diff --git a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
--- a/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp
@@ -2855,7 +2855,7 @@
     auto *Ty = llvm::ArrayType::get(CGM.Int32Ty, WarpSize);
     unsigned SharedAddressSpace = C.getTargetAddressSpace(LangAS::cuda_shared);
     TransferMedium = new llvm::GlobalVariable(
-        M, Ty, /*isConstant=*/false, llvm::GlobalVariable::InternalLinkage,
+        M, Ty, /*isConstant=*/false, llvm::GlobalVariable::WeakAnyLinkage,
         llvm::UndefValue::get(Ty), TransferMediumName,
         /*InsertBefore=*/nullptr, llvm::GlobalVariable::NotThreadLocal,
         SharedAddressSpace);
@@ -4791,7 +4791,7 @@
       llvm::Type *LLVMStaticTy = CGM.getTypes().ConvertTypeForMem(StaticTy);
       auto *GV = new llvm::GlobalVariable(
           CGM.getModule(), LLVMStaticTy,
-          /*isConstant=*/false, llvm::GlobalValue::InternalLinkage,
+          /*isConstant=*/false, llvm::GlobalValue::WeakAnyLinkage,
           llvm::UndefValue::get(LLVMStaticTy),
           "_openmp_shared_static_glob_rd_$_", /*InsertBefore=*/nullptr,
           llvm::GlobalValue::NotThreadLocal,
diff --git a/clang/test/OpenMP/nvptx_data_sharing.cpp b/clang/test/OpenMP/nvptx_data_sharing.cpp
--- a/clang/test/OpenMP/nvptx_data_sharing.cpp
+++ b/clang/test/OpenMP/nvptx_data_sharing.cpp
@@ -28,8 +28,8 @@
   }
 }
 // SEQ: [[MEM_TY:%.+]] = type { [128 x i8] }
-// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = weak addrspace(3) global [[MEM_TY]] undef
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* undef
 // SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i64 8
 // SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
diff --git a/clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp b/clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
--- a/clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_distribute_parallel_generic_mode_codegen.cpp
@@ -35,8 +35,8 @@
 }
 
 // SEQ: [[MEM_TY:%.+]] = type { [128 x i8] }
-// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = weak addrspace(3) global [[MEM_TY]] undef
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* undef
 // SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 40
 // SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 // CHECK-DAG: @__omp_offloading_{{.*}}_main_[[LINE:l.+]]_exec_mode = weak constant i8 0
diff --git a/clang/test/OpenMP/nvptx_parallel_codegen.cpp b/clang/test/OpenMP/nvptx_parallel_codegen.cpp
--- a/clang/test/OpenMP/nvptx_parallel_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_parallel_codegen.cpp
@@ -76,8 +76,8 @@
 }
 
 // SEQ: [[MEM_TY:%.+]] = type { [128 x i8] }
-// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = weak addrspace(3) global [[MEM_TY]] undef
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* undef
 // SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
 // SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
diff --git a/clang/test/OpenMP/nvptx_parallel_for_codegen.cpp b/clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
--- a/clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_parallel_for_codegen.cpp
@@ -32,8 +32,8 @@
 }
 
 // SEQ: [[MEM_TY:%.+]] = type { [128 x i8] }
-// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = weak addrspace(3) global [[MEM_TY]] undef
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* undef
 // SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
 // SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
diff --git a/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp b/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
--- a/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_target_parallel_reduction_codegen.cpp
@@ -9,7 +9,7 @@
 #define HEADER
 
 // Check for the data transfer medium in shared memory to transfer the reduction list to the first warp.
-// CHECK-DAG: [[TRANSFER_STORAGE:@.+]] = common addrspace([[SHARED_ADDRSPACE:[0-9]+]]) global [32 x i32]
+// CHECK-DAG: [[TRANSFER_STORAGE:@.+]] = weak addrspace([[SHARED_ADDRSPACE:[0-9]+]]) global [32 x i32]
 
 // Check that the execution mode of all 3 target regions is set to Spmd Mode.
 // CHECK-DAG: {{@__omp_offloading_.+l27}}_exec_mode = weak constant i8 0
diff --git a/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp b/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
--- a/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_codegen.cpp
@@ -93,8 +93,8 @@
 }
 
 // SEQ-DAG: [[MEM_TY:%.+]] = type { [128 x i8] }
-// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = weak addrspace(3) global [[MEM_TY]] undef
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* undef
 // SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
 // SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
diff --git a/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp b/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
--- a/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_target_teams_distribute_parallel_for_simd_codegen.cpp
@@ -76,8 +76,8 @@
 }
 
 // SEQ-DAG: [[MEM_TY:%.+]] = type { [128 x i8] }
-// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = weak addrspace(3) global [[MEM_TY]] undef
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* undef
 // SEQ-DAG: [[KERNEL_SIZE:@.+]] = internal unnamed_addr constant i{{64|32}} 4
 // SEQ-DAG: [[KERNEL_SHARED:@.+]] = internal unnamed_addr constant i16 1
 
diff --git a/clang/test/OpenMP/nvptx_teams_codegen.cpp b/clang/test/OpenMP/nvptx_teams_codegen.cpp
--- a/clang/test/OpenMP/nvptx_teams_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_teams_codegen.cpp
@@ -30,8 +30,8 @@
 }
 
 // SEQ: [[MEM_TY:%.+]] = type { [128 x i8] }
-// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ-DAG: [[SHARED_GLOBAL_RD:@.+]] = weak addrspace(3) global [[MEM_TY]] undef
+// SEQ-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* undef
 // SEQ-DAG: [[KERNEL_SIZE1:@.+]] = internal unnamed_addr constant i{{64|32}} 4
 // SEQ-DAG: [[KERNEL_SIZE2:@.+]] = internal unnamed_addr constant i{{64|32}} {{8|4}}
 // SEQ-DAG: [[KERNEL_SHARED1:@.+]] = internal unnamed_addr constant i16 1
@@ -119,8 +119,8 @@
 }
 
 // SEQ2: [[MEM_TY:%.+]] = type { [128 x i8] }
-// SEQ2-DAG: [[SHARED_GLOBAL_RD:@.+]] = common addrspace(3) global [[MEM_TY]] zeroinitializer
-// SEQ2-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* null
+// SEQ2-DAG: [[SHARED_GLOBAL_RD:@.+]] = weak addrspace(3) global [[MEM_TY]] undef
+// SEQ2-DAG: [[KERNEL_PTR:@.+]] = internal addrspace(3) global i8* undef
 // SEQ2-DAG: [[KERNEL_SIZE1:@.+]] = internal unnamed_addr constant i{{64|32}} 4
 // SEQ2-DAG: [[KERNEL_SIZE2:@.+]] = internal unnamed_addr constant i{{64|32}} {{8|4}}
 // SEQ2-DAG: [[KERNEL_SHARED1:@.+]] = internal unnamed_addr constant i16 1
diff --git a/clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp b/clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
--- a/clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_teams_reduction_codegen.cpp
@@ -24,7 +24,7 @@
 // SEQ-DAG: [[KERNEL_SIZE2:@.+]] = internal unnamed_addr constant i{{64|32}} 16
 
 // Check for the data transfer medium in shared memory to transfer the reduction list to the first warp.
-// CHECK-DAG: [[TRANSFER_STORAGE:@.+]] = internal addrspace([[SHARED_ADDRSPACE:[0-9]+]]) global [32 x i32]
+// CHECK-DAG: [[TRANSFER_STORAGE:@.+]] = weak addrspace([[SHARED_ADDRSPACE:[0-9]+]]) global [32 x i32]
 
 // Check that the execution mode of 2 target regions is set to Non-SPMD and the 3rd is in SPMD.
 // CHECK-DAG: {{@__omp_offloading_.+l44}}_exec_mode = weak constant i8 1
@@ -220,7 +220,7 @@
   // CHECK: [[BASE_ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32*
   // CHECK: [[ELT:%.+]] = getelementptr i32, i32* [[BASE_ELT]], i32 [[CNT]]
   //
-  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[WARPID]]
+  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]]
   // CHECK: [[ELT_VAL:%.+]] = load i32, i32* [[ELT]],
   // CHECK: store volatile i32 [[ELT_VAL]], i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]],
   // CHECK: br label {{%?}}[[COPY_CONT:.+]]
@@ -238,7 +238,7 @@
   // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]]
   //
   // CHECK: [[DO_READ]]
-  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[TID]]
+  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]]
   // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [1 x i8*], [1 x i8*]* [[RED_LIST:%.+]], i{{32|64}} 0, i{{32|64}} 0
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
   // CHECK: [[ELT_BASE:%.+]] = bitcast i8* [[ELT_VOID]] to i32*
@@ -531,7 +531,7 @@
   // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[RED_LIST]], i{{32|64}} 0, i{{32|64}} 0
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
   //
-  // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[WARPID]]
+  // CHECK: [[MEDIUM_ELT64:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]]
   // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT64]] to i8 addrspace([[SHARED_ADDRSPACE]])*
   // CHECK: [[ELT_VAL:%.+]] = load i8, i8* [[ELT_VOID]], align
   // CHECK: store volatile i8 [[ELT_VAL]], i8 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align
@@ -550,7 +550,7 @@
   // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]]
   //
   // CHECK: [[DO_READ]]
-  // CHECK: [[MEDIUM_ELT32:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[TID]]
+  // CHECK: [[MEDIUM_ELT32:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]]
   // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT32]] to i8 addrspace([[SHARED_ADDRSPACE]])*
   // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[RED_LIST:%.+]], i{{32|64}} 0, i{{32|64}} 0
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
@@ -571,7 +571,7 @@
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
   // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32*
   //
-  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[WARPID]]
+  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]]
   // CHECK: [[ELT_VAL:%.+]] = load i32, i32* [[ELT]], align
   // CHECK: store volatile i32 [[ELT_VAL]], i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align
   // CHECK: br label {{%?}}[[COPY_CONT:.+]]
@@ -589,7 +589,7 @@
   // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]]
   //
   // CHECK: [[DO_READ]]
-  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[TID]]
+  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]]
   // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [2 x i8*], [2 x i8*]* [[RED_LIST:%.+]], i{{32|64}} 0, i{{32|64}} 1
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
   // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32*
@@ -982,7 +982,7 @@
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
   // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32*
   //
-  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[WARPID]]
+  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]]
   // CHECK: [[ELT_VAL:%.+]] = load i32, i32* [[ELT]], align
   // CHECK: store volatile i32 [[ELT_VAL]], i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align
   // CHECK: br label {{%?}}[[COPY_CONT:.+]]
@@ -1000,7 +1000,7 @@
   // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]]
   //
   // CHECK: [[DO_READ]]
-  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[TID]]
+  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]]
   // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 0
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
   // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32*
@@ -1021,7 +1021,7 @@
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
   // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i16*
   //
-  // CHECK: [[MEDIUM_ELT32:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[WARPID]]
+  // CHECK: [[MEDIUM_ELT32:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]]
   // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT32]] to i16 addrspace([[SHARED_ADDRSPACE]])*
   // CHECK: [[ELT_VAL:%.+]] = load i16, i16* [[ELT]], align
   // CHECK: store volatile i16 [[ELT_VAL]], i16 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align
@@ -1040,7 +1040,7 @@
   // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]]
   //
   // CHECK: [[DO_READ]]
-  // CHECK: [[MEDIUM_ELT32:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[TID]]
+  // CHECK: [[MEDIUM_ELT32:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]]
   // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT32]] to i16 addrspace([[SHARED_ADDRSPACE]])*
   // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i[[SZ]] 0, i[[SZ]] 1
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
@@ -1216,7 +1216,7 @@
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
   // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32*
   //
-  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[WARPID]]
+  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]]
   // CHECK: [[ELT_VAL:%.+]] = load i32, i32* [[ELT]], align
   // CHECK: store volatile i32 [[ELT_VAL]], i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align
   // CHECK: br label {{%?}}[[COPY_CONT:.+]]
@@ -1234,7 +1234,7 @@
   // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]]
   //
   // CHECK: [[DO_READ]]
-  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[TID]]
+  // CHECK: [[MEDIUM_ELT:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]]
   // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i{{32|64}} 0, i{{32|64}} 0
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
   // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i32*
@@ -1255,7 +1255,7 @@
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],
   // CHECK: [[ELT:%.+]] = bitcast i8* [[ELT_VOID]] to i16*
   //
-  // CHECK: [[MEDIUM_ELT32:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[WARPID]]
+  // CHECK: [[MEDIUM_ELT32:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[WARPID]]
   // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT32]] to i16 addrspace([[SHARED_ADDRSPACE]])*
   // CHECK: [[ELT_VAL:%.+]] = load i16, i16* [[ELT]], align
   // CHECK: store volatile i16 [[ELT_VAL]], i16 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT]], align
@@ -1274,7 +1274,7 @@
   // CHECK: br i1 [[IS_W0_ACTIVE_THREAD]], label {{%?}}[[DO_READ:.+]], label {{%?}}[[READ_ELSE:.+]]
   //
   // CHECK: [[DO_READ]]
-  // CHECK: [[MEDIUM_ELT32:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE:@.+]], i64 0, i32 [[TID]]
+  // CHECK: [[MEDIUM_ELT32:%.+]] = getelementptr inbounds [32 x i32], [32 x i32] addrspace([[SHARED_ADDRSPACE]])* [[TRANSFER_STORAGE]], i64 0, i32 [[TID]]
   // CHECK: [[MEDIUM_ELT:%.+]] = bitcast i32 addrspace([[SHARED_ADDRSPACE]])* [[MEDIUM_ELT32]] to i16 addrspace([[SHARED_ADDRSPACE]])*
   // CHECK: [[ELT_REF:%.+]] = getelementptr inbounds [[RLT]], [[RLT]]* [[RED_LIST:%.+]], i{{32|64}} 0, i{{32|64}} 1
   // CHECK: [[ELT_VOID:%.+]] = load i8*, i8** [[ELT_REF]],