[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/hash/ctx_hash.cu

@@ -0,0 +1,69 @@
+//===----------------------------------------------------------------------===//
+//
+// 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.
+//
+//===----------------------------------------------------------------------===//
+
+#include <cuda/experimental/__stf/graph/graph_ctx.cuh>
+#include <cuda/experimental/__stf/stream/stream_ctx.cuh>
+
+using namespace cuda::experimental::stf;
+
+template <typename S>
+__global__ void inc_kernel(S sA)
+{
+  sA(threadIdx.x)++;
+}
+
+template <typename S1, typename S2>
+__global__ void copy_kernel(S1 sA, S2 sB)
+{
+  sB(threadIdx.x) = sA(threadIdx.x);
+}
+
+template <typename Ctx>
+void run()
+{
+  int A[10] = {0};
+  int B[10] = {0};
+  Ctx ctx;
+
+  auto lA = ctx.logical_data(A);
+  auto lB = ctx.logical_data(B);
+
+  for (size_t k = 0; k < 10; k++)
+  {
+    // fprintf(stderr, "iter %zu - 0 : ctx.hash %zu\n", k, ctx.hash());
+    ctx.task(lA.rw())->*[](cudaStream_t stream, auto sA) {
+      inc_kernel<<<1, 10, 0, stream>>>(sA);
+    };
+
+    // fprintf(stderr, "iter %zu - 1 : ctx.hash %zu\n", k, ctx.hash());
+    ctx.task(lA.read(), lB.rw())->*[](cudaStream_t stream, auto sA, auto sB) {
+      copy_kernel<<<1, 10, 0, stream>>>(sA, sB);
+    };
+
+    // fprintf(stderr, "iter %zu - 2 : ctx.hash %zu\n", k, ctx.hash());
+    ctx.task(lB.rw())->*[](cudaStream_t stream, auto sB) {
+      inc_kernel<<<1, 10, 0, stream>>>(sB);
+    };
+
+    // fprintf(stderr, "iter %zu - 3 : ctx.hash %zu\n", k, ctx.hash());
+  }
+
+  ctx.host_launch(lA.read(), lB.read())->*[&](auto /*unused*/, auto /*unused*/) {
+    // fprintf(stderr, "HOST END : ctx.hash %zu\n", ctx.hash());
+  };
+
+  ctx.finalize();
+}
+
+int main()
+{
+  run<stream_ctx>();
+  run<graph_ctx>();
+}

cccl_upstream/cudax/test/stf/hash/logical_data.cu

@@ -0,0 +1,51 @@
+//===----------------------------------------------------------------------===//
+//
+// 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.
+//
+//===----------------------------------------------------------------------===//
+
+#include <cuda/experimental/__stf/graph/graph_ctx.cuh>
+#include <cuda/experimental/__stf/stream/stream_ctx.cuh>
+
+using namespace cuda::experimental::stf;
+
+template <typename S>
+__global__ void inc_kernel(S sA)
+{
+  sA(threadIdx.x)++;
+}
+
+template <typename Ctx>
+void run()
+{
+  int A[10] = {0};
+  stream_ctx ctx;
+
+  auto l = ctx.logical_data(A);
+
+  for (size_t k = 0; k < 10; k++)
+  {
+    // size_t h = l.hash();
+    // fprintf(stderr, "iter %zu : logical data hash %zu ctx.hash %zu\n", k, h, ctx.hash());
+
+    ctx.task(l.rw())->*[](cudaStream_t stream, auto sA) {
+      inc_kernel<<<1, 10, 0, stream>>>(sA);
+    };
+  }
+
+  ctx.host_launch(l.read())->*[&](auto /*unused*/) {
+    // fprintf(stderr, "HOST end : logical data hash %zu ctx.hash %zu\n", l.hash(), ctx.hash());
+  };
+
+  ctx.finalize();
+}
+
+int main()
+{
+  run<stream_ctx>();
+  run<graph_ctx>();
+}