[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

cccl_upstream/examples/CMakeLists.txt

@@ -0,0 +1,110 @@
+# SPDX-FileCopyrightText: Copyright (c) 2023 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+enable_language(CUDA) # Ensure that CUDA compiler vars are defined
+
+set(
+  cmake_opts
+  "--log-level=VERBOSE"
+  "-DCMAKE_BUILD_TYPE=${CMAKE_BUILD_TYPE}"
+  "-DCMAKE_MAKE_PROGRAM=${CMAKE_MAKE_PROGRAM}"
+  "-DCMAKE_CXX_COMPILER=${CMAKE_CXX_COMPILER}"
+  "-DCMAKE_CUDA_COMPILER=${CMAKE_CUDA_COMPILER}"
+  "-DCMAKE_CUDA_HOST_COMPILER=${CMAKE_CUDA_HOST_COMPILER}"
+  "-DCMAKE_CUDA_ARCHITECTURES=75"
+)
+
+set(
+  CCCL_EXAMPLE_CPM_REPOSITORY
+  "${CCCL_SOURCE_DIR}"
+  CACHE STRING
+  "Git repository used for CPM examples."
+)
+set(
+  CCCL_EXAMPLE_CPM_TAG
+  "HEAD"
+  CACHE STRING
+  "Git tag/branch used for CPM examples."
+)
+set(
+  CCCL_EXAMPLE_CTEST_COMMAND
+  "${CMAKE_CTEST_COMMAND}"
+  CACHE STRING
+  "CTest command used for CCCL example build-and-tests."
+)
+
+set(
+  cmake_cpm_opts
+  "-DCCCL_REPOSITORY=${CCCL_EXAMPLE_CPM_REPOSITORY}"
+  "-DCCCL_TAG=${CCCL_EXAMPLE_CPM_TAG}"
+)
+
+if (MSVC)
+  message(STATUS "Skipping example build-and-test CTests on MSVC")
+  return()
+endif()
+
+cccl_add_compile_test(
+  test_name
+  cccl.example
+  basic
+  "default"
+  CTEST_COMMAND "${CCCL_EXAMPLE_CTEST_COMMAND}"
+  ${cmake_opts}
+  ${cmake_cpm_opts}
+)
+
+cccl_add_compile_test(
+  test_name
+  cccl.example
+  image_pipeline
+  "default"
+  CTEST_COMMAND "${CCCL_EXAMPLE_CTEST_COMMAND}"
+  ${cmake_opts}
+  ${cmake_cpm_opts}
+)
+
+cccl_add_compile_test(
+  test_name
+  cccl.example
+  cudax
+  "default"
+  CTEST_COMMAND "${CCCL_EXAMPLE_CTEST_COMMAND}"
+  ${cmake_opts}
+  ${cmake_cpm_opts}
+)
+
+cccl_add_compile_test(
+  test_name
+  cccl.example
+  cudax_stf
+  "default"
+  CTEST_COMMAND "${CCCL_EXAMPLE_CTEST_COMMAND}"
+  ${cmake_opts}
+  ${cmake_cpm_opts}
+)
+
+foreach (DEVICE_SYSTEM IN ITEMS CUDA OMP TBB CPP)
+  cccl_add_compile_test(
+    test_name
+    cccl.example
+    thrust_flexible_device_system
+    "${DEVICE_SYSTEM}"
+    CTEST_COMMAND "${CCCL_EXAMPLE_CTEST_COMMAND}"
+    "-DCCCL_THRUST_DEVICE_SYSTEM=${DEVICE_SYSTEM}"
+    ${cmake_opts}
+    ${cmake_cpm_opts}
+  )
+endforeach()