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
24 lines
555 B
CMake
24 lines
555 B
CMake
# Configures a target for the Places framework.
|
|
function(cudax_places_configure_target target_name)
|
|
target_link_libraries(
|
|
${target_name}
|
|
PRIVATE #
|
|
CUDA::cudart_static
|
|
CUDA::cuda_driver
|
|
)
|
|
|
|
target_compile_options(
|
|
${target_name}
|
|
PRIVATE
|
|
$<$<COMPILE_LANG_AND_ID:CUDA,NVIDIA>:--extended-lambda>
|
|
$<$<COMPILE_LANG_AND_ID:CUDA,NVIDIA>:--expt-relaxed-constexpr>
|
|
)
|
|
|
|
set_target_properties(
|
|
${target_name}
|
|
PROPERTIES #
|
|
CUDA_RUNTIME_LIBRARY Static
|
|
CUDA_SEPARABLE_COMPILATION ON
|
|
)
|
|
endfunction()
|