56fd68e7dd
CCCL (CUDA C++ Core Libraries) provides: - CUB: device/block/warp-level GPU primitives (reduce, scan, sort, topk) - Thrust: high-level parallel algorithms (transform_reduce, sort, scan) - libcudacxx: CUDA C++ standard library (atomics, barriers, memory) - cudax: experimental features (memory resources, allocators) - Tuning policies: per-SM hardware-specific algorithm parameters Competition optimization vectors mapped to CCCL: - Output TPS (83% weight): warp_reduce, block_reduce, device_topk - Input TPS (14% weight): device_scan, block_load, prefetch - Cache TPS (3% weight): prefix caching strategy patterns - Memory (0.9 util): pooled/cached/buddy allocators Source: https://github.com/NVIDIA/cccl (shallow clone, HEAD only) License: Apache-2.0
50 lines
1.3 KiB
CMake
50 lines
1.3 KiB
CMake
if (NOT CCCL_ENABLE_LIBCUDACXX)
|
|
include(cmake/libcudacxxAddSubdir.cmake)
|
|
return()
|
|
endif()
|
|
|
|
cmake_minimum_required(VERSION 3.21)
|
|
set(PACKAGE_NAME libcudacxx)
|
|
set(PACKAGE_VERSION 11.0)
|
|
set(PACKAGE_STRING "${PACKAGE_NAME} ${PACKAGE_VERSION}")
|
|
project(libcudacxx LANGUAGES CXX)
|
|
|
|
# Add codegen module
|
|
option(
|
|
libcudacxx_ENABLE_CODEGEN
|
|
"Enable libcudacxx's atomics backend codegen and tests."
|
|
OFF
|
|
)
|
|
if (libcudacxx_ENABLE_CODEGEN)
|
|
add_subdirectory(codegen)
|
|
endif()
|
|
|
|
list(PREPEND CMAKE_MODULE_PATH "${libcudacxx_SOURCE_DIR}/cmake")
|
|
set(LLVM_PATH "${libcudacxx_SOURCE_DIR}" CACHE STRING "" FORCE)
|
|
|
|
# Configuration options.
|
|
option(LIBCUDACXX_ENABLE_CUDA "Enable the CUDA language support." ON)
|
|
if (LIBCUDACXX_ENABLE_CUDA)
|
|
enable_language(CUDA)
|
|
endif()
|
|
|
|
option(LIBCUDACXX_ENABLE_LIBCUDACXX_TESTS "Enable libcu++ tests." ON)
|
|
if (LIBCUDACXX_ENABLE_LIBCUDACXX_TESTS)
|
|
enable_testing()
|
|
|
|
# Create the compiler targets with the common compile flags
|
|
include(cmake/LibcudacxxBuildCompilerTargets.cmake)
|
|
libcudacxx_build_compiler_targets()
|
|
|
|
# Test all public and internal headers
|
|
include(cmake/LibcudacxxInternalHeaderTesting.cmake)
|
|
include(cmake/LibcudacxxPublicHeaderTesting.cmake)
|
|
include(cmake/LibcudacxxPublicHeaderTestingHost.cmake)
|
|
|
|
add_subdirectory(test)
|
|
endif()
|
|
|
|
if (CCCL_ENABLE_BENCHMARKS)
|
|
add_subdirectory(benchmarks)
|
|
endif()
|