Index: lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
===================================================================
--- lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -248,6 +248,10 @@
 static StringRef computeDataLayout(const Triple &TT) {
   if (TT.getArch() == Triple::r600) {
     // 32-bit pointers.
+    if (TT.getEnvironmentName() == "amdgiz" ||
+        TT.getEnvironmentName() == "amdgizcl")
+      return "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128"
+             "-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5";
     return "e-p:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128"
             "-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64";
   }
Index: test/CodeGen/AMDGPU/private-memory-r600.ll
===================================================================
--- test/CodeGen/AMDGPU/private-memory-r600.ll
+++ test/CodeGen/AMDGPU/private-memory-r600.ll
@@ -1,5 +1,6 @@
-; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck %s -check-prefix=R600 -check-prefix=FUNC
-; RUN: opt -S -mtriple=r600-unknown-unknown -mcpu=redwood -amdgpu-promote-alloca < %s | FileCheck -check-prefix=OPT %s
+; RUN: llc -march=r600 -mtriple=r600---amdgiz -mcpu=redwood < %s | FileCheck %s -check-prefix=R600 -check-prefix=FUNC
+; RUN: opt -S -mtriple=r600-unknown-unknown-amdgiz -mcpu=redwood -amdgpu-promote-alloca < %s | FileCheck -check-prefix=OPT %s
+target datalayout = "A5"
 
 declare i32 @llvm.r600.read.tidig.x() nounwind readnone
 
@@ -18,19 +19,19 @@
 
 define amdgpu_kernel void @mova_same_clause(i32 addrspace(1)* nocapture %out, i32 addrspace(1)* nocapture %in) #0 {
 entry:
-  %stack = alloca [5 x i32], align 4
+  %stack = alloca [5 x i32], align 4, addrspace(5)
   %0 = load i32, i32 addrspace(1)* %in, align 4
-  %arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %0
-  store i32 4, i32* %arrayidx1, align 4
+  %arrayidx1 = getelementptr inbounds [5 x i32], [5 x i32] addrspace(5)* %stack, i32 0, i32 %0
+  store i32 4, i32 addrspace(5)* %arrayidx1, align 4
   %arrayidx2 = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
   %1 = load i32, i32 addrspace(1)* %arrayidx2, align 4
-  %arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 %1
-  store i32 5, i32* %arrayidx3, align 4
-  %arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 0
-  %2 = load i32, i32* %arrayidx10, align 4
+  %arrayidx3 = getelementptr inbounds [5 x i32], [5 x i32] addrspace(5)* %stack, i32 0, i32 %1
+  store i32 5, i32 addrspace(5)* %arrayidx3, align 4
+  %arrayidx10 = getelementptr inbounds [5 x i32], [5 x i32] addrspace(5)* %stack, i32 0, i32 0
+  %2 = load i32, i32 addrspace(5)* %arrayidx10, align 4
   store i32 %2, i32 addrspace(1)* %out, align 4
-  %arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32]* %stack, i32 0, i32 1
-  %3 = load i32, i32* %arrayidx12
+  %arrayidx12 = getelementptr inbounds [5 x i32], [5 x i32] addrspace(5)* %stack, i32 0, i32 1
+  %3 = load i32, i32 addrspace(5)* %arrayidx12
   %arrayidx13 = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 1
   store i32 %3, i32 addrspace(1)* %arrayidx13
   ret void
@@ -49,20 +50,20 @@
 
 define amdgpu_kernel void @multiple_structs(i32 addrspace(1)* %out) #0 {
 entry:
-  %a = alloca %struct.point
-  %b = alloca %struct.point
-  %a.x.ptr = getelementptr inbounds %struct.point, %struct.point* %a, i32 0, i32 0
-  %a.y.ptr = getelementptr inbounds %struct.point, %struct.point* %a, i32 0, i32 1
-  %b.x.ptr = getelementptr inbounds %struct.point, %struct.point* %b, i32 0, i32 0
-  %b.y.ptr = getelementptr inbounds %struct.point, %struct.point* %b, i32 0, i32 1
-  store i32 0, i32* %a.x.ptr
-  store i32 1, i32* %a.y.ptr
-  store i32 2, i32* %b.x.ptr
-  store i32 3, i32* %b.y.ptr
-  %a.indirect.ptr = getelementptr inbounds %struct.point, %struct.point* %a, i32 0, i32 0
-  %b.indirect.ptr = getelementptr inbounds %struct.point, %struct.point* %b, i32 0, i32 0
-  %a.indirect = load i32, i32* %a.indirect.ptr
-  %b.indirect = load i32, i32* %b.indirect.ptr
+  %a = alloca %struct.point, addrspace(5)
+  %b = alloca %struct.point, addrspace(5)
+  %a.x.ptr = getelementptr inbounds %struct.point, %struct.point addrspace(5)* %a, i32 0, i32 0
+  %a.y.ptr = getelementptr inbounds %struct.point, %struct.point addrspace(5)* %a, i32 0, i32 1
+  %b.x.ptr = getelementptr inbounds %struct.point, %struct.point addrspace(5)* %b, i32 0, i32 0
+  %b.y.ptr = getelementptr inbounds %struct.point, %struct.point addrspace(5)* %b, i32 0, i32 1
+  store i32 0, i32 addrspace(5)* %a.x.ptr
+  store i32 1, i32 addrspace(5)* %a.y.ptr
+  store i32 2, i32 addrspace(5)* %b.x.ptr
+  store i32 3, i32 addrspace(5)* %b.y.ptr
+  %a.indirect.ptr = getelementptr inbounds %struct.point, %struct.point addrspace(5)* %a, i32 0, i32 0
+  %b.indirect.ptr = getelementptr inbounds %struct.point, %struct.point addrspace(5)* %b, i32 0, i32 0
+  %a.indirect = load i32, i32 addrspace(5)* %a.indirect.ptr
+  %b.indirect = load i32, i32 addrspace(5)* %b.indirect.ptr
   %0 = add i32 %a.indirect, %b.indirect
   store i32 %0, i32 addrspace(1)* %out
   ret void
@@ -77,32 +78,32 @@
 
 define amdgpu_kernel void @direct_loop(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
 entry:
-  %prv_array_const = alloca [2 x i32]
-  %prv_array = alloca [2 x i32]
+  %prv_array_const = alloca [2 x i32], addrspace(5)
+  %prv_array = alloca [2 x i32], addrspace(5)
   %a = load i32, i32 addrspace(1)* %in
   %b_src_ptr = getelementptr inbounds i32, i32 addrspace(1)* %in, i32 1
   %b = load i32, i32 addrspace(1)* %b_src_ptr
-  %a_dst_ptr = getelementptr inbounds [2 x i32], [2 x i32]* %prv_array_const, i32 0, i32 0
-  store i32 %a, i32* %a_dst_ptr
-  %b_dst_ptr = getelementptr inbounds [2 x i32], [2 x i32]* %prv_array_const, i32 0, i32 1
-  store i32 %b, i32* %b_dst_ptr
+  %a_dst_ptr = getelementptr inbounds [2 x i32], [2 x i32] addrspace(5)* %prv_array_const, i32 0, i32 0
+  store i32 %a, i32 addrspace(5)* %a_dst_ptr
+  %b_dst_ptr = getelementptr inbounds [2 x i32], [2 x i32] addrspace(5)* %prv_array_const, i32 0, i32 1
+  store i32 %b, i32 addrspace(5)* %b_dst_ptr
   br label %for.body
 
 for.body:
   %inc = phi i32 [0, %entry], [%count, %for.body]
-  %x_ptr = getelementptr inbounds [2 x i32], [2 x i32]* %prv_array_const, i32 0, i32 0
-  %x = load i32, i32* %x_ptr
-  %y_ptr = getelementptr inbounds [2 x i32], [2 x i32]* %prv_array, i32 0, i32 0
-  %y = load i32, i32* %y_ptr
+  %x_ptr = getelementptr inbounds [2 x i32], [2 x i32] addrspace(5)* %prv_array_const, i32 0, i32 0
+  %x = load i32, i32 addrspace(5)* %x_ptr
+  %y_ptr = getelementptr inbounds [2 x i32], [2 x i32] addrspace(5)* %prv_array, i32 0, i32 0
+  %y = load i32, i32 addrspace(5)* %y_ptr
   %xy = add i32 %x, %y
-  store i32 %xy, i32* %y_ptr
+  store i32 %xy, i32 addrspace(5)* %y_ptr
   %count = add i32 %inc, 1
   %done = icmp eq i32 %count, 4095
   br i1 %done, label %for.end, label %for.body
 
 for.end:
-  %value_ptr = getelementptr inbounds [2 x i32], [2 x i32]* %prv_array, i32 0, i32 0
-  %value = load i32, i32* %value_ptr
+  %value_ptr = getelementptr inbounds [2 x i32], [2 x i32] addrspace(5)* %prv_array, i32 0, i32 0
+  %value = load i32, i32 addrspace(5)* %value_ptr
   store i32 %value, i32 addrspace(1)* %out
   ret void
 }
@@ -112,13 +113,13 @@
 ; R600: MOVA_INT
 define amdgpu_kernel void @short_array(i32 addrspace(1)* %out, i32 %index) #0 {
 entry:
-  %0 = alloca [2 x i16]
-  %1 = getelementptr inbounds [2 x i16], [2 x i16]* %0, i32 0, i32 0
-  %2 = getelementptr inbounds [2 x i16], [2 x i16]* %0, i32 0, i32 1
-  store i16 0, i16* %1
-  store i16 1, i16* %2
-  %3 = getelementptr inbounds [2 x i16], [2 x i16]* %0, i32 0, i32 %index
-  %4 = load i16, i16* %3
+  %0 = alloca [2 x i16], addrspace(5)
+  %1 = getelementptr inbounds [2 x i16], [2 x i16] addrspace(5)* %0, i32 0, i32 0
+  %2 = getelementptr inbounds [2 x i16], [2 x i16] addrspace(5)* %0, i32 0, i32 1
+  store i16 0, i16 addrspace(5)* %1
+  store i16 1, i16 addrspace(5)* %2
+  %3 = getelementptr inbounds [2 x i16], [2 x i16] addrspace(5)* %0, i32 0, i32 %index
+  %4 = load i16, i16 addrspace(5)* %3
   %5 = sext i16 %4 to i32
   store i32 %5, i32 addrspace(1)* %out
   ret void
@@ -129,13 +130,13 @@
 ; R600: MOVA_INT
 define amdgpu_kernel void @char_array(i32 addrspace(1)* %out, i32 %index) #0 {
 entry:
-  %0 = alloca [2 x i8]
-  %1 = getelementptr inbounds [2 x i8], [2 x i8]* %0, i32 0, i32 0
-  %2 = getelementptr inbounds [2 x i8], [2 x i8]* %0, i32 0, i32 1
-  store i8 0, i8* %1
-  store i8 1, i8* %2
-  %3 = getelementptr inbounds [2 x i8], [2 x i8]* %0, i32 0, i32 %index
-  %4 = load i8, i8* %3
+  %0 = alloca [2 x i8], addrspace(5)
+  %1 = getelementptr inbounds [2 x i8], [2 x i8] addrspace(5)* %0, i32 0, i32 0
+  %2 = getelementptr inbounds [2 x i8], [2 x i8] addrspace(5)* %0, i32 0, i32 1
+  store i8 0, i8 addrspace(5)* %1
+  store i8 1, i8 addrspace(5)* %2
+  %3 = getelementptr inbounds [2 x i8], [2 x i8] addrspace(5)* %0, i32 0, i32 %index
+  %4 = load i8, i8 addrspace(5)* %3
   %5 = sext i8 %4 to i32
   store i32 %5, i32 addrspace(1)* %out
   ret void
@@ -150,13 +151,13 @@
 ; R600-NOT: MOV * TO.X
 define amdgpu_kernel void @work_item_info(i32 addrspace(1)* %out, i32 %in) #0 {
 entry:
-  %0 = alloca [2 x i32]
-  %1 = getelementptr inbounds [2 x i32], [2 x i32]* %0, i32 0, i32 0
-  %2 = getelementptr inbounds [2 x i32], [2 x i32]* %0, i32 0, i32 1
-  store i32 0, i32* %1
-  store i32 1, i32* %2
-  %3 = getelementptr inbounds [2 x i32], [2 x i32]* %0, i32 0, i32 %in
-  %4 = load i32, i32* %3
+  %0 = alloca [2 x i32], addrspace(5)
+  %1 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(5)* %0, i32 0, i32 0
+  %2 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(5)* %0, i32 0, i32 1
+  store i32 0, i32 addrspace(5)* %1
+  store i32 1, i32 addrspace(5)* %2
+  %3 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(5)* %0, i32 0, i32 %in
+  %4 = load i32, i32 addrspace(5)* %3
   %5 = call i32 @llvm.r600.read.tidig.x()
   %6 = add i32 %4, %5
   store i32 %6, i32 addrspace(1)* %out
@@ -171,22 +172,22 @@
 ; R600-NOT: [[CHAN]]+
 define amdgpu_kernel void @no_overlap(i32 addrspace(1)* %out, i32 %in) #0 {
 entry:
-  %0 = alloca [3 x i8], align 1
-  %1 = alloca [2 x i8], align 1
-  %2 = getelementptr inbounds [3 x i8], [3 x i8]* %0, i32 0, i32 0
-  %3 = getelementptr inbounds [3 x i8], [3 x i8]* %0, i32 0, i32 1
-  %4 = getelementptr inbounds [3 x i8], [3 x i8]* %0, i32 0, i32 2
-  %5 = getelementptr inbounds [2 x i8], [2 x i8]* %1, i32 0, i32 0
-  %6 = getelementptr inbounds [2 x i8], [2 x i8]* %1, i32 0, i32 1
-  store i8 0, i8* %2
-  store i8 1, i8* %3
-  store i8 2, i8* %4
-  store i8 1, i8* %5
-  store i8 0, i8* %6
-  %7 = getelementptr inbounds [3 x i8], [3 x i8]* %0, i32 0, i32 %in
-  %8 = getelementptr inbounds [2 x i8], [2 x i8]* %1, i32 0, i32 %in
-  %9 = load i8, i8* %7
-  %10 = load i8, i8* %8
+  %0 = alloca [3 x i8], align 1, addrspace(5)
+  %1 = alloca [2 x i8], align 1, addrspace(5)
+  %2 = getelementptr inbounds [3 x i8], [3 x i8] addrspace(5)* %0, i32 0, i32 0
+  %3 = getelementptr inbounds [3 x i8], [3 x i8] addrspace(5)* %0, i32 0, i32 1
+  %4 = getelementptr inbounds [3 x i8], [3 x i8] addrspace(5)* %0, i32 0, i32 2
+  %5 = getelementptr inbounds [2 x i8], [2 x i8] addrspace(5)* %1, i32 0, i32 0
+  %6 = getelementptr inbounds [2 x i8], [2 x i8] addrspace(5)* %1, i32 0, i32 1
+  store i8 0, i8 addrspace(5)* %2
+  store i8 1, i8 addrspace(5)* %3
+  store i8 2, i8 addrspace(5)* %4
+  store i8 1, i8 addrspace(5)* %5
+  store i8 0, i8 addrspace(5)* %6
+  %7 = getelementptr inbounds [3 x i8], [3 x i8] addrspace(5)* %0, i32 0, i32 %in
+  %8 = getelementptr inbounds [2 x i8], [2 x i8] addrspace(5)* %1, i32 0, i32 %in
+  %9 = load i8, i8 addrspace(5)* %7
+  %10 = load i8, i8 addrspace(5)* %8
   %11 = add i8 %9, %10
   %12 = sext i8 %11 to i32
   store i32 %12, i32 addrspace(1)* %out
@@ -195,13 +196,13 @@
 
 define amdgpu_kernel void @char_array_array(i32 addrspace(1)* %out, i32 %index) #0 {
 entry:
-  %alloca = alloca [2 x [2 x i8]]
-  %gep0 = getelementptr inbounds [2 x [2 x i8]], [2 x [2 x i8]]* %alloca, i32 0, i32 0, i32 0
-  %gep1 = getelementptr inbounds [2 x [2 x i8]], [2 x [2 x i8]]* %alloca, i32 0, i32 0, i32 1
-  store i8 0, i8* %gep0
-  store i8 1, i8* %gep1
-  %gep2 = getelementptr inbounds [2 x [2 x i8]], [2 x [2 x i8]]* %alloca, i32 0, i32 0, i32 %index
-  %load = load i8, i8* %gep2
+  %alloca = alloca [2 x [2 x i8]], addrspace(5)
+  %gep0 = getelementptr inbounds [2 x [2 x i8]], [2 x [2 x i8]] addrspace(5)* %alloca, i32 0, i32 0, i32 0
+  %gep1 = getelementptr inbounds [2 x [2 x i8]], [2 x [2 x i8]] addrspace(5)* %alloca, i32 0, i32 0, i32 1
+  store i8 0, i8 addrspace(5)* %gep0
+  store i8 1, i8 addrspace(5)* %gep1
+  %gep2 = getelementptr inbounds [2 x [2 x i8]], [2 x [2 x i8]] addrspace(5)* %alloca, i32 0, i32 0, i32 %index
+  %load = load i8, i8 addrspace(5)* %gep2
   %sext = sext i8 %load to i32
   store i32 %sext, i32 addrspace(1)* %out
   ret void
@@ -209,26 +210,26 @@
 
 define amdgpu_kernel void @i32_array_array(i32 addrspace(1)* %out, i32 %index) #0 {
 entry:
-  %alloca = alloca [2 x [2 x i32]]
-  %gep0 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 0
-  %gep1 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 1
-  store i32 0, i32* %gep0
-  store i32 1, i32* %gep1
-  %gep2 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]]* %alloca, i32 0, i32 0, i32 %index
-  %load = load i32, i32* %gep2
+  %alloca = alloca [2 x [2 x i32]], addrspace(5)
+  %gep0 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]] addrspace(5)* %alloca, i32 0, i32 0, i32 0
+  %gep1 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]] addrspace(5)* %alloca, i32 0, i32 0, i32 1
+  store i32 0, i32 addrspace(5)* %gep0
+  store i32 1, i32 addrspace(5)* %gep1
+  %gep2 = getelementptr inbounds [2 x [2 x i32]], [2 x [2 x i32]] addrspace(5)* %alloca, i32 0, i32 0, i32 %index
+  %load = load i32, i32 addrspace(5)* %gep2
   store i32 %load, i32 addrspace(1)* %out
   ret void
 }
 
 define amdgpu_kernel void @i64_array_array(i64 addrspace(1)* %out, i32 %index) #0 {
 entry:
-  %alloca = alloca [2 x [2 x i64]]
-  %gep0 = getelementptr inbounds [2 x [2 x i64]], [2 x [2 x i64]]* %alloca, i32 0, i32 0, i32 0
-  %gep1 = getelementptr inbounds [2 x [2 x i64]], [2 x [2 x i64]]* %alloca, i32 0, i32 0, i32 1
-  store i64 0, i64* %gep0
-  store i64 1, i64* %gep1
-  %gep2 = getelementptr inbounds [2 x [2 x i64]], [2 x [2 x i64]]* %alloca, i32 0, i32 0, i32 %index
-  %load = load i64, i64* %gep2
+  %alloca = alloca [2 x [2 x i64]], addrspace(5)
+  %gep0 = getelementptr inbounds [2 x [2 x i64]], [2 x [2 x i64]] addrspace(5)* %alloca, i32 0, i32 0, i32 0
+  %gep1 = getelementptr inbounds [2 x [2 x i64]], [2 x [2 x i64]] addrspace(5)* %alloca, i32 0, i32 0, i32 1
+  store i64 0, i64 addrspace(5)* %gep0
+  store i64 1, i64 addrspace(5)* %gep1
+  %gep2 = getelementptr inbounds [2 x [2 x i64]], [2 x [2 x i64]] addrspace(5)* %alloca, i32 0, i32 0, i32 %index
+  %load = load i64, i64 addrspace(5)* %gep2
   store i64 %load, i64 addrspace(1)* %out
   ret void
 }
@@ -237,40 +238,40 @@
 
 define amdgpu_kernel void @struct_array_array(i32 addrspace(1)* %out, i32 %index) #0 {
 entry:
-  %alloca = alloca [2 x [2 x %struct.pair32]]
-  %gep0 = getelementptr inbounds [2 x [2 x %struct.pair32]], [2 x [2 x %struct.pair32]]* %alloca, i32 0, i32 0, i32 0, i32 1
-  %gep1 = getelementptr inbounds [2 x [2 x %struct.pair32]], [2 x [2 x %struct.pair32]]* %alloca, i32 0, i32 0, i32 1, i32 1
-  store i32 0, i32* %gep0
-  store i32 1, i32* %gep1
-  %gep2 = getelementptr inbounds [2 x [2 x %struct.pair32]], [2 x [2 x %struct.pair32]]* %alloca, i32 0, i32 0, i32 %index, i32 0
-  %load = load i32, i32* %gep2
+  %alloca = alloca [2 x [2 x %struct.pair32]], addrspace(5)
+  %gep0 = getelementptr inbounds [2 x [2 x %struct.pair32]], [2 x [2 x %struct.pair32]] addrspace(5)* %alloca, i32 0, i32 0, i32 0, i32 1
+  %gep1 = getelementptr inbounds [2 x [2 x %struct.pair32]], [2 x [2 x %struct.pair32]] addrspace(5)* %alloca, i32 0, i32 0, i32 1, i32 1
+  store i32 0, i32 addrspace(5)* %gep0
+  store i32 1, i32 addrspace(5)* %gep1
+  %gep2 = getelementptr inbounds [2 x [2 x %struct.pair32]], [2 x [2 x %struct.pair32]] addrspace(5)* %alloca, i32 0, i32 0, i32 %index, i32 0
+  %load = load i32, i32 addrspace(5)* %gep2
   store i32 %load, i32 addrspace(1)* %out
   ret void
 }
 
 define amdgpu_kernel void @struct_pair32_array(i32 addrspace(1)* %out, i32 %index) #0 {
 entry:
-  %alloca = alloca [2 x %struct.pair32]
-  %gep0 = getelementptr inbounds [2 x %struct.pair32], [2 x %struct.pair32]* %alloca, i32 0, i32 0, i32 1
-  %gep1 = getelementptr inbounds [2 x %struct.pair32], [2 x %struct.pair32]* %alloca, i32 0, i32 1, i32 0
-  store i32 0, i32* %gep0
-  store i32 1, i32* %gep1
-  %gep2 = getelementptr inbounds [2 x %struct.pair32], [2 x %struct.pair32]* %alloca, i32 0, i32 %index, i32 0
-  %load = load i32, i32* %gep2
+  %alloca = alloca [2 x %struct.pair32], addrspace(5)
+  %gep0 = getelementptr inbounds [2 x %struct.pair32], [2 x %struct.pair32] addrspace(5)* %alloca, i32 0, i32 0, i32 1
+  %gep1 = getelementptr inbounds [2 x %struct.pair32], [2 x %struct.pair32] addrspace(5)* %alloca, i32 0, i32 1, i32 0
+  store i32 0, i32 addrspace(5)* %gep0
+  store i32 1, i32 addrspace(5)* %gep1
+  %gep2 = getelementptr inbounds [2 x %struct.pair32], [2 x %struct.pair32] addrspace(5)* %alloca, i32 0, i32 %index, i32 0
+  %load = load i32, i32 addrspace(5)* %gep2
   store i32 %load, i32 addrspace(1)* %out
   ret void
 }
 
 define amdgpu_kernel void @select_private(i32 addrspace(1)* %out, i32 %in) nounwind {
 entry:
-  %tmp = alloca [2 x i32]
-  %tmp1 = getelementptr inbounds  [2 x i32], [2 x i32]* %tmp, i32 0, i32 0
-  %tmp2 = getelementptr inbounds [2 x i32], [2 x i32]* %tmp, i32 0, i32 1
-  store i32 0, i32* %tmp1
-  store i32 1, i32* %tmp2
+  %tmp = alloca [2 x i32], addrspace(5)
+  %tmp1 = getelementptr inbounds  [2 x i32], [2 x i32] addrspace(5)* %tmp, i32 0, i32 0
+  %tmp2 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(5)* %tmp, i32 0, i32 1
+  store i32 0, i32 addrspace(5)* %tmp1
+  store i32 1, i32 addrspace(5)* %tmp2
   %cmp = icmp eq i32 %in, 0
-  %sel = select i1 %cmp, i32* %tmp1, i32* %tmp2
-  %load = load i32, i32* %sel
+  %sel = select i1 %cmp, i32 addrspace(5)* %tmp1, i32 addrspace(5)* %tmp2
+  %load = load i32, i32 addrspace(5)* %sel
   store i32 %load, i32 addrspace(1)* %out
   ret void
 }
@@ -283,14 +284,14 @@
 ; SI: buffer_store_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen
 ; SI: buffer_load_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offen ;
 define amdgpu_kernel void @ptrtoint(i32 addrspace(1)* %out, i32 %a, i32 %b) #0 {
-  %alloca = alloca [16 x i32]
-  %tmp0 = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 %a
-  store i32 5, i32* %tmp0
-  %tmp1 = ptrtoint [16 x i32]* %alloca to i32
+  %alloca = alloca [16 x i32], addrspace(5)
+  %tmp0 = getelementptr inbounds [16 x i32], [16 x i32] addrspace(5)* %alloca, i32 0, i32 %a
+  store i32 5, i32 addrspace(5)* %tmp0
+  %tmp1 = ptrtoint [16 x i32] addrspace(5)* %alloca to i32
   %tmp2 = add i32 %tmp1, 5
-  %tmp3 = inttoptr i32 %tmp2 to i32*
-  %tmp4 = getelementptr inbounds i32, i32* %tmp3, i32 %b
-  %tmp5 = load i32, i32* %tmp4
+  %tmp3 = inttoptr i32 %tmp2 to i32 addrspace(5)*
+  %tmp4 = getelementptr inbounds i32, i32 addrspace(5)* %tmp3, i32 %b
+  %tmp5 = load i32, i32 addrspace(5)* %tmp4
   store i32 %tmp5, i32 addrspace(1)* %out
   ret void
 }
Index: test/CodeGen/AMDGPU/unknown-processor.ll
===================================================================
--- test/CodeGen/AMDGPU/unknown-processor.ll
+++ test/CodeGen/AMDGPU/unknown-processor.ll
@@ -1,5 +1,6 @@
-; RUN: llc -march=amdgcn -mcpu=unknown -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=ERROR -check-prefix=GCN %s
-; RUN: llc -march=r600 -mcpu=unknown -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=ERROR -check-prefix=R600 %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn---amdgiz -mcpu=unknown -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=ERROR -check-prefix=GCN %s
+; RUN: llc -march=r600 -mtriple=r600---amdgiz -mcpu=unknown -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=ERROR -check-prefix=R600 %s
+target datalayout = "A5"
 
 ; Should not crash when the processor is not recognized and the
 ; wavefront size feature not set.
@@ -14,7 +15,7 @@
 
 ; R600: MOV
 define amdgpu_kernel void @foo() {
-  %alloca = alloca i32, align 4
-  store volatile i32 0, i32* %alloca
+  %alloca = alloca i32, align 4, addrspace(5)
+  store volatile i32 0, i32 addrspace(5)* %alloca
   ret void
 }