Files
project_6/cccl_upstream/cub/cmake/CubCudaConfig.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

63 lines
1.1 KiB
CMake

#
# Architecture options:
#
option(
CUB_ENABLE_RDC_TESTS
"Enable tests that require separable compilation."
ON
)
option(
CUB_FORCE_RDC
"Enable separable compilation on all targets that support it."
OFF
)
option(
CUB_ENABLE_LAUNCH_NO_LAUNCHER
"Enable tests/examples without explicit launch variants."
ON
)
option(
CUB_ENABLE_LAUNCH_HOST_LAUNCHER
"Enable host launch variants (lid_0)."
ON
)
option(
CUB_ENABLE_LAUNCH_DEVICE_LAUNCHER
"Enable device launch variants (lid_1)."
ON
)
option(
CUB_ENABLE_LAUNCH_GRAPH_LAUNCHER
"Enable graph launch variants (lid_2)."
ON
)
option(
CUB_ENABLE_LAUNCH_VARIANTS
"Deprecated: use CUB_ENABLE_LAUNCH_DEVICE_LAUNCHER/GRAPH_LAUNCHER to control lid_1/lid_2."
ON
)
if (NOT CUB_ENABLE_LAUNCH_VARIANTS)
message(
WARNING
"CUB_ENABLE_LAUNCH_VARIANTS is deprecated; disabling lid_1/lid_2 launch variants."
)
set(
CUB_ENABLE_LAUNCH_DEVICE_LAUNCHER
OFF
CACHE BOOL
"Enable device launch variants (lid_1)."
FORCE
)
set(
CUB_ENABLE_LAUNCH_GRAPH_LAUNCHER
OFF
CACHE BOOL
"Enable graph launch variants (lid_2)."
FORCE
)
endif()