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
18 lines
710 B
CMake
18 lines
710 B
CMake
# For every public header, build a translation unit containing `#include <header>`
|
|
# to let the compiler try to figure out warnings in that header if it is not otherwise
|
|
# included in tests, and also to verify if the headers are modular enough.
|
|
# .inl files are not globbed for, because they are not supposed to be used as public
|
|
# entrypoints.
|
|
|
|
set(target_name cccl.c.parallel.headers)
|
|
|
|
cccl_generate_header_tests(
|
|
${target_name}
|
|
c/parallel/include
|
|
NO_METATARGETS # Metatargets collide with the existing cccl.c.parallel target
|
|
LANGUAGE C
|
|
GLOBS "cccl/c/*.h"
|
|
)
|
|
target_link_libraries(${target_name} PUBLIC cccl.c.parallel)
|
|
target_include_directories(${target_name} PRIVATE ${CUDAToolkit_INCLUDE_DIRS})
|