Files
project_6/cccl_upstream/cudax/cmake/cudaxSTFConfigureTarget.cmake
EngineX CI 56fd68e7dd [INFRA] Import NVIDIA/CCCL upstream as optimization reference library
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
2026-07-30 09:35:51 +00:00

59 lines
1.2 KiB
CMake

# Configures a target for the STF framework.
function(cudax_stf_configure_target target_name)
set(options LINK_MATHLIBS)
set(oneValueArgs)
set(multiValueArgs)
cmake_parse_arguments(
CSCT
"${options}"
"${oneValueArgs}"
"${multiValueArgs}"
${ARGN}
)
target_link_libraries(
${target_name}
PRIVATE #
CUDA::cudart_static
CUDA::curand
CUDA::cuda_driver
)
if (cudax_ENABLE_CUDASTF_CODE_GENERATION)
target_compile_options(
${target_name}
PRIVATE $<$<COMPILE_LANG_AND_ID:CUDA,NVIDIA>:--extended-lambda>
)
else()
target_compile_definitions(
${target_name}
PRIVATE "CUDASTF_DISABLE_CODE_GENERATION"
)
endif()
target_compile_options(
${target_name}
PRIVATE $<$<COMPILE_LANG_AND_ID:CUDA,NVIDIA>:--expt-relaxed-constexpr>
)
set_target_properties(
${target_name}
PROPERTIES #
CUDA_RUNTIME_LIBRARY Static
CUDA_SEPARABLE_COMPILATION ON
)
if (CSCT_LINK_MATHLIBS)
target_link_libraries(
${target_name}
PRIVATE #
CUDA::cublas
CUDA::cusolver
)
endif()
if (cudax_ENABLE_CUDASTF_BOUNDSCHECK)
target_compile_definitions(${target_name} PRIVATE "CUDASTF_BOUNDSCHECK")
endif()
endfunction()