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

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.

Reviewed By: jdoerfert

Differential Revision: https://reviews.llvm.org/D119311

Author: shiltian

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

@@ -1170,15 +1170,17 @@ class DeviceRTLTy {
         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))