Index: polly/trunk/lib/CodeGen/PPCGCodeGeneration.cpp
===================================================================
--- polly/trunk/lib/CodeGen/PPCGCodeGeneration.cpp
+++ polly/trunk/lib/CodeGen/PPCGCodeGeneration.cpp
@@ -1273,12 +1273,17 @@
 ///
 /// @param is64Bit Are we looking for a 64 bit architecture?
 static std::string computeNVPTXDataLayout(bool is64Bit) {
-  std::string Ret = "e";
+  std::string Ret = "";
 
-  if (!is64Bit)
-    Ret += "-p:32:32";
-
-  Ret += "-i64:64-v16:16-v32:32-n16:32:64";
+  if (!is64Bit) {
+    Ret += "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:"
+           "64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:"
+           "64-v128:128:128-n16:32:64";
+  } else {
+    Ret += "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:"
+           "64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:"
+           "64-v128:128:128-n16:32:64";
+  }
 
   return Ret;
 }
@@ -1298,7 +1303,8 @@
       const ScopArrayInfo *SAI = ScopArrayInfo::getFromId(Id);
       Args.push_back(SAI->getElementType());
     } else {
-      Args.push_back(Builder.getInt8PtrTy());
+      static const int UseGlobalMemory = 1;
+      Args.push_back(Builder.getInt8PtrTy(UseGlobalMemory));
     }
   }
 
Index: polly/trunk/test/GPGPU/cuda-annotations.ll
===================================================================
--- polly/trunk/test/GPGPU/cuda-annotations.ll
+++ polly/trunk/test/GPGPU/cuda-annotations.ll
@@ -4,11 +4,11 @@
 
 ; REQUIRES: pollyacc
 
-; KERNEL: define ptx_kernel void @kernel_0(i8* %MemRef_A, i64 %n) #0 {
+; KERNEL: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A, i64 %n) #0 {
 
 ; KERNEL: !nvvm.annotations = !{!0}
 
-; KERNEL: !0 = !{void (i8*, i64)* @kernel_0, !"maxntidx", i32 32, !"maxntidy", i32 1, !"maxntidz", i32 1}
+; KERNEL: !0 = !{void (i8 addrspace(1)*, i64)* @kernel_0, !"maxntidx", i32 32, !"maxntidy", i32 1, !"maxntidz", i32 1}
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
Index: polly/trunk/test/GPGPU/host-control-flow.ll
===================================================================
--- polly/trunk/test/GPGPU/host-control-flow.ll
+++ polly/trunk/test/GPGPU/host-control-flow.ll
@@ -42,7 +42,7 @@
 ; IR-NEXT:   %polly.loop_cond = icmp sle i64 %polly.indvar, 98
 ; IR-NEXT:   br i1 %polly.loop_cond, label %polly.loop_header, label %polly.loop_exit
 
-; KERNEL-IR: define ptx_kernel void @kernel_0(i8* %MemRef_A, i64 %c0)
+; KERNEL-IR: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A, i64 %c0)
 ; KERNEL-IR-LABEL: entry:
 ; KERNEL-IR-NEXT:   %0 = call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
 ; KERNEL-IR-NEXT:   %b0 = zext i32 %0 to i64
@@ -65,35 +65,35 @@
 ; KERNEL-IR-NEXT:   br label %polly.stmt.for.body3
 
 ; KERNEL-IR-LABEL: polly.stmt.for.body3:                             ; preds = %polly.then
-; KERNEL-IR-NEXT:   %polly.access.cast.MemRef_A = bitcast i8* %MemRef_A to float*
+; KERNEL-IR-NEXT:   %polly.access.cast.MemRef_A = bitcast i8 addrspace(1)* %MemRef_A to float addrspace(1)*
 ; KERNEL-IR-NEXT:   %pexp.pdiv_r = urem i64 %c0, 2
 ; KERNEL-IR-NEXT:   %polly.access.mul.MemRef_A = mul nsw i64 %pexp.pdiv_r, 100
 ; KERNEL-IR-NEXT:   %7 = mul nsw i64 32, %b0
 ; KERNEL-IR-NEXT:   %8 = add nsw i64 %7, %t0
 ; KERNEL-IR-NEXT:   %polly.access.add.MemRef_A = add nsw i64 %polly.access.mul.MemRef_A, %8
-; KERNEL-IR-NEXT:   %polly.access.MemRef_A = getelementptr float, float* %polly.access.cast.MemRef_A, i64 %polly.access.add.MemRef_A
-; KERNEL-IR-NEXT:   %tmp_p_scalar_ = load float, float* %polly.access.MemRef_A, align 4
-; KERNEL-IR-NEXT:   %polly.access.cast.MemRef_A1 = bitcast i8* %MemRef_A to float*
+; KERNEL-IR-NEXT:   %polly.access.MemRef_A = getelementptr float, float addrspace(1)* %polly.access.cast.MemRef_A, i64 %polly.access.add.MemRef_A
+; KERNEL-IR-NEXT:   %tmp_p_scalar_ = load float, float addrspace(1)* %polly.access.MemRef_A, align 4
+; KERNEL-IR-NEXT:   %polly.access.cast.MemRef_A1 = bitcast i8 addrspace(1)* %MemRef_A to float addrspace(1)*
 ; KERNEL-IR-NEXT:   %pexp.pdiv_r2 = urem i64 %c0, 2
 ; KERNEL-IR-NEXT:   %polly.access.mul.MemRef_A3 = mul nsw i64 %pexp.pdiv_r2, 100
 ; KERNEL-IR-NEXT:   %9 = mul nsw i64 32, %b0
 ; KERNEL-IR-NEXT:   %10 = add nsw i64 %9, %t0
 ; KERNEL-IR-NEXT:   %11 = add nsw i64 %10, 1
 ; KERNEL-IR-NEXT:   %polly.access.add.MemRef_A4 = add nsw i64 %polly.access.mul.MemRef_A3, %11
-; KERNEL-IR-NEXT:   %polly.access.MemRef_A5 = getelementptr float, float* %polly.access.cast.MemRef_A1, i64 %polly.access.add.MemRef_A4
-; KERNEL-IR-NEXT:   %tmp2_p_scalar_ = load float, float* %polly.access.MemRef_A5, align 4
+; KERNEL-IR-NEXT:   %polly.access.MemRef_A5 = getelementptr float, float addrspace(1)* %polly.access.cast.MemRef_A1, i64 %polly.access.add.MemRef_A4
+; KERNEL-IR-NEXT:   %tmp2_p_scalar_ = load float, float addrspace(1)* %polly.access.MemRef_A5, align 4
 ; KERNEL-IR-NEXT:   %p_add = fadd float %tmp_p_scalar_, %tmp2_p_scalar_
-; KERNEL-IR-NEXT:   %polly.access.cast.MemRef_A6 = bitcast i8* %MemRef_A to float*
+; KERNEL-IR-NEXT:   %polly.access.cast.MemRef_A6 = bitcast i8 addrspace(1)* %MemRef_A to float addrspace(1)*
 ; KERNEL-IR-NEXT:   %pexp.pdiv_r7 = urem i64 %c0, 2
 ; KERNEL-IR-NEXT:   %polly.access.mul.MemRef_A8 = mul nsw i64 %pexp.pdiv_r7, 100
 ; KERNEL-IR-NEXT:   %12 = mul nsw i64 32, %b0
 ; KERNEL-IR-NEXT:   %13 = add nsw i64 %12, %t0
 ; KERNEL-IR-NEXT:   %14 = add nsw i64 %13, 2
 ; KERNEL-IR-NEXT:   %polly.access.add.MemRef_A9 = add nsw i64 %polly.access.mul.MemRef_A8, %14
-; KERNEL-IR-NEXT:   %polly.access.MemRef_A10 = getelementptr float, float* %polly.access.cast.MemRef_A6, i64 %polly.access.add.MemRef_A9
-; KERNEL-IR-NEXT:   %tmp3_p_scalar_ = load float, float* %polly.access.MemRef_A10, align 4
+; KERNEL-IR-NEXT:   %polly.access.MemRef_A10 = getelementptr float, float addrspace(1)* %polly.access.cast.MemRef_A6, i64 %polly.access.add.MemRef_A9
+; KERNEL-IR-NEXT:   %tmp3_p_scalar_ = load float, float addrspace(1)* %polly.access.MemRef_A10, align 4
 ; KERNEL-IR-NEXT:   %p_add12 = fadd float %p_add, %tmp3_p_scalar_
-; KERNEL-IR-NEXT:   %polly.access.cast.MemRef_A11 = bitcast i8* %MemRef_A to float*
+; KERNEL-IR-NEXT:   %polly.access.cast.MemRef_A11 = bitcast i8 addrspace(1)* %MemRef_A to float addrspace(1)*
 ; KERNEL-IR-NEXT:   %15 = add nsw i64 %c0, 1
 ; KERNEL-IR-NEXT:   %pexp.pdiv_r12 = urem i64 %15, 2
 ; KERNEL-IR-NEXT:   %polly.access.mul.MemRef_A13 = mul nsw i64 %pexp.pdiv_r12, 100
@@ -101,10 +101,10 @@
 ; KERNEL-IR-NEXT:   %17 = add nsw i64 %16, %t0
 ; KERNEL-IR-NEXT:   %18 = add nsw i64 %17, 1
 ; KERNEL-IR-NEXT:   %polly.access.add.MemRef_A14 = add nsw i64 %polly.access.mul.MemRef_A13, %18
-; KERNEL-IR-NEXT:   %polly.access.MemRef_A15 = getelementptr float, float* %polly.access.cast.MemRef_A11, i64 %polly.access.add.MemRef_A14
-; KERNEL-IR-NEXT:   %tmp4_p_scalar_ = load float, float* %polly.access.MemRef_A15, align 4
+; KERNEL-IR-NEXT:   %polly.access.MemRef_A15 = getelementptr float, float addrspace(1)* %polly.access.cast.MemRef_A11, i64 %polly.access.add.MemRef_A14
+; KERNEL-IR-NEXT:   %tmp4_p_scalar_ = load float, float addrspace(1)* %polly.access.MemRef_A15, align 4
 ; KERNEL-IR-NEXT:   %p_add17 = fadd float %tmp4_p_scalar_, %p_add12
-; KERNEL-IR-NEXT:   %polly.access.cast.MemRef_A16 = bitcast i8* %MemRef_A to float*
+; KERNEL-IR-NEXT:   %polly.access.cast.MemRef_A16 = bitcast i8 addrspace(1)* %MemRef_A to float addrspace(1)*
 ; KERNEL-IR-NEXT:   %19 = add nsw i64 %c0, 1
 ; KERNEL-IR-NEXT:   %pexp.pdiv_r17 = urem i64 %19, 2
 ; KERNEL-IR-NEXT:   %polly.access.mul.MemRef_A18 = mul nsw i64 %pexp.pdiv_r17, 100
@@ -112,8 +112,8 @@
 ; KERNEL-IR-NEXT:   %21 = add nsw i64 %20, %t0
 ; KERNEL-IR-NEXT:   %22 = add nsw i64 %21, 1
 ; KERNEL-IR-NEXT:   %polly.access.add.MemRef_A19 = add nsw i64 %polly.access.mul.MemRef_A18, %22
-; KERNEL-IR-NEXT:   %polly.access.MemRef_A20 = getelementptr float, float* %polly.access.cast.MemRef_A16, i64 %polly.access.add.MemRef_A19
-; KERNEL-IR-NEXT:   store float %p_add17, float* %polly.access.MemRef_A20, align 4
+; KERNEL-IR-NEXT:   %polly.access.MemRef_A20 = getelementptr float, float addrspace(1)* %polly.access.cast.MemRef_A16, i64 %polly.access.add.MemRef_A19
+; KERNEL-IR-NEXT:   store float %p_add17, float addrspace(1)* %polly.access.MemRef_A20, align 4
 ; KERNEL-IR-NEXT:   br label %polly.merge
 
 ; KERNEL-IR-LABEL: polly.else:                                       ; preds = %polly.cond
Index: polly/trunk/test/GPGPU/kernel-params-only-some-arrays.ll
===================================================================
--- polly/trunk/test/GPGPU/kernel-params-only-some-arrays.ll
+++ polly/trunk/test/GPGPU/kernel-params-only-some-arrays.ll
@@ -18,10 +18,10 @@
 
 ; KERNEL: ; ModuleID = 'kernel_0'
 ; KERNEL-NEXT: source_filename = "kernel_0"
-; KERNEL-NEXT: target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
+; KERNEL-NEXT: target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
 ; KERNEL-NEXT: target triple = "nvptx64-nvidia-cuda"
 
-; KERNEL: define ptx_kernel void @kernel_0(i8* %MemRef_A)
+; KERNEL: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A)
 ; KERNEL-NEXT:   entry:
 ; KERNEL-NEXT:     %0 = call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
 ; KERNEL-NEXT:     %b0 = zext i32 %0 to i64
@@ -33,10 +33,10 @@
 
 ; KERNEL: ; ModuleID = 'kernel_1'
 ; KERNEL-NEXT: source_filename = "kernel_1"
-; KERNEL-NEXT: target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
+; KERNEL-NEXT: target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
 ; KERNEL-NEXT: target triple = "nvptx64-nvidia-cuda"
 
-; KERNEL: define ptx_kernel void @kernel_1(i8* %MemRef_B)
+; KERNEL: define ptx_kernel void @kernel_1(i8 addrspace(1)* %MemRef_B)
 ; KERNEL-NEXT:   entry:
 ; KERNEL-NEXT:     %0 = call i32 @llvm.nvvm.read.ptx.sreg.ctaid.x()
 ; KERNEL-NEXT:     %b0 = zext i32 %0 to i64
Index: polly/trunk/test/GPGPU/kernel-params-scop-parameter.ll
===================================================================
--- polly/trunk/test/GPGPU/kernel-params-scop-parameter.ll
+++ polly/trunk/test/GPGPU/kernel-params-scop-parameter.ll
@@ -9,7 +9,7 @@
 ;        A[i] += 42;
 ;    }
 
-; KERNEL-IR: define ptx_kernel void @kernel_0(i8* %MemRef_A, i64 %n)
+; KERNEL-IR: define ptx_kernel void @kernel_0(i8 addrspace(1)* %MemRef_A, i64 %n)
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
Index: polly/trunk/test/GPGPU/non-read-only-scalars.ll
===================================================================
--- polly/trunk/test/GPGPU/non-read-only-scalars.ll
+++ polly/trunk/test/GPGPU/non-read-only-scalars.ll
@@ -87,10 +87,10 @@
 ; CODE-NEXT: Stmt_bb20(c0);
 
 ; KERNEL-IR:       store float %p_tmp23, float* %sum.0.phiops
-; KERNEL-IR-NEXT:  [[REGA:%.+]] = bitcast i8* %MemRef_sum_0__phi to float*
+; KERNEL-IR-NEXT:  [[REGA:%.+]] = addrspacecast i8 addrspace(1)* %MemRef_sum_0__phi to float*
 ; KERNEL-IR-NEXT:  [[REGB:%.+]] = load float, float* %sum.0.phiops
 ; KERNEL-IR-NEXT:  store float [[REGB]], float* [[REGA]]
-; KERNEL-IR-NEXT:  [[REGC:%.+]] = bitcast i8* %MemRef_sum_0 to float*
+; KERNEL-IR-NEXT:  [[REGC:%.+]] = addrspacecast i8 addrspace(1)* %MemRef_sum_0 to float*
 ; KERNEL-IR-NEXT:  [[REGD:%.+]] = load float, float* %sum.0.s2a
 ; KERNEL-IR-NEXT:  store float [[REGD]], float* [[REGC]]
 ; KERNEL-IR-NEXT:  ret void
Index: polly/trunk/test/GPGPU/phi-nodes-in-kernel.ll
===================================================================
--- polly/trunk/test/GPGPU/phi-nodes-in-kernel.ll
+++ polly/trunk/test/GPGPU/phi-nodes-in-kernel.ll
@@ -49,10 +49,10 @@
 ; KERNEL-IR: entry:
 ; KERNEL-IR-NEXT:   %out_l.055.s2a = alloca i32
 ; KERNEL-IR-NEXT:   %out_l.055.phiops = alloca i32
-; KERNEL-IR-NEXT:   %1 = bitcast i8* %MemRef_out_l_055__phi to i32*
+; KERNEL-IR-NEXT:   %1 = addrspacecast i8 addrspace(1)* %MemRef_out_l_055__phi to i32*
 ; KERNEL-IR-NEXT:   %2 = load i32, i32* %1
 ; KERNEL-IR-NEXT:   store i32 %2, i32* %out_l.055.phiops
-; KERNEL-IR-NEXT:   %3 = bitcast i8* %MemRef_out_l_055 to i32*
+; KERNEL-IR-NEXT:   %3 = addrspacecast i8 addrspace(1)* %MemRef_out_l_055 to i32*
 ; KERNEL-IR-NEXT:   %4 = load i32, i32* %3
 ; KERNEL-IR-NEXT:   store i32 %4, i32* %out_l.055.s2a
 
Index: polly/trunk/test/GPGPU/private-memory.ll
===================================================================
--- polly/trunk/test/GPGPU/private-memory.ll
+++ polly/trunk/test/GPGPU/private-memory.ll
@@ -28,17 +28,17 @@
 
 ; KERNEL:   %polly.access.cast.private_array = bitcast [1 x float]* %private_array to float*
 ; KERNEL-NEXT:   %polly.access.private_array = getelementptr float, float* %polly.access.cast.private_array, i64 0
-; KERNEL-NEXT:   %polly.access.cast.MemRef_A = bitcast i8* %MemRef_A to float*
-; KERNEL-NEXT:   %polly.access.MemRef_A = getelementptr float, float* %polly.access.cast.MemRef_A, i64 %t0
-; KERNEL-NEXT:   %shared.read = load float, float* %polly.access.MemRef_A
+; KERNEL-NEXT:   %polly.access.cast.MemRef_A = bitcast i8 addrspace(1)* %MemRef_A to float addrspace(1)*
+; KERNEL-NEXT:   %polly.access.MemRef_A = getelementptr float, float addrspace(1)* %polly.access.cast.MemRef_A, i64 %t0
+; KERNEL-NEXT:   %shared.read = load float, float addrspace(1)* %polly.access.MemRef_A
 ; KERNEL-NEXT:   store float %shared.read, float* %polly.access.private_array
 
 ; KERNEL:   %polly.access.cast.private_array5 = bitcast [1 x float]* %private_array to float*
 ; KERNEL-NEXT:   %polly.access.private_array6 = getelementptr float, float* %polly.access.cast.private_array5, i64 0
-; KERNEL-NEXT:   %polly.access.cast.MemRef_A7 = bitcast i8* %MemRef_A to float*
-; KERNEL-NEXT:   %polly.access.MemRef_A8 = getelementptr float, float* %polly.access.cast.MemRef_A7, i64 %t0
+; KERNEL-NEXT:   %polly.access.cast.MemRef_A7 = bitcast i8 addrspace(1)* %MemRef_A to float addrspace(1)*
+; KERNEL-NEXT:   %polly.access.MemRef_A8 = getelementptr float, float addrspace(1)* %polly.access.cast.MemRef_A7, i64 %t0
 ; KERNEL-NEXT:   %shared.write = load float, float* %polly.access.private_array6
-; KERNEL-NEXT:   store float %shared.write, float* %polly.access.MemRef_A8
+; KERNEL-NEXT:   store float %shared.write, float addrspace(1)* %polly.access.MemRef_A8
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 
Index: polly/trunk/test/GPGPU/remove-dead-instructions-in-stmt-2.ll
===================================================================
--- polly/trunk/test/GPGPU/remove-dead-instructions-in-stmt-2.ll
+++ polly/trunk/test/GPGPU/remove-dead-instructions-in-stmt-2.ll
@@ -7,7 +7,7 @@
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 
-; KERNEL-IR: store i32 0, i32* %polly.access.MemRef_sum_c, align 4
+; KERNEL-IR: store i32 0, i32 addrspace(1)* %polly.access.MemRef_sum_c, align 4
 ; KERNEL-IR-NEXT: br label %polly.merge
 
 define void @kernel_dynprog([50 x [50 x i32]]* %sum_c) {
Index: polly/trunk/test/GPGPU/remove-dead-instructions-in-stmt.ll
===================================================================
--- polly/trunk/test/GPGPU/remove-dead-instructions-in-stmt.ll
+++ polly/trunk/test/GPGPU/remove-dead-instructions-in-stmt.ll
@@ -10,7 +10,7 @@
 ; condition. This code referred to CPU registers and consequently resulted
 ; in invalid bitcode.
 
-; KERNEL-IR: store i32 0, i32* %polly.access.MemRef_sum_c, align 4
+; KERNEL-IR: store i32 0, i32 addrspace(1)* %polly.access.MemRef_sum_c, align 4
 ; KERNEL-IR-NEXT: br label %polly.merge
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
Index: polly/trunk/test/GPGPU/shared-memory-two-dimensional.ll
===================================================================
--- polly/trunk/test/GPGPU/shared-memory-two-dimensional.ll
+++ polly/trunk/test/GPGPU/shared-memory-two-dimensional.ll
@@ -36,8 +36,8 @@
 
 ; KERNEL:        %polly.access.mul.MemRef_b = mul nsw i64 %polly.indvar, 8
 ; KERNEL-NEXT:   %polly.access.add.MemRef_b = add nsw i64 %polly.access.mul.MemRef_b, %t0
-; KERNEL-NEXT:   %polly.access.MemRef_b = getelementptr float, float* %polly.access.cast.MemRef_b, i64 %polly.access.add.MemRef_b
-; KERNEL-NEXT:   %shared.read = load float, float* %polly.access.MemRef_b
+; KERNEL-NEXT:   %polly.access.MemRef_b = getelementptr float, float addrspace(1)* %polly.access.cast.MemRef_b, i64 %polly.access.add.MemRef_b
+; KERNEL-NEXT:   %shared.read = load float, float addrspace(1)* %polly.access.MemRef_b
 ; KERNEL-NEXT:   store float %shared.read, float addrspace(3)* %polly.access.shared_MemRef_b
 
 
Index: polly/trunk/test/GPGPU/shared-memory.ll
===================================================================
--- polly/trunk/test/GPGPU/shared-memory.ll
+++ polly/trunk/test/GPGPU/shared-memory.ll
@@ -29,16 +29,16 @@
 ; KERNEL: @shared_MemRef_A = internal addrspace(3) global [32 x float] zeroinitializer, align 4
 
 ; KERNEL:   %polly.access.shared_MemRef_A = getelementptr float, float addrspace(3)* getelementptr inbounds ([32 x float], [32 x float] addrspace(3)* @shared_MemRef_A, i32 0, i32 0), i64 %t0
-; KERNEL-NEXT:   %polly.access.cast.MemRef_A = bitcast i8* %MemRef_A to float*
-; KERNEL-NEXT:   %polly.access.MemRef_A = getelementptr float, float* %polly.access.cast.MemRef_A, i64 %t0
-; KERNEL-NEXT:   %shared.read = load float, float* %polly.access.MemRef_A
+; KERNEL-NEXT:   %polly.access.cast.MemRef_A = bitcast i8 addrspace(1)* %MemRef_A to float addrspace(1)*
+; KERNEL-NEXT:   %polly.access.MemRef_A = getelementptr float, float addrspace(1)* %polly.access.cast.MemRef_A, i64 %t0
+; KERNEL-NEXT:   %shared.read = load float, float addrspace(1)* %polly.access.MemRef_A
 ; KERNEL-NEXT:   store float %shared.read, float addrspace(3)* %polly.access.shared_MemRef_A
 
 ; KERNEL:   %polly.access.shared_MemRef_A3 = getelementptr float, float addrspace(3)* getelementptr inbounds ([32 x float], [32 x float] addrspace(3)* @shared_MemRef_A, i32 0, i32 0), i64 %t0
-; KERNEL-NEXT:   %polly.access.cast.MemRef_A4 = bitcast i8* %MemRef_A to float*
-; KERNEL-NEXT:   %polly.access.MemRef_A5 = getelementptr float, float* %polly.access.cast.MemRef_A4, i64 %t0
+; KERNEL-NEXT:   %polly.access.cast.MemRef_A4 = bitcast i8 addrspace(1)* %MemRef_A to float addrspace(1)*
+; KERNEL-NEXT:   %polly.access.MemRef_A5 = getelementptr float, float addrspace(1)* %polly.access.cast.MemRef_A4, i64 %t0
 ; KERNEL-NEXT:   %shared.write = load float, float addrspace(3)* %polly.access.shared_MemRef_A3
-; KERNEL-NEXT:   store float %shared.write, float* %polly.access.MemRef_A5
+; KERNEL-NEXT:   store float %shared.write, float addrspace(1)* %polly.access.MemRef_A5
 
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"