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
31 lines
951 B
CMake
31 lines
951 B
CMake
set(places_example_sources thrust_device_data_place_allocator.cu)
|
|
|
|
## cudax_add_places_example
|
|
#
|
|
# Add a places example executable and register it with ctest.
|
|
#
|
|
# target_name_var: Variable name to overwrite with the name of the example
|
|
# target. Useful for modifying the example/target after creation.
|
|
# source: The source file for the example.
|
|
#
|
|
function(cudax_add_places_example target_name_var source)
|
|
get_filename_component(filename ${source} NAME_WE)
|
|
|
|
set(example_target cudax.example.places.${filename})
|
|
|
|
cccl_add_executable(${example_target} SOURCES ${source} ADD_CTEST)
|
|
cudax_places_configure_target(${example_target})
|
|
target_link_libraries(
|
|
${example_target}
|
|
PRIVATE #
|
|
cudax.compiler_interface
|
|
cudax.examples.thrust
|
|
)
|
|
|
|
set(${target_name_var} ${example_target} PARENT_SCOPE)
|
|
endfunction()
|
|
|
|
foreach (source IN LISTS places_example_sources)
|
|
cudax_add_places_example(example_target "${source}")
|
|
endforeach()
|