2a7ca101d7
Sparse-checkout from NVIDIA/cccl main branch to complete cccl_upstream: Added: - python/cuda_cccl/ (226 files) — Python bindings for device-level algorithms Critical for muh toolchain: cuda.compute.reduce_into, scan, radix_sort, etc. Includes 204 .py files with full test coverage for all 27 algorithms - ci/ (163 files) — Build/test infrastructure build_cub.sh, test_cub.sh, build_and_test_targets.sh, matrix.yaml Directly maps to our [INFRA-CI] and [INFRA-BUILD] items - .agent/skills/ (7 files) — NVIDIA's own agent skills for CCCL cccl-style/SKILL.md, cccl-test/SKILL.md, sass-diff/SKILL.md - docs/ (491 files) — Official CCCL documentation CI references, CMake guides, Python compute docs, libcudacxx PTX docs - test/ (12 files) — Top-level integration tests (cuda_smoke, stdpar) - Root configs: .clang-format, .clang-tidy, CONTRIBUTING.md, pyproject.toml - CLAUDE.md symlink → AGENTS.md (NVIDIA's standard) cccl_upstream now mirrors full NVIDIA/cccl structure: Before: 42M (cub + thrust + libcudacxx + cudax + c + examples + benchmarks) After: 53M (+python +ci +docs +.agent +test +configs) This completes the CCCL base needed for: - [muh-bench] items: ci/util/build_and_test_targets.sh for targeted builds - [CCCL-verify] items: python/cuda_cccl/tests/ as reference implementations - [CCCL-test] items: ci/test_cub.sh, ci/test_thrust.sh - Agent workflow: .agent/skills/ for consistent style and test patterns
33 lines
1010 B
Bash
Executable File
33 lines
1010 B
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -euo pipefail
|
|
|
|
# shellcheck source=ci/build_common.sh
|
|
source "$(dirname "${BASH_SOURCE[0]}")/build_common.sh"
|
|
|
|
print_environment_details
|
|
|
|
# If the cudax_ENABLE_CUFILE variable is specified, we don't modify it. Otherwise if we got an nvcc binary, check the
|
|
# nvcc version and if it's less than 12.9, disable the cuFile support. NVHPC Toolkit doesn't come with cuFile, too, so
|
|
# we don't enable cuFile support if the host compiler is nvc++.
|
|
if [[ -z "${cudax_ENABLE_CUFILE:-}" ]]; then
|
|
cudax_ENABLE_CUFILE="false"
|
|
if [[ -n "${NVCC_VERSION:-}" ]] && [[ "$(basename "${HOST_COMPILER}")" != "nvc++" ]]; then
|
|
if util/version_compare.sh "${NVCC_VERSION}" ge 12.9; then
|
|
cudax_ENABLE_CUFILE="true"
|
|
fi
|
|
fi
|
|
fi
|
|
|
|
PRESET="cudax"
|
|
|
|
CMAKE_OPTIONS=(
|
|
"-Dcudax_ENABLE_CUFILE=${cudax_ENABLE_CUFILE}"
|
|
"-DCMAKE_CXX_STANDARD=${CXX_STANDARD}"
|
|
"-DCMAKE_CUDA_STANDARD=${CXX_STANDARD}"
|
|
)
|
|
|
|
configure_and_build_preset "CUDA Experimental" "$PRESET" "${CMAKE_OPTIONS[@]}"
|
|
|
|
print_time_summary
|