[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/benchmarks/scripts/cccl/bench/logger.py

@@ -0,0 +1,20 @@
+import logging
+
+
+class Logger:
+    _instance = None
+
+    def __new__(cls, *args, **kwargs):
+        if cls._instance is None:
+            cls._instance = super().__new__(cls, *args, **kwargs)
+            logger = logging.getLogger()
+            logger.setLevel(logging.DEBUG)
+            file_handler = logging.FileHandler("cccl_meta_bench.log")
+            file_handler.setFormatter(logging.Formatter("%(asctime)s: %(message)s"))
+            logger.addHandler(file_handler)
+            cls._instance.logger = logger
+
+        return cls._instance
+
+    def info(self, message):
+        self.logger.info(message)