diff --git a/openmp/libomptarget/plugins/amdgpu/src/rtl.cpp b/openmp/libomptarget/plugins/amdgpu/src/rtl.cpp
--- a/openmp/libomptarget/plugins/amdgpu/src/rtl.cpp
+++ b/openmp/libomptarget/plugins/amdgpu/src/rtl.cpp
@@ -2042,13 +2042,11 @@
 
   // All args are references.
   std::vector<void *> args(arg_num);
-  std::vector<void *> ptrs(arg_num);
 
   DP("Arg_num: %d\n", arg_num);
   for (int32_t i = 0; i < arg_num; ++i) {
-    ptrs[i] = (void *)((intptr_t)tgt_args[i] + tgt_offsets[i]);
-    args[i] = &ptrs[i];
-    DP("Offseted base: arg[%d]:" DPxMOD "\n", i, DPxPTR(ptrs[i]));
+    args[i] = &tgt_args[i];
+    DP("Offseted base: arg[%d]:" DPxMOD "\n", i, DPxPTR(tgt_args[i]));
   }
 
   KernelTy *KernelInfo = (KernelTy *)tgt_entry_ptr;
diff --git a/openmp/libomptarget/plugins/cuda/src/rtl.cpp b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
--- a/openmp/libomptarget/plugins/cuda/src/rtl.cpp
+++ b/openmp/libomptarget/plugins/cuda/src/rtl.cpp
@@ -1063,12 +1063,8 @@
 
     // All args are references.
     std::vector<void *> Args(ArgNum);
-    std::vector<void *> Ptrs(ArgNum);
-
-    for (int I = 0; I < ArgNum; ++I) {
-      Ptrs[I] = (void *)((intptr_t)TgtArgs[I] + TgtOffsets[I]);
-      Args[I] = &Ptrs[I];
-    }
+    for (int I = 0; I < ArgNum; ++I)
+      Args[I] = &TgtArgs[I];
 
     KernelTy *KernelInfo = reinterpret_cast<KernelTy *>(TgtEntryPtr);
 
diff --git a/openmp/libomptarget/plugins/generic-elf-64bit/src/rtl.cpp b/openmp/libomptarget/plugins/generic-elf-64bit/src/rtl.cpp
--- a/openmp/libomptarget/plugins/generic-elf-64bit/src/rtl.cpp
+++ b/openmp/libomptarget/plugins/generic-elf-64bit/src/rtl.cpp
@@ -301,12 +301,9 @@
   // All args are references.
   std::vector<ffi_type *> args_types(arg_num, &ffi_type_pointer);
   std::vector<void *> args(arg_num);
-  std::vector<void *> ptrs(arg_num);
 
-  for (int32_t i = 0; i < arg_num; ++i) {
-    ptrs[i] = (void *)((intptr_t)tgt_args[i] + tgt_offsets[i]);
-    args[i] = &ptrs[i];
-  }
+  for (int32_t i = 0; i < arg_num; ++i)
+    args[i] = &tgt_args[i];
 
   ffi_status status = ffi_prep_cif(&cif, FFI_DEFAULT_ABI, arg_num,
                                    &ffi_type_void, &args_types[0]);
diff --git a/openmp/libomptarget/plugins/remote/src/Client.cpp b/openmp/libomptarget/plugins/remote/src/Client.cpp
--- a/openmp/libomptarget/plugins/remote/src/Client.cpp
+++ b/openmp/libomptarget/plugins/remote/src/Client.cpp
@@ -546,10 +546,6 @@
           Request->add_tgt_args((uint64_t)*ArgPtr);
         }
 
-        char *OffsetPtr = (char *)TgtOffsets;
-        for (auto I = 0; I < ArgNum; I++, OffsetPtr++)
-          Request->add_tgt_offsets((uint64_t)*OffsetPtr);
-
         Request->set_arg_num(ArgNum);
         Request->set_team_num(TeamNum);
         Request->set_thread_limit(ThreadLimit);
diff --git a/openmp/libomptarget/src/omptarget.cpp b/openmp/libomptarget/src/omptarget.cpp
--- a/openmp/libomptarget/src/omptarget.cpp
+++ b/openmp/libomptarget/src/omptarget.cpp
@@ -1425,12 +1425,11 @@
   assert(TargetTable && "Global data has not been mapped\n");
 
   std::vector<void *> TgtArgs;
-  std::vector<ptrdiff_t> TgtOffsets;
-
   PrivateArgumentManagerTy PrivateArgumentManager(Device, AsyncInfo);
 
   int Ret;
   if (ArgNum) {
+    std::vector<ptrdiff_t> TgtOffsets;
     // Process data, such as data mapping, before launching the kernel
     Ret = processDataBefore(loc, DeviceId, HostPtr, ArgNum, ArgBases, Args,
                             ArgSizes, ArgTypes, ArgNames, ArgMappers, TgtArgs,
@@ -1439,6 +1438,9 @@
       REPORT("Failed to process data before launching the kernel.\n");
       return OFFLOAD_FAIL;
     }
+
+    for (int I = 0; I < TgtArgs.size(); ++I)
+      TgtArgs[I] = (void *)((intptr_t)TgtArgs[I] + TgtOffsets[I]);
   }
 
   // Get loop trip count
@@ -1453,11 +1455,11 @@
     TIMESCOPE_WITH_NAME_AND_IDENT(
         IsTeamConstruct ? "runTargetTeamRegion" : "runTargetRegion", loc);
     if (IsTeamConstruct)
-      Ret = Device.runTeamRegion(TgtEntryPtr, &TgtArgs[0], &TgtOffsets[0],
-                                 TgtArgs.size(), TeamNum, ThreadLimit,
-                                 LoopTripCount, AsyncInfo);
+      Ret = Device.runTeamRegion(
+          TgtEntryPtr, &TgtArgs[0], nullptr /* TgtOffsets */, TgtArgs.size(),
+          TeamNum, ThreadLimit, LoopTripCount, AsyncInfo);
     else
-      Ret = Device.runRegion(TgtEntryPtr, &TgtArgs[0], &TgtOffsets[0],
+      Ret = Device.runRegion(TgtEntryPtr, &TgtArgs[0], nullptr /* TgtOffsets */,
                              TgtArgs.size(), AsyncInfo);
   }