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
19 lines
404 B
CMake
19 lines
404 B
CMake
file(
|
|
GLOB_RECURSE example_srcs
|
|
RELATIVE "${CMAKE_CURRENT_LIST_DIR}"
|
|
CONFIGURE_DEPENDS
|
|
example_*.cu
|
|
)
|
|
|
|
foreach (example_src IN LISTS example_srcs)
|
|
get_filename_component(example_name "${example_src}" NAME_WE)
|
|
string(
|
|
REGEX REPLACE
|
|
"^example_device_"
|
|
"device."
|
|
example_name
|
|
"${example_name}"
|
|
)
|
|
cub_add_example(target_name ${example_name} "${example_src}")
|
|
endforeach()
|