[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/cudax/test/stf/reductions/many_inc.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/stream/interfaces/slice_reduction_ops.cuh>
+#include <cuda/experimental/__stf/stream/stream_ctx.cuh>
+
+using namespace cuda::experimental::stf;
+
+__global__ void add(int* ptr)
+{
+  *ptr = *ptr + 1;
+}
+
+int main()
+{
+  stream_ctx ctx;
+
+  auto redux_op = std::make_shared<slice_reduction_op_sum<int>>();
+
+  int a = 17;
+
+  auto handle = ctx.logical_data(make_slice(&a, 1));
+
+  int ndevs;
+  cuda_safe_call(cudaGetDeviceCount(&ndevs));
+
+  int K = 1024;
+  for (int i = 0; i < K; i++)
+  {
+    // Increment the variable by 1
+    ctx.task(exec_place::device(i % ndevs), handle.relaxed(redux_op))->*[](auto stream, auto s) {
+      add<<<1, 1, 0, stream>>>(s.data_handle());
+    };
+  }
+
+  // Total value should be initial value + K
+  ctx.task(exec_place::host(), handle.read())->*[&](auto stream, auto s) {
+    cuda_safe_call(cudaStreamSynchronize(stream));
+    EXPECT(s(0) == 17 + K);
+    // printf("VALUE %d expected %d\n", s(0), 17 + K);
+  };
+
+  ctx.finalize();
+}