diff --git a/.dockerignore b/.dockerignore new file mode 100644 index 0000000..55d189e --- /dev/null +++ b/.dockerignore @@ -0,0 +1,9 @@ +# all start with .(dot), including directories and files +.* +CHANGELOG.md +CODE_OF_CONDUCT.md +CONTRIBUTING.md +compose.yml +LICENSE* +Makefile +README.md diff --git a/.editorconfig b/.editorconfig new file mode 100644 index 0000000..b59892f --- /dev/null +++ b/.editorconfig @@ -0,0 +1,14 @@ +root = true + +[*] +charset = utf-8 +end_of_line = lf +indent_size = 4 +indent_style = space +insert_final_newline = true +max_line_length = 120 +tab_width = 4 +trim_trailing_whitespace = true + +[Makefile] +indent_style = tab \ No newline at end of file diff --git a/.github/ISSUE_TEMPLATE/bug_report.md b/.github/ISSUE_TEMPLATE/bug_report.md new file mode 100644 index 0000000..7eba570 --- /dev/null +++ b/.github/ISSUE_TEMPLATE/bug_report.md @@ -0,0 +1,44 @@ +--- +name: Bug report +about: Create a report to help us improve +title: 'bug: ' +labels: bug +assignees: '' + +--- + +## Bug description + + + +- Would you like to work on a fix? [y/n] + +## To Reproduce + +Steps to reproduce the behavior: + +1. ... +2. ... +3. ... +4. ... + + + +## Expected behavior + + + +## Screenshots + + + +## Environment + + + +- OS: [e.g. Ubuntu 20.04] +- example-cuda-cmake version: [e.g. 0.1.0] + +## Additional context + + diff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.yml new file mode 100644 index 0000000..0086358 --- /dev/null +++ b/.github/ISSUE_TEMPLATE/config.yml @@ -0,0 +1 @@ +blank_issues_enabled: true diff --git a/.github/ISSUE_TEMPLATE/feature_request.md b/.github/ISSUE_TEMPLATE/feature_request.md new file mode 100644 index 0000000..9b061bb --- /dev/null +++ b/.github/ISSUE_TEMPLATE/feature_request.md @@ -0,0 +1,28 @@ +--- +name: Feature request +about: Suggest an idea for this project +title: 'Feature Request: ' +labels: enhancement +assignees: '' + +--- + +## Motivations + + + +- Would you like to implement this feature? [y/n] + +## Solution + + + +## Alternatives + + + +## Additional context + + diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md new file mode 100644 index 0000000..87fe941 --- /dev/null +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -0,0 +1,9 @@ + + + diff --git a/.github/configs/labeler.yml b/.github/configs/labeler.yml new file mode 100644 index 0000000..f4ed978 --- /dev/null +++ b/.github/configs/labeler.yml @@ -0,0 +1,63 @@ +version: 1 + +labels: + # Type: Build-related changes + - label: "@type/build" + title: '^build(?:\(.+\))?\!?:' + + # Type: CI-related changes + - label: "@type/ci" + title: '^ci(?:\(.+\))?\!?:' + files: + - '\.github/.+' + + # Type: Documentation changes + - label: "@type/docs" + title: '^docs(?:\(.+\))?\!?:' + files: + - "docs/.+" + - "**/*.md" + + # Type: New feature + - label: "@type/feature" + title: '^feat(?:\(.+\))?\!?:' + + # Type: Bug fix + - label: "@type/fix" + title: '^fix(?:\(.+\))?\!?:' + + # Type: Improvements such as style changes, refactoring, or performance improvements + - label: "@type/improve" + title: '^(style|refactor|perf)(?:\(.+\))?\!?:' + + # Type: Dependency changes + - label: "@type/dependency" + title: '^(chore|build)(?:\(deps\))?\!?:' + + # Type: Test-related changes + - label: "@type/test" + title: '^test(?:\(.+\))?\!?:' + files: + - "tests/.+" + - "spec/.+" + + # Type: Security-related changes + - label: "@type/security" + title: '^security(?:\(.+\))?\!?:' + files: + - "**/security/.+" + + # Issue Type Only: Feature Request + - label: "Feature Request" + type: issue + title: "^Feature Request:" + + # Issue Type Only: Documentation + - label: "Documentation" + type: issue + title: "^.*(\b[Dd]ocumentation|doc(s)?\b).*" + + # Issue Type Only: Bug Report + - label: "Bug Report" + type: issue + title: "^.*(\b[Bb]ug|b(u)?g(s)?\b).*" diff --git a/.github/dependabot.yml b/.github/dependabot.yml new file mode 100644 index 0000000..c44b6f1 --- /dev/null +++ b/.github/dependabot.yml @@ -0,0 +1,8 @@ +version: 2 +updates: + - package-ecosystem: "github-actions" + directory: "/" + # Check for updates every Monday + schedule: + interval: "weekly" + open-pull-requests-limit: 10 diff --git a/.github/renovate.json b/.github/renovate.json new file mode 100644 index 0000000..f9c2c32 --- /dev/null +++ b/.github/renovate.json @@ -0,0 +1,6 @@ +{ + "$schema": "https://docs.renovatebot.com/renovate-schema.json", + "extends": [ + "config:base" + ] +} diff --git a/.github/workflows/cd.yml b/.github/workflows/cd.yml new file mode 100644 index 0000000..694b52f --- /dev/null +++ b/.github/workflows/cd.yml @@ -0,0 +1,14 @@ +name: CD # Continuous Deployment or Delivery + +on: + push: + # e.g. 1.0.0, v2.0.0, v0.1.0, v0.2.0-alpha, v0.3.0+build-71edf32 + tags: + - '[v]?[0-9]+\.[0-9]+\.[0-9]+.*' + +jobs: + dd: + name: Deploy or Delivery + runs-on: ubuntu-latest + steps: + - uses: actions/checkout@v4 diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml new file mode 100644 index 0000000..a4b6b49 --- /dev/null +++ b/.github/workflows/ci.yml @@ -0,0 +1,34 @@ +name: CI # Continuous Integration + +on: + push: + branches: + - main + pull_request: + +jobs: + build-and-test: + strategy: + matrix: + os: [ubuntu-22.04, windows-2022] + + name: ${{ matrix.os }} + runs-on: ${{ matrix.os }} + steps: + - uses: actions/checkout@v4 + + - uses: Jimver/cuda-toolkit@v0.2.17 + id: cuda-toolkit + with: + log-file-suffix: ${{ matrix.os }}.txt + cuda: '12.5.0' + method: 'network' + sub-packages: '["nvcc", "cudart", "cublas"]' + + - name: Build + run: make build + + - name: Test + run: | + make run + make test diff --git a/.github/workflows/docker.yml b/.github/workflows/docker.yml new file mode 100644 index 0000000..ed650c5 --- /dev/null +++ b/.github/workflows/docker.yml @@ -0,0 +1,51 @@ +name: Build and Push Docker Image + +on: + push: + tags: + - '^v[0-9]+\.[0-9]+\.[0-9]+.*$' + +jobs: + docker: + runs-on: ubuntu-latest + steps: + - + name: Checkout + uses: actions/checkout@v4 + - + name: Set up QEMU + uses: docker/setup-qemu-action@v3 + - + name: Set up Docker Buildx + uses: docker/setup-buildx-action@v3 + - + name: Login to GitHub Container Registry + uses: docker/login-action@v3 + with: + registry: ghcr.io + username: ${{ github.repository_owner }} + password: ${{ secrets.GITHUB_TOKEN }} + - + name: Build and Export to Docker + uses: docker/build-push-action@v6 + with: + context: . + load: true + tags: | + ghcr.io/x-pt/example-cuda-cmake:latest + ghcr.io/x-pt/example-cuda-cmake:${GITHUB_REF_NAME:1} + - + name: Test it before Push + run: | + docker run --rm ghcr.io/x-pt/example-cuda-cmake:latest + docker run --rm ghcr.io/x-pt/example-cuda-cmake:${GITHUB_REF_NAME:1} + - + name: Build and Push + uses: docker/build-push-action@v6 + with: + context: . + platforms: linux/amd64,linux/arm64 + push: true + tags: | + ghcr.io/x-pt/example-cuda-cmake:latest + ghcr.io/x-pt/example-cuda-cmake:${GITHUB_REF_NAME:1} diff --git a/.github/workflows/labeler.yml b/.github/workflows/labeler.yml new file mode 100644 index 0000000..91499a4 --- /dev/null +++ b/.github/workflows/labeler.yml @@ -0,0 +1,15 @@ +name: Labeler + +on: + - pull_request + - issues + +jobs: + labeler: + runs-on: ubuntu-latest + steps: + - uses: srvaroa/labeler@master + with: + config_path: .github/configs/labeler.yml + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml new file mode 100644 index 0000000..80ff4eb --- /dev/null +++ b/.github/workflows/release.yml @@ -0,0 +1,60 @@ +name: Example Cuda Cmake Release + +on: + push: + tags: + - "v*.*.*" + +jobs: + changelog: + runs-on: ubuntu-latest + steps: + - name: Checkout Code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Get Tag Version + id: tag_version + run: echo "CURRENT_TAG=${GITHUB_REF#refs/tags/}" >> $GITHUB_ENV + + - name: Generate Full Changelog + uses: orhun/git-cliff-action@v4 + with: + config: cliff.toml + args: --verbose + env: + OUTPUT: CHANGELOG.md + GITHUB_REPO: ${{ github.repository }} + + - name: Commit Changelog + run: | + git config user.name 'github-actions[bot]' + git config user.email 'github-actions[bot]@users.noreply.github.com' + set +e + git switch main + git add CHANGELOG.md + git commit -m "chore(release-bot): prepare for release notes on ${CURRENT_TAG}" + git push + + release: + runs-on: ubuntu-latest + steps: + - name: Checkout Code + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - name: Generate Latest Release Notes + id: latest_release_notes + uses: orhun/git-cliff-action@v4 + with: + config: cliff.toml + args: --latest --strip all + env: + OUTPUT: CHANGELOG.txt + + - name: Create GitHub Release + uses: softprops/action-gh-release@v2 + with: + body_path: CHANGELOG.txt diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..02ca01e --- /dev/null +++ b/.gitignore @@ -0,0 +1,114 @@ +### C++ template +# Prerequisites +*.d + +# Compiled Object files +*.slo +*.lo +*.o +*.obj + +# Precompiled Headers +*.gch +*.pch + +# Compiled Dynamic libraries +*.so +*.dylib +*.dll + +# Fortran module files (optional, in case your project integrates Fortran) +*.mod +*.smod + +# Compiled Static libraries +*.lai +*.la +*.a +*.lib + +# Executables +*.exe +*.out +*.app + +# Debug and other temporary files +*.dSYM/ +*.su +*.idb +*.pdb +*.log + +### CMake +CMakeLists.txt.user +CMakeCache.txt +CMakeFiles/ +CMakeScripts/ +Testing/ +cmake_install.cmake +install_manifest.txt +compile_commands.json +CTestTestfile.cmake +_deps/ + +### Visual Studio Code +.vscode/ + +### JetBrains IDEs (CLion, IntelliJ, etc.) +.idea/ +.idea_modules/ +out/ + +# CMake generated build directories +cmake-build-*/ + +### Visual Studio +.vs/ +*.vcxproj.user +*.vcxproj.filters +*.rsuser +*.suo +*.user +*.userosscache +*.VC.db +*.VC.opendb + +# Visual Studio build results +[Bb]in/ +[Oo]bj/ +[Dd]ebug*/ +[Rr]elease*/ +x64/ +x86/ + +# Visual Studio cache files +*.sdf +*.ipch +*.aps +*.ncb + +# Visual Studio profiler +*.psess +*.vsp +*.vspx + +# Other Visual Studio-related files +*.log +*.tlog +*.tlb +*.tli +*.tlh + +### Miscellaneous +.DS_Store +*.tmp +*.temp +*.bak +*.swp +*.swo +*~ + +# Backup and temporary files +*.old +*.orig +*.backup diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml new file mode 100644 index 0000000..b2f11ab --- /dev/null +++ b/.pre-commit-config.yaml @@ -0,0 +1,17 @@ +repos: + - repo: https://github.com/pre-commit/pre-commit-hooks + rev: v5.0.0 + hooks: + - id: check-merge-conflict + - id: check-toml + - id: check-yaml + - id: end-of-file-fixer + - id: mixed-line-ending + args: [ --fix=lf ] + - id: trailing-whitespace + - repo: https://github.com/commitizen-tools/commitizen + rev: v3.30.1 + hooks: + - id: commitizen + - id: commitizen-branch + stages: [ pre-push ] diff --git a/CHANGELOG.md b/CHANGELOG.md new file mode 100644 index 0000000..f8863f8 --- /dev/null +++ b/CHANGELOG.md @@ -0,0 +1,20 @@ +# Changelog + +All notable changes to this project will be documented in this file. + +The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/), +and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). + +## [Unreleased] + +### Added + +- support some features + +### Changed + +- change some existed behaviors/logic + +### Fixed + +- fix some bugs diff --git a/CMakeLists.txt b/CMakeLists.txt new file mode 100644 index 0000000..d8a905a --- /dev/null +++ b/CMakeLists.txt @@ -0,0 +1,76 @@ +cmake_minimum_required(VERSION 3.25) + +project(example-cuda-cmake + VERSION 0.0.1 + DESCRIPTION "A nice example project" + HOMEPAGE_URL "https://github.com/x-pt/example-cuda-cmake" + LANGUAGES CXX CUDA +) + +# Custom modules +list(APPEND CMAKE_MODULE_PATH ${CMAKE_SOURCE_DIR}/cmake) + +# Build settings +set(CMAKE_CXX_STANDARD 20) +set(CMAKE_CXX_STANDARD_REQUIRED ON) +set(CMAKE_CXX_EXTENSIONS OFF) + +set(CMAKE_CUDA_STANDARD 17) +set(CMAKE_CUDA_STANDARD_REQUIRED ON) +set(CMAKE_CUDA_EXTENSIONS OFF) +set(CMAKE_CUDA_ARCHITECTURES 80) + +set(CMAKE_EXPORT_COMPILE_COMMANDS ON) + +# Set architecture for macOS (if applicable) +if(APPLE) + set(CMAKE_OSX_ARCHITECTURES "arm64") +endif() + +# Build type configuration +if(NOT CMAKE_BUILD_TYPE) + set(CMAKE_BUILD_TYPE Release) +endif() + +# Find dependencies +find_package(CUDAToolkit REQUIRED) + +# Set output directories +set(CMAKE_RUNTIME_OUTPUT_DIRECTORY "$<1:${CMAKE_BINARY_DIR}/bin>") +set(CMAKE_LIBRARY_OUTPUT_DIRECTORY "$<1:${CMAKE_BINARY_DIR}/lib>") +set(CMAKE_ARCHIVE_OUTPUT_DIRECTORY "$<1:${CMAKE_BINARY_DIR}/lib>") + +# Source files configuration +set(SRC_DIR ${CMAKE_SOURCE_DIR}/src) +set(INCLUDE_DIR ${CMAKE_SOURCE_DIR}/include) +file(GLOB_RECURSE SOURCES CONFIGURE_DEPENDS + ${SRC_DIR}/*.cpp + ${SRC_DIR}/*.cu +) +list(FILTER SOURCES EXCLUDE REGEX ".*main\\.cpp$") +file(GLOB_RECURSE HEADERS CONFIGURE_DEPENDS + ${INCLUDE_DIR}/*.h +) + +# Library target +add_library(${PROJECT_NAME}_lib ${SOURCES} ${HEADERS}) +target_include_directories(${PROJECT_NAME}_lib + PUBLIC + $ +) +target_link_libraries(${PROJECT_NAME}_lib + PUBLIC + CUDA::cudart + CUDA::cublas +) +set_target_properties(${PROJECT_NAME}_lib PROPERTIES + CUDA_SEPARABLE_COMPILATION ON + POSITION_INDEPENDENT_CODE ON +) + +# Executable target +add_executable(${PROJECT_NAME} ${SRC_DIR}/main.cpp) +target_link_libraries(${PROJECT_NAME} PRIVATE ${PROJECT_NAME}_lib) + +# Tests +add_subdirectory(tests) diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md new file mode 100644 index 0000000..d12c6a2 --- /dev/null +++ b/CODE_OF_CONDUCT.md @@ -0,0 +1,136 @@ +# Contributor Covenant Code of Conduct + +## Our Pledge + +We as members, contributors, and leaders pledge to make participation in our +community a harassment-free experience for everyone, regardless of age, body +size, visible or invisible disability, ethnicity, sex characteristics, gender +identity and expression, level of experience, education, socio-economic status, +nationality, personal appearance, race, caste, color, religion, or sexual +identity and orientation. + +We pledge to act and interact in ways that contribute to an open, welcoming, +diverse, inclusive, and healthy community. + +## Our Standards + +Examples of behavior that contributes to a positive environment for our +community include: + +- Demonstrating empathy and kindness toward other people +- Being respectful of differing opinions, viewpoints, and experiences +- Giving and gracefully accepting constructive feedback +- Accepting responsibility and apologizing to those affected by our mistakes, + and learning from the experience +- Focusing on what is best not just for us as individuals, but for the overall + community + +Examples of unacceptable behavior include: + +- The use of sexualized language or imagery, and sexual attention or advances of + any kind +- Trolling, insulting or derogatory comments, and personal or political attacks +- Public or private harassment +- Publishing others' private information, such as a physical or email address, + without their explicit permission +- Other conduct which could reasonably be considered inappropriate in a + professional setting + +## Enforcement Responsibilities + +Community leaders are responsible for clarifying and enforcing our standards of +acceptable behavior and will take appropriate and fair corrective action in +response to any behavior that they deem inappropriate, threatening, offensive, +or harmful. + +Community leaders have the right and responsibility to remove, edit, or reject +comments, commits, code, wiki edits, issues, and other contributions that are +not aligned to this Code of Conduct, and will communicate reasons for moderation +decisions when appropriate. + +## Scope + +This Code of Conduct applies within all community spaces, and also applies when +an individual is officially representing the community in public spaces. +Examples of representing our community include using an official e-mail address, +posting via an official social media account, or acting as an appointed +representative at an online or offline event. + +## Enforcement + +Instances of abusive, harassing, or otherwise unacceptable behavior may be +reported to the community leaders responsible for enforcement at +[INSERT CONTACT METHOD]. +All complaints will be reviewed and investigated promptly and fairly. + +All community leaders are obligated to respect the privacy and security of the +reporter of any incident. + +## Enforcement Guidelines + +Community leaders will follow these Community Impact Guidelines in determining +the consequences for any action they deem in violation of this Code of Conduct: + +### 1. Correction + +**Community Impact**: Use of inappropriate language or other behavior deemed +unprofessional or unwelcome in the community. + +**Consequence**: A private, written warning from community leaders, providing +clarity around the nature of the violation and an explanation of why the +behavior was inappropriate. A public apology may be requested. + +### 2. Warning + +**Community Impact**: A violation through a single incident or series of +actions. + +**Consequence**: A warning with consequences for continued behavior. No +interaction with the people involved, including unsolicited interaction with +those enforcing the Code of Conduct, for a specified period of time. This +includes avoiding interactions in community spaces as well as external channels +like social media. Violating these terms may lead to a temporary or permanent +ban. + +### 3. Temporary Ban + +**Community Impact**: A serious violation of community standards, including +sustained inappropriate behavior. + +**Consequence**: A temporary ban from any sort of interaction or public +communication with the community for a specified period of time. No public or +private interaction with the people involved, including unsolicited interaction +with those enforcing the Code of Conduct, is allowed during this period. +Violating these terms may lead to a permanent ban. + +### 4. Permanent Ban + +**Community Impact**: Demonstrating a pattern of violation of community +standards, including sustained inappropriate behavior, harassment of an +individual, or aggression toward or disparagement of classes of individuals. + +**Consequence**: A permanent ban from any sort of public interaction within the +community. + +## Attribution + +This Code of Conduct is adapted from the [Contributor Covenant][homepage], +version 2.1, available at +[https://www.contributor-covenant.org/version/2/1/code_of_conduct.html][v2.1]. + +Community Impact Guidelines were inspired by +[Mozilla's code of conduct enforcement ladder][Mozilla CoC]. + +For answers to common questions about this code of conduct, see the FAQ at +[https://www.contributor-covenant.org/faq][FAQ]. Translations are available at +[https://www.contributor-covenant.org/translations][translations]. + +[homepage]: https://www.contributor-covenant.org + +[v2.1]: https://www.contributor-covenant.org/version/2/1/code_of_conduct.html + +[Mozilla CoC]: https://github.com/mozilla/diversity + +[FAQ]: https://www.contributor-covenant.org/faq + +[translations]: https://www.contributor-covenant.org/translations diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md new file mode 100644 index 0000000..6e7f146 --- /dev/null +++ b/CONTRIBUTING.md @@ -0,0 +1,50 @@ +# Contribution guidelines + +First off, thank you for considering contributing to `example-cuda-cmake`. + +If your contribution is not straightforward, please first discuss the change you +wish to make by creating a new issue before making the change. + +## Reporting issues + +Before reporting an issue on the +[issue tracker](https://github.com/x-pt/example-cuda-cmake/issues), +please check that it has not already been reported by searching for some related +keywords. + +## Pull requests + +Try to do one pull request per change. + +### Updating the changelog + +Update the changes you have made in +[CHANGELOG](CHANGELOG.md) +file under the **Unreleased** section. + +Add the changes of your pull request to one of the following subsections, +depending on the types of changes defined by +[Keep a changelog](https://keepachangelog.com/en/1.0.0/): + +- `Added` for new features. +- `Changed` for changes in existing functionality. +- `Deprecated` for soon-to-be removed features. +- `Removed` for now removed features. +- `Fixed` for any bug fixes. +- `Security` in case of vulnerabilities. + +If the required subsection does not exist yet under **Unreleased**, create it! + +## Developing + +### Set up + +This is no different from other C++ projects. + +```shell +git clone https://github.com/x-pt/example-cuda-cmake +cd example-cuda-cmake +make test +``` + +### Useful Commands diff --git a/Dockerfile b/Dockerfile new file mode 100644 index 0000000..87a3fb1 --- /dev/null +++ b/Dockerfile @@ -0,0 +1,29 @@ +# BUILDING +FROM rockylinux:9 AS builder +LABEL author="X Author Name" +WORKDIR /app + +# build deps +RUN dnf upgrade --refresh -y && \ + dnf --enablerepo=crb install -y \ + cmake \ + gcc \ + gcc-c++ \ + make \ + # enable repo crb to install the following packages for building static binary + libstdc++-static \ + glibc-static && \ + # due to this Dockerfile is a multi-stage, the following clean steps are redundant. + dnf clean all && \ + rm -fr /var/cache/yum + +COPY .. . + +RUN cmake -B build && cmake --build build --target example-cuda-cmake --config Release --parallel 8 + +# DEPLOYING +FROM rockylinux:9-minimal + +COPY --from=builder /app/build/example-cuda-cmake /example-cuda-cmake + +CMD ["/example-cuda-cmake"] diff --git a/LICENSE-APACHE b/LICENSE-APACHE new file mode 100644 index 0000000..1b5ec8b --- /dev/null +++ b/LICENSE-APACHE @@ -0,0 +1,176 @@ + Apache License + Version 2.0, January 2004 + http://www.apache.org/licenses/ + +TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION + +1. Definitions. + + "License" shall mean the terms and conditions for use, reproduction, + and distribution as defined by Sections 1 through 9 of this document. + + "Licensor" shall mean the copyright owner or entity authorized by + the copyright owner that is granting the License. + + "Legal Entity" shall mean the union of the acting entity and all + other entities that control, are controlled by, or are under common + control with that entity. For the purposes of this definition, + "control" means (i) the power, direct or indirect, to cause the + direction or management of such entity, whether by contract or + otherwise, or (ii) ownership of fifty percent (50%) or more of the + outstanding shares, or (iii) beneficial ownership of such entity. + + "You" (or "Your") shall mean an individual or Legal Entity + exercising permissions granted by this License. + + "Source" form shall mean the preferred form for making modifications, + including but not limited to software source code, documentation + source, and configuration files. + + "Object" form shall mean any form resulting from mechanical + transformation or translation of a Source form, including but + not limited to compiled object code, generated documentation, + and conversions to other media types. + + "Work" shall mean the work of authorship, whether in Source or + Object form, made available under the License, as indicated by a + copyright notice that is included in or attached to the work + (an example is provided in the Appendix below). + + "Derivative Works" shall mean any work, whether in Source or Object + form, that is based on (or derived from) the Work and for which the + editorial revisions, annotations, elaborations, or other modifications + represent, as a whole, an original work of authorship. For the purposes + of this License, Derivative Works shall not include works that remain + separable from, or merely link (or bind by name) to the interfaces of, + the Work and Derivative Works thereof. + + "Contribution" shall mean any work of authorship, including + the original version of the Work and any modifications or additions + to that Work or Derivative Works thereof, that is intentionally + submitted to Licensor for inclusion in the Work by the copyright owner + or by an individual or Legal Entity authorized to submit on behalf of + the copyright owner. For the purposes of this definition, "submitted" + means any form of electronic, verbal, or written communication sent + to the Licensor or its representatives, including but not limited to + communication on electronic mailing lists, source code control systems, + and issue tracking systems that are managed by, or on behalf of, the + Licensor for the purpose of discussing and improving the Work, but + excluding communication that is conspicuously marked or otherwise + designated in writing by the copyright owner as "Not a Contribution." + + "Contributor" shall mean Licensor and any individual or Legal Entity + on behalf of whom a Contribution has been received by Licensor and + subsequently incorporated within the Work. + +2. Grant of Copyright License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + copyright license to reproduce, prepare Derivative Works of, + publicly display, publicly perform, sublicense, and distribute the + Work and such Derivative Works in Source or Object form. + +3. Grant of Patent License. Subject to the terms and conditions of + this License, each Contributor hereby grants to You a perpetual, + worldwide, non-exclusive, no-charge, royalty-free, irrevocable + (except as stated in this section) patent license to make, have made, + use, offer to sell, sell, import, and otherwise transfer the Work, + where such license applies only to those patent claims licensable + by such Contributor that are necessarily infringed by their + Contribution(s) alone or by combination of their Contribution(s) + with the Work to which such Contribution(s) was submitted. If You + institute patent litigation against any entity (including a + cross-claim or counterclaim in a lawsuit) alleging that the Work + or a Contribution incorporated within the Work constitutes direct + or contributory patent infringement, then any patent licenses + granted to You under this License for that Work shall terminate + as of the date such litigation is filed. + +4. Redistribution. You may reproduce and distribute copies of the + Work or Derivative Works thereof in any medium, with or without + modifications, and in Source or Object form, provided that You + meet the following conditions: + + (a) You must give any other recipients of the Work or + Derivative Works a copy of this License; and + + (b) You must cause any modified files to carry prominent notices + stating that You changed the files; and + + (c) You must retain, in the Source form of any Derivative Works + that You distribute, all copyright, patent, trademark, and + attribution notices from the Source form of the Work, + excluding those notices that do not pertain to any part of + the Derivative Works; and + + (d) If the Work includes a "NOTICE" text file as part of its + distribution, then any Derivative Works that You distribute must + include a readable copy of the attribution notices contained + within such NOTICE file, excluding those notices that do not + pertain to any part of the Derivative Works, in at least one + of the following places: within a NOTICE text file distributed + as part of the Derivative Works; within the Source form or + documentation, if provided along with the Derivative Works; or, + within a display generated by the Derivative Works, if and + wherever such third-party notices normally appear. The contents + of the NOTICE file are for informational purposes only and + do not modify the License. You may add Your own attribution + notices within Derivative Works that You distribute, alongside + or as an addendum to the NOTICE text from the Work, provided + that such additional attribution notices cannot be construed + as modifying the License. + + You may add Your own copyright statement to Your modifications and + may provide additional or different license terms and conditions + for use, reproduction, or distribution of Your modifications, or + for any such Derivative Works as a whole, provided Your use, + reproduction, and distribution of the Work otherwise complies with + the conditions stated in this License. + +5. Submission of Contributions. Unless You explicitly state otherwise, + any Contribution intentionally submitted for inclusion in the Work + by You to the Licensor shall be under the terms and conditions of + this License, without any additional terms or conditions. + Notwithstanding the above, nothing herein shall supersede or modify + the terms of any separate license agreement you may have executed + with Licensor regarding such Contributions. + +6. Trademarks. This License does not grant permission to use the trade + names, trademarks, service marks, or product names of the Licensor, + except as required for reasonable and customary use in describing the + origin of the Work and reproducing the content of the NOTICE file. + +7. Disclaimer of Warranty. Unless required by applicable law or + agreed to in writing, Licensor provides the Work (and each + Contributor provides its Contributions) on an "AS IS" BASIS, + WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or + implied, including, without limitation, any warranties or conditions + of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A + PARTICULAR PURPOSE. You are solely responsible for determining the + appropriateness of using or redistributing the Work and assume any + risks associated with Your exercise of permissions under this License. + +8. Limitation of Liability. In no event and under no legal theory, + whether in tort (including negligence), contract, or otherwise, + unless required by applicable law (such as deliberate and grossly + negligent acts) or agreed to in writing, shall any Contributor be + liable to You for damages, including any direct, indirect, special, + incidental, or consequential damages of any character arising as a + result of this License or out of the use or inability to use the + Work (including but not limited to damages for loss of goodwill, + work stoppage, computer failure or malfunction, or any and all + other commercial damages or losses), even if such Contributor + has been advised of the possibility of such damages. + +9. Accepting Warranty or Additional Liability. While redistributing + the Work or Derivative Works thereof, You may choose to offer, + and charge a fee for, acceptance of support, warranty, indemnity, + or other liability obligations and/or rights consistent with this + License. However, in accepting such obligations, You may act only + on Your own behalf and on Your sole responsibility, not on behalf + of any other Contributor, and only if You agree to indemnify, + defend, and hold each Contributor harmless for any liability + incurred by, or claims asserted against, such Contributor by reason + of your accepting any such warranty or additional liability. + +END OF TERMS AND CONDITIONS diff --git a/LICENSE-MIT b/LICENSE-MIT new file mode 100644 index 0000000..38b41f0 --- /dev/null +++ b/LICENSE-MIT @@ -0,0 +1,21 @@ +MIT License + +Copyright (c) 2024 X Author Name + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. diff --git a/Makefile b/Makefile new file mode 100644 index 0000000..78ae45f --- /dev/null +++ b/Makefile @@ -0,0 +1,42 @@ +.PHONY: help init build image +.DEFAULT_GOAL := help + +APP_NAME := example-cuda-cmake + +# init +init: + @pre-commit install --hook-type commit-msg --hook-type pre-push + +# compile and build +build: + @cmake -S . -B build + @cmake --build build --parallel + +# run +run: + @./build/bin/$(APP_NAME) + +# test +test: + @./build/bin/$(APP_NAME)-tests + +# build image +image: + @docker image build -t $(APP_NAME) . + +# Show help +help: + @echo "" + @echo "Usage:" + @echo " make [target]" + @echo "" + @echo "Targets:" + @awk '/^[a-zA-Z\-_0-9]+:/ \ + { \ + helpMessage = match(lastLine, /^# (.*)/); \ + if (helpMessage) { \ + helpCommand = substr($$1, 0, index($$1, ":")-1); \ + helpMessage = substr(lastLine, RSTART + 2, RLENGTH); \ + printf "\033[36m%-22s\033[0m %s\n", helpCommand,helpMessage; \ + } \ + } { lastLine = $$0 }' $(MAKEFILE_LIST) diff --git a/README.md b/README.md new file mode 100644 index 0000000..953af2a --- /dev/null +++ b/README.md @@ -0,0 +1,41 @@ +# example-cuda-cmake + +[![CI](https://github.com/x-pt/example-cuda-cmake/workflows/CI/badge.svg)](https://github.com/x-pt/example-cuda-cmake/actions) +[![Coverage Status](https://coveralls.io/repos/github/x-pt/example-cuda-cmake/badge.svg?branch=main)](https://coveralls.io/github/x-pt/example-cuda-cmake?branch=main) + +## Installation + +### Build + +- Ensure you have a C++ compiler installed (e.g., `g++`, `clang++`). + +- Install [CMake](https://cmake.org/install/) and any necessary dependencies. + +- Clone the repository: + + ```sh + git clone https://github.com/x-pt/example-cuda-cmake.git + cd example-cuda-cmake + make build + make run + make test + ``` + +## License + +Licensed under either of + +- Apache License, Version 2.0 + ([LICENSE-APACHE](LICENSE-APACHE) or http://www.apache.org/licenses/LICENSE-2.0) +- MIT license + ([LICENSE-MIT](LICENSE-MIT) or http://opensource.org/licenses/MIT) + +at your option. + +## Contribution + +Unless you explicitly state otherwise, any contribution intentionally submitted +for inclusion in the work by you, as defined in the Apache-2.0 license, shall be +dual licensed as above, without any additional terms or conditions. + +See [CONTRIBUTING.md](CONTRIBUTING.md). diff --git a/SECURITY.md b/SECURITY.md new file mode 100644 index 0000000..abdcf15 --- /dev/null +++ b/SECURITY.md @@ -0,0 +1,25 @@ +# Security Policy + +## Supported Versions + + + +| Version | Supported | +|---------|--------------------| +| 5.1.x | :white_check_mark: | +| 5.0.x | :x: | +| 4.0.x | :white_check_mark: | +| < 4.0 | :x: | + +## Reporting a Vulnerability + + diff --git a/cliff.toml b/cliff.toml new file mode 100644 index 0000000..0a046f4 --- /dev/null +++ b/cliff.toml @@ -0,0 +1,131 @@ +# git-cliff ~ default configuration file +# https://git-cliff.org/docs/configuration +# +# Lines starting with "#" are comments. +# Configuration options are organized into tables and keys. +# See documentation for more information on available options. + +[remote.github] +owner = "x-pt" +repo = "example-cuda-cmake" + +[changelog] +# template for the changelog footer +header = """ +# Changelog\n +All notable changes to this project will be documented in this file.\n +""" +# template for the changelog body +# https://keats.github.io/tera/docs/#introduction +body = """ +{%- macro remote_url() -%} + https://github.com/{{ remote.github.owner }}/{{ remote.github.repo }} +{%- endmacro -%} + +{% macro print_commit(commit) -%} + - {% if commit.scope %}*({{ commit.scope }})* {% endif %}\ + {% if commit.breaking %}[**breaking**] {% endif %}\ + {{ commit.message | upper_first }} - \ + ([{{ commit.id | truncate(length=7, end="") }}]({{ self::remote_url() }}/commit/{{ commit.id }}))\ +{% endmacro -%} + +{% if version %}\ + {% if previous.version %}\ + ## [{{ version | trim_start_matches(pat="v") }}]\ + ({{ self::remote_url() }}/compare/{{ previous.version }}..{{ version }}) - {{ timestamp | date(format="%Y-%m-%d") }} + {% else %}\ + ## [{{ version | trim_start_matches(pat="v") }}] - {{ timestamp | date(format="%Y-%m-%d") }} + {% endif %}\ +{% else %}\ + ## [unreleased] +{% endif %}\ + +{% for group, commits in commits | group_by(attribute="group") %} + ### {{ group | striptags | trim | upper_first }} + {% for commit in commits + | filter(attribute="scope") + | sort(attribute="scope") %} + {{ self::print_commit(commit=commit) }} + {%- endfor %} + {% for commit in commits %} + {%- if not commit.scope -%} + {{ self::print_commit(commit=commit) }} + {% endif -%} + {% endfor -%} +{% endfor -%} +{%- if github -%} +{% if github.contributors | filter(attribute="is_first_time", value=true) | length != 0 %} + ## New Contributors โค๏ธ +{% endif %}\ +{% for contributor in github.contributors | filter(attribute="is_first_time", value=true) %} + * @{{ contributor.username }} made their first contribution + {%- if contributor.pr_number %} in \ + [#{{ contributor.pr_number }}]({{ self::remote_url() }}/pull/{{ contributor.pr_number }}) \ + {%- endif %} +{%- endfor -%} +{%- endif %} + + +""" + +# template for the changelog footer +footer = """ + +""" +# remove the leading and trailing s +trim = true +# postprocessors +postprocessors = [ + { pattern = '', replace = "https://github.com/x-pt/example-cuda-cmake" }, # replace repository URL +] + +[git] +# parse the commits based on https://www.conventionalcommits.org +conventional_commits = true +# filter out the commits that are not conventional +filter_unconventional = true +# process each line of a commit as an individual commit +split_commits = false +# regex for preprocessing the commit messages +commit_preprocessors = [ + # Replace issue numbers + { pattern = '\((\w+\s)?#([0-9]+)\)', replace = "([#${2}](/issues/${2}))"}, + # Check spelling of the commit with https://github.com/crate-ci/typos + # If the spelling is incorrect, it will be automatically fixed. + #{ pattern = '.*', replace_command = 'typos --write-changes -' }, +] +# regex for parsing and grouping commits +commit_parsers = [ + { message = "^feat", group = "๐Ÿš€ Features" }, + { message = "^fix", group = "๐Ÿ› Bug Fixes" }, + { message = "^doc", group = "๐Ÿ“š Documentation" }, + { message = "^perf", group = "โšก Performance" }, + { message = "^refactor", group = "๐Ÿšœ Refactor" }, + { message = "^style", group = "๐ŸŽจ Styling" }, + { message = "^test", group = "๐Ÿงช Testing" }, + { message = "^chore\\(release\\): prepare for", skip = true }, + { message = "^chore\\(release-bot\\): prepare for", skip = true }, + { message = "^chore: bump version to", skip = true }, + { message = "^chore\\(deps.*\\)", skip = true }, + { message = "^chore\\(pr\\)", skip = true }, + { message = "^chore\\(pull\\)", skip = true }, + { message = "^chore|^ci", group = "โš™๏ธ Miscellaneous Tasks" }, + { body = ".*security", group = "๐Ÿ›ก๏ธ Security" }, + { message = "^revert", group = "โ—€๏ธ Revert" }, +] +# protect breaking changes from being skipped due to matching a skipping commit_parser +protect_breaking_commits = false +# filter out the commits that are not matched by commit parsers +filter_commits = false +# regex for matching git tags +# tag_pattern = "v[0-9].*" +# regex for skipping tags +# skip_tags = "" +# regex for ignoring tags +# ignore_tags = "" +# sort the tags topologically +topo_order = false +# sort the commits inside sections by oldest/newest order +sort_commits = "newest" +# limit the number of commits included in the changelog. +# limit_commits = 42 diff --git a/cmake/FindXXX.cmake b/cmake/FindXXX.cmake new file mode 100644 index 0000000..c39c418 --- /dev/null +++ b/cmake/FindXXX.cmake @@ -0,0 +1,93 @@ +# FindXXX.cmake - Locate XXX library and headers +# +# This module defines the following variables: +# XXX_FOUND - True if the XXX library and headers are found +# XXX_INCLUDE_DIRS - The include directories for XXX +# XXX_LIBRARIES - The libraries to link against for XXX +# XXX_VERSION - The version string of XXX (if available) + +# Early return if target is already defined +if(TARGET XXX::XXX) + return() +endif() + +# Define search paths +set(XXX_SEARCH_PATHS + ${CMAKE_PREFIX_PATH} + /usr/local/xxx + /usr/local + /usr + /opt/xxx + /opt + # Add other common installation paths here +) + +# Locate the header files +find_path(XXX_INCLUDE_DIR + NAMES xxx.h + HINTS ${XXX_ROOT} $ENV{XXX_ROOT} + PATHS ${XXX_SEARCH_PATHS} + PATH_SUFFIXES include + DOC "XXX include directory" +) + +# Define library components +set(XXX_LIB_COMPONENTS xxx) # Add more components if needed + +# Locate the libraries +set(XXX_LIBRARIES) +foreach(_comp ${XXX_LIB_COMPONENTS}) + find_library(XXX_${_comp}_LIBRARY + NAMES ${_comp} + HINTS ${XXX_ROOT} $ENV{XXX_ROOT} + PATHS ${XXX_SEARCH_PATHS} + PATH_SUFFIXES lib lib64 + DOC "XXX ${_comp} library" + ) + if(XXX_${_comp}_LIBRARY) + list(APPEND XXX_LIBRARIES ${XXX_${_comp}_LIBRARY}) + endif() +endforeach() + +# Set include directories +set(XXX_INCLUDE_DIRS ${XXX_INCLUDE_DIR}) + +# Version detection (customize based on your library's version format) +if(XXX_INCLUDE_DIR AND EXISTS "${XXX_INCLUDE_DIR}/xxx_version.h") + file(STRINGS "${XXX_INCLUDE_DIR}/xxx_version.h" XXX_VERSION_MAJOR_LINE REGEX "^#define[ \t]+XXX_VERSION_MAJOR[ \t]+[0-9]+") + file(STRINGS "${XXX_INCLUDE_DIR}/xxx_version.h" XXX_VERSION_MINOR_LINE REGEX "^#define[ \t]+XXX_VERSION_MINOR[ \t]+[0-9]+") + file(STRINGS "${XXX_INCLUDE_DIR}/xxx_version.h" XXX_VERSION_PATCH_LINE REGEX "^#define[ \t]+XXX_VERSION_PATCH[ \t]+[0-9]+") + + string(REGEX REPLACE "^#define[ \t]+XXX_VERSION_MAJOR[ \t]+([0-9]+).*" "\\1" XXX_VERSION_MAJOR "${XXX_VERSION_MAJOR_LINE}") + string(REGEX REPLACE "^#define[ \t]+XXX_VERSION_MINOR[ \t]+([0-9]+).*" "\\1" XXX_VERSION_MINOR "${XXX_VERSION_MINOR_LINE}") + string(REGEX REPLACE "^#define[ \t]+XXX_VERSION_PATCH[ \t]+([0-9]+).*" "\\1" XXX_VERSION_PATCH "${XXX_VERSION_PATCH_LINE}") + + set(XXX_VERSION "${XXX_VERSION_MAJOR}.${XXX_VERSION_MINOR}.${XXX_VERSION_PATCH}") +endif() + +# Handle the QUIETLY and REQUIRED arguments, set XXX_FOUND to TRUE if all listed variables are TRUE +include(FindPackageHandleStandardArgs) +find_package_handle_standard_args(XXX + REQUIRED_VARS XXX_LIBRARIES XXX_INCLUDE_DIRS + VERSION_VAR XXX_VERSION +) + +# Create imported target +if(XXX_FOUND AND NOT TARGET XXX::XXX) + add_library(XXX::XXX UNKNOWN IMPORTED) + set_target_properties(XXX::XXX PROPERTIES + IMPORTED_LOCATION "${XXX_LIBRARIES}" + INTERFACE_INCLUDE_DIRECTORIES "${XXX_INCLUDE_DIRS}" + ) + + # Optional: Add more properties if needed + # set_property(TARGET XXX::XXX PROPERTY + # INTERFACE_COMPILE_DEFINITIONS XXX_SOME_DEFINITION + # ) +endif() + +# Mark variables as advanced +mark_as_advanced(XXX_INCLUDE_DIR) +foreach(_comp ${XXX_LIB_COMPONENTS}) + mark_as_advanced(XXX_${_comp}_LIBRARY) +endforeach() diff --git a/compose.yml b/compose.yml new file mode 100644 index 0000000..e46e263 --- /dev/null +++ b/compose.yml @@ -0,0 +1,11 @@ +service: + example_cuda_cmake: + build: . + image: example-cuda-cmake + +networks: + example_cuda_cmake-net: + name: example_cuda_cmake-net + ipam: + config: + - subnet: 172.16.238.0/24 diff --git a/include/cuda_utils.h b/include/cuda_utils.h new file mode 100644 index 0000000..e086ae7 --- /dev/null +++ b/include/cuda_utils.h @@ -0,0 +1,23 @@ +#pragma once + +#include +#include +#include + +#define CUDA_CHECK(call) \ +do { \ + cudaError_t err = call; \ + if (err != cudaSuccess) { \ + std::cerr << "CUDA error: " << cudaGetErrorString(err) << " at " << __FILE__ << ":" << __LINE__ << std::endl; \ + exit(EXIT_FAILURE); \ + } \ +} while (0) + +#define CUBLAS_CHECK(call) \ +do { \ + cublasStatus_t status = call; \ + if (status != CUBLAS_STATUS_SUCCESS) { \ + std::cerr << "cuBLAS error: " << status << " at " << __FILE__ << ":" << __LINE__ << std::endl; \ + exit(EXIT_FAILURE); \ + } \ +} while (0) diff --git a/include/hi.h b/include/hi.h new file mode 100644 index 0000000..bf7fcf6 --- /dev/null +++ b/include/hi.h @@ -0,0 +1,3 @@ +#pragma once + +void say_hi(); diff --git a/include/matrix_add.h b/include/matrix_add.h new file mode 100644 index 0000000..ac919d1 --- /dev/null +++ b/include/matrix_add.h @@ -0,0 +1,19 @@ +#pragma once + +#include + +namespace cuda_kernel { + +// CUDA kernel for matrix addition +template +__global__ void addMatricesKernel(const T* matrixA, const T* matrixB, T* resultMatrix, int numRows, int numCols); + +} // namespace cuda_kernel + +// Function to perform matrix addition on the GPU +template +void addMatricesOnGPU(const T* hostMatrixA, const T* hostMatrixB, T* hostResultMatrix, int numRows, int numCols); + +// Explicit instantiation declarations for addMatricesOnGPU +extern template void addMatricesOnGPU(const float*, const float*, float*, int, int); +extern template void addMatricesOnGPU(const double*, const double*, double*, int, int); diff --git a/include/matrix_mult.h b/include/matrix_mult.h new file mode 100644 index 0000000..3b9794b --- /dev/null +++ b/include/matrix_mult.h @@ -0,0 +1,13 @@ +#pragma once + +#include +#include + +// Function to perform matrix multiplication on the GPU using cuBLAS +template +void multiplyMatricesOnGPU(const T* hostMatrixA, const T* hostMatrixB, T* hostResultMatrix, + int numRowsA, int numColsA, int numColsB); + +// Explicit instantiation declarations for multiplyMatricesOnGPU +extern template void multiplyMatricesOnGPU(const float*, const float*, float*, int, int, int); +extern template void multiplyMatricesOnGPU(const double*, const double*, double*, int, int, int); diff --git a/include/my_lib.h b/include/my_lib.h new file mode 100644 index 0000000..156d621 --- /dev/null +++ b/include/my_lib.h @@ -0,0 +1,9 @@ +#pragma once + +#include +#include + +int add(int a, int b); +int sub(int a, int b); +int mul(int a, int b); +double divide(double a, double b); diff --git a/src/hi.cpp b/src/hi.cpp new file mode 100644 index 0000000..4641cb3 --- /dev/null +++ b/src/hi.cpp @@ -0,0 +1,7 @@ +#include "hi.h" + +#include + +void say_hi() { + std::cout << "Hello, World!" << std::endl; +} diff --git a/src/main.cpp b/src/main.cpp new file mode 100644 index 0000000..a4a0b5a --- /dev/null +++ b/src/main.cpp @@ -0,0 +1,13 @@ +#include +#include "hi.h" +#include "my_lib.h" + +int main() +{ + say_hi(); + std::cout << "add(1, 2) = " << add(1, 2) << std::endl; + std::cout << "sub(1, 2) = " << sub(1, 2) << std::endl; + std::cout << "mul(1, 2) = " << mul(1, 2) << std::endl; + std::cout << "divide(1, 2) = " << divide(1, 2) << std::endl; + return 0; +} diff --git a/src/matrix_add.cu b/src/matrix_add.cu new file mode 100644 index 0000000..35b27cb --- /dev/null +++ b/src/matrix_add.cu @@ -0,0 +1,82 @@ +#include "cuda_utils.h" // Custom CUDA utilities for error checking, etc. +#include "matrix_add.h" // Header file for this matrix addition module + +// Namespace to encapsulate CUDA kernel functions +namespace cuda_kernel { + +// CUDA Kernel: Adds two matrices element-wise on the GPU +// Each thread computes a single element of the result matrix +// Parameters: +// - matrixA: Device pointer to the input matrix A +// - matrixB: Device pointer to the input matrix B +// - resultMatrix: Device pointer to the output result matrix +// - numRows: Number of rows in the matrices +// - numCols: Number of columns in the matrices +template +__global__ void addMatricesKernel(const T* matrixA, const T* matrixB, T* resultMatrix, int numRows, int numCols) { + // Calculate the row and column indices for this thread + int row = blockIdx.y * blockDim.y + threadIdx.y; + int col = blockIdx.x * blockDim.x + threadIdx.x; + + // Ensure the thread is within valid matrix bounds + if (row < numRows && col < numCols) { + int index = row * numCols + col; + resultMatrix[index] = matrixA[index] + matrixB[index]; // Perform element-wise addition + } +} + +} // namespace cuda_kernel + +// C++ Function: Handles matrix addition on the GPU +// Transfers matrices from the host (CPU) to the device (GPU), performs the computation, +// and then copies the result back to the host. +// Parameters: +// - hostMatrixA: Pointer to matrix A on the host (CPU) +// - hostMatrixB: Pointer to matrix B on the host (CPU) +// - hostResultMatrix: Pointer to the result matrix on the host (CPU) +// - numRows: Number of rows in the matrices +// - numCols: Number of columns in the matrices +template +void addMatricesOnGPU(const T* hostMatrixA, const T* hostMatrixB, T* hostResultMatrix, int numRows, int numCols) { + // Calculate the size of the matrices in bytes + size_t matrixSizeBytes = numRows * numCols * sizeof(T); + + // Device (GPU) memory pointers + T *deviceMatrixA, *deviceMatrixB, *deviceResultMatrix; + + // Allocate memory on the device (GPU) + CUDA_CHECK(cudaMalloc(&deviceMatrixA, matrixSizeBytes)); // Allocate memory for matrix A + CUDA_CHECK(cudaMalloc(&deviceMatrixB, matrixSizeBytes)); // Allocate memory for matrix B + CUDA_CHECK(cudaMalloc(&deviceResultMatrix, matrixSizeBytes)); // Allocate memory for the result matrix + + // Copy input matrices from host (CPU) to device (GPU) + CUDA_CHECK(cudaMemcpy(deviceMatrixA, hostMatrixA, matrixSizeBytes, cudaMemcpyHostToDevice)); + CUDA_CHECK(cudaMemcpy(deviceMatrixB, hostMatrixB, matrixSizeBytes, cudaMemcpyHostToDevice)); + + // Define grid and block dimensions for launching the kernel + dim3 threadsPerBlock(16, 16); // Each block contains 16x16 threads + dim3 numBlocks((numCols + threadsPerBlock.x - 1) / threadsPerBlock.x, + (numRows + threadsPerBlock.y - 1) / threadsPerBlock.y); // Calculate number of blocks required + + // Launch the CUDA kernel to add the matrices on the device + cuda_kernel::addMatricesKernel<<>>( + deviceMatrixA, deviceMatrixB, deviceResultMatrix, numRows, numCols); + + // Check for kernel launch errors + CUDA_CHECK(cudaGetLastError()); + + // Synchronize the device to ensure kernel execution is complete + CUDA_CHECK(cudaDeviceSynchronize()); + + // Copy the result matrix from device (GPU) back to host (CPU) + CUDA_CHECK(cudaMemcpy(hostResultMatrix, deviceResultMatrix, matrixSizeBytes, cudaMemcpyDeviceToHost)); + + // Free the allocated memory on the device + CUDA_CHECK(cudaFree(deviceMatrixA)); + CUDA_CHECK(cudaFree(deviceMatrixB)); + CUDA_CHECK(cudaFree(deviceResultMatrix)); +} + +// Explicit template instantiations for float and double types +template void addMatricesOnGPU(const float*, const float*, float*, int, int); +template void addMatricesOnGPU(const double*, const double*, double*, int, int); diff --git a/src/matrix_mult.cu b/src/matrix_mult.cu new file mode 100644 index 0000000..b03a0d9 --- /dev/null +++ b/src/matrix_mult.cu @@ -0,0 +1,83 @@ +#include "cuda_utils.h" // Custom CUDA utility functions and macros for error checking +#include "matrix_mult.h" // Header for this matrix multiplication module + +// Function to perform matrix multiplication on the GPU using cuBLAS +// This function transfers the input matrices from the host (CPU) to the device (GPU), +// executes the matrix multiplication on the GPU, and retrieves the result back to the host. +// Parameters: +// - hostMatrixA: Pointer to the first matrix (A) on the host (CPU) +// - hostMatrixB: Pointer to the second matrix (B) on the host (CPU) +// - hostResultMatrix: Pointer to the result matrix (C) on the host (CPU) +// - numRowsA: Number of rows in matrix A +// - numColsA: Number of columns in matrix A (and rows in matrix B) +// - numColsB: Number of columns in matrix B +template +void multiplyMatricesOnGPU(const T* hostMatrixA, const T* hostMatrixB, T* hostResultMatrix, + int numRowsA, int numColsA, int numColsB) { + // Calculate the size of matrices A, B, and C in bytes + size_t byteSizeA = numRowsA * numColsA * sizeof(T); + size_t byteSizeB = numColsA * numColsB * sizeof(T); + size_t byteSizeC = numRowsA * numColsB * sizeof(T); + + // Device (GPU) memory pointers for matrices A, B, and result matrix C + T *deviceMatrixA, *deviceMatrixB, *deviceResultMatrix; + + // Allocate memory for matrices on the GPU + CUDA_CHECK(cudaMalloc(&deviceMatrixA, byteSizeA)); // Allocate memory for matrix A on the GPU + CUDA_CHECK(cudaMalloc(&deviceMatrixB, byteSizeB)); // Allocate memory for matrix B on the GPU + CUDA_CHECK(cudaMalloc(&deviceResultMatrix, byteSizeC)); // Allocate memory for result matrix C on the GPU + + // Copy matrices A and B from the host (CPU) to the device (GPU) + CUDA_CHECK(cudaMemcpy(deviceMatrixA, hostMatrixA, byteSizeA, cudaMemcpyHostToDevice)); + CUDA_CHECK(cudaMemcpy(deviceMatrixB, hostMatrixB, byteSizeB, cudaMemcpyHostToDevice)); + + // Create a cuBLAS handle for matrix multiplication + cublasHandle_t cublasHandle; + CUBLAS_CHECK(cublasCreate(&cublasHandle)); + + // Define alpha and beta scalars for the matrix multiplication: C = alpha * A * B + beta * C + const T alpha = 1.0; + const T beta = 0.0; + + // Perform matrix multiplication using cuBLAS based on the type of T (float or double) + // For float: Use cublasSgemm (single precision) + if constexpr (std::is_same_v) { + CUBLAS_CHECK(cublasSgemm(cublasHandle, + CUBLAS_OP_N, CUBLAS_OP_N, // No transposition for both matrices + numColsB, numRowsA, numColsA, // Dimensions of matrices + &alpha, // Scalar alpha + deviceMatrixB, numColsB, // Matrix B in device memory + deviceMatrixA, numColsA, // Matrix A in device memory + &beta, // Scalar beta + deviceResultMatrix, numColsB)); // Result matrix C in device memory + } + // For double: Use cublasDgemm (double precision) + else if constexpr (std::is_same_v) { + CUBLAS_CHECK(cublasDgemm(cublasHandle, + CUBLAS_OP_N, CUBLAS_OP_N, // No transposition for both matrices + numColsB, numRowsA, numColsA, // Dimensions of matrices + &alpha, // Scalar alpha + deviceMatrixB, numColsB, // Matrix B in device memory + deviceMatrixA, numColsA, // Matrix A in device memory + &beta, // Scalar beta + deviceResultMatrix, numColsB)); // Result matrix C in device memory + } + // If neither float nor double, throw a compile-time error + else { + static_assert(std::is_same_v || std::is_same_v, + "Only float and double types are supported for matrix multiplication"); + } + + // Copy the result matrix from the device (GPU) back to the host (CPU) + CUDA_CHECK(cudaMemcpy(hostResultMatrix, deviceResultMatrix, byteSizeC, cudaMemcpyDeviceToHost)); + + // Clean up: Destroy cuBLAS handle and free the allocated GPU memory + CUBLAS_CHECK(cublasDestroy(cublasHandle)); // Destroy cuBLAS context + CUDA_CHECK(cudaFree(deviceMatrixA)); // Free memory for matrix A + CUDA_CHECK(cudaFree(deviceMatrixB)); // Free memory for matrix B + CUDA_CHECK(cudaFree(deviceResultMatrix)); // Free memory for result matrix C +} + +// Explicit template instantiations for float and double types +template void multiplyMatricesOnGPU(const float*, const float*, float*, int, int, int); +template void multiplyMatricesOnGPU(const double*, const double*, double*, int, int, int); diff --git a/src/my_lib.cpp b/src/my_lib.cpp new file mode 100644 index 0000000..11a98a7 --- /dev/null +++ b/src/my_lib.cpp @@ -0,0 +1,25 @@ +#include "my_lib.h" + +int add(const int a, const int b) +{ + return a + b; +} + +int sub(const int a, const int b) +{ + return a - b; +} + +int mul(const int a, const int b) +{ + return a * b; +} + +double divide(const double a, const double b) +{ + if (b == 0.0) + { + throw std::invalid_argument("Division by zero"); + } + return a / b; +} diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt new file mode 100644 index 0000000..c3b778f --- /dev/null +++ b/tests/CMakeLists.txt @@ -0,0 +1,25 @@ +# Enable testing +enable_testing() + +# Fetch and make available Google Test +include(FetchContent) +FetchContent_Declare( + googletest + URL https://github.com/google/googletest/archive/refs/tags/v1.15.2.tar.gz +) +set(gtest_force_shared_crt ON CACHE BOOL "" FORCE) +FetchContent_MakeAvailable(googletest) + +# Collect test source files +file(GLOB_RECURSE TEST_SOURCES ${CMAKE_CURRENT_SOURCE_DIR}/*.cpp) + +# Create test executable +add_executable(${PROJECT_NAME}-tests ${TEST_SOURCES}) +target_link_libraries(${PROJECT_NAME}-tests PRIVATE + GTest::gtest_main + ${PROJECT_NAME}_lib +) + +# Enable test discovery +include(GoogleTest) +gtest_discover_tests(${PROJECT_NAME}-tests) diff --git a/tests/test_matrix.cpp b/tests/test_matrix.cpp new file mode 100644 index 0000000..9494a64 --- /dev/null +++ b/tests/test_matrix.cpp @@ -0,0 +1,121 @@ +#include +#include + +#include "matrix_add.h" +#include "matrix_mult.h" + +// Template-based parameterized test for matrix operations +template +class MatrixOperationsTest : public testing::Test { +protected: + // Static constants for default matrix configuration + static constexpr int kDefaultMatrixSize = 2; + static constexpr int kDefaultMatrixElements = kDefaultMatrixSize * kDefaultMatrixSize; + + // Helper function to create a matrix from initializer list + std::vector createMatrix(std::initializer_list values) { + return std::vector(values); + } + + // Helper function to verify matrix calculation results + static void verifyResult(const std::vector& result, const std::vector& expected) { + // Check matrix size + ASSERT_EQ(result.size(), expected.size()) + << "Result matrix size does not match expected matrix size"; + + // Compare elements with near-equality + for (size_t i = 0; i < expected.size(); i++) { + EXPECT_NEAR(result[i], expected[i], 1e-5) + << "Mismatch at index " << i + << ": expected " << expected[i] + << ", got " << result[i]; + } + } +}; + +// Register type-parameterized test suite +TYPED_TEST_SUITE_P(MatrixOperationsTest); + +// Test case 1: Square matrix addition +TYPED_TEST_P(MatrixOperationsTest, SquareMatrixAddition) { + constexpr int size = this->kDefaultMatrixSize; + + // Prepare test data + auto matrixA = this->createMatrix({1, 2, 3, 4}); + auto matrixB = this->createMatrix({5, 6, 7, 8}); + std::vector resultMatrix(size * size); + + // Call GPU matrix addition function + addMatricesOnGPU(matrixA.data(), matrixB.data(), resultMatrix.data(), size, size); + + // Verify result + auto expectedSum = this->createMatrix({6, 8, 10, 12}); + this->verifyResult(resultMatrix, expectedSum); +} + +// Test case 2: Square matrix multiplication +TYPED_TEST_P(MatrixOperationsTest, SquareMatrixMultiplication) { + constexpr int size = this->kDefaultMatrixSize; + + // Prepare test data + auto matrixA = this->createMatrix({1, 2, 3, 4}); + auto matrixB = this->createMatrix({5, 6, 7, 8}); + std::vector resultMatrix(size * size); + + // Call GPU matrix multiplication function + multiplyMatricesOnGPU(matrixA.data(), matrixB.data(), resultMatrix.data(), size, size, size); + + // Verify result + auto expectedProduct = this->createMatrix({19, 22, 43, 50}); + this->verifyResult(resultMatrix, expectedProduct); +} + +// Test case 3: Non-square matrix addition +TYPED_TEST_P(MatrixOperationsTest, NonSquareMatrixAddition) { + constexpr int rows = 2; + constexpr int cols = 3; + + // Prepare test data + auto nonSquareA = this->createMatrix({1, 2, 3, 4, 5, 6}); + auto nonSquareB = this->createMatrix({7, 8, 9, 10, 11, 12}); + std::vector nonSquareResult(rows * cols); + + // Call GPU matrix addition function + addMatricesOnGPU(nonSquareA.data(), nonSquareB.data(), nonSquareResult.data(), rows, cols); + + // Verify result + auto expectedSum = this->createMatrix({8, 10, 12, 14, 16, 18}); + this->verifyResult(nonSquareResult, expectedSum); +} + +// Test case 4: Non-square matrix multiplication +TYPED_TEST_P(MatrixOperationsTest, NonSquareMatrixMultiplication) { + constexpr int rowsA = 2; + constexpr int colsA = 3; + constexpr int colsB = 2; + + // Prepare test data + auto nonSquareA = this->createMatrix({1, 2, 3, 4, 5, 6}); + auto nonSquareB = this->createMatrix({7, 8, 9, 10, 11, 12}); + std::vector nonSquareResult(rowsA * colsB); + + // Call GPU matrix multiplication function + multiplyMatricesOnGPU(nonSquareA.data(), nonSquareB.data(), nonSquareResult.data(), rowsA, colsA, colsB); + + // Verify result + auto expectedProduct = this->createMatrix({58, 64, 139, 154}); + this->verifyResult(nonSquareResult, expectedProduct); +} + +// Register test cases +REGISTER_TYPED_TEST_SUITE_P( + MatrixOperationsTest, + SquareMatrixAddition, + SquareMatrixMultiplication, + NonSquareMatrixAddition, + NonSquareMatrixMultiplication +); + +// Specify test types +using TestTypes = testing::Types; +INSTANTIATE_TYPED_TEST_SUITE_P(MatrixOps, MatrixOperationsTest, TestTypes); diff --git a/tests/test_my_lib.cpp b/tests/test_my_lib.cpp new file mode 100644 index 0000000..f5b83d8 --- /dev/null +++ b/tests/test_my_lib.cpp @@ -0,0 +1,73 @@ +#include "gtest/gtest.h" +#include "my_lib.h" + +// Group: Add Function Tests +TEST(AddTest, HandlesZeroInputs) +{ + EXPECT_EQ(add(0, 0), 0); +} + +TEST(AddTest, HandlesPositiveInputs) +{ + EXPECT_EQ(add(1, 2), 3); + EXPECT_EQ(add(10, 5), 15); +} + +TEST(AddTest, HandlesNegativeInputs) +{ + EXPECT_EQ(add(-1, -2), -3); + EXPECT_EQ(add(-5, 5), 0); +} + +// Group: Subtract Function Tests +TEST(SubtractTest, HandlesZeroInputs) +{ + EXPECT_EQ(sub(0, 0), 0); +} + +TEST(SubtractTest, HandlesPositiveInputs) +{ + EXPECT_EQ(sub(10, 5), 5); + EXPECT_EQ(sub(5, 10), -5); +} + +TEST(SubtractTest, HandlesNegativeInputs) +{ + EXPECT_EQ(sub(-10, -5), -5); + EXPECT_EQ(sub(-5, -10), 5); +} + +// Group: Multiply Function Tests +TEST(MultiplyTest, HandlesZeroInputs) +{ + EXPECT_EQ(mul(0, 0), 0); +} + +TEST(MultiplyTest, HandlesPositiveInputs) +{ + EXPECT_EQ(mul(2, 3), 6); + EXPECT_EQ(mul(6, 3), 18); +} + +TEST(MultiplyTest, HandlesNegativeInputs) +{ + EXPECT_EQ(mul(-2, -3), 6); + EXPECT_EQ(mul(-2, 3), -6); +} + +// Group: Divide Function Tests +TEST(DivideTest, HandlesZeroDivision) +{ + EXPECT_THROW(divide(10.0, 0.0), std::invalid_argument); +} + +TEST(DivideTest, HandlesPositiveInputs) +{ + EXPECT_NEAR(divide(10.0, 3.0), 3.33333, 1e-5); + EXPECT_NEAR(divide(10.0, 2.0), 5.0, 1e-5); +} + +TEST(DivideTest, HandlesNegativeInputs) +{ + EXPECT_NEAR(divide(-10.0, 2.0), -5.0, 1e-5); +}