[INIT] Fix fallback for unsupported user-specified runtime unroll factor (#1780)

* [INIT] Fix fallback for unsupported user-specified runtime unroll factor
* Add CollTrace guard
* Move `commSetUnrollFactor()` to rccl_wrap.cc
* Modify comments in the device-code generator script

[ROCm/rccl commit: 2c099fe29a]

projects/rccl/src/include/enqueue.h

@@ -17,6 +17,8 @@
 #define NCCL_SIMPLE_ALIGNMENT (WARP_SIZE * 8LL * 16LL)
 #define NCCL_BYTES_ALIGNMENT 16
 
+void* rcclGetKernelIndex(int unroll, bool useCollTrace, struct ncclTaskColl* task = NULL);
+
 ncclResult_t ncclInitKernelsForDevice(int cudaArch, int maxSharedMem, size_t* maxStackSize);
 ncclResult_t ncclEnqueueCheck(struct ncclInfo* info);
 ncclResult_t ncclLaunchPrepare(struct ncclComm* comm);