[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/thrust/CMakeLists.txt

@@ -0,0 +1,65 @@
+if (NOT CCCL_ENABLE_THRUST)
+  include(cmake/ThrustAddSubdir.cmake)
+  return()
+endif()
+
+cmake_minimum_required(VERSION 3.21)
+project(Thrust LANGUAGES CXX) # CUDA enabled later only if needed
+
+option(
+  THRUST_ENABLE_HEADER_TESTING
+  "Test that all public headers compile."
+  "ON"
+)
+option(THRUST_ENABLE_TESTING "Build Thrust testing suite." "ON")
+option(THRUST_ENABLE_EXAMPLES "Build Thrust examples." "ON")
+
+# Allow the user to optionally select offset type dispatch to fixed 32 or 64 bit types
+set(
+  THRUST_DISPATCH_TYPE
+  "Dynamic"
+  CACHE STRING
+  "Select Thrust offset type dispatch."
+)
+set_property(
+  CACHE THRUST_DISPATCH_TYPE
+  PROPERTY STRINGS "Dynamic" "Force32bit" "Force64bit"
+)
+
+#include first:
+include(cmake/ThrustUtilities.cmake)
+
+include(cmake/ThrustBuildCompilerTargets.cmake)
+include(cmake/ThrustBuildTargetList.cmake)
+include(cmake/ThrustFindThrust.cmake)
+include(cmake/ThrustMultiConfig.cmake)
+
+thrust_configure_multiconfig()
+thrust_find_thrust()
+thrust_build_compiler_targets()
+thrust_update_system_found_flags()
+if (THRUST_CUDA_FOUND)
+  include(cmake/ThrustCudaConfig.cmake)
+endif()
+thrust_build_target_list()
+
+message(STATUS "CPP system found?  ${THRUST_CPP_FOUND}")
+message(STATUS "CUDA system found? ${THRUST_CUDA_FOUND}")
+message(STATUS "TBB system found?  ${THRUST_TBB_FOUND}")
+message(STATUS "OMP system found?  ${THRUST_OMP_FOUND}")
+
+if (THRUST_ENABLE_HEADER_TESTING)
+  include(cmake/ThrustHeaderTesting.cmake)
+endif()
+
+if (THRUST_ENABLE_TESTING)
+  add_subdirectory(testing)
+endif()
+
+if (THRUST_ENABLE_EXAMPLES)
+  add_subdirectory(examples)
+endif()
+
+if (CCCL_ENABLE_BENCHMARKS)
+  add_subdirectory(benchmarks)
+endif()