[OpenMP] fix clang warning about printf format in CUDA plugin

[ye-luo]

Summary

Warnings are printed by clang when building LIBOMPTARGET_ENABLE_DEBUG=ON due incorrect format string.

[tianshilei1992]

Thank you for the patch. Just one tiny comment: are these everything for the warning about the debug output?

[ye-luo]

In D82789#2120848, @tianshilei1992 wrote:

Thank you for the patch. Just one tiny comment: are these everything for the warning about the debug output?

I think so.
I don't have commit rights. Please land the patch for me.

[tianshilei1992]

LGTM

openmp/libomptarget/plugins/cuda/src/rtl.cpp

 /// FIXME: we may need this to be per device and per library.
 std::list<KernelTy> KernelsList;
 
 namespace {
 bool checkResult(CUresult Err, const char *ErrMsg) {
   if (Err == CUDA_SUCCESS)
     return true;
 
-  DP(ErrMsg);
+  DP("%s", ErrMsg);
   CUDA_ERR_STRING(Err);
   return false;
 }
 
 int memcpyDtoD(const void *SrcPtr, void *DstPtr, int64_t Size,
                CUstream Stream) {
   CUresult Err =
       cuMemcpyDtoDAsync((CUdeviceptr)DstPtr, (CUdeviceptr)SrcPtr, Size, Stream);
if (SrcDevId != DstDevId) {
 
       Err = cuMemcpyPeerAsync((CUdeviceptr)DstPtr, DeviceData[DstDevId].Context,
                               (CUdeviceptr)SrcPtr, DeviceData[SrcDevId].Context,
                               Size, Stream);
       if (Err == CUDA_SUCCESS)
         return OFFLOAD_SUCCESS;
 
       DP("Error returned from cuMemcpyPeerAsync. src_ptr = " DPxMOD
-         ", src_id =%" PRId32 ", dst_ptr = %" DPxMOD ", dst_id =%" PRId32 "\n",
-         SrcPtr, SrcDevId, DstPtr, DstDevId);
+         ", src_id =%" PRId32 ", dst_ptr = " DPxMOD ", dst_id =%" PRId32 "\n",
+         DPxPTR(SrcPtr), SrcDevId, DPxPTR(DstPtr), DstDevId);
       CUDA_ERR_STRING(Err);
     }
 
     return memcpyDtoD(SrcPtr, DstPtr, Size, Stream);
   }
 
   int dataDelete(const int DeviceId, void *TgtPtr) const {
     CUresult Err = cuCtxSetCurrent(DeviceData[DeviceId].Context);
if (TeamNum <= 0) {
           //   #pragma omp parallel for
           //   for(...) {}
           // }
           //
           // Threads within a team will execute the iterations of the `parallel`
           // loop.
           CudaBlocksPerGrid = LoopTripCount;
         }
-        DP("Using %d teams due to loop trip count %" PRIu64
+        DP("Using %d teams due to loop trip count %" PRIu32
            " and number of threads per block %d\n",
            CudaBlocksPerGrid, LoopTripCount, CudaThreadsPerBlock);
       } else {
         DP("Using default number of teams %d\n", DeviceData[DeviceId].NumTeams);
         CudaBlocksPerGrid = DeviceData[DeviceId].NumTeams;
       }
     } else if (TeamNum > DeviceData[DeviceId].BlocksPerGrid) {
       DP("Capping number of teams to team limit %d\n",