[CCCL] Add missing CCCL components: c2h, nvbench_helper, cmake, cudax, AGENTS.md

Added 863 files from NVIDIA/cccl sparse checkout:
- c2h/ (27 files): Catch2 test helpers — generators, validators, runner
- nvbench_helper/ (10 files): Benchmark harness utilities
- cmake/ (29 files): CMake presets and build helpers
- cudax/ (794 files): Experimental CUDA extensions
- AGENTS.md: NVIDIA's official AI agent instructions for CCCL
- CMakePresets.json: Standardized build configurations
- cccl-version.json: Version tracking

Also added CCCL_ASSET_MAP.md mapping all 4295 CCCL files to
competition value and PRD items.

cccl_upstream now covers 100% of competition-critical assets:
- 27 tuning headers (SM80/90/100 benchmark data)
- 32 dispatch headers (algorithm implementations)
- 60 Thrust examples (correctness verification)
- 217 CUB Catch2 tests (regression matrix)
- 153 CUB benchmarks (parameter space search)
- 18 CUB examples (API verification)
- 27 test helpers + benchmark harness
- 794 cudax experimental extensions

cccl_upstream/cudax/examples/cub_reduce.cu

@@ -0,0 +1,53 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of CUDA Experimental in CUDA C++ Core Libraries,
+// under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+// SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES.
+//
+//===----------------------------------------------------------------------===//
+
+// Example of using `cub::DeviceReduce::Reduce` with cudax environment.
+
+#include <cub/device/device_reduce.cuh>
+
+#include <cuda/experimental/container.cuh>
+#include <cuda/experimental/memory_resource.cuh>
+#include <cuda/experimental/stream.cuh>
+
+#include <iostream>
+
+namespace cudax = cuda::experimental;
+
+int main()
+{
+  constexpr int num_items = 50000;
+
+  // A CUDA stream on which to execute the reduction
+  cuda::stream stream{cuda::devices[0]};
+  cuda::device_memory_pool_ref mr = cuda::device_default_memory_pool(cuda::devices[0]);
+
+  // Allocate input and output, but do not zero initialize output (`cuda::no_init`)
+  auto d_in  = cuda::make_buffer<int>(stream, mr, num_items, 1);
+  auto d_out = cuda::make_buffer<float>(stream, mr, 1, cuda::no_init);
+
+  // An environment we use to pass all necessary information to CUB
+  cudax::env_t<cuda::mr::device_accessible> env{mr, stream};
+  auto error = cub::DeviceReduce::Reduce(d_in.begin(), d_out.begin(), num_items, cuda::std::plus{}, 0, env);
+  if (error != cudaSuccess)
+  {
+    std::cerr << "cub::DeviceReduce::Reduce failed: " << cudaGetErrorString(error) << "\n";
+    exit(EXIT_FAILURE);
+  }
+
+  auto h_out = cuda::make_buffer<float>(stream, cuda::pinned_default_memory_pool(), d_out);
+
+  stream.sync();
+
+  if (h_out.get_unsynchronized(0) != num_items)
+  {
+    std::cerr << "Result verification failed: " << h_out.get_unsynchronized(0) << " != " << num_items << "\n";
+    exit(EXIT_FAILURE);
+  }
+}