[OpenMP][CUDA] Refine the logic to determine grid size

[tianshilei1992]

Summary

This patch refines the logic to determine grid size as previous method
can escape the check of whether CudaBlocksPerGrid could be greater than the actual
hardware limit.

[tianshilei1992]

ping

[jdoerfert]

LG, please make a ticket and backport to 14

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

if (TeamNum <= 0) {
         }
         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",
-         DeviceData[DeviceId].BlocksPerGrid);
-      CudaBlocksPerGrid = DeviceData[DeviceId].BlocksPerGrid;
     } else {
       DP("Using requested number of teams %d\n", TeamNum);
       CudaBlocksPerGrid = TeamNum;
     }
 
+    if (CudaBlocksPerGrid > DeviceData[DeviceId].BlocksPerGrid) {
+      DP("Capping number of teams to team limit %d\n",
+         DeviceData[DeviceId].BlocksPerGrid);
+      CudaBlocksPerGrid = DeviceData[DeviceId].BlocksPerGrid;
+    }
+
     INFO(OMP_INFOTYPE_PLUGIN_KERNEL, DeviceId,
          "Launching kernel %s with %d blocks and %d threads in %s mode\n",
          (getOffloadEntry(DeviceId, TgtEntryPtr))
              ? getOffloadEntry(DeviceId, TgtEntryPtr)->name
              : "(null)",
          CudaBlocksPerGrid, CudaThreadsPerBlock,
          (!IsSPMDMode ? (IsGenericMode ? "Generic" : "SPMD-Generic") : "SPMD"));