[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/test/stf/dot/sections_stackable.cu

@@ -0,0 +1,61 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of CUDASTF 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) 2022-2024 NVIDIA CORPORATION & AFFILIATES.
+//
+//===----------------------------------------------------------------------===//
+
+/**
+ * @file
+ * @brief This test makes sure we can generate a dot file with sections and stackable contexts
+ */
+
+#include <cuda/experimental/stf.cuh>
+
+using namespace cuda::experimental::stf;
+
+int main()
+{
+// TODO (miscco): Make it work for windows
+#if !_CCCL_COMPILER(MSVC)
+  // Test configuration constants
+  constexpr size_t buffer_size    = 64;
+  constexpr size_t num_iterations = 3;
+
+  stackable_ctx ctx;
+
+  // Create logical data for the computation pipeline
+  auto lA = ctx.logical_data(shape_of<slice<char>>(buffer_size));
+  auto lB = ctx.logical_data(shape_of<slice<char>>(buffer_size));
+  auto lC = ctx.logical_data(shape_of<slice<char>>(buffer_size));
+
+  // Initialize all logical data in a dedicated DOT section
+  auto r_init = ctx.dot_section("init");
+  ctx.task(lA.write()).set_symbol("initA")->*[](cudaStream_t, auto) {};
+  ctx.task(lB.write()).set_symbol("initB")->*[](cudaStream_t, auto) {};
+  ctx.task(lC.write()).set_symbol("initC")->*[](cudaStream_t, auto) {};
+  r_init.end();
+
+  // Test nested DOT sections with stackable contexts
+  // This creates a hierarchical structure to verify DOT graph generation
+  for (size_t j = 0; j < num_iterations; j++)
+  {
+    auto r0 = ctx.dot_section("lvl0");
+    ctx.task(lA.rw()).set_symbol("f1")->*[](cudaStream_t, auto) {};
+
+    ctx.push();
+    {
+      auto r1 = ctx.dot_section("lvl1");
+      ctx.task(lA.read(), lB.rw()).set_symbol("f2")->*[](cudaStream_t, auto, auto) {};
+      ctx.task(lA.read(), lC.rw()).set_symbol("f2")->*[](cudaStream_t, auto, auto) {};
+      ctx.task(lB.read(), lC.read(), lA.rw()).set_symbol("f3")->*[](cudaStream_t, auto, auto, auto) {};
+    }
+    ctx.pop();
+  }
+  ctx.finalize();
+
+#endif // !_CCCL_COMPILER(MSVC)
+}