add artifact

.gitignore

@@ -0,0 +1,197 @@
+# Prerequisites
+*.d
+
+# Compiled Object files
+*.slo
+*.lo
+*.o
+*.obj
+
+# Precompiled Headers
+*.gch
+*.pch
+
+# Compiled Dynamic libraries
+*.so
+*.dylib
+*.dll
+
+# Fortran module files
+*.mod
+*.smod
+
+# Compiled Static libraries
+*.lai
+*.la
+*.a
+*.lib
+
+# Executables
+*.exe
+*.out
+*.app
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintainted in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+.idea/
+
+# pycharm line profiler result
+**/*.pclprof
+
+outs
+build-release
+
+# nsight compute report
+*.ncu-rep
+
+# cache for kernel binary
+.hidet_cache/

.gitmodules

@@ -0,0 +1,6 @@
+[submodule "3rdparty/cutlass"]
+	path = 3rdparty/cutlass
+	url = git@github.com:NVIDIA/cutlass.git
+[submodule "3rdparty/tvm"]
+	path = 3rdparty/tvm
+	url = git@github.com:apache/tvm.git

CMakeLists.txt

@@ -0,0 +1,65 @@
+cmake_minimum_required(VERSION 3.19)
+
+project(hidet C CXX CUDA)
+
+# common configs
+set(CMAKE_C_COMPILER_LAUNCHER ccache)
+set(CMAKE_CXX_COMPILER_LAUNCHER ccache)
+set(CMAKE_CUDA_COMPILER_LAUNCHER ccache)
+
+# submodules
+include(cmake/TVM.cmake)
+
+# config hidet
+if(EXISTS "${CMAKE_BINARY_DIR}/config.cmake")
+    include(${CMAKE_BINARY_DIR}/config.cmake)
+else()
+    include(${CMAKE_SOURCE_DIR}/config.cmake)
+endif()
+
+set(CMAKE_BUILD_TYPE ${HIDET_BUILD_TYPE})
+message(STATUS "Build type: ${CMAKE_BUILD_TYPE}")
+
+# add runtime target
+add_library(hidet_runtime SHARED
+        src/hidet/runtime/cuda_context.cpp
+        )
+target_include_directories(hidet_runtime PRIVATE
+        ${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES}
+        ${CMAKE_SOURCE_DIR}/include
+        /usr/include
+        )
+set_target_properties(hidet_runtime PROPERTIES
+        CUDA_RUNTIME_LIBRARY SHARED
+        CUDA_ARCHITECTURES ${HIDET_CUDA_ARCH}
+        LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/lib
+        )
+
+# add main target
+add_library(hidet SHARED
+        src/hidet/packedfunc.cpp
+        src/hidet/logging.cpp
+        src/hidet/cuda_api.cpp
+        src/hidet/cuda_kernels.cu
+        )
+
+target_include_directories(hidet PRIVATE
+        ${CMAKE_CUDA_TOOLKIT_INCLUDE_DIRECTORIES}
+        ${CMAKE_SOURCE_DIR}/include
+        )
+
+target_link_directories(hidet PRIVATE ${CMAKE_CUDA_IMPLICIT_LINK_DIRECTORIES})
+
+target_link_libraries(hidet cudart cublas curand)
+target_link_libraries(hidet "-Wl,--no-as-needed" hidet_runtime)
+
+set_target_properties(hidet PROPERTIES
+        CUDA_RUNTIME_LIBRARY SHARED
+        CUDA_ARCHITECTURES ${HIDET_CUDA_ARCH}
+        LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/lib
+        )
+
+# add -lineinfo option to nvcc, allowing us to get the source code from binary
+# do not influence optimization, can be used in nsight compute profiling
+target_compile_options(hidet PRIVATE $<$<COMPILE_LANGUAGE:CUDA>:-lineinfo>)
+