[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/libcudacxx/test/utils/nvidia/getsm/main.cu

@@ -0,0 +1,25 @@
+#include <stdio.h>
+
+#define CUDA_CALL(...)                                                                \
+  do                                                                                  \
+  {                                                                                   \
+    cudaError_t err = __VA_ARGS__;                                                    \
+    if (err != cudaSuccess)                                                           \
+    {                                                                                 \
+      printf("CUDA ERROR: %s: %s\n", cudaGetErrorName(err), cudaGetErrorString(err)); \
+      return err;                                                                     \
+    }                                                                                 \
+  } while (false)
+
+int main()
+{
+  int selected_device;
+  CUDA_CALL(cudaGetDevice(&selected_device));
+
+  cudaDeviceProp device_prop;
+  CUDA_CALL(cudaGetDeviceProperties(&device_prop, selected_device));
+
+  FILE* output = fopen("sm", "w");
+  fprintf(output, "%d%d\n", device_prop.major, device_prop.minor);
+  fclose(output);
+}