[AMDGPU] Switch to the new addr space mapping by default for clang

[yaxunl]

Summary

Will clean up the old addr space mapping in separate patch.

[arsenm]

LGTM

lib/Basic/Targets/AMDGPU.h

     return TT.getArch() == llvm::Triple::amdgcn;
   }
 
-  static bool isGenericZero(const llvm::Triple &TT) {
-    return TT.getEnvironmentName() == "amdgiz" ||
-           TT.getEnvironmentName() == "amdgizcl";
-  }
+  static bool isGenericZero(const llvm::Triple &TT) { return true; }
 
 public:
   AMDGPUTargetInfo(const llvm::Triple &Triple, const TargetOptions &Opts);

lib/Basic/Targets/AMDGPU.cpp

 
 static const char *const DataLayoutStringR600 =
     "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";
+    "-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-A5";
 
 static const char *const DataLayoutStringSIPrivateIsZero =
     "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32"

test/CodeGen/address-space.c

 // RUN: %clang_cc1 -triple x86_64-apple-darwin -emit-llvm < %s | FileCheck -check-prefixes=CHECK,X86,GIZ %s
-// RUN: %clang_cc1 -triple amdgcn -emit-llvm < %s | FileCheck -check-prefixes=CHECK,PIZ %s
 // RUN: %clang_cc1 -triple amdgcn---amdgiz -emit-llvm < %s | FileCheck -check-prefixes=CHECK,AMDGIZ,GIZ %s
 
 // CHECK: @foo = common addrspace(1) global

 // CHECK-LABEL: define void @test3()
 // X86: load i32 addrspace(2)*, i32 addrspace(2)** @B
 // AMDGIZ: load i32 addrspace(2)*, i32 addrspace(2)** addrspacecast (i32 addrspace(2)* addrspace(1)* @B to i32 addrspace(2)**)
-// PIZ: load i32 addrspace(2)*, i32 addrspace(2)* addrspace(4)* addrspacecast (i32 addrspace(2)* addrspace(1)* @B to i32 addrspace(2)* addrspace(4)*)
 // CHECK: load i32, i32 addrspace(2)*
 // X86: load i32 addrspace(2)*, i32 addrspace(2)** @A
 // AMDGIZ: load i32 addrspace(2)*, i32 addrspace(2)** addrspacecast (i32 addrspace(2)* addrspace(1)* @A to i32 addrspace(2)**)
-// PIZ: load i32 addrspace(2)*, i32 addrspace(2)* addrspace(4)* addrspacecast (i32 addrspace(2)* addrspace(1)* @A to i32 addrspace(2)* addrspace(4)*)
 // CHECK: store i32 {{.*}}, i32 addrspace(2)*
 void test3() {
   *A = *B;

 // CHECK-LABEL: define void @test4(
 // GIZ: call void @llvm.memcpy.p0i8.p2i8
 // GIZ: call void @llvm.memcpy.p2i8.p0i8
-// PIZ: call void @llvm.memcpy.p4i8.p2i8
-// PIZ: call void @llvm.memcpy.p2i8.p4i8
 void test4(MyStruct __attribute__((address_space(2))) *pPtr) {
   MyStruct s = pPtr[0];
   pPtr[0] = s;

test/CodeGen/default-address-space.c

-// RUN: %clang_cc1 -triple amdgcn -emit-llvm < %s | FileCheck -check-prefixes=PIZ,COM %s
 // RUN: %clang_cc1 -triple amdgcn---amdgiz -emit-llvm < %s | FileCheck -check-prefixes=CHECK,COM %s
 
-// PIZ-DAG: @foo = common addrspace(1) global i32 0
 // CHECK-DAG: @foo = common addrspace(1) global i32 0
 int foo;
 
-// PIZ-DAG: @ban = common addrspace(1) global [10 x i32] zeroinitializer
 // CHECK-DAG: @ban = common addrspace(1) global [10 x i32] zeroinitializer
 int ban[10];
 
-// PIZ-DAG: @A = common addrspace(1) global i32 addrspace(4)* null
-// PIZ-DAG: @B = common addrspace(1) global i32 addrspace(4)* null
 // CHECK-DAG: @A = common addrspace(1) global i32* null
 // CHECK-DAG: @B = common addrspace(1) global i32* null
 int *A;
 int *B;
 
 // COM-LABEL: define i32 @test1()
-// PIZ: load i32, i32 addrspace(4)* addrspacecast{{[^@]+}} @foo
 // CHECK: load i32, i32* addrspacecast{{[^@]+}} @foo
 int test1() { return foo; }
 
 // COM-LABEL: define i32 @test2(i32 %i)
 // COM: %[[addr:.*]] = getelementptr
-// PIZ: load i32, i32 addrspace(4)* %[[addr]]
-// PIZ-NEXT: ret i32
 // CHECK: load i32, i32* %[[addr]]
 // CHECK-NEXT: ret i32
 int test2(int i) { return ban[i]; }
 
 // COM-LABEL: define void @test3()
-// PIZ: load i32 addrspace(4)*, i32 addrspace(4)* addrspace(4)* addrspacecast{{[^@]+}} @B
-// PIZ: load i32, i32 addrspace(4)*
-// PIZ: load i32 addrspace(4)*, i32 addrspace(4)* addrspace(4)* addrspacecast{{[^@]+}} @A
-// PIZ: store i32 {{.*}}, i32 addrspace(4)*
 // CHECK: load i32*, i32** addrspacecast{{.*}} @B
 // CHECK: load i32, i32*
 // CHECK: load i32*, i32** addrspacecast{{.*}} @A

   *A = *B;
 }
 
-// PIZ-LABEL: define void @test4(i32 addrspace(4)* %a)
-// PIZ: %[[alloca:.*]] = alloca i32 addrspace(4)*
-// PIZ: %[[a_addr:.*]] = addrspacecast{{.*}} %[[alloca]] to i32 addrspace(4)* addrspace(4)*
-// PIZ: store i32 addrspace(4)* %a, i32 addrspace(4)* addrspace(4)* %[[a_addr]]
-// PIZ: %[[r0:.*]] = load i32 addrspace(4)*, i32 addrspace(4)* addrspace(4)* %[[a_addr]]
-// PIZ: %[[arrayidx:.*]] = getelementptr inbounds i32, i32 addrspace(4)* %[[r0]]
-// PIZ: store i32 0, i32 addrspace(4)* %[[arrayidx]]
 // CHECK-LABEL: define void @test4(i32* %a)
 // CHECK: %[[alloca:.*]] = alloca i32*, align 8, addrspace(5)
 // CHECK: %[[a_addr:.*]] = addrspacecast{{.*}} %[[alloca]] to i32**

test/CodeGen/target-data.c

 
 // RUN: %clang_cc1 -triple r600-unknown -o - -emit-llvm %s | \
 // RUN: FileCheck %s -check-prefix=R600
-// R600: target datalayout = "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"
+// R600: target datalayout = "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"
 
 // RUN: %clang_cc1 -triple r600-unknown -target-cpu cayman -o - -emit-llvm %s \
 // RUN: | FileCheck %s -check-prefix=R600D
-// R600D: target datalayout = "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"
+// R600D: target datalayout = "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"
 
 // RUN: %clang_cc1 -triple amdgcn-unknown -target-cpu hawaii -o - -emit-llvm %s \
 // RUN: | FileCheck %s -check-prefix=R600SI
-// R600SI: target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
+// R600SI: target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:32:32-p5:32:32-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"
 
 // Test default -target-cpu
 // RUN: %clang_cc1 -triple amdgcn-unknown -o - -emit-llvm %s \
 // RUN: | FileCheck %s -check-prefix=R600SIDefault
-// R600SIDefault: target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
+// R600SIDefault: target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:32:32-p5:32:32-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"
 
 // RUN: %clang_cc1 -triple arm64-unknown -o - -emit-llvm %s | \
 // RUN: FileCheck %s -check-prefix=AARCH64

test/CodeGenOpenCL/address-spaces.cl

 // RUN: %clang_cc1 %s -O0 -ffake-address-space-map -emit-llvm -o - | FileCheck %s --check-prefixes=CHECK,SPIR
 // RUN: %clang_cc1 %s -O0 -DCL20 -cl-std=CL2.0 -ffake-address-space-map -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20SPIR
-// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-opencl -emit-llvm -o - | FileCheck --check-prefixes=CHECK,SPIR %s
-// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-opencl -DCL20 -cl-std=CL2.0 -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20SPIR
-// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-amdgizcl -emit-llvm -o - | FileCheck %s -check-prefixes=CHECK,GIZ
-// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-amdgizcl -DCL20 -cl-std=CL2.0 -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20GIZ
-// RUN: %clang_cc1 %s -O0 -triple amdgcn-mesa-mesa3d -emit-llvm -o - | FileCheck --check-prefixes=CHECK,SPIR %s
-// RUN: %clang_cc1 %s -O0 -triple r600-- -emit-llvm -o - | FileCheck --check-prefixes=CHECK,SPIR %s
+// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-opencl -emit-llvm -o - | FileCheck --check-prefixes=CHECK,GIZ %s
+// RUN: %clang_cc1 %s -O0 -triple amdgcn-amd-amdhsa-opencl -DCL20 -cl-std=CL2.0 -emit-llvm -o - | FileCheck %s --check-prefixes=CL20,CL20GIZ
+// RUN: %clang_cc1 %s -O0 -triple amdgcn-mesa-mesa3d -emit-llvm -o - | FileCheck --check-prefixes=CHECK,GIZ %s
+// RUN: %clang_cc1 %s -O0 -triple r600-- -emit-llvm -o - | FileCheck --check-prefixes=CHECK,GIZ %s
 
 // SPIR: %struct.S = type { i32, i32, i32* }
 // CL20SPIR: %struct.S = type { i32, i32, i32 addrspace(4)* }

test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl

 // REQUIRES: amdgpu-registered-target
-// RUN: %clang_cc1 -triple amdgcn-unknown-unknown-amdgiz -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,AMDGCN %s
-// RUN: %clang_cc1 -triple r600-unknown-unknown -S -emit-llvm -o - %s | FileCheck -check-prefixes=CHECK,R600 %s
+// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
+// RUN: %clang_cc1 -triple r600-unknown-unknown -S -emit-llvm -o - %s | FileCheck %s
 
 typedef __attribute__(( ext_vector_type(2) )) char char2;
 typedef __attribute__(( ext_vector_type(3) )) char char3;

 // CHECK: void @func_different_size_type_pair_arg(i64 %arg1.coerce0, i32 %arg1.coerce1)
 void func_different_size_type_pair_arg(different_size_type_pair arg1) { }
 
-// AMDGCN: void @func_flexible_array_arg(%struct.flexible_array addrspace(5)* byval nocapture align 4 %arg)
-// R600: void @func_flexible_array_arg(%struct.flexible_array* byval nocapture align 4 %arg)
+// CHECK: void @func_flexible_array_arg(%struct.flexible_array addrspace(5)* byval nocapture align 4 %arg)
 void func_flexible_array_arg(flexible_array arg) { }
 
 // CHECK: define float @func_f32_ret()

   return s;
 }
 
-// AMDGCN: define void @func_ret_struct_arr32(%struct.struct_arr32 addrspace(5)* noalias nocapture sret %agg.result)
-// R600: define void @func_ret_struct_arr32(%struct.struct_arr32* noalias nocapture sret %agg.result)
+// CHECK: define void @func_ret_struct_arr32(%struct.struct_arr32 addrspace(5)* noalias nocapture sret %agg.result)
 struct_arr32 func_ret_struct_arr32()
 {
   struct_arr32 s = { 0 };
   return s;
 }
 
-// AMDGCN: define void @func_ret_struct_arr33(%struct.struct_arr33 addrspace(5)* noalias nocapture sret %agg.result)
-// R600: define void @func_ret_struct_arr33(%struct.struct_arr33* noalias nocapture sret %agg.result)
+// CHECK: define void @func_ret_struct_arr33(%struct.struct_arr33 addrspace(5)* noalias nocapture sret %agg.result)
 struct_arr33 func_ret_struct_arr33()
 {
   struct_arr33 s = { 0 };

   return s;
 }
 
-// AMDGCN: define void @func_flexible_array_ret(%struct.flexible_array addrspace(5)* noalias nocapture sret %agg.result)
-// R600: define void @func_flexible_array_ret(%struct.flexible_array* noalias nocapture sret %agg.result)
+// CHECK: define void @func_flexible_array_ret(%struct.flexible_array addrspace(5)* noalias nocapture sret %agg.result)
 flexible_array func_flexible_array_ret()
 {
   flexible_array s = { 0 };

 // CHECK: define void @func_reg_state_lo(<4 x i32> %arg0, <4 x i32> %arg1, <4 x i32> %arg2, i32 %arg3, i32 %s.coerce0, float %s.coerce1, i32 %s.coerce2)
 void func_reg_state_lo(int4 arg0, int4 arg1, int4 arg2, int arg3, struct_arg_t s) { }
 
-// AMDGCN: define void @func_reg_state_hi(<4 x i32> %arg0, <4 x i32> %arg1, <4 x i32> %arg2, i32 %arg3, i32 %arg4, %struct.struct_arg addrspace(5)* byval nocapture align 4 %s)
-// R600: define void @func_reg_state_hi(<4 x i32> %arg0, <4 x i32> %arg1, <4 x i32> %arg2, i32 %arg3, i32 %arg4, %struct.struct_arg* byval nocapture align 4 %s)
+// CHECK: define void @func_reg_state_hi(<4 x i32> %arg0, <4 x i32> %arg1, <4 x i32> %arg2, i32 %arg3, i32 %arg4, %struct.struct_arg addrspace(5)* byval nocapture align 4 %s)
 void func_reg_state_hi(int4 arg0, int4 arg1, int4 arg2, int arg3, int arg4, struct_arg_t s) { }
 
 // XXX - Why don't the inner structs flatten?
-// AMDGCN: define void @func_reg_state_num_regs_nested_struct(<4 x i32> %arg0, i32 %arg1, i32 %arg2.coerce0, %struct.nested %arg2.coerce1, i32 %arg3.coerce0, %struct.nested %arg3.coerce1, %struct.num_regs_nested_struct addrspace(5)* byval nocapture align 8 %arg4)
-// R600: define void @func_reg_state_num_regs_nested_struct(<4 x i32> %arg0, i32 %arg1, i32 %arg2.coerce0, %struct.nested %arg2.coerce1, i32 %arg3.coerce0, %struct.nested %arg3.coerce1, %struct.num_regs_nested_struct* byval nocapture align 8 %arg4)
+// CHECK: define void @func_reg_state_num_regs_nested_struct(<4 x i32> %arg0, i32 %arg1, i32 %arg2.coerce0, %struct.nested %arg2.coerce1, i32 %arg3.coerce0, %struct.nested %arg3.coerce1, %struct.num_regs_nested_struct addrspace(5)* byval nocapture align 8 %arg4)
 void func_reg_state_num_regs_nested_struct(int4 arg0, int arg1, num_regs_nested_struct arg2, num_regs_nested_struct arg3, num_regs_nested_struct arg4) { }
 
 // CHECK: define void @func_double_nested_struct_arg(<4 x i32> %arg0, i32 %arg1, i32 %arg2.coerce0, %struct.double_nested %arg2.coerce1, i16 %arg2.coerce2)

 // CHECK: define void @func_large_struct_padding_arg_direct(i8 %arg.coerce0, i32 %arg.coerce1, i8 %arg.coerce2, i32 %arg.coerce3, i8 %arg.coerce4, i8 %arg.coerce5, i16 %arg.coerce6, i16 %arg.coerce7, [3 x i8] %arg.coerce8, i64 %arg.coerce9, i32 %arg.coerce10, i8 %arg.coerce11, i32 %arg.coerce12, i16 %arg.coerce13, i8 %arg.coerce14)
 void func_large_struct_padding_arg_direct(large_struct_padding arg) { }
 
-// AMDGCN: define void @func_large_struct_padding_arg_store(%struct.large_struct_padding addrspace(1)* nocapture %out, %struct.large_struct_padding addrspace(5)* byval nocapture readonly align 8 %arg)
-// R600: define void @func_large_struct_padding_arg_store(%struct.large_struct_padding addrspace(1)* nocapture %out, %struct.large_struct_padding* byval nocapture readonly align 8 %arg)
+// CHECK: define void @func_large_struct_padding_arg_store(%struct.large_struct_padding addrspace(1)* nocapture %out, %struct.large_struct_padding addrspace(5)* byval nocapture readonly align 8 %arg)
 void func_large_struct_padding_arg_store(global large_struct_padding* out, large_struct_padding arg) {
   *out = arg;
 }

 
 // Function signature from blender, nothing should be passed byval. The v3i32
 // should not count as 4 passed registers.
-// AMDGCN: define void @v3i32_pair_reg_count(%struct.int3_pair addrspace(5)* nocapture %arg0, <3 x i32> %arg1.coerce0, <3 x i32> %arg1.coerce1, <3 x i32> %arg2, <3 x i32> %arg3.coerce0, <3 x i32> %arg3.coerce1, <3 x i32> %arg4, float %arg5)
-// R600: define void @v3i32_pair_reg_count(%struct.int3_pair* nocapture %arg0, <3 x i32> %arg1.coerce0, <3 x i32> %arg1.coerce1, <3 x i32> %arg2, <3 x i32> %arg3.coerce0, <3 x i32> %arg3.coerce1, <3 x i32> %arg4, float %arg5)
+// CHECK: define void @v3i32_pair_reg_count(%struct.int3_pair addrspace(5)* nocapture %arg0, <3 x i32> %arg1.coerce0, <3 x i32> %arg1.coerce1, <3 x i32> %arg2, <3 x i32> %arg3.coerce0, <3 x i32> %arg3.coerce1, <3 x i32> %arg4, float %arg5)
 void v3i32_pair_reg_count(int3_pair *arg0, int3_pair arg1, int3 arg2, int3_pair arg3, int3 arg4, float arg5) { }
 
 // Each short4 should fit pack into 2 registers.

 void v4i16_reg_count(short4 arg0, short4 arg1, short4 arg2, short4 arg3,
                      short4 arg4, short4 arg5, struct_4regs arg6) { }
 
-// AMDGCN: define void @v4i16_pair_reg_count_over(<4 x i16> %arg0, <4 x i16> %arg1, <4 x i16> %arg2, <4 x i16> %arg3, <4 x i16> %arg4, <4 x i16> %arg5, <4 x i16> %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
-// R600: define void @v4i16_pair_reg_count_over(<4 x i16> %arg0, <4 x i16> %arg1, <4 x i16> %arg2, <4 x i16> %arg3, <4 x i16> %arg4, <4 x i16> %arg5, <4 x i16> %arg6, %struct.struct_4regs* byval nocapture align 4 %arg7)
+// CHECK: define void @v4i16_pair_reg_count_over(<4 x i16> %arg0, <4 x i16> %arg1, <4 x i16> %arg2, <4 x i16> %arg3, <4 x i16> %arg4, <4 x i16> %arg5, <4 x i16> %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
 void v4i16_pair_reg_count_over(short4 arg0, short4 arg1, short4 arg2, short4 arg3,
                                short4 arg4, short4 arg5, short4 arg6, struct_4regs arg7) { }
 

 void v3i16_reg_count(short3 arg0, short3 arg1, short3 arg2, short3 arg3,
                      short3 arg4, short3 arg5, struct_4regs arg6) { }
 
-// AMDGCN: define void @v3i16_reg_count_over(<3 x i16> %arg0, <3 x i16> %arg1, <3 x i16> %arg2, <3 x i16> %arg3, <3 x i16> %arg4, <3 x i16> %arg5, <3 x i16> %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
-// R600: define void @v3i16_reg_count_over(<3 x i16> %arg0, <3 x i16> %arg1, <3 x i16> %arg2, <3 x i16> %arg3, <3 x i16> %arg4, <3 x i16> %arg5, <3 x i16> %arg6, %struct.struct_4regs* byval nocapture align 4 %arg7)
+// CHECK: define void @v3i16_reg_count_over(<3 x i16> %arg0, <3 x i16> %arg1, <3 x i16> %arg2, <3 x i16> %arg3, <3 x i16> %arg4, <3 x i16> %arg5, <3 x i16> %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
 void v3i16_reg_count_over(short3 arg0, short3 arg1, short3 arg2, short3 arg3,
                           short3 arg4, short3 arg5, short3 arg6, struct_4regs arg7) { }
 

                      short2 arg8, short2 arg9, short2 arg10, short2 arg11,
                      struct_4regs arg13) { }
 
-// AMDGCN: define void @v2i16_reg_count_over(<2 x i16> %arg0, <2 x i16> %arg1, <2 x i16> %arg2, <2 x i16> %arg3, <2 x i16> %arg4, <2 x i16> %arg5, <2 x i16> %arg6, <2 x i16> %arg7, <2 x i16> %arg8, <2 x i16> %arg9, <2 x i16> %arg10, <2 x i16> %arg11, <2 x i16> %arg12, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg13)
-// R600: define void @v2i16_reg_count_over(<2 x i16> %arg0, <2 x i16> %arg1, <2 x i16> %arg2, <2 x i16> %arg3, <2 x i16> %arg4, <2 x i16> %arg5, <2 x i16> %arg6, <2 x i16> %arg7, <2 x i16> %arg8, <2 x i16> %arg9, <2 x i16> %arg10, <2 x i16> %arg11, <2 x i16> %arg12, %struct.struct_4regs* byval nocapture align 4 %arg13)
+// CHECK: define void @v2i16_reg_count_over(<2 x i16> %arg0, <2 x i16> %arg1, <2 x i16> %arg2, <2 x i16> %arg3, <2 x i16> %arg4, <2 x i16> %arg5, <2 x i16> %arg6, <2 x i16> %arg7, <2 x i16> %arg8, <2 x i16> %arg9, <2 x i16> %arg10, <2 x i16> %arg11, <2 x i16> %arg12, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg13)
 void v2i16_reg_count_over(short2 arg0, short2 arg1, short2 arg2, short2 arg3,
                           short2 arg4, short2 arg5, short2 arg6, short2 arg7,
                           short2 arg8, short2 arg9, short2 arg10, short2 arg11,

 void v2i8_reg_count(char2 arg0, char2 arg1, char2 arg2, char2 arg3,
                     char2 arg4, char2 arg5, struct_4regs arg6) { }
 
-// AMDGCN: define void @v2i8_reg_count_over(<2 x i8> %arg0, <2 x i8> %arg1, <2 x i8> %arg2, <2 x i8> %arg3, <2 x i8> %arg4, <2 x i8> %arg5, i32 %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
-// R600: define void @v2i8_reg_count_over(<2 x i8> %arg0, <2 x i8> %arg1, <2 x i8> %arg2, <2 x i8> %arg3, <2 x i8> %arg4, <2 x i8> %arg5, i32 %arg6, %struct.struct_4regs* byval nocapture align 4 %arg7)
+// CHECK: define void @v2i8_reg_count_over(<2 x i8> %arg0, <2 x i8> %arg1, <2 x i8> %arg2, <2 x i8> %arg3, <2 x i8> %arg4, <2 x i8> %arg5, i32 %arg6, %struct.struct_4regs addrspace(5)* byval nocapture align 4 %arg7)
 void v2i8_reg_count_over(char2 arg0, char2 arg1, char2 arg2, char2 arg3,
                          char2 arg4, char2 arg5, int arg6, struct_4regs arg7) { }
 

test/CodeGenOpenCL/amdgpu-alignment.cl

 }
 
 // CHECK-LABEL: @private_memory_alignment_alloca(
-// CHECK: %private_i8 = alloca [4 x i8], align 1
-// CHECK: %private_v2i8 = alloca [4 x <2 x i8>], align 2
-// CHECK: %private_v3i8 = alloca [4 x <3 x i8>], align 4
-// CHECK: %private_v4i8 = alloca [4 x <4 x i8>], align 4
-// CHECK: %private_v8i8 = alloca [4 x <8 x i8>], align 8
-// CHECK: %private_v16i8 = alloca [4 x <16 x i8>], align 16
-// CHECK: %private_i16 = alloca [4 x i16], align 2
-// CHECK: %private_v2i16 = alloca [4 x <2 x i16>], align 4
-// CHECK: %private_v3i16 = alloca [4 x <3 x i16>], align 8
-// CHECK: %private_v4i16 = alloca [4 x <4 x i16>], align 8
-// CHECK: %private_v8i16 = alloca [4 x <8 x i16>], align 16
-// CHECK: %private_v16i16 = alloca [4 x <16 x i16>], align 32
-// CHECK: %private_i32 = alloca [4 x i32], align 4
-// CHECK: %private_v2i32 = alloca [4 x <2 x i32>], align 8
-// CHECK: %private_v3i32 = alloca [4 x <3 x i32>], align 16
-// CHECK: %private_v4i32 = alloca [4 x <4 x i32>], align 16
-// CHECK: %private_v8i32 = alloca [4 x <8 x i32>], align 32
-// CHECK: %private_v16i32 = alloca [4 x <16 x i32>], align 64
-// CHECK: %private_i64 = alloca [4 x i64], align 8
-// CHECK: %private_v2i64 = alloca [4 x <2 x i64>], align 16
-// CHECK: %private_v3i64 = alloca [4 x <3 x i64>], align 32
-// CHECK: %private_v4i64 = alloca [4 x <4 x i64>], align 32
-// CHECK: %private_v8i64 = alloca [4 x <8 x i64>], align 64
-// CHECK: %private_v16i64 = alloca [4 x <16 x i64>], align 128
-// CHECK: %private_f16 = alloca [4 x half], align 2
-// CHECK: %private_v2f16 = alloca [4 x <2 x half>], align 4
-// CHECK: %private_v3f16 = alloca [4 x <3 x half>], align 8
-// CHECK: %private_v4f16 = alloca [4 x <4 x half>], align 8
-// CHECK: %private_v8f16 = alloca [4 x <8 x half>], align 16
-// CHECK: %private_v16f16 = alloca [4 x <16 x half>], align 32
-// CHECK: %private_f32 = alloca [4 x float], align 4
-// CHECK: %private_v2f32 = alloca [4 x <2 x float>], align 8
-// CHECK: %private_v3f32 = alloca [4 x <3 x float>], align 16
-// CHECK: %private_v4f32 = alloca [4 x <4 x float>], align 16
-// CHECK: %private_v8f32 = alloca [4 x <8 x float>], align 32
-// CHECK: %private_v16f32 = alloca [4 x <16 x float>], align 64
-// CHECK: %private_f64 = alloca [4 x double], align 8
-// CHECK: %private_v2f64 = alloca [4 x <2 x double>], align 16
-// CHECK: %private_v3f64 = alloca [4 x <3 x double>], align 32
-// CHECK: %private_v4f64 = alloca [4 x <4 x double>], align 32
-// CHECK: %private_v8f64 = alloca [4 x <8 x double>], align 64
-// CHECK: %private_v16f64 = alloca [4 x <16 x double>], align 128
-
-// CHECK: store volatile i8 0, i8* %arraydecay, align 1
-// CHECK: store volatile <2 x i8> zeroinitializer, <2 x i8>* %arraydecay{{[0-9]+}}, align 2
-// CHECK: store volatile <4 x i8> <i8 0, i8 0, i8 0, i8 undef>, <4 x i8>* %storetmp, align 4
-// CHECK: store volatile <4 x i8> zeroinitializer, <4 x i8>* %arraydecay{{[0-9]+}}, align 4
-// CHECK: store volatile <8 x i8> zeroinitializer, <8 x i8>* %arraydecay{{[0-9]+}}, align 8
-// CHECK: store volatile <16 x i8> zeroinitializer, <16 x i8>* %arraydecay{{[0-9]+}}, align 16
-// CHECK: store volatile i16 0, i16* %arraydecay{{[0-9]+}}, align 2
-// CHECK: store volatile <2 x i16> zeroinitializer, <2 x i16>* %arraydecay{{[0-9]+}}, align 4
-// CHECK: store volatile <4 x i16> <i16 0, i16 0, i16 0, i16 undef>, <4 x i16>* %storetmp{{[0-9]+}}, align 8
-// CHECK: store volatile <4 x i16> zeroinitializer, <4 x i16>* %arraydecay{{[0-9]+}}, align 8
-// CHECK: store volatile <8 x i16> zeroinitializer, <8 x i16>* %arraydecay{{[0-9]+}}, align 16
-// CHECK: store volatile <16 x i16> zeroinitializer, <16 x i16>* %arraydecay{{[0-9]+}}, align 32
-// CHECK: store volatile i32 0, i32* %arraydecay{{[0-9]+}}, align 4
-// CHECK: store volatile <2 x i32> zeroinitializer, <2 x i32>* %arraydecay{{[0-9]+}}, align 8
-// CHECK: store volatile <4 x i32> <i32 0, i32 0, i32 0, i32 undef>, <4 x i32>* %storetmp16, align 16
-// CHECK: store volatile <4 x i32> zeroinitializer, <4 x i32>* %arraydecay{{[0-9]+}}, align 16
-// CHECK: store volatile <8 x i32> zeroinitializer, <8 x i32>* %arraydecay{{[0-9]+}}, align 32
-// CHECK: store volatile <16 x i32> zeroinitializer, <16 x i32>* %arraydecay{{[0-9]+}}, align 64
-// CHECK: store volatile i64 0, i64* %arraydecay{{[0-9]+}}, align 8
-// CHECK: store volatile <2 x i64> zeroinitializer, <2 x i64>* %arraydecay{{[0-9]+}}, align 16
-// CHECK: store volatile <4 x i64> <i64 0, i64 0, i64 0, i64 undef>, <4 x i64>* %storetmp23, align 32
-// CHECK: store volatile <4 x i64> zeroinitializer, <4 x i64>* %arraydecay{{[0-9]+}}, align 32
-// CHECK: store volatile <8 x i64> zeroinitializer, <8 x i64>* %arraydecay{{[0-9]+}}, align 64
-// CHECK: store volatile <16 x i64> zeroinitializer, <16 x i64>* %arraydecay{{[0-9]+}}, align 128
-// CHECK: store volatile half 0xH0000, half* %arraydecay{{[0-9]+}}, align 2
-// CHECK: store volatile <2 x half> zeroinitializer, <2 x half>* %arraydecay{{[0-9]+}}, align 4
-// CHECK: store volatile <4 x half> <half 0xH0000, half 0xH0000, half 0xH0000, half undef>, <4 x half>* %storetmp{{[0-9]+}}, align 8
-// CHECK: store volatile <4 x half> zeroinitializer, <4 x half>* %arraydecay{{[0-9]+}}, align 8
-// CHECK: store volatile <8 x half> zeroinitializer, <8 x half>* %arraydecay{{[0-9]+}}, align 16
-// CHECK: store volatile <16 x half> zeroinitializer, <16 x half>* %arraydecay{{[0-9]+}}, align 32
-// CHECK: store volatile float 0.000000e+00, float* %arraydecay34, align 4
-// CHECK: store volatile <2 x float> zeroinitializer, <2 x float>* %arraydecay{{[0-9]+}}, align 8
-// CHECK: store volatile <4 x float> <float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float undef>, <4 x float>* %storetmp{{[0-9]+}}, align 16
-// CHECK: store volatile <4 x float> zeroinitializer, <4 x float>* %arraydecay{{[0-9]+}}, align 16
-// CHECK: store volatile <8 x float> zeroinitializer, <8 x float>* %arraydecay{{[0-9]+}}, align 32
-// CHECK: store volatile <16 x float> zeroinitializer, <16 x float>* %arraydecay{{[0-9]+}}, align 64
-// CHECK: store volatile double 0.000000e+00, double* %arraydecay{{[0-9]+}}, align 8
-// CHECK: store volatile <2 x double> zeroinitializer, <2 x double>* %arraydecay{{[0-9]+}}, align 16
-// CHECK: store volatile <4 x double> <double 0.000000e+00, double 0.000000e+00, double 0.000000e+00, double undef>, <4 x double>* %storetmp{{[0-9]+}}, align 32
-// CHECK: store volatile <4 x double> zeroinitializer, <4 x double>* %arraydecay{{[0-9]+}}, align 32
-// CHECK: store volatile <8 x double> zeroinitializer, <8 x double>* %arraydecay{{[0-9]+}}, align 64
-// CHECK: store volatile <16 x double> zeroinitializer, <16 x double>* %arraydecay{{[0-9]+}}, align 128
+// CHECK: %private_i8 = alloca [4 x i8], align 1, addrspace(5)
+// CHECK: %private_v2i8 = alloca [4 x <2 x i8>], align 2, addrspace(5)
+// CHECK: %private_v3i8 = alloca [4 x <3 x i8>], align 4, addrspace(5)
+// CHECK: %private_v4i8 = alloca [4 x <4 x i8>], align 4, addrspace(5)
+// CHECK: %private_v8i8 = alloca [4 x <8 x i8>], align 8, addrspace(5)
+// CHECK: %private_v16i8 = alloca [4 x <16 x i8>], align 16, addrspace(5)
+// CHECK: %private_i16 = alloca [4 x i16], align 2, addrspace(5)
+// CHECK: %private_v2i16 = alloca [4 x <2 x i16>], align 4, addrspace(5)
+// CHECK: %private_v3i16 = alloca [4 x <3 x i16>], align 8, addrspace(5)
+// CHECK: %private_v4i16 = alloca [4 x <4 x i16>], align 8, addrspace(5)
+// CHECK: %private_v8i16 = alloca [4 x <8 x i16>], align 16, addrspace(5)
+// CHECK: %private_v16i16 = alloca [4 x <16 x i16>], align 32, addrspace(5)
+// CHECK: %private_i32 = alloca [4 x i32], align 4, addrspace(5)
+// CHECK: %private_v2i32 = alloca [4 x <2 x i32>], align 8, addrspace(5)
+// CHECK: %private_v3i32 = alloca [4 x <3 x i32>], align 16, addrspace(5)
+// CHECK: %private_v4i32 = alloca [4 x <4 x i32>], align 16, addrspace(5)
+// CHECK: %private_v8i32 = alloca [4 x <8 x i32>], align 32, addrspace(5)
+// CHECK: %private_v16i32 = alloca [4 x <16 x i32>], align 64, addrspace(5)
+// CHECK: %private_i64 = alloca [4 x i64], align 8, addrspace(5)
+// CHECK: %private_v2i64 = alloca [4 x <2 x i64>], align 16, addrspace(5)
+// CHECK: %private_v3i64 = alloca [4 x <3 x i64>], align 32, addrspace(5)
+// CHECK: %private_v4i64 = alloca [4 x <4 x i64>], align 32, addrspace(5)
+// CHECK: %private_v8i64 = alloca [4 x <8 x i64>], align 64, addrspace(5)
+// CHECK: %private_v16i64 = alloca [4 x <16 x i64>], align 128, addrspace(5)
+// CHECK: %private_f16 = alloca [4 x half], align 2, addrspace(5)
+// CHECK: %private_v2f16 = alloca [4 x <2 x half>], align 4, addrspace(5)
+// CHECK: %private_v3f16 = alloca [4 x <3 x half>], align 8, addrspace(5)
+// CHECK: %private_v4f16 = alloca [4 x <4 x half>], align 8, addrspace(5)
+// CHECK: %private_v8f16 = alloca [4 x <8 x half>], align 16, addrspace(5)
+// CHECK: %private_v16f16 = alloca [4 x <16 x half>], align 32, addrspace(5)
+// CHECK: %private_f32 = alloca [4 x float], align 4, addrspace(5)
+// CHECK: %private_v2f32 = alloca [4 x <2 x float>], align 8, addrspace(5)
+// CHECK: %private_v3f32 = alloca [4 x <3 x float>], align 16, addrspace(5)
+// CHECK: %private_v4f32 = alloca [4 x <4 x float>], align 16, addrspace(5)
+// CHECK: %private_v8f32 = alloca [4 x <8 x float>], align 32, addrspace(5)
+// CHECK: %private_v16f32 = alloca [4 x <16 x float>], align 64, addrspace(5)
+// CHECK: %private_f64 = alloca [4 x double], align 8, addrspace(5)
+// CHECK: %private_v2f64 = alloca [4 x <2 x double>], align 16, addrspace(5)
+// CHECK: %private_v3f64 = alloca [4 x <3 x double>], align 32, addrspace(5)
+// CHECK: %private_v4f64 = alloca [4 x <4 x double>], align 32, addrspace(5)
+// CHECK: %private_v8f64 = alloca [4 x <8 x double>], align 64, addrspace(5)
+// CHECK: %private_v16f64 = alloca [4 x <16 x double>], align 128, addrspace(5)
+
+// CHECK: store volatile i8 0, i8 addrspace(5)* %arraydecay, align 1
+// CHECK: store volatile <2 x i8> zeroinitializer, <2 x i8> addrspace(5)* %arraydecay{{[0-9]+}}, align 2
+// CHECK: store volatile <4 x i8> <i8 0, i8 0, i8 0, i8 undef>, <4 x i8> addrspace(5)* %storetmp, align 4
+// CHECK: store volatile <4 x i8> zeroinitializer, <4 x i8> addrspace(5)* %arraydecay{{[0-9]+}}, align 4
+// CHECK: store volatile <8 x i8> zeroinitializer, <8 x i8> addrspace(5)* %arraydecay{{[0-9]+}}, align 8
+// CHECK: store volatile <16 x i8> zeroinitializer, <16 x i8> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
+// CHECK: store volatile i16 0, i16 addrspace(5)* %arraydecay{{[0-9]+}}, align 2
+// CHECK: store volatile <2 x i16> zeroinitializer, <2 x i16> addrspace(5)* %arraydecay{{[0-9]+}}, align 4
+// CHECK: store volatile <4 x i16> <i16 0, i16 0, i16 0, i16 undef>, <4 x i16> addrspace(5)* %storetmp{{[0-9]+}}, align 8
+// CHECK: store volatile <4 x i16> zeroinitializer, <4 x i16> addrspace(5)* %arraydecay{{[0-9]+}}, align 8
+// CHECK: store volatile <8 x i16> zeroinitializer, <8 x i16> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
+// CHECK: store volatile <16 x i16> zeroinitializer, <16 x i16> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
+// CHECK: store volatile i32 0, i32 addrspace(5)* %arraydecay{{[0-9]+}}, align 4
+// CHECK: store volatile <2 x i32> zeroinitializer, <2 x i32> addrspace(5)* %arraydecay{{[0-9]+}}, align 8
+// CHECK: store volatile <4 x i32> <i32 0, i32 0, i32 0, i32 undef>, <4 x i32> addrspace(5)* %storetmp16, align 16
+// CHECK: store volatile <4 x i32> zeroinitializer, <4 x i32> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
+// CHECK: store volatile <8 x i32> zeroinitializer, <8 x i32> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
+// CHECK: store volatile <16 x i32> zeroinitializer, <16 x i32> addrspace(5)* %arraydecay{{[0-9]+}}, align 64
+// CHECK: store volatile i64 0, i64 addrspace(5)* %arraydecay{{[0-9]+}}, align 8
+// CHECK: store volatile <2 x i64> zeroinitializer, <2 x i64> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
+// CHECK: store volatile <4 x i64> <i64 0, i64 0, i64 0, i64 undef>, <4 x i64> addrspace(5)* %storetmp23, align 32
+// CHECK: store volatile <4 x i64> zeroinitializer, <4 x i64> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
+// CHECK: store volatile <8 x i64> zeroinitializer, <8 x i64> addrspace(5)* %arraydecay{{[0-9]+}}, align 64
+// CHECK: store volatile <16 x i64> zeroinitializer, <16 x i64> addrspace(5)* %arraydecay{{[0-9]+}}, align 128
+// CHECK: store volatile half 0xH0000, half addrspace(5)* %arraydecay{{[0-9]+}}, align 2
+// CHECK: store volatile <2 x half> zeroinitializer, <2 x half> addrspace(5)* %arraydecay{{[0-9]+}}, align 4
+// CHECK: store volatile <4 x half> <half 0xH0000, half 0xH0000, half 0xH0000, half undef>, <4 x half> addrspace(5)* %storetmp{{[0-9]+}}, align 8
+// CHECK: store volatile <4 x half> zeroinitializer, <4 x half> addrspace(5)* %arraydecay{{[0-9]+}}, align 8
+// CHECK: store volatile <8 x half> zeroinitializer, <8 x half> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
+// CHECK: store volatile <16 x half> zeroinitializer, <16 x half> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
+// CHECK: store volatile float 0.000000e+00, float addrspace(5)* %arraydecay34, align 4
+// CHECK: store volatile <2 x float> zeroinitializer, <2 x float> addrspace(5)* %arraydecay{{[0-9]+}}, align 8
+// CHECK: store volatile <4 x float> <float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float undef>, <4 x float> addrspace(5)* %storetmp{{[0-9]+}}, align 16
+// CHECK: store volatile <4 x float> zeroinitializer, <4 x float> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
+// CHECK: store volatile <8 x float> zeroinitializer, <8 x float> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
+// CHECK: store volatile <16 x float> zeroinitializer, <16 x float> addrspace(5)* %arraydecay{{[0-9]+}}, align 64
+// CHECK: store volatile double 0.000000e+00, double addrspace(5)* %arraydecay{{[0-9]+}}, align 8
+// CHECK: store volatile <2 x double> zeroinitializer, <2 x double> addrspace(5)* %arraydecay{{[0-9]+}}, align 16
+// CHECK: store volatile <4 x double> <double 0.000000e+00, double 0.000000e+00, double 0.000000e+00, double undef>, <4 x double> addrspace(5)* %storetmp{{[0-9]+}}, align 32
+// CHECK: store volatile <4 x double> zeroinitializer, <4 x double> addrspace(5)* %arraydecay{{[0-9]+}}, align 32
+// CHECK: store volatile <8 x double> zeroinitializer, <8 x double> addrspace(5)* %arraydecay{{[0-9]+}}, align 64
+// CHECK: store volatile <16 x double> zeroinitializer, <16 x double> addrspace(5)* %arraydecay{{[0-9]+}}, align 128
 kernel void private_memory_alignment_alloca()
 {
   volatile private char private_i8[4];

test/CodeGenOpenCL/amdgpu-debug-info-variable-expression.cl

 
 kernel void kernel1(
     // CHECK-DAG: ![[KERNELARG0:[0-9]+]] = !DILocalVariable(name: "KernelArg0", arg: {{[0-9]+}}, scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-    // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)** {{.*}}, metadata ![[KERNELARG0]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+    // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)* addrspace(5)* {{.*}}, metadata ![[KERNELARG0]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
     global int *KernelArg0,
     // CHECK-DAG: ![[KERNELARG1:[0-9]+]] = !DILocalVariable(name: "KernelArg1", arg: {{[0-9]+}}, scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-    // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)** {{.*}}, metadata ![[KERNELARG1]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+    // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)* addrspace(5)* {{.*}}, metadata ![[KERNELARG1]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
     constant int *KernelArg1,
     // CHECK-DAG: ![[KERNELARG2:[0-9]+]] = !DILocalVariable(name: "KernelArg2", arg: {{[0-9]+}}, scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-    // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)** {{.*}}, metadata ![[KERNELARG2]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+    // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)* addrspace(5)* {{.*}}, metadata ![[KERNELARG2]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
     local int *KernelArg2) {
   private int *Tmp0;
   int *Tmp1;
 
   // CHECK-DAG: ![[FUNCVAR0:[0-9]+]] = !DILocalVariable(name: "FuncVar0", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)** {{.*}}, metadata ![[FUNCVAR0]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR0]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
   global int *FuncVar0 = KernelArg0;
   // CHECK-DAG: ![[FUNCVAR1:[0-9]+]] = !DILocalVariable(name: "FuncVar1", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)** {{.*}}, metadata ![[FUNCVAR1]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR1]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
   constant int *FuncVar1 = KernelArg1;
   // CHECK-DAG: ![[FUNCVAR2:[0-9]+]] = !DILocalVariable(name: "FuncVar2", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)** {{.*}}, metadata ![[FUNCVAR2]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR2]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
   local int *FuncVar2 = KernelArg2;
   // CHECK-DAG: ![[FUNCVAR3:[0-9]+]] = !DILocalVariable(name: "FuncVar3", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32** {{.*}}, metadata ![[FUNCVAR3]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(5)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR3]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
   private int *FuncVar3 = Tmp0;
   // CHECK-DAG: ![[FUNCVAR4:[0-9]+]] = !DILocalVariable(name: "FuncVar4", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(4)** {{.*}}, metadata ![[FUNCVAR4]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32* addrspace(5)* {{.*}}, metadata ![[FUNCVAR4]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
   int *FuncVar4 = Tmp1;
 
   // CHECK-DAG: ![[FUNCVAR5:[0-9]+]] = distinct !DIGlobalVariable(name: "FuncVar5", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}}, isLocal: true, isDefinition: true)

   int *local FuncVar14; FuncVar14 = Tmp1;
 
   // CHECK-DAG: ![[FUNCVAR15:[0-9]+]] = !DILocalVariable(name: "FuncVar15", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)** {{.*}}, metadata ![[FUNCVAR15]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(1)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR15]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
   global int *private FuncVar15 = KernelArg0;
   // CHECK-DAG: ![[FUNCVAR16:[0-9]+]] = !DILocalVariable(name: "FuncVar16", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)** {{.*}}, metadata ![[FUNCVAR16]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(2)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR16]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
   constant int *private FuncVar16 = KernelArg1;
   // CHECK-DAG: ![[FUNCVAR17:[0-9]+]] = !DILocalVariable(name: "FuncVar17", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)** {{.*}}, metadata ![[FUNCVAR17]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(3)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR17]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
   local int *private FuncVar17 = KernelArg2;
   // CHECK-DAG: ![[FUNCVAR18:[0-9]+]] = !DILocalVariable(name: "FuncVar18", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32** {{.*}}, metadata ![[FUNCVAR18]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(5)* addrspace(5)* {{.*}}, metadata ![[FUNCVAR18]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
   private int *private FuncVar18 = Tmp0;
   // CHECK-DAG: ![[FUNCVAR19:[0-9]+]] = !DILocalVariable(name: "FuncVar19", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
-  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32 addrspace(4)** {{.*}}, metadata ![[FUNCVAR19]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
+  // CHECK-DAG: call void @llvm.dbg.declare(metadata i32* addrspace(5)* {{.*}}, metadata ![[FUNCVAR19]], metadata !DIExpression(DW_OP_constu, 1, DW_OP_swap, DW_OP_xderef)), !dbg !{{[0-9]+}}
   int *private FuncVar19 = Tmp1;
 }

test/CodeGenOpenCL/amdgpu-enqueue-kernel.cl

                  }, 100);
 }
 
-// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_kernel(<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>)
+// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_kernel(<{ i32, i32, i8*, i8 addrspace(1)*, i8 }>)
 // CHECK-SAME: #[[ATTR:[0-9]+]] !kernel_arg_addr_space !{{.*}} !kernel_arg_access_qual !{{.*}} !kernel_arg_type !{{.*}} !kernel_arg_base_type !{{.*}} !kernel_arg_type_qual !{{.*}}
 // CHECK: entry:
-// CHECK:  %1 = alloca <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>, align 8
-// CHECK:  store <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }> %0, <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %1, align 8
-// CHECK:  %2 = addrspacecast <{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i8 }>* %1 to i8 addrspace(4)*
-// CHECK:  call void @__test_block_invoke(i8 addrspace(4)* %2)
+// CHECK:  %1 = alloca <{ i32, i32, i8*, i8 addrspace(1)*, i8 }>, align 8, addrspace(5)
+// CHECK:  store <{ i32, i32, i8*, i8 addrspace(1)*, i8 }> %0, <{ i32, i32, i8*, i8 addrspace(1)*, i8 }> addrspace(5)* %1, align 8
+// CHECK:  %2 = addrspacecast <{ i32, i32, i8*, i8 addrspace(1)*, i8 }> addrspace(5)* %1 to i8*
+// CHECK:  call void @__test_block_invoke(i8* %2)
 // CHECK:  ret void
 // CHECK:}
 
-// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_2_kernel(<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>)
+// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_2_kernel(<{ i32, i32, i8*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>)
 // CHECK-SAME: #[[ATTR]] !kernel_arg_addr_space !{{.*}} !kernel_arg_access_qual !{{.*}} !kernel_arg_type !{{.*}} !kernel_arg_base_type !{{.*}} !kernel_arg_type_qual !{{.*}}
 
-// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_3_kernel(<{ i32, i32, i8 addrspace(4)*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, i8 addrspace(3)*)
+// CHECK-LABEL: define internal amdgpu_kernel void @__test_block_invoke_3_kernel(<{ i32, i32, i8*, i8 addrspace(1)*, i64 addrspace(1)*, i64, i8 }>, i8 addrspace(3)*)
 // CHECK-SAME: #[[ATTR]] !kernel_arg_addr_space !{{.*}} !kernel_arg_access_qual !{{.*}} !kernel_arg_type !{{.*}} !kernel_arg_base_type !{{.*}} !kernel_arg_type_qual !{{.*}}
 
 // CHECK: attributes #[[ATTR]] = { nounwind "enqueued-block" }

test/CodeGenOpenCL/amdgpu-env-amdgiz.cl

 // RUN: %clang_cc1 %s -O0 -triple amdgcn -emit-llvm -o - | FileCheck %s
 // RUN: %clang_cc1 %s -O0 -triple amdgcn---opencl -emit-llvm -o - | FileCheck %s
-// RUN: %clang_cc1 %s -O0 -triple amdgcn---amdgiz -emit-llvm -o - | FileCheck -check-prefix=GIZ %s
-// RUN: %clang_cc1 %s -O0 -triple amdgcn---amdgizcl -emit-llvm -o - | FileCheck -check-prefix=GIZ %s
 
-// CHECK: target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
-// GIZ: target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:32:32-p5:32:32-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"
+// CHECK: target datalayout = "e-p:64:64-p1:64:64-p2:64:64-p3:32:32-p4:32:32-p5:32:32-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"
 void foo(void) {}
-

test/CodeGenOpenCL/amdgpu-nullptr.cl

 
 // Test 0 as initializer.
 
-// CHECK: @private_p = local_unnamed_addr addrspace(1) global i8* null, align 4
+// CHECK: @private_p = local_unnamed_addr addrspace(1) global i8 addrspace(5)* null, align 4
 private char *private_p = 0;
 
-// CHECK: @local_p = local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
+// CHECK: @local_p = local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), align 4
 local char *local_p = 0;
 
 // CHECK: @global_p = local_unnamed_addr addrspace(1) global i8 addrspace(1)* null, align 8

 // CHECK: @constant_p = local_unnamed_addr addrspace(1) global i8 addrspace(2)* null, align 8
 constant char *constant_p = 0;
 
-// CHECK: @generic_p = local_unnamed_addr addrspace(1) global i8 addrspace(4)* null, align 8
+// CHECK: @generic_p = local_unnamed_addr addrspace(1) global i8* null, align 8
 generic char *generic_p = 0;
 
 // Test NULL as initializer.
 
-// CHECK: @private_p_NULL = local_unnamed_addr addrspace(1) global i8* null, align 4
+// CHECK: @private_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(5)* null, align 4
 private char *private_p_NULL = NULL;
 
-// CHECK: @local_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
+// CHECK: @local_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), align 4
 local char *local_p_NULL = NULL;
 
 // CHECK: @global_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(1)* null, align 8

 // CHECK: @constant_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(2)* null, align 8
 constant char *constant_p_NULL = NULL;
 
-// CHECK: @generic_p_NULL = local_unnamed_addr addrspace(1) global i8 addrspace(4)* null, align 8
+// CHECK: @generic_p_NULL = local_unnamed_addr addrspace(1) global i8* null, align 8
 generic char *generic_p_NULL = NULL;
 
 // Test constant folding of null pointer.
 // A null pointer should be folded to a null pointer in the target address space.
 
-// CHECK: @fold_generic = local_unnamed_addr addrspace(1) global i32 addrspace(4)* null, align 8
+// CHECK: @fold_generic = local_unnamed_addr addrspace(1) global i32* null, align 8
 generic int *fold_generic = (global int*)(generic float*)(private char*)0;
 
-// CHECK: @fold_priv = local_unnamed_addr addrspace(1) global i16* null, align 4
+// CHECK: @fold_priv = local_unnamed_addr addrspace(1) global i16 addrspace(5)* null, align 4
 private short *fold_priv = (private short*)(generic int*)(global void*)0;
 
-// CHECK: @fold_priv_arith = local_unnamed_addr addrspace(1) global i8* inttoptr (i32 10 to i8*), align 4
+// CHECK: @fold_priv_arith = local_unnamed_addr addrspace(1) global i8 addrspace(5)* inttoptr (i32 10 to i8 addrspace(5)*), align 4
 private char *fold_priv_arith = (private char*)0 + 10;
 
 // CHECK: @fold_int = local_unnamed_addr addrspace(1) global i32 14, align 4

 
 // Test static variable initialization.
 
-// NOOPT: @test_static_var_private.sp1 = internal addrspace(1) global i8* null, align 4
-// NOOPT: @test_static_var_private.sp2 = internal addrspace(1) global i8* null, align 4
-// NOOPT: @test_static_var_private.sp3 = internal addrspace(1) global i8* null, align 4
-// NOOPT: @test_static_var_private.sp4 = internal addrspace(1) global i8* null, align 4
-// NOOPT: @test_static_var_private.sp5 = internal addrspace(1) global i8* null, align 4
-// NOOPT: @test_static_var_private.SS1 = internal addrspace(1) global %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, align 8
+// NOOPT: @test_static_var_private.sp1 = internal addrspace(1) global i8 addrspace(5)* null, align 4
+// NOOPT: @test_static_var_private.sp2 = internal addrspace(1) global i8 addrspace(5)* null, align 4
+// NOOPT: @test_static_var_private.sp3 = internal addrspace(1) global i8 addrspace(5)* null, align 4
+// NOOPT: @test_static_var_private.sp4 = internal addrspace(1) global i8 addrspace(5)* null, align 4
+// NOOPT: @test_static_var_private.sp5 = internal addrspace(1) global i8 addrspace(5)* null, align 4
+// NOOPT: @test_static_var_private.SS1 = internal addrspace(1) global %struct.StructTy1 { i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8* null }, align 8
 // NOOPT: @test_static_var_private.SS2 = internal addrspace(1) global %struct.StructTy2 zeroinitializer, align 8
 
 void test_static_var_private(void) {

   static StructTy2 SS2;
 }
 
-// NOOPT: @test_static_var_local.sp1 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
-// NOOPT: @test_static_var_local.sp2 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
-// NOOPT: @test_static_var_local.sp3 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
+// NOOPT: @test_static_var_local.sp1 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), align 4
+// NOOPT: @test_static_var_local.sp2 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), align 4
+// NOOPT: @test_static_var_local.sp3 = internal addrspace(1) global i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), align 4
 // NOOPT: @test_static_var_local.sp4 = internal addrspace(1) global i8 addrspace(3)* null, align 4
 // NOOPT: @test_static_var_local.sp5 = internal addrspace(1) global i8 addrspace(3)* null, align 4
-// NOOPT: @test_static_var_local.SS1 = internal addrspace(1) global %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, align 8
+// NOOPT: @test_static_var_local.SS1 = internal addrspace(1) global %struct.StructTy1 { i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8* null }, align 8
 // NOOPT: @test_static_var_local.SS2 = internal addrspace(1) global %struct.StructTy2 zeroinitializer, align 8
 void test_static_var_local(void) {
   static local char *sp1 = 0;

 
 // Test function-scope variable initialization.
 // NOOPT-LABEL: @test_func_scope_var_private(
-// NOOPT: store i8* null, i8** %sp1, align 4
-// NOOPT: store i8* null, i8** %sp2, align 4
-// NOOPT: store i8* null, i8** %sp3, align 4
-// NOOPT: store i8* null, i8** %sp4, align 4
-// NOOPT: %[[SS1:.*]] = bitcast %struct.StructTy1* %SS1 to i8*
-// NOOPT: call void @llvm.memcpy.p0i8.p2i8.i64(i8* %[[SS1]], i8 addrspace(2)* bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_private.SS1 to i8 addrspace(2)*), i64 32, i32 8, i1 false)
-// NOOPT: %[[SS2:.*]] = bitcast %struct.StructTy2* %SS2 to i8*
-// NOOPT: call void @llvm.memset.p0i8.i64(i8* %[[SS2]], i8 0, i64 24, i32 8, i1 false)
+// NOOPT: store i8 addrspace(5)* null, i8 addrspace(5)* addrspace(5)* %sp1, align 4
+// NOOPT: store i8 addrspace(5)* null, i8 addrspace(5)* addrspace(5)* %sp2, align 4
+// NOOPT: store i8 addrspace(5)* null, i8 addrspace(5)* addrspace(5)* %sp3, align 4
+// NOOPT: store i8 addrspace(5)* null, i8 addrspace(5)* addrspace(5)* %sp4, align 4
+// NOOPT: %[[SS1:.*]] = bitcast %struct.StructTy1 addrspace(5)* %SS1 to i8 addrspace(5)*
+// NOOPT: call void @llvm.memcpy.p5i8.p2i8.i64(i8 addrspace(5)* %[[SS1]], i8 addrspace(2)* bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_private.SS1 to i8 addrspace(2)*), i64 32, i32 8, i1 false)
+// NOOPT: %[[SS2:.*]] = bitcast %struct.StructTy2 addrspace(5)* %SS2 to i8 addrspace(5)*
+// NOOPT: call void @llvm.memset.p5i8.i64(i8 addrspace(5)* %[[SS2]], i8 0, i64 24, i32 8, i1 false)
 void test_func_scope_var_private(void) {
   private char *sp1 = 0;
   private char *sp2 = NULL;

 
 // Test function-scope variable initialization.
 // NOOPT-LABEL: @test_func_scope_var_local(
-// NOOPT: store i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(3)** %sp1, align 4
-// NOOPT: store i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(3)** %sp2, align 4
-// NOOPT: store i8 addrspace(3)* null, i8 addrspace(3)** %sp3, align 4
-// NOOPT: store i8 addrspace(3)* null, i8 addrspace(3)** %sp4, align 4
-// NOOPT: %[[SS1:.*]] = bitcast %struct.StructTy1* %SS1 to i8*
-// NOOPT: call void @llvm.memcpy.p0i8.p2i8.i64(i8* %[[SS1]], i8 addrspace(2)* bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_local.SS1 to i8 addrspace(2)*), i64 32, i32 8, i1 false)
-// NOOPT: %[[SS2:.*]] = bitcast %struct.StructTy2* %SS2 to i8*
-// NOOPT: call void @llvm.memset.p0i8.i64(i8* %[[SS2]], i8 0, i64 24, i32 8, i1 false)
+// NOOPT: store i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(3)* addrspace(5)* %sp1, align 4
+// NOOPT: store i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(3)* addrspace(5)* %sp2, align 4
+// NOOPT: store i8 addrspace(3)* null, i8 addrspace(3)* addrspace(5)* %sp3, align 4
+// NOOPT: store i8 addrspace(3)* null, i8 addrspace(3)* addrspace(5)* %sp4, align 4
+// NOOPT: %[[SS1:.*]] = bitcast %struct.StructTy1 addrspace(5)* %SS1 to i8 addrspace(5)*
+// NOOPT: call void @llvm.memcpy.p5i8.p2i8.i64(i8 addrspace(5)* %[[SS1]], i8 addrspace(2)* bitcast (%struct.StructTy1 addrspace(2)* @test_func_scope_var_local.SS1 to i8 addrspace(2)*), i64 32, i32 8, i1 false)
+// NOOPT: %[[SS2:.*]] = bitcast %struct.StructTy2 addrspace(5)* %SS2 to i8 addrspace(5)*
+// NOOPT: call void @llvm.memset.p5i8.i64(i8 addrspace(5)* %[[SS2]], i8 0, i64 24, i32 8, i1 false)
 void test_func_scope_var_local(void) {
   local char *sp1 = 0;
   local char *sp2 = NULL;

 // cannot have common linkage since common linkage requires zero initialization
 // and does not have explicit section.
 
-// CHECK: @p1 = common local_unnamed_addr addrspace(1) global i8* null, align 4
+// CHECK: @p1 = common local_unnamed_addr addrspace(1) global i8 addrspace(5)* null, align 4
 private char *p1;
 
-// CHECK: @p2 = weak local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), align 4
+// CHECK: @p2 = weak local_unnamed_addr addrspace(1) global i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), align 4
 local char *p2;
 
 // CHECK: @p3 = common local_unnamed_addr addrspace(1) global i8 addrspace(2)* null, align 8

 // CHECK: @p4 = common local_unnamed_addr addrspace(1) global i8 addrspace(1)* null, align 8
 global char *p4;
 
-// CHECK: @p5 = common local_unnamed_addr addrspace(1) global i8 addrspace(4)* null, align 8
+// CHECK: @p5 = common local_unnamed_addr addrspace(1) global i8* null, align 8
 generic char *p5;
 
 // Test default initialization of sturcture.
 
-// CHECK: @S1 = weak local_unnamed_addr addrspace(1) global %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, align 8
+// CHECK: @S1 = weak local_unnamed_addr addrspace(1) global %struct.StructTy1 { i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8* null }, align 8
 StructTy1 S1;
 
 // CHECK: @S2 = common local_unnamed_addr addrspace(1) global %struct.StructTy2 zeroinitializer, align 8
 StructTy2 S2;
 
 // Test default initialization of array.
-// CHECK: @A1 = weak local_unnamed_addr addrspace(1) global [2 x %struct.StructTy1] [%struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }, %struct.StructTy1 { i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8 addrspace(4)* null }], align 8
+// CHECK: @A1 = weak local_unnamed_addr addrspace(1) global [2 x %struct.StructTy1] [%struct.StructTy1 { i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8* null }, %struct.StructTy1 { i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(2)* null, i8 addrspace(1)* null, i8* null }], align 8
 StructTy1 A1[2];
 
 // CHECK: @A2 = common local_unnamed_addr addrspace(1) global [2 x %struct.StructTy2] zeroinitializer, align 8

 // Test comparison with 0.
 
 // CHECK-LABEL: cmp_private
-// CHECK: icmp eq i8* %p, null
+// CHECK: icmp eq i8 addrspace(5)* %p, null
 void cmp_private(private char* p) {
   if (p != 0)
     *p = 0;
 }
 
 // CHECK-LABEL: cmp_local
-// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*)
+// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8* null to i8 addrspace(3)*)
 void cmp_local(local char* p) {
   if (p != 0)
     *p = 0;

 }
 
 // CHECK-LABEL: cmp_generic
-// CHECK: icmp eq i8 addrspace(4)* %p, null
+// CHECK: icmp eq i8* %p, null
 void cmp_generic(generic char* p) {
   if (p != 0)
     *p = 0;

 // Test comparison with NULL.
 
 // CHECK-LABEL: cmp_NULL_private
-// CHECK: icmp eq i8* %p, null
+// CHECK: icmp eq i8 addrspace(5)* %p, null
 void cmp_NULL_private(private char* p) {
   if (p != NULL)
     *p = 0;
 }
 
 // CHECK-LABEL: cmp_NULL_local
-// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*)
+// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8* null to i8 addrspace(3)*)
 void cmp_NULL_local(local char* p) {
   if (p != NULL)
     *p = 0;

 }
 
 // CHECK-LABEL: cmp_NULL_generic
-// CHECK: icmp eq i8 addrspace(4)* %p, null
+// CHECK: icmp eq i8* %p, null
 void cmp_NULL_generic(generic char* p) {
   if (p != NULL)
     *p = 0;

 
 // Test storage 0 as null pointer.
 // CHECK-LABEL: test_storage_null_pointer
-// CHECK: store i8* null, i8* addrspace(4)* %arg_private
-// CHECK: store i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(3)* addrspace(4)* %arg_local
-// CHECK: store i8 addrspace(1)* null, i8 addrspace(1)* addrspace(4)* %arg_global
-// CHECK: store i8 addrspace(2)* null, i8 addrspace(2)* addrspace(4)* %arg_constant
-// CHECK: store i8 addrspace(4)* null, i8 addrspace(4)* addrspace(4)* %arg_generic
+// CHECK: store i8 addrspace(5)* null, i8 addrspace(5)** %arg_private
+// CHECK: store i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(3)** %arg_local
+// CHECK: store i8 addrspace(1)* null, i8 addrspace(1)** %arg_global
+// CHECK: store i8 addrspace(2)* null, i8 addrspace(2)** %arg_constant
+// CHECK: store i8* null, i8** %arg_generic
 void test_storage_null_pointer(private char** arg_private,
                                local char** arg_local,
                                global char** arg_global,

 
 // Test storage NULL as null pointer.
 // CHECK-LABEL: test_storage_null_pointer_NULL
-// CHECK: store i8* null, i8* addrspace(4)* %arg_private
-// CHECK: store i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(3)* addrspace(4)* %arg_local
-// CHECK: store i8 addrspace(1)* null, i8 addrspace(1)* addrspace(4)* %arg_global
-// CHECK: store i8 addrspace(2)* null, i8 addrspace(2)* addrspace(4)* %arg_constant
-// CHECK: store i8 addrspace(4)* null, i8 addrspace(4)* addrspace(4)* %arg_generic
+// CHECK: store i8 addrspace(5)* null, i8 addrspace(5)** %arg_private
+// CHECK: store i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(3)** %arg_local
+// CHECK: store i8 addrspace(1)* null, i8 addrspace(1)** %arg_global
+// CHECK: store i8 addrspace(2)* null, i8 addrspace(2)** %arg_constant
+// CHECK: store i8* null, i8** %arg_generic
 void test_storage_null_pointer_NULL(private char** arg_private,
                                     local char** arg_local,
                                     global char** arg_global,

                                       generic char* arg_generic);
 
 // CHECK-LABEL: test_pass_null_pointer_arg
-// CHECK: call void @test_pass_null_pointer_arg_calee(i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(1)* null, i8 addrspace(2)* null, i8 addrspace(4)* null)
-// CHECK: call void @test_pass_null_pointer_arg_calee(i8* null, i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*), i8 addrspace(1)* null, i8 addrspace(2)* null, i8 addrspace(4)* null)
+// CHECK: call void @test_pass_null_pointer_arg_calee(i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(1)* null, i8 addrspace(2)* null, i8* null)
+// CHECK: call void @test_pass_null_pointer_arg_calee(i8 addrspace(5)* null, i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*), i8 addrspace(1)* null, i8 addrspace(2)* null, i8* null)
 void test_pass_null_pointer_arg(void) {
   test_pass_null_pointer_arg_calee(0, 0, 0, 0, 0);
   test_pass_null_pointer_arg_calee(NULL, NULL, NULL, NULL, NULL);

                                            size_t arg_generic);
 
 // CHECK-LABEL: test_cast_null_pointer_to_sizet
-// CHECK: call void @test_cast_null_pointer_to_sizet_calee(i64 0, i64 ptrtoint (i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*) to i64), i64 0, i64 0, i64 0)
-// CHECK: call void @test_cast_null_pointer_to_sizet_calee(i64 0, i64 ptrtoint (i8 addrspace(3)* addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*) to i64), i64 0, i64 0, i64 0)
+// CHECK: call void @test_cast_null_pointer_to_sizet_calee(i64 0, i64 ptrtoint (i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*) to i64), i64 0, i64 0, i64 0)
+// CHECK: call void @test_cast_null_pointer_to_sizet_calee(i64 0, i64 ptrtoint (i8 addrspace(3)* addrspacecast (i8* null to i8 addrspace(3)*) to i64), i64 0, i64 0, i64 0)
 void test_cast_null_pointer_to_sizet(void) {
   test_cast_null_pointer_to_sizet_calee((size_t)((private char*)0),
                                         (size_t)((local char*)0),

 // Test cast to bool.
 
 // CHECK-LABEL: cast_bool_private
-// CHECK: icmp eq i8* %p, null
+// CHECK: icmp eq i8 addrspace(5)* %p, null
 void cast_bool_private(private char* p) {
   if (p)
     *p = 0;
 }
 
 // CHECK-LABEL: cast_bool_local
-// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*)
+// CHECK: icmp eq i8 addrspace(3)* %p, addrspacecast (i8* null to i8 addrspace(3)*)
 void cast_bool_local(local char* p) {
   if (p)
     *p = 0;

 }
 
 // CHECK-LABEL: cast_bool_generic
-// CHECK: icmp eq i8 addrspace(4)* %p, null
+// CHECK: icmp eq i8* %p, null
 void cast_bool_generic(generic char* p) {
   if (p)
     *p = 0;

 } StructTy3;
 
 // CHECK-LABEL: test_memset_private
-// CHECK: call void @llvm.memset.p0i8.i64(i8* nonnull {{.*}}, i8 0, i64 40, i32 8, i1 false)
+// CHECK: call void @llvm.memset.p5i8.i64(i8 addrspace(5)* {{.*}}, i8 0, i64 40, i32 8, i1 false)
 void test_memset_private(private StructTy3 *ptr) {
   StructTy3 S3 = {0, 0, 0, 0, 0};
   *ptr = S3;

 // A 0 literal casted to pointer should become a null pointer.
 
 // CHECK-LABEL: test_cast_0_to_local_ptr
-// CHECK: ret i32 addrspace(3)* addrspacecast (i32 addrspace(4)* null to i32 addrspace(3)*)
+// CHECK: ret i32 addrspace(3)* addrspacecast (i32* null to i32 addrspace(3)*)
 local int* test_cast_0_to_local_ptr(void) {
   return (local int*)0;
 }
 
 // CHECK-LABEL: test_cast_0_to_private_ptr
-// CHECK: ret i32* null
+// CHECK: ret i32 addrspace(5)* null
 private int* test_cast_0_to_private_ptr(void) {
   return (private int*)0;
 }

 // zero value.
 
 // CHECK-LABEL: test_cast_int_to_ptr1_private
-// CHECK: ret i32* null
+// CHECK: ret i32 addrspace(5)* null
 private int* test_cast_int_to_ptr1_private(void) {
   return (private int*)((void)0, 0);
 }

 }
 
 // CHECK-LABEL: test_cast_int_to_ptr2
-// CHECK: ret i32* null
+// CHECK: ret i32 addrspace(5)* null
 private int* test_cast_int_to_ptr2(void) {
   int x = 0;
   return (private int*)x;

 }
 
 // CHECK-LABEL: test_not_private_ptr
-// CHECK: %[[lnot:.*]] = icmp eq i8* %p, null
+// CHECK: %[[lnot:.*]] = icmp eq i8 addrspace(5)* %p, null
 // CHECK: %[[lnot_ext:.*]] = zext i1 %[[lnot]] to i32
 // CHECK: ret i32 %[[lnot_ext]]
 int test_not_private_ptr(private char* p) {

 }
 
 // CHECK-LABEL: test_not_local_ptr
-// CHECK: %[[lnot:.*]] = icmp eq i8 addrspace(3)* %p, addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*)
+// CHECK: %[[lnot:.*]] = icmp eq i8 addrspace(3)* %p, addrspacecast (i8* null to i8 addrspace(3)*)
 // CHECK: %[[lnot_ext:.*]] = zext i1 %[[lnot]] to i32
 // CHECK: ret i32 %[[lnot_ext]]
 int test_not_local_ptr(local char* p) {

 
 
 // CHECK-LABEL: test_and_ptr
-// CHECK: %[[tobool:.*]] = icmp ne i8* %p1, null
-// CHECK: %[[tobool1:.*]] = icmp ne i8 addrspace(3)* %p2, addrspacecast (i8 addrspace(4)* null to i8 addrspace(3)*)
+// CHECK: %[[tobool:.*]] = icmp ne i8 addrspace(5)* %p1, null
+// CHECK: %[[tobool1:.*]] = icmp ne i8 addrspace(3)* %p2, addrspacecast (i8* null to i8 addrspace(3)*)
 // CHECK: %[[res:.*]] = and i1 %[[tobool]], %[[tobool1]]
 // CHECK: %[[land_ext:.*]] = zext i1 %[[res]] to i32
 // CHECK: ret i32 %[[land_ext]]

 // Test folding of null pointer in function scope.
 // NOOPT-LABEL: test_fold_private
 // NOOPT: call void @test_fold_callee
-// NOOPT: store i32 addrspace(1)* null, i32 addrspace(1)** %glob, align 8
+// NOOPT: store i32 addrspace(1)* null, i32 addrspace(1)* addrspace(5)* %glob, align 8
 // NOOPT: %{{.*}} = sub i64 %{{.*}}, 0
 // NOOPT: call void @test_fold_callee
 // NOOPT: %{{.*}} = add nsw i64 %{{.*}}, 0

 
 // NOOPT-LABEL: test_fold_local
 // NOOPT: call void @test_fold_callee
-// NOOPT: store i32 addrspace(1)* null, i32 addrspace(1)** %glob, align 8
+// NOOPT: store i32 addrspace(1)* null, i32 addrspace(1)* addrspace(5)* %glob, align 8
 // NOOPT: %{{.*}} = sub i64 %{{.*}}, 0
 // NOOPT: call void @test_fold_callee
-// NOOPT: %{{.*}} = add nsw i64 %{{.*}}, sext (i32 ptrtoint (i32 addrspace(3)* addrspacecast (i32 addrspace(4)* null to i32 addrspace(3)*) to i32) to i64)
+// NOOPT: %{{.*}} = add nsw i64 %{{.*}}, sext (i32 ptrtoint (i32 addrspace(3)* addrspacecast (i32* null to i32 addrspace(3)*) to i32) to i64)
 // NOOPT: %{{.*}} = sub nsw i64 %{{.*}}, 1
 void test_fold_local(void) {
   global int* glob = (test_fold_callee(), (global int*)(generic char*)0);

test/CodeGenOpenCL/blocks.cl

 // RUN: %clang_cc1 %s -cl-std=CL2.0 -emit-llvm -o - -O0 -triple spir-unknown-unknown | FileCheck -check-prefixes=COMMON,SPIR %s
 // RUN: %clang_cc1 %s -cl-std=CL2.0 -emit-llvm -o - -O0 -triple amdgcn-amd-amdhsa-opencl | FileCheck -check-prefixes=COMMON,AMD %s
 
-// COMMON: %struct.__opencl_block_literal_generic = type { i32, i32, i8 addrspace(4)* }
+// SPIR: %struct.__opencl_block_literal_generic = type { i32, i32, i8 addrspace(4)* }
+// AMD: %struct.__opencl_block_literal_generic = type { i32, i32, i8* }
 // SPIR: @__block_literal_global = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 12, i32 4, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* @block_A_block_invoke to i8*) to i8 addrspace(4)*) }
-// AMD: @__block_literal_global = internal addrspace(1) constant { i32, i32, i8 addrspace(4)* } { i32 16, i32 8, i8 addrspace(4)* addrspacecast (i8* bitcast (void (i8 addrspace(4)*, i8 addrspace(3)*)* @block_A_block_invoke to i8*) to i8 addrspace(4)*) }
+// AMD: @__block_literal_global = internal addrspace(1) constant { i32, i32, i8* } { i32 16, i32 8, i8* bitcast (void (i8*, i8 addrspace(3)*)* @block_A_block_invoke to i8*) }
 // COMMON-NOT: .str
 
-// COMMON-LABEL: define internal {{.*}}void @block_A_block_invoke(i8 addrspace(4)* %.block_descriptor, i8 addrspace(3)* %a)
+// SPIR-LABEL: define internal {{.*}}void @block_A_block_invoke(i8 addrspace(4)* %.block_descriptor, i8 addrspace(3)* %a)
+// AMD-LABEL: define internal {{.*}}void @block_A_block_invoke(i8* %.block_descriptor, i8 addrspace(3)* %a)
 void (^block_A)(local void *) = ^(local void *a) {
   return;
 };

   // COMMON-NOT: %block.flags
   // COMMON-NOT: %block.reserved
   // COMMON-NOT: %block.descriptor
-  // COMMON: %[[block_size:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %block, i32 0, i32 0
+  // SPIR: %[[block_size:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %block, i32 0, i32 0
+  // AMD: %[[block_size:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }> addrspace(5)* %block, i32 0, i32 0
   // SPIR: store i32 16, i32* %[[block_size]]
-  // AMD: store i32 20, i32* %[[block_size]]
-  // COMMON: %[[block_align:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %block, i32 0, i32 1
+  // AMD: store i32 20, i32 addrspace(5)* %[[block_size]]
+  // SPIR: %[[block_align:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %block, i32 0, i32 1
+  // AMD: %[[block_align:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }> addrspace(5)* %block, i32 0, i32 1
   // SPIR: store i32 4, i32* %[[block_align]]
-  // AMD: store i32 8, i32* %[[block_align]]
-  // COMMON: %[[block_invoke:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block:.*]], i32 0, i32 2
-  // COMMON: store i8 addrspace(4)* addrspacecast (i8* bitcast (i32 (i8 addrspace(4)*)* @__foo_block_invoke to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %[[block_invoke]]
-  // COMMON: %[[block_captured:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]], i32 0, i32 3
-  // COMMON: %[[i_value:.*]] = load i32, i32* %i
-  // COMMON: store i32 %[[i_value]], i32* %[[block_captured]],
-  // COMMON: %[[blk_ptr:.*]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]] to i32 ()*
-  // COMMON: %[[blk_gen_ptr:.*]] = addrspacecast i32 ()* %[[blk_ptr]] to i32 () addrspace(4)*
-  // COMMON: store i32 () addrspace(4)* %[[blk_gen_ptr]], i32 () addrspace(4)** %[[block_B:.*]],
-  // COMMON: %[[blk_gen_ptr:.*]] = load i32 () addrspace(4)*, i32 () addrspace(4)** %[[block_B]]
-  // COMMON: %[[block_literal:.*]] = bitcast i32 () addrspace(4)* %[[blk_gen_ptr]] to %struct.__opencl_block_literal_generic addrspace(4)*
-  // COMMON: %[[invoke_addr:.*]] = getelementptr inbounds %struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]], i32 0, i32 2
-  // COMMON: %[[blk_gen_ptr:.*]] = bitcast %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]] to i8 addrspace(4)*
-  // COMMON: %[[invoke_func_ptr:.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* %[[invoke_addr]]
-  // COMMON: %[[invoke_func:.*]] = addrspacecast i8 addrspace(4)* %[[invoke_func_ptr]] to i32 (i8 addrspace(4)*)*
-  // COMMON: call {{.*}}i32 %[[invoke_func]](i8 addrspace(4)* %[[blk_gen_ptr]])
+  // AMD: store i32 8, i32 addrspace(5)* %[[block_align]]
+  // SPIR: %[[block_invoke:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block:.*]], i32 0, i32 2
+  // SPIR: store i8 addrspace(4)* addrspacecast (i8* bitcast (i32 (i8 addrspace(4)*)* @__foo_block_invoke to i8*) to i8 addrspace(4)*), i8 addrspace(4)** %[[block_invoke]]
+  // SPIR: %[[block_captured:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]], i32 0, i32 3
+  // SPIR: %[[i_value:.*]] = load i32, i32* %i
+  // SPIR: store i32 %[[i_value]], i32* %[[block_captured]],
+  // SPIR: %[[blk_ptr:.*]] = bitcast <{ i32, i32, i8 addrspace(4)*, i32 }>* %[[block]] to i32 ()*
+  // SPIR: %[[blk_gen_ptr:.*]] = addrspacecast i32 ()* %[[blk_ptr]] to i32 () addrspace(4)*
+  // SPIR: store i32 () addrspace(4)* %[[blk_gen_ptr]], i32 () addrspace(4)** %[[block_B:.*]],
+  // SPIR: %[[blk_gen_ptr:.*]] = load i32 () addrspace(4)*, i32 () addrspace(4)** %[[block_B]]
+  // SPIR: %[[block_literal:.*]] = bitcast i32 () addrspace(4)* %[[blk_gen_ptr]] to %struct.__opencl_block_literal_generic addrspace(4)*
+  // SPIR: %[[invoke_addr:.*]] = getelementptr inbounds %struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]], i32 0, i32 2
+  // SPIR: %[[blk_gen_ptr:.*]] = bitcast %struct.__opencl_block_literal_generic addrspace(4)* %[[block_literal]] to i8 addrspace(4)*
+  // SPIR: %[[invoke_func_ptr:.*]] = load i8 addrspace(4)*, i8 addrspace(4)* addrspace(4)* %[[invoke_addr]]
+  // SPIR: %[[invoke_func:.*]] = addrspacecast i8 addrspace(4)* %[[invoke_func_ptr]] to i32 (i8 addrspace(4)*)*
+  // SPIR: call {{.*}}i32 %[[invoke_func]](i8 addrspace(4)* %[[blk_gen_ptr]])
+  // AMD: %[[block_invoke:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }> addrspace(5)* %[[block:.*]], i32 0, i32 2
+  // AMD: store i8* bitcast (i32 (i8*)* @__foo_block_invoke to i8*), i8* addrspace(5)* %[[block_invoke]]
+  // AMD: %[[block_captured:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }> addrspace(5)* %[[block]], i32 0, i32 3
+  // AMD: %[[i_value:.*]] = load i32, i32 addrspace(5)* %i
+  // AMD: store i32 %[[i_value]], i32 addrspace(5)* %[[block_captured]],
+  // AMD: %[[blk_ptr:.*]] = bitcast <{ i32, i32, i8*, i32 }> addrspace(5)* %[[block]] to i32 () addrspace(5)*
+  // AMD: %[[blk_gen_ptr:.*]] = addrspacecast i32 () addrspace(5)* %[[blk_ptr]] to i32 ()*
+  // AMD: store i32 ()* %[[blk_gen_ptr]], i32 ()* addrspace(5)* %[[block_B:.*]],
+  // AMD: %[[blk_gen_ptr:.*]] = load i32 ()*, i32 ()* addrspace(5)* %[[block_B]]
+  // AMD: %[[block_literal:.*]] = bitcast i32 ()* %[[blk_gen_ptr]] to %struct.__opencl_block_literal_generic*
+  // AMD: %[[invoke_addr:.*]] = getelementptr inbounds %struct.__opencl_block_literal_generic, %struct.__opencl_block_literal_generic* %[[block_literal]], i32 0, i32 2
+  // AMD: %[[blk_gen_ptr:.*]] = bitcast %struct.__opencl_block_literal_generic* %[[block_literal]] to i8*
+  // AMD: %[[invoke_func_ptr:.*]] = load i8*, i8** %[[invoke_addr]]
+  // AMD: %[[invoke_func:.*]] = bitcast i8* %[[invoke_func_ptr]] to i32 (i8*)*
+  // AMD: call {{.*}}i32 %[[invoke_func]](i8* %[[blk_gen_ptr]])
 
   int (^ block_B)(void) = ^{
     return i;

   block_B();
 }
 
-// COMMON-LABEL: define internal {{.*}}i32 @__foo_block_invoke(i8 addrspace(4)* %.block_descriptor)
-// COMMON:  %[[block:.*]] = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)*, i32 }> addrspace(4)*
-// COMMON:  %[[block_capture_addr:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }> addrspace(4)* %[[block]], i32 0, i32 3
-// COMMON:  %[[block_capture:.*]] = load i32, i32 addrspace(4)* %[[block_capture_addr]]
+// SPIR-LABEL: define internal {{.*}}i32 @__foo_block_invoke(i8 addrspace(4)* %.block_descriptor)
+// SPIR:  %[[block:.*]] = bitcast i8 addrspace(4)* %.block_descriptor to <{ i32, i32, i8 addrspace(4)*, i32 }> addrspace(4)*
+// SPIR:  %[[block_capture_addr:.*]] = getelementptr inbounds <{ i32, i32, i8 addrspace(4)*, i32 }>, <{ i32, i32, i8 addrspace(4)*, i32 }> addrspace(4)* %[[block]], i32 0, i32 3
+// SPIR:  %[[block_capture:.*]] = load i32, i32 addrspace(4)* %[[block_capture_addr]]
+// AMD-LABEL: define internal {{.*}}i32 @__foo_block_invoke(i8* %.block_descriptor)
+// AMD:  %[[block:.*]] = bitcast i8* %.block_descriptor to <{ i32, i32, i8*, i32 }>*
+// AMD:  %[[block_capture_addr:.*]] = getelementptr inbounds <{ i32, i32, i8*, i32 }>, <{ i32, i32, i8*, i32 }>* %[[block]], i32 0, i32 3
+// AMD:  %[[block_capture:.*]] = load i32, i32* %[[block_capture_addr]]
 
 // COMMON-NOT: define{{.*}}@__foo_block_invoke_kernel

test/CodeGenOpenCL/byval.cl

 // RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn %s | FileCheck %s
 // RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn---opencl %s | FileCheck %s
-// RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn---amdgizcl %s | FileCheck %s -check-prefix=AMDGIZ
 
 struct A {
   int x[100];

 
 int g() {
   struct A a;
-  // CHECK: call i32 @f(%struct.A* byval{{.*}}%a)
-  // AMDGIZ: call i32 @f(%struct.A addrspace(5)* byval{{.*}}%a)
+  // CHECK: call i32 @f(%struct.A addrspace(5)* byval{{.*}}%a)
   return f(a);
 }
 
-// CHECK: declare i32 @f(%struct.A* byval{{.*}})
-// AMDGIZ: declare i32 @f(%struct.A addrspace(5)* byval{{.*}})
+// CHECK: declare i32 @f(%struct.A addrspace(5)* byval{{.*}})

test/CodeGenOpenCL/opencl_types.cl

   sampler_t smp = CLK_ADDRESS_CLAMP_TO_EDGE|CLK_NORMALIZED_COORDS_TRUE|CLK_FILTER_LINEAR;
   // CHECK-COM: alloca %opencl.sampler_t addrspace(2)*
   event_t evt;
-  // CHECK-COM: alloca %opencl.event_t*
+  // CHECK-SPIR: alloca %opencl.event_t*
+  // CHECK-AMDGCN: alloca %opencl.event_t addrspace(5)*
   clk_event_t clk_evt;
   // CHECK-SPIR: alloca %opencl.clk_event_t*
   // CHECK-AMDGCN: alloca %opencl.clk_event_t addrspace(1)*

test/CodeGenOpenCL/size_t.cl

 // RUN: %clang_cc1 %s -cl-std=CL2.0 -finclude-default-header -emit-llvm -O0 -triple spir-unknown-unknown -o - | FileCheck --check-prefix=SZ32 %s
 // RUN: %clang_cc1 %s -cl-std=CL2.0 -finclude-default-header -emit-llvm -O0 -triple spir64-unknown-unknown -o - | FileCheck --check-prefix=SZ64 --check-prefix=SZ64ONLY %s
-// RUN: %clang_cc1 %s -cl-std=CL2.0 -finclude-default-header -emit-llvm -O0 -triple amdgcn -o - | FileCheck --check-prefix=SZ64 --check-prefix=AMDONLY %s
-// RUN: %clang_cc1 %s -cl-std=CL2.0 -finclude-default-header -emit-llvm -O0 -triple amdgcn---opencl -o - | FileCheck --check-prefix=SZ64 --check-prefix=AMDONLY %s
+// RUN: %clang_cc1 %s -cl-std=CL2.0 -finclude-default-header -emit-llvm -O0 -triple amdgcn -o - | FileCheck --check-prefix=SZ64 --check-prefix=AMDGCN %s
+// RUN: %clang_cc1 %s -cl-std=CL2.0 -finclude-default-header -emit-llvm -O0 -triple amdgcn---opencl -o - | FileCheck --check-prefix=SZ64 --check-prefix=AMDGCN %s
 
 //SZ32: define{{.*}} i32 @test_ptrtoint_private(i8* %x)
 //SZ32: ptrtoint i8* %{{.*}} to i32
-//SZ64: define{{.*}} i64 @test_ptrtoint_private(i8* %x)
-//SZ64: ptrtoint i8* %{{.*}} to i64
+//SZ64ONLY: define{{.*}} i64 @test_ptrtoint_private(i8* %x)
+//SZ64ONLY: ptrtoint i8* %{{.*}} to i64
+//AMDGCN: define{{.*}} i64 @test_ptrtoint_private(i8 addrspace(5)* %x)
+//AMDGCN: ptrtoint i8 addrspace(5)* %{{.*}} to i64
 size_t test_ptrtoint_private(private char* x) {
   return (size_t)x;
 }

 
 //SZ32: define{{.*}} i32 @test_ptrtoint_generic(i8 addrspace(4)* %x)
 //SZ32: ptrtoint i8 addrspace(4)* %{{.*}} to i32
-//SZ64: define{{.*}} i64 @test_ptrtoint_generic(i8 addrspace(4)* %x)
-//SZ64: ptrtoint i8 addrspace(4)* %{{.*}} to i64
+//SZ64ONLY: define{{.*}} i64 @test_ptrtoint_generic(i8 addrspace(4)* %x)
+//SZ64ONLY: ptrtoint i8 addrspace(4)* %{{.*}} to i64
+//AMDGCN: define{{.*}} i64 @test_ptrtoint_generic(i8* %x)
+//AMDGCN: ptrtoint i8* %{{.*}} to i64
 size_t test_ptrtoint_generic(generic char* x) {
   return (size_t)x;
 }
 
 //SZ32: define{{.*}} i8* @test_inttoptr_private(i32 %x)
 //SZ32: inttoptr i32 %{{.*}} to i8*
-//SZ64: define{{.*}} i8* @test_inttoptr_private(i64 %x)
-//AMDONLY: trunc i64 %{{.*}} to i32
-//AMDONLY: inttoptr i32 %{{.*}} to i8*
+//SZ64ONLY: define{{.*}} i8* @test_inttoptr_private(i64 %x)
 //SZ64ONLY: inttoptr i64 %{{.*}} to i8*
+//AMDGCN: define{{.*}} i8 addrspace(5)* @test_inttoptr_private(i64 %x)
+//AMDGCN: trunc i64 %{{.*}} to i32
+//AMDGCN: inttoptr i32 %{{.*}} to i8 addrspace(5)*
 private char* test_inttoptr_private(size_t x) {
   return (private char*)x;
 }

 //SZ32: define{{.*}} i8 addrspace(3)* @test_add_local(i8 addrspace(3)* %x, i32 %y)
 //SZ32: getelementptr inbounds i8, i8 addrspace(3)* %{{.*}}, i32
 //SZ64: define{{.*}} i8 addrspace(3)* @test_add_local(i8 addrspace(3)* %x, i64 %y)
-//AMDONLY: trunc i64 %{{.*}} to i32
-//AMDONLY: getelementptr inbounds i8, i8 addrspace(3)* %{{.*}}, i32
+//AMDGCN: trunc i64 %{{.*}} to i32
+//AMDGCN: getelementptr inbounds i8, i8 addrspace(3)* %{{.*}}, i32
 //SZ64ONLY: getelementptr inbounds i8, i8 addrspace(3)* %{{.*}}, i64
 local char* test_add_local(local char* x, ptrdiff_t y) {
   return x + y;

 //SZ32: define{{.*}} i32 @test_sub_private(i8* %x, i8* %y)
 //SZ32: ptrtoint i8* %{{.*}} to i32
 //SZ32: ptrtoint i8* %{{.*}} to i32
-//SZ64: define{{.*}} i64 @test_sub_private(i8* %x, i8* %y)
-//SZ64: ptrtoint i8* %{{.*}} to i64
-//SZ64: ptrtoint i8* %{{.*}} to i64
+//SZ64ONLY: define{{.*}} i64 @test_sub_private(i8* %x, i8* %y)
+//SZ64ONLY: ptrtoint i8* %{{.*}} to i64
+//SZ64ONLY: ptrtoint i8* %{{.*}} to i64
+//AMDGCN: define{{.*}} i64 @test_sub_private(i8 addrspace(5)* %x, i8 addrspace(5)* %y)
+//AMDGCN: ptrtoint i8 addrspace(5)* %{{.*}} to i64
+//AMDGCN: ptrtoint i8 addrspace(5)* %{{.*}} to i64
 ptrdiff_t test_sub_private(private char* x, private char *y) {
   return x - y;
 }

 //SZ32: define{{.*}} i32 @test_sub_mix(i8* %x, i8 addrspace(4)* %y)
 //SZ32: ptrtoint i8* %{{.*}} to i32
 //SZ32: ptrtoint i8 addrspace(4)* %{{.*}} to i32
-//SZ64: define{{.*}} i64 @test_sub_mix(i8* %x, i8 addrspace(4)* %y)
-//SZ64: ptrtoint i8* %{{.*}} to i64
-//SZ64: ptrtoint i8 addrspace(4)* %{{.*}} to i64
+//SZ64ONLY: define{{.*}} i64 @test_sub_mix(i8* %x, i8 addrspace(4)* %y)
+//SZ64ONLY: ptrtoint i8* %{{.*}} to i64
+//SZ64ONLY: ptrtoint i8 addrspace(4)* %{{.*}} to i64
+//AMDGCN: define{{.*}} i64 @test_sub_mix(i8 addrspace(5)* %x, i8* %y)
+//AMDGCN: ptrtoint i8 addrspace(5)* %{{.*}} to i64
+//AMDGCN: ptrtoint i8* %{{.*}} to i64
 ptrdiff_t test_sub_mix(private char* x, generic char *y) {
   return x - y;
 }