +# documentation regardless of this setting. +# Minimum value: 0, maximum value: 10000, default value: 30. + +MAX_INITIALIZER_LINES = 30 + +# Set the SHOW_USED_FILES tag to NO to disable the list of files generated at +# the bottom of the documentation of classes and structs. If set to YES, the +# list will mention the files that were used to generate the documentation. +# The default value is: YES. + +SHOW_USED_FILES = YES + +# Set the SHOW_FILES tag to NO to disable the generation of the Files page. This +# will remove the Files entry from the Quick Index and from the Folder Tree View +# (if specified). +# The default value is: YES. + +SHOW_FILES = YES + +# Set the SHOW_NAMESPACES tag to NO to disable the generation of the Namespaces +# page. This will remove the Namespaces entry from the Quick Index and from the +# Folder Tree View (if specified). +# The default value is: YES. + +SHOW_NAMESPACES = YES + +# The FILE_VERSION_FILTER tag can be used to specify a program or script that +# Doxygen should invoke to get the current version for each file (typically from +# the version control system). Doxygen will invoke the program by executing (via +# popen()) the command command input-file, where command is the value of the +# FILE_VERSION_FILTER tag, and input-file is the name of an input file provided +# by Doxygen. Whatever the program writes to standard output is used as the file +# version. For an example see the documentation. + +FILE_VERSION_FILTER = + +# The LAYOUT_FILE tag can be used to specify a layout file which will be parsed +# by Doxygen. The layout file controls the global structure of the generated +# output files in an output format independent way. To create the layout file +# that represents Doxygen's defaults, run Doxygen with the -l option. You can +# optionally specify a file name after the option, if omitted DoxygenLayout.xml +# will be used as the name of the layout file. See also section "Changing the +# layout of pages" for information. +# +# Note that if you run Doxygen from a directory containing a file called +# DoxygenLayout.xml, Doxygen will parse it automatically even if the LAYOUT_FILE +# tag is left empty. + +LAYOUT_FILE = + +# The CITE_BIB_FILES tag can be used to specify one or more bib files containing +# the reference definitions. This must be a list of .bib files. The .bib +# extension is automatically appended if omitted. This requires the bibtex tool +# to be installed. See also https://en.wikipedia.org/wiki/BibTeX for more info. +# For LaTeX the style of the bibliography can be controlled using +# LATEX_BIB_STYLE. To use this feature you need bibtex and perl available in the +# search path. See also \cite for info how to create references. + +CITE_BIB_FILES = + +# The EXTERNAL_TOOL_PATH tag can be used to extend the search path (PATH +# environment variable) so that external tools such as latex and gs can be +# found. +# Note: Directories specified with EXTERNAL_TOOL_PATH are added in front of the +# path already specified by the PATH variable, and are added in the order +# specified. +# Note: This option is particularly useful for macOS version 14 (Sonoma) and +# higher, when running Doxygen from Doxywizard, because in this case any user- +# defined changes to the PATH are ignored. A typical example on macOS is to set +# EXTERNAL_TOOL_PATH = /Library/TeX/texbin /usr/local/bin +# together with the standard path, the full search path used by doxygen when +# launching external tools will then become +# PATH=/Library/TeX/texbin:/usr/local/bin:/usr/bin:/bin:/usr/sbin:/sbin + +EXTERNAL_TOOL_PATH = + +#--------------------------------------------------------------------------- +# Configuration options related to warning and progress messages +#--------------------------------------------------------------------------- + +# The QUIET tag can be used to turn on/off the messages that are generated to +# standard output by Doxygen. If QUIET is set to YES this implies that the +# messages are off. +# The default value is: NO. + +QUIET = NO + +# The WARNINGS tag can be used to turn on/off the warning messages that are +# generated to standard error (stderr) by Doxygen. If WARNINGS is set to YES +# this implies that the warnings are on. +# +# Tip: Turn warnings on while writing the documentation. +# The default value is: YES. + +WARNINGS = YES + +# If the WARN_IF_UNDOCUMENTED tag is set to YES then Doxygen will generate +# warnings for undocumented members. If EXTRACT_ALL is set to YES then this flag +# will automatically be disabled. +# The default value is: YES. + +WARN_IF_UNDOCUMENTED = YES + +# If the WARN_IF_DOC_ERROR tag is set to YES, Doxygen will generate warnings for +# potential errors in the documentation, such as documenting some parameters in +# a documented function twice, or documenting parameters that don't exist or +# using markup commands wrongly. +# The default value is: YES. + +WARN_IF_DOC_ERROR = YES + +# If WARN_IF_INCOMPLETE_DOC is set to YES, Doxygen will warn about incomplete +# function parameter documentation. If set to NO, Doxygen will accept that some +# parameters have no documentation without warning. +# The default value is: YES. + +WARN_IF_INCOMPLETE_DOC = YES + +# This WARN_NO_PARAMDOC option can be enabled to get warnings for functions that +# are documented, but have no documentation for their parameters or return +# value. If set to NO, Doxygen will only warn about wrong parameter +# documentation, but not about the absence of documentation. If EXTRACT_ALL is +# set to YES then this flag will automatically be disabled. See also +# WARN_IF_INCOMPLETE_DOC +# The default value is: NO. + +WARN_NO_PARAMDOC = NO + +# If WARN_IF_UNDOC_ENUM_VAL option is set to YES, Doxygen will warn about +# undocumented enumeration values. If set to NO, Doxygen will accept +# undocumented enumeration values. If EXTRACT_ALL is set to YES then this flag +# will automatically be disabled. +# The default value is: NO. + +WARN_IF_UNDOC_ENUM_VAL = NO + +# If the WARN_AS_ERROR tag is set to YES then Doxygen will immediately stop when +# a warning is encountered. If the WARN_AS_ERROR tag is set to FAIL_ON_WARNINGS +# then Doxygen will continue running as if WARN_AS_ERROR tag is set to NO, but +# at the end of the Doxygen process Doxygen will return with a non-zero status. +# If the WARN_AS_ERROR tag is set to FAIL_ON_WARNINGS_PRINT then Doxygen behaves +# like FAIL_ON_WARNINGS but in case no WARN_LOGFILE is defined Doxygen will not +# write the warning messages in between other messages but write them at the end +# of a run, in case a WARN_LOGFILE is defined the warning messages will be +# besides being in the defined file also be shown at the end of a run, unless +# the WARN_LOGFILE is defined as - i.e. standard output (stdout) in that case +# the behavior will remain as with the setting FAIL_ON_WARNINGS. +# Possible values are: NO, YES, FAIL_ON_WARNINGS and FAIL_ON_WARNINGS_PRINT. +# The default value is: NO. + +WARN_AS_ERROR = NO + +# The WARN_FORMAT tag determines the format of the warning messages that Doxygen +# can produce. The string should contain the $file, $line, and $text tags, which +# will be replaced by the file and line number from which the warning originated +# and the warning text. Optionally the format may contain $version, which will +# be replaced by the version of the file (if it could be obtained via +# FILE_VERSION_FILTER) +# See also: WARN_LINE_FORMAT +# The default value is: $file:$line: $text. + +WARN_FORMAT = "$file:$line: $text" + +# In the $text part of the WARN_FORMAT command it is possible that a reference +# to a more specific place is given. To make it easier to jump to this place +# (outside of Doxygen) the user can define a custom "cut" / "paste" string. +# Example: +# WARN_LINE_FORMAT = "'vi $file +$line'" +# See also: WARN_FORMAT +# The default value is: at line $line of file $file. + +WARN_LINE_FORMAT = "at line $line of file $file" + +# The WARN_LOGFILE tag can be used to specify a file to which warning and error +# messages should be written. If left blank the output is written to standard +# error (stderr). In case the file specified cannot be opened for writing the +# warning and error messages are written to standard error. When as file - is +# specified the warning and error messages are written to standard output +# (stdout). + +WARN_LOGFILE = + +#--------------------------------------------------------------------------- +# Configuration options related to the input files +#--------------------------------------------------------------------------- + +# The INPUT tag is used to specify the files and/or directories that contain +# documented source files. You may enter file names like myfile.cpp or +# directories like /usr/src/myproject. Separate the files or directories with +# spaces. See also FILE_PATTERNS and EXTENSION_MAPPING +# Note: If this tag is empty the current directory is searched. + +INPUT = ../functional_modeler \ + ../program_mapper \ + ../common \ + ../p_isa_utilities \ + ../README.md \ + ../docs \ + ../docsrc/srcs + +# This tag can be used to specify the character encoding of the source files +# that Doxygen parses. Internally Doxygen uses the UTF-8 encoding. Doxygen uses +# libiconv (or the iconv built into libc) for the transcoding. See the libiconv +# documentation (see: +# https://www.gnu.org/software/libiconv/) for the list of possible encodings. +# See also: INPUT_FILE_ENCODING +# The default value is: UTF-8. + +INPUT_ENCODING = UTF-8 + +# This tag can be used to specify the character encoding of the source files +# that Doxygen parses The INPUT_FILE_ENCODING tag can be used to specify +# character encoding on a per file pattern basis. Doxygen will compare the file +# name with each pattern and apply the encoding instead of the default +# INPUT_ENCODING) if there is a match. The character encodings are a list of the +# form: pattern=encoding (like *.php=ISO-8859-1). +# See also: INPUT_ENCODING for further information on supported encodings. + +INPUT_FILE_ENCODING = + +# If the value of the INPUT tag contains directories, you can use the +# FILE_PATTERNS tag to specify one or more wildcard patterns (like *.cpp and +# *.h) to filter out the source-files in the directories. +# +# Note that for custom extensions or not directly supported extensions you also +# need to set EXTENSION_MAPPING for the extension otherwise the files are not +# read by Doxygen. +# +# Note the list of default checked file patterns might differ from the list of +# default file extension mappings. +# +# If left blank the following patterns are tested:*.c, *.cc, *.cxx, *.cxxm, +# *.cpp, *.cppm, *.ccm, *.c++, *.c++m, *.java, *.ii, *.ixx, *.ipp, *.i++, *.inl, +# *.idl, *.ddl, *.odl, *.h, *.hh, *.hxx, *.hpp, *.h++, *.ixx, *.l, *.cs, *.d, +# *.php, *.php4, *.php5, *.phtml, *.inc, *.m, *.markdown, *.md, *.mm, *.dox (to +# be provided as Doxygen C comment), *.py, *.pyw, *.f90, *.f95, *.f03, *.f08, +# *.f18, *.f, *.for, *.vhd, *.vhdl, *.ucf, *.qsf and *.ice. + +FILE_PATTERNS = *.cpp \ + *.h \ + *.md \ + *.hpp + +# The RECURSIVE tag can be used to specify whether or not subdirectories should +# be searched for input files as well. +# The default value is: NO. + +RECURSIVE = YES + +# The EXCLUDE tag can be used to specify files and/or directories that should be +# excluded from the INPUT source files. This way you can easily exclude a +# subdirectory from a directory tree whose root is specified with the INPUT tag. +# +# Note that relative paths are relative to the directory from which Doxygen is +# run. + +EXCLUDE = + +# The EXCLUDE_SYMLINKS tag can be used to select whether or not files or +# directories that are symbolic links (a Unix file system feature) are excluded +# from the input. +# The default value is: NO. + +EXCLUDE_SYMLINKS = NO + +# If the value of the INPUT tag contains directories, you can use the +# EXCLUDE_PATTERNS tag to specify one or more wildcard patterns to exclude +# certain files from those directories. +# +# Note that the wildcards are matched against the file with absolute path, so to +# exclude all test directories for example use the pattern */test/* + +EXCLUDE_PATTERNS = ./build/* \ + */project/* + +# The EXCLUDE_SYMBOLS tag can be used to specify one or more symbol names +# (namespaces, classes, functions, etc.) that should be excluded from the +# output. The symbol name can be a fully qualified name, a word, or if the +# wildcard * is used, a substring. Examples: ANamespace, AClass, +# ANamespace::AClass, ANamespace::*Test + +EXCLUDE_SYMBOLS = + +# The EXAMPLE_PATH tag can be used to specify one or more files or directories +# that contain example code fragments that are included (see the \include +# command). + +EXAMPLE_PATH = . + +# If the value of the EXAMPLE_PATH tag contains directories, you can use the +# EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp and +# *.h) to filter out the source-files in the directories. If left blank all +# files are included. + +EXAMPLE_PATTERNS = * + +# If the EXAMPLE_RECURSIVE tag is set to YES then subdirectories will be +# searched for input files to be used with the \include or \dontinclude commands +# irrespective of the value of the RECURSIVE tag. +# The default value is: NO. + +EXAMPLE_RECURSIVE = YES + +# The IMAGE_PATH tag can be used to specify one or more files or directories +# that contain images that are to be included in the documentation (see the +# \image command). + +IMAGE_PATH = . + +# The INPUT_FILTER tag can be used to specify a program that Doxygen should +# invoke to filter for each input file. Doxygen will invoke the filter program +# by executing (via popen()) the command: +# +# +# +# where is the value of the INPUT_FILTER tag, and is the +# name of an input file. Doxygen will then use the output that the filter +# program writes to standard output. If FILTER_PATTERNS is specified, this tag +# will be ignored. +# +# Note that the filter must not add or remove lines; it is applied before the +# code is scanned, but not when the output code is generated. If lines are added +# or removed, the anchors will not be placed correctly. +# +# Note that Doxygen will use the data processed and written to standard output +# for further processing, therefore nothing else, like debug statements or used +# commands (so in case of a Windows batch file always use @echo OFF), should be +# written to standard output. +# +# Note that for custom extensions or not directly supported extensions you also +# need to set EXTENSION_MAPPING for the extension otherwise the files are not +# properly processed by Doxygen. + +INPUT_FILTER = + +# The FILTER_PATTERNS tag can be used to specify filters on a per file pattern +# basis. Doxygen will compare the file name with each pattern and apply the +# filter if there is a match. The filters are a list of the form: pattern=filter +# (like *.cpp=my_cpp_filter). See INPUT_FILTER for further information on how +# filters are used. If the FILTER_PATTERNS tag is empty or if none of the +# patterns match the file name, INPUT_FILTER is applied. +# +# Note that for custom extensions or not directly supported extensions you also +# need to set EXTENSION_MAPPING for the extension otherwise the files are not +# properly processed by Doxygen. + +FILTER_PATTERNS = + +# If the FILTER_SOURCE_FILES tag is set to YES, the input filter (if set using +# INPUT_FILTER) will also be used to filter the input files that are used for +# producing the source files to browse (i.e. when SOURCE_BROWSER is set to YES). +# The default value is: NO. + +FILTER_SOURCE_FILES = NO + +# The FILTER_SOURCE_PATTERNS tag can be used to specify source filters per file +# pattern. A pattern will override the setting for FILTER_PATTERN (if any) and +# it is also possible to disable source filtering for a specific pattern using +# *.ext= (so without naming a filter). +# This tag requires that the tag FILTER_SOURCE_FILES is set to YES. + +FILTER_SOURCE_PATTERNS = + +# If the USE_MDFILE_AS_MAINPAGE tag refers to the name of a markdown file that +# is part of the input, its contents will be placed on the main page +# (index.html). This can be useful if you have a project on for instance GitHub +# and want to reuse the introduction page also for the Doxygen output. + +USE_MDFILE_AS_MAINPAGE = README.md + +# The Fortran standard specifies that for fixed formatted Fortran code all +# characters from position 72 are to be considered as comment. A common +# extension is to allow longer lines before the automatic comment starts. The +# setting FORTRAN_COMMENT_AFTER will also make it possible that longer lines can +# be processed before the automatic comment starts. +# Minimum value: 7, maximum value: 10000, default value: 72. + +FORTRAN_COMMENT_AFTER = 72 + +#--------------------------------------------------------------------------- +# Configuration options related to source browsing +#--------------------------------------------------------------------------- + +# If the SOURCE_BROWSER tag is set to YES then a list of source files will be +# generated. Documented entities will be cross-referenced with these sources. +# +# Note: To get rid of all source code in the generated output, make sure that +# also VERBATIM_HEADERS is set to NO. +# The default value is: NO. + +SOURCE_BROWSER = YES + +# Setting the INLINE_SOURCES tag to YES will include the body of functions, +# multi-line macros, enums or list initialized variables directly into the +# documentation. +# The default value is: NO. + +INLINE_SOURCES = YES + +# Setting the STRIP_CODE_COMMENTS tag to YES will instruct Doxygen to hide any +# special comment blocks from generated source code fragments. Normal C, C++ and +# Fortran comments will always remain visible. +# The default value is: YES. + +STRIP_CODE_COMMENTS = YES + +# If the REFERENCED_BY_RELATION tag is set to YES then for each documented +# entity all documented functions referencing it will be listed. +# The default value is: NO. + +REFERENCED_BY_RELATION = YES + +# If the REFERENCES_RELATION tag is set to YES then for each documented function +# all documented entities called/used by that function will be listed. +# The default value is: NO. + +REFERENCES_RELATION = YES + +# If the REFERENCES_LINK_SOURCE tag is set to YES and SOURCE_BROWSER tag is set +# to YES then the hyperlinks from functions in REFERENCES_RELATION and +# REFERENCED_BY_RELATION lists will link to the source code. Otherwise they will +# link to the documentation. +# The default value is: YES. + +REFERENCES_LINK_SOURCE = YES + +# If SOURCE_TOOLTIPS is enabled (the default) then hovering a hyperlink in the +# source code will show a tooltip with additional information such as prototype, +# brief description and links to the definition and documentation. Since this +# will make the HTML file larger and loading of large files a bit slower, you +# can opt to disable this feature. +# The default value is: YES. +# This tag requires that the tag SOURCE_BROWSER is set to YES. + +SOURCE_TOOLTIPS = YES + +# If the USE_HTAGS tag is set to YES then the references to source code will +# point to the HTML generated by the htags(1) tool instead of Doxygen built-in +# source browser. The htags tool is part of GNU's global source tagging system +# (see https://www.gnu.org/software/global/global.html). You will need version +# 4.8.6 or higher. +# +# To use it do the following: +# - Install the latest version of global +# - Enable SOURCE_BROWSER and USE_HTAGS in the configuration file +# - Make sure the INPUT points to the root of the source tree +# - Run doxygen as normal +# +# Doxygen will invoke htags (and that will in turn invoke gtags), so these +# tools must be available from the command line (i.e. in the search path). +# +# The result: instead of the source browser generated by Doxygen, the links to +# source code will now point to the output of htags. +# The default value is: NO. +# This tag requires that the tag SOURCE_BROWSER is set to YES. + +USE_HTAGS = NO + +# If the VERBATIM_HEADERS tag is set the YES then Doxygen will generate a +# verbatim copy of the header file for each class for which an include is +# specified. Set to NO to disable this. +# See also: Section \class. +# The default value is: YES. + +VERBATIM_HEADERS = YES + +#--------------------------------------------------------------------------- +# Configuration options related to the alphabetical class index +#--------------------------------------------------------------------------- + +# If the ALPHABETICAL_INDEX tag is set to YES, an alphabetical index of all +# compounds will be generated. Enable this if the project contains a lot of +# classes, structs, unions or interfaces. +# The default value is: YES. + +ALPHABETICAL_INDEX = YES + +# The IGNORE_PREFIX tag can be used to specify a prefix (or a list of prefixes) +# that should be ignored while generating the index headers. The IGNORE_PREFIX +# tag works for classes, function and member names. The entity will be placed in +# the alphabetical list under the first letter of the entity name that remains +# after removing the prefix. +# This tag requires that the tag ALPHABETICAL_INDEX is set to YES. + +IGNORE_PREFIX = + +#--------------------------------------------------------------------------- +# Configuration options related to the HTML output +#--------------------------------------------------------------------------- + +# If the GENERATE_HTML tag is set to YES, Doxygen will generate HTML output +# The default value is: YES. + +GENERATE_HTML = YES + +# The HTML_OUTPUT tag is used to specify where the HTML docs will be put. If a +# relative path is entered the value of OUTPUT_DIRECTORY will be put in front of +# it. +# The default directory is: html. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_OUTPUT = html + +# The HTML_FILE_EXTENSION tag can be used to specify the file extension for each +# generated HTML page (for example: .htm, .php, .asp). +# The default value is: .html. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_FILE_EXTENSION = .html + +# The HTML_HEADER tag can be used to specify a user-defined HTML header file for +# each generated HTML page. If the tag is left blank Doxygen will generate a +# standard header. +# +# To get valid HTML the header file that includes any scripts and style sheets +# that Doxygen needs, which is dependent on the configuration options used (e.g. +# the setting GENERATE_TREEVIEW). It is highly recommended to start with a +# default header using +# doxygen -w html new_header.html new_footer.html new_stylesheet.css +# YourConfigFile +# and then modify the file new_header.html. See also section "Doxygen usage" +# for information on how to generate the default header that Doxygen normally +# uses. +# Note: The header is subject to change so you typically have to regenerate the +# default header when upgrading to a newer version of Doxygen. For a description +# of the possible markers and block names see the documentation. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_HEADER = + +# The HTML_FOOTER tag can be used to specify a user-defined HTML footer for each +# generated HTML page. If the tag is left blank Doxygen will generate a standard +# footer. See HTML_HEADER for more information on how to generate a default +# footer and what special commands can be used inside the footer. See also +# section "Doxygen usage" for information on how to generate the default footer +# that Doxygen normally uses. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_FOOTER = + +# The HTML_STYLESHEET tag can be used to specify a user-defined cascading style +# sheet that is used by each HTML page. It can be used to fine-tune the look of +# the HTML output. If left blank Doxygen will generate a default style sheet. +# See also section "Doxygen usage" for information on how to generate the style +# sheet that Doxygen normally uses. +# Note: It is recommended to use HTML_EXTRA_STYLESHEET instead of this tag, as +# it is more robust and this tag (HTML_STYLESHEET) will in the future become +# obsolete. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_STYLESHEET = + +# The HTML_EXTRA_STYLESHEET tag can be used to specify additional user-defined +# cascading style sheets that are included after the standard style sheets +# created by Doxygen. Using this option one can overrule certain style aspects. +# This is preferred over using HTML_STYLESHEET since it does not replace the +# standard style sheet and is therefore more robust against future updates. +# Doxygen will copy the style sheet files to the output directory. +# Note: The order of the extra style sheet files is of importance (e.g. the last +# style sheet in the list overrules the setting of the previous ones in the +# list). +# Note: Since the styling of scrollbars can currently not be overruled in +# Webkit/Chromium, the styling will be left out of the default doxygen.css if +# one or more extra stylesheets have been specified. So if scrollbar +# customization is desired it has to be added explicitly. For an example see the +# documentation. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_EXTRA_STYLESHEET = + +# The HTML_EXTRA_FILES tag can be used to specify one or more extra images or +# other source files which should be copied to the HTML output directory. Note +# that these files will be copied to the base HTML output directory. Use the +# $relpath^ marker in the HTML_HEADER and/or HTML_FOOTER files to load these +# files. In the HTML_STYLESHEET file, use the file name only. Also note that the +# files will be copied as-is; there are no commands or markers available. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_EXTRA_FILES = + +# The HTML_COLORSTYLE tag can be used to specify if the generated HTML output +# should be rendered with a dark or light theme. +# Possible values are: LIGHT always generates light mode output, DARK always +# generates dark mode output, AUTO_LIGHT automatically sets the mode according +# to the user preference, uses light mode if no preference is set (the default), +# AUTO_DARK automatically sets the mode according to the user preference, uses +# dark mode if no preference is set and TOGGLE allows a user to switch between +# light and dark mode via a button. +# The default value is: AUTO_LIGHT. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_COLORSTYLE = AUTO_LIGHT + +# The HTML_COLORSTYLE_HUE tag controls the color of the HTML output. Doxygen +# will adjust the colors in the style sheet and background images according to +# this color. Hue is specified as an angle on a color-wheel, see +# https://en.wikipedia.org/wiki/Hue for more information. For instance the value +# 0 represents red, 60 is yellow, 120 is green, 180 is cyan, 240 is blue, 300 +# purple, and 360 is red again. +# Minimum value: 0, maximum value: 359, default value: 220. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_COLORSTYLE_HUE = 220 + +# The HTML_COLORSTYLE_SAT tag controls the purity (or saturation) of the colors +# in the HTML output. For a value of 0 the output will use gray-scales only. A +# value of 255 will produce the most vivid colors. +# Minimum value: 0, maximum value: 255, default value: 100. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_COLORSTYLE_SAT = 100 + +# The HTML_COLORSTYLE_GAMMA tag controls the gamma correction applied to the +# luminance component of the colors in the HTML output. Values below 100 +# gradually make the output lighter, whereas values above 100 make the output +# darker. The value divided by 100 is the actual gamma applied, so 80 represents +# a gamma of 0.8, The value 220 represents a gamma of 2.2, and 100 does not +# change the gamma. +# Minimum value: 40, maximum value: 240, default value: 80. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_COLORSTYLE_GAMMA = 80 + +# If the HTML_DYNAMIC_MENUS tag is set to YES then the generated HTML +# documentation will contain a main index with vertical navigation menus that +# are dynamically created via JavaScript. If disabled, the navigation index will +# consists of multiple levels of tabs that are statically embedded in every HTML +# page. Disable this option to support browsers that do not have JavaScript, +# like the Qt help browser. +# The default value is: YES. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_DYNAMIC_MENUS = YES + +# If the HTML_DYNAMIC_SECTIONS tag is set to YES then the generated HTML +# documentation will contain sections that can be hidden and shown after the +# page has loaded. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_DYNAMIC_SECTIONS = NO + +# If the HTML_CODE_FOLDING tag is set to YES then classes and functions can be +# dynamically folded and expanded in the generated HTML source code. +# The default value is: YES. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_CODE_FOLDING = YES + +# If the HTML_COPY_CLIPBOARD tag is set to YES then Doxygen will show an icon in +# the top right corner of code and text fragments that allows the user to copy +# its content to the clipboard. Note this only works if supported by the browser +# and the web page is served via a secure context (see: +# https://www.w3.org/TR/secure-contexts/), i.e. using the https: or file: +# protocol. +# The default value is: YES. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_COPY_CLIPBOARD = YES + +# Doxygen stores a couple of settings persistently in the browser (via e.g. +# cookies). By default these settings apply to all HTML pages generated by +# Doxygen across all projects. The HTML_PROJECT_COOKIE tag can be used to store +# the settings under a project specific key, such that the user preferences will +# be stored separately. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_PROJECT_COOKIE = + +# With HTML_INDEX_NUM_ENTRIES one can control the preferred number of entries +# shown in the various tree structured indices initially; the user can expand +# and collapse entries dynamically later on. Doxygen will expand the tree to +# such a level that at most the specified number of entries are visible (unless +# a fully collapsed tree already exceeds this amount). So setting the number of +# entries 1 will produce a full collapsed tree by default. 0 is a special value +# representing an infinite number of entries and will result in a full expanded +# tree by default. +# Minimum value: 0, maximum value: 9999, default value: 100. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_INDEX_NUM_ENTRIES = 100 + +# If the GENERATE_DOCSET tag is set to YES, additional index files will be +# generated that can be used as input for Apple's Xcode 3 integrated development +# environment (see: +# https://developer.apple.com/xcode/), introduced with OSX 10.5 (Leopard). To +# create a documentation set, Doxygen will generate a Makefile in the HTML +# output directory. Running make will produce the docset in that directory and +# running make install will install the docset in +# ~/Library/Developer/Shared/Documentation/DocSets so that Xcode will find it at +# startup. See https://developer.apple.com/library/archive/featuredarticles/Doxy +# genXcode/_index.html for more information. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_DOCSET = NO + +# This tag determines the name of the docset feed. A documentation feed provides +# an umbrella under which multiple documentation sets from a single provider +# (such as a company or product suite) can be grouped. +# The default value is: Doxygen generated docs. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_FEEDNAME = "Doxygen generated docs" + +# This tag determines the URL of the docset feed. A documentation feed provides +# an umbrella under which multiple documentation sets from a single provider +# (such as a company or product suite) can be grouped. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_FEEDURL = + +# This tag specifies a string that should uniquely identify the documentation +# set bundle. This should be a reverse domain-name style string, e.g. +# com.mycompany.MyDocSet. Doxygen will append .docset to the name. +# The default value is: org.doxygen.Project. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_BUNDLE_ID = org.doxygen.Project + +# The DOCSET_PUBLISHER_ID tag specifies a string that should uniquely identify +# the documentation publisher. This should be a reverse domain-name style +# string, e.g. com.mycompany.MyDocSet.documentation. +# The default value is: org.doxygen.Publisher. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_PUBLISHER_ID = org.doxygen.Publisher + +# The DOCSET_PUBLISHER_NAME tag identifies the documentation publisher. +# The default value is: Publisher. +# This tag requires that the tag GENERATE_DOCSET is set to YES. + +DOCSET_PUBLISHER_NAME = Publisher + +# If the GENERATE_HTMLHELP tag is set to YES then Doxygen generates three +# additional HTML index files: index.hhp, index.hhc, and index.hhk. The +# index.hhp is a project file that can be read by Microsoft's HTML Help Workshop +# on Windows. In the beginning of 2021 Microsoft took the original page, with +# a.o. the download links, offline the HTML help workshop was already many years +# in maintenance mode). You can download the HTML help workshop from the web +# archives at Installation executable (see: +# http://web.archive.org/web/20160201063255/http://download.microsoft.com/downlo +# ad/0/A/9/0A939EF6-E31C-430F-A3DF-DFAE7960D564/htmlhelp.exe). +# +# The HTML Help Workshop contains a compiler that can convert all HTML output +# generated by Doxygen into a single compiled HTML file (.chm). Compiled HTML +# files are now used as the Windows 98 help format, and will replace the old +# Windows help format (.hlp) on all Windows platforms in the future. Compressed +# HTML files also contain an index, a table of contents, and you can search for +# words in the documentation. The HTML workshop also contains a viewer for +# compressed HTML files. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_HTMLHELP = NO + +# The CHM_FILE tag can be used to specify the file name of the resulting .chm +# file. You can add a path in front of the file if the result should not be +# written to the html output directory. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +CHM_FILE = + +# The HHC_LOCATION tag can be used to specify the location (absolute path +# including file name) of the HTML help compiler (hhc.exe). If non-empty, +# Doxygen will try to run the HTML help compiler on the generated index.hhp. +# The file has to be specified with full path. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +HHC_LOCATION = + +# The GENERATE_CHI flag controls if a separate .chi index file is generated +# (YES) or that it should be included in the main .chm file (NO). +# The default value is: NO. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +GENERATE_CHI = NO + +# The CHM_INDEX_ENCODING is used to encode HtmlHelp index (hhk), content (hhc) +# and project file content. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +CHM_INDEX_ENCODING = + +# The BINARY_TOC flag controls whether a binary table of contents is generated +# (YES) or a normal table of contents (NO) in the .chm file. Furthermore it +# enables the Previous and Next buttons. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +BINARY_TOC = NO + +# The TOC_EXPAND flag can be set to YES to add extra items for group members to +# the table of contents of the HTML help documentation and to the tree view. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTMLHELP is set to YES. + +TOC_EXPAND = NO + +# The SITEMAP_URL tag is used to specify the full URL of the place where the +# generated documentation will be placed on the server by the user during the +# deployment of the documentation. The generated sitemap is called sitemap.xml +# and placed on the directory specified by HTML_OUTPUT. In case no SITEMAP_URL +# is specified no sitemap is generated. For information about the sitemap +# protocol see https://www.sitemaps.org +# This tag requires that the tag GENERATE_HTML is set to YES. + +SITEMAP_URL = + +# If the GENERATE_QHP tag is set to YES and both QHP_NAMESPACE and +# QHP_VIRTUAL_FOLDER are set, an additional index file will be generated that +# can be used as input for Qt's qhelpgenerator to generate a Qt Compressed Help +# (.qch) of the generated HTML documentation. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_QHP = NO + +# If the QHG_LOCATION tag is specified, the QCH_FILE tag can be used to specify +# the file name of the resulting .qch file. The path specified is relative to +# the HTML output folder. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QCH_FILE = + +# The QHP_NAMESPACE tag specifies the namespace to use when generating Qt Help +# Project output. For more information please see Qt Help Project / Namespace +# (see: +# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#namespace). +# The default value is: org.doxygen.Project. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_NAMESPACE = org.doxygen.Project + +# The QHP_VIRTUAL_FOLDER tag specifies the namespace to use when generating Qt +# Help Project output. For more information please see Qt Help Project / Virtual +# Folders (see: +# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#virtual-folders). +# The default value is: doc. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_VIRTUAL_FOLDER = doc + +# If the QHP_CUST_FILTER_NAME tag is set, it specifies the name of a custom +# filter to add. For more information please see Qt Help Project / Custom +# Filters (see: +# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-filters). +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_CUST_FILTER_NAME = + +# The QHP_CUST_FILTER_ATTRS tag specifies the list of the attributes of the +# custom filter to add. For more information please see Qt Help Project / Custom +# Filters (see: +# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#custom-filters). +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_CUST_FILTER_ATTRS = + +# The QHP_SECT_FILTER_ATTRS tag specifies the list of the attributes this +# project's filter section matches. Qt Help Project / Filter Attributes (see: +# https://doc.qt.io/archives/qt-4.8/qthelpproject.html#filter-attributes). +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHP_SECT_FILTER_ATTRS = + +# The QHG_LOCATION tag can be used to specify the location (absolute path +# including file name) of Qt's qhelpgenerator. If non-empty Doxygen will try to +# run qhelpgenerator on the generated .qhp file. +# This tag requires that the tag GENERATE_QHP is set to YES. + +QHG_LOCATION = + +# If the GENERATE_ECLIPSEHELP tag is set to YES, additional index files will be +# generated, together with the HTML files, they form an Eclipse help plugin. To +# install this plugin and make it available under the help contents menu in +# Eclipse, the contents of the directory containing the HTML and XML files needs +# to be copied into the plugins directory of eclipse. The name of the directory +# within the plugins directory should be the same as the ECLIPSE_DOC_ID value. +# After copying Eclipse needs to be restarted before the help appears. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_ECLIPSEHELP = NO + +# A unique identifier for the Eclipse help plugin. When installing the plugin +# the directory name containing the HTML and XML files should also have this +# name. Each documentation set should have its own identifier. +# The default value is: org.doxygen.Project. +# This tag requires that the tag GENERATE_ECLIPSEHELP is set to YES. + +ECLIPSE_DOC_ID = org.doxygen.Project + +# If you want full control over the layout of the generated HTML pages it might +# be necessary to disable the index and replace it with your own. The +# DISABLE_INDEX tag can be used to turn on/off the condensed index (tabs) at top +# of each HTML page. A value of NO enables the index and the value YES disables +# it. Since the tabs in the index contain the same information as the navigation +# tree, you can set this option to YES if you also set GENERATE_TREEVIEW to YES. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +DISABLE_INDEX = NO + +# The GENERATE_TREEVIEW tag is used to specify whether a tree-like index +# structure should be generated to display hierarchical information. If the tag +# value is set to YES, a side panel will be generated containing a tree-like +# index structure (just like the one that is generated for HTML Help). For this +# to work a browser that supports JavaScript, DHTML, CSS and frames is required +# (i.e. any modern browser). Windows users are probably better off using the +# HTML help feature. Via custom style sheets (see HTML_EXTRA_STYLESHEET) one can +# further fine tune the look of the index (see "Fine-tuning the output"). As an +# example, the default style sheet generated by Doxygen has an example that +# shows how to put an image at the root of the tree instead of the PROJECT_NAME. +# Since the tree basically has the same information as the tab index, you could +# consider setting DISABLE_INDEX to YES when enabling this option. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +GENERATE_TREEVIEW = YES + +# When both GENERATE_TREEVIEW and DISABLE_INDEX are set to YES, then the +# FULL_SIDEBAR option determines if the side bar is limited to only the treeview +# area (value NO) or if it should extend to the full height of the window (value +# YES). Setting this to YES gives a layout similar to +# https://docs.readthedocs.io with more room for contents, but less room for the +# project logo, title, and description. If either GENERATE_TREEVIEW or +# DISABLE_INDEX is set to NO, this option has no effect. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +FULL_SIDEBAR = NO + +# The ENUM_VALUES_PER_LINE tag can be used to set the number of enum values that +# Doxygen will group on one line in the generated HTML documentation. +# +# Note that a value of 0 will completely suppress the enum values from appearing +# in the overview section. +# Minimum value: 0, maximum value: 20, default value: 4. +# This tag requires that the tag GENERATE_HTML is set to YES. + +ENUM_VALUES_PER_LINE = 4 + +# When the SHOW_ENUM_VALUES tag is set doxygen will show the specified +# enumeration values besides the enumeration mnemonics. +# The default value is: NO. + +SHOW_ENUM_VALUES = NO + +# If the treeview is enabled (see GENERATE_TREEVIEW) then this tag can be used +# to set the initial width (in pixels) of the frame in which the tree is shown. +# Minimum value: 0, maximum value: 1500, default value: 250. +# This tag requires that the tag GENERATE_HTML is set to YES. + +TREEVIEW_WIDTH = 250 + +# If the EXT_LINKS_IN_WINDOW option is set to YES, Doxygen will open links to +# external symbols imported via tag files in a separate window. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +EXT_LINKS_IN_WINDOW = NO + +# If the OBFUSCATE_EMAILS tag is set to YES, Doxygen will obfuscate email +# addresses. +# The default value is: YES. +# This tag requires that the tag GENERATE_HTML is set to YES. + +OBFUSCATE_EMAILS = YES + +# If the HTML_FORMULA_FORMAT option is set to svg, Doxygen will use the pdf2svg +# tool (see https://github.com/dawbarton/pdf2svg) or inkscape (see +# https://inkscape.org) to generate formulas as SVG images instead of ONGs for +# the HTML output. These images will generally look nicer at scaled resolutions. +# Possible values are: png (the default) and svg (looks nicer but requires the +# pdf2svg or inkscape tool). +# The default value is: png. +# This tag requires that the tag GENERATE_HTML is set to YES. + +HTML_FORMULA_FORMAT = png + +# Use this tag to change the font size of LaTeX formulas included as images in +# the HTML documentation. When you change the font size after a successful +# Doxygen run you need to manually remove any form_*.png images from the HTML +# output directory to force them to be regenerated. +# Minimum value: 8, maximum value: 50, default value: 10. +# This tag requires that the tag GENERATE_HTML is set to YES. + +FORMULA_FONTSIZE = 10 + +# The FORMULA_MACROFILE can contain LaTeX \newcommand and \renewcommand commands +# to create new LaTeX commands to be used in formulas as building blocks. See +# the section "Including formulas" for details. + +FORMULA_MACROFILE = + +# Enable the USE_MATHJAX option to render LaTeX formulas using MathJax (see +# https://www.mathjax.org) which uses client side JavaScript for the rendering +# instead of using pre-rendered bitmaps. Use this if you do not have LaTeX +# installed or if you want to formulas look prettier in the HTML output. When +# enabled you may also need to install MathJax separately and configure the path +# to it using the MATHJAX_RELPATH option. +# The default value is: NO. +# This tag requires that the tag GENERATE_HTML is set to YES. + +USE_MATHJAX = YES + +# With MATHJAX_VERSION it is possible to specify the MathJax version to be used. +# Note that the different versions of MathJax have different requirements with +# regards to the different settings, so it is possible that also other MathJax +# settings have to be changed when switching between the different MathJax +# versions. +# Possible values are: MathJax_2 and MathJax_3. +# The default value is: MathJax_2. +# This tag requires that the tag USE_MATHJAX is set to YES. + +MATHJAX_VERSION = MathJax_2 + +# When MathJax is enabled you can set the default output format to be used for +# the MathJax output. For more details about the output format see MathJax +# version 2 (see: +# http://docs.mathjax.org/en/v2.7-latest/output.html) and MathJax version 3 +# (see: +# http://docs.mathjax.org/en/latest/web/components/output.html). +# Possible values are: HTML-CSS (which is slower, but has the best +# compatibility. This is the name for Mathjax version 2, for MathJax version 3 +# this will be translated into chtml), NativeMML (i.e. MathML. Only supported +# for MathJax 2. For MathJax version 3 chtml will be used instead.), chtml (This +# is the name for Mathjax version 3, for MathJax version 2 this will be +# translated into HTML-CSS) and SVG. +# The default value is: HTML-CSS. +# This tag requires that the tag USE_MATHJAX is set to YES. + +MATHJAX_FORMAT = HTML-CSS + +# When MathJax is enabled you need to specify the location relative to the HTML +# output directory using the MATHJAX_RELPATH option. The destination directory +# should contain the MathJax.js script. For instance, if the mathjax directory +# is located at the same level as the HTML output directory, then +# MATHJAX_RELPATH should be ../mathjax. The default value points to the MathJax +# Content Delivery Network so you can quickly see the result without installing +# MathJax. However, it is strongly recommended to install a local copy of +# MathJax from https://www.mathjax.org before deployment. The default value is: +# - in case of MathJax version 2: https://cdn.jsdelivr.net/npm/mathjax@2 +# - in case of MathJax version 3: https://cdn.jsdelivr.net/npm/mathjax@3 +# This tag requires that the tag USE_MATHJAX is set to YES. + +MATHJAX_RELPATH = http://cdn.mathjax.org/mathjax/latest + +# The MATHJAX_EXTENSIONS tag can be used to specify one or more MathJax +# extension names that should be enabled during MathJax rendering. For example +# for MathJax version 2 (see +# https://docs.mathjax.org/en/v2.7-latest/tex.html#tex-and-latex-extensions): +# MATHJAX_EXTENSIONS = TeX/AMSmath TeX/AMSsymbols +# For example for MathJax version 3 (see +# http://docs.mathjax.org/en/latest/input/tex/extensions/index.html): +# MATHJAX_EXTENSIONS = ams +# This tag requires that the tag USE_MATHJAX is set to YES. + +MATHJAX_EXTENSIONS = + +# The MATHJAX_CODEFILE tag can be used to specify a file with JavaScript pieces +# of code that will be used on startup of the MathJax code. See the MathJax site +# (see: +# http://docs.mathjax.org/en/v2.7-latest/output.html) for more details. For an +# example see the documentation. +# This tag requires that the tag USE_MATHJAX is set to YES. + +MATHJAX_CODEFILE = + +# When the SEARCHENGINE tag is enabled Doxygen will generate a search box for +# the HTML output. The underlying search engine uses JavaScript and DHTML and +# should work on any modern browser. Note that when using HTML help +# (GENERATE_HTMLHELP), Qt help (GENERATE_QHP), or docsets (GENERATE_DOCSET) +# there is already a search function so this one should typically be disabled. +# For large projects the JavaScript based search engine can be slow, then +# enabling SERVER_BASED_SEARCH may provide a better solution. It is possible to +# search using the keyboard; to jump to the search box use + S +# (what the is depends on the OS and browser, but it is typically +# , /