diff --git a/clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl b/clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
index aec00e7..8b03fb0 100644
--- a/clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
+++ b/clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
@@ -309,7 +309,7 @@
 // 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) { }
 
-// CHECK: void @func_flexible_array_arg(%struct.flexible_array addrspace(5)* byval nocapture align 4 %arg)
+// CHECK: void @func_flexible_array_arg(%struct.flexible_array addrspace(5)* nocapture byval align 4 %arg)
 void func_flexible_array_arg(flexible_array arg) { }
 
 // CHECK: define float @func_f32_ret()
@@ -450,11 +450,11 @@
 // 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) { }
 
-// 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)
+// 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)* nocapture byval 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?
-// 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)
+// 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)* nocapture byval 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)
@@ -469,7 +469,7 @@
 // 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) { }
 
-// 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)
+// CHECK: define void @func_large_struct_padding_arg_store(%struct.large_struct_padding addrspace(1)* nocapture %out, %struct.large_struct_padding addrspace(5)* nocapture readonly byval align 8 %arg)
 void func_large_struct_padding_arg_store(global large_struct_padding* out, large_struct_padding arg) {
   *out = arg;
 }
@@ -487,7 +487,7 @@
 void v4i16_reg_count(short4 arg0, short4 arg1, short4 arg2, short4 arg3,
                      short4 arg4, short4 arg5, struct_4regs arg6) { }
 
-// 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)
+// 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)* nocapture byval 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) { }
 
@@ -495,7 +495,7 @@
 void v3i16_reg_count(short3 arg0, short3 arg1, short3 arg2, short3 arg3,
                      short3 arg4, short3 arg5, struct_4regs arg6) { }
 
-// 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)
+// 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)* nocapture byval 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) { }
 
@@ -505,7 +505,7 @@
                      short2 arg8, short2 arg9, short2 arg10, short2 arg11,
                      struct_4regs 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)
+// 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)* nocapture byval 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,
@@ -515,7 +515,7 @@
 void v2i8_reg_count(char2 arg0, char2 arg1, char2 arg2, char2 arg3,
                     char2 arg4, char2 arg5, struct_4regs arg6) { }
 
-// 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)
+// 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)* nocapture byval  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) { }
 
diff --git a/clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl b/clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl
index 5bb52e9..4392ef9 100644
--- a/clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl
+++ b/clang/test/CodeGenOpenCL/kernels-have-spir-cc-by-default.cl
@@ -27,7 +27,7 @@
 kernel void test_single(int_single input, global int* output) {
 // CHECK: spir_kernel
 // AMDGCN: define amdgpu_kernel void @test_single
-// CHECK: struct.int_single* byval nocapture
+// CHECK: struct.int_single* nocapture {{.*}} byval
 // CHECK: i32* nocapture %output
  output[0] = input.a;
 }
@@ -35,7 +35,7 @@
 kernel void test_pair(int_pair input, global int* output) {
 // CHECK: spir_kernel
 // AMDGCN: define amdgpu_kernel void @test_pair
-// CHECK: struct.int_pair* byval nocapture
+// CHECK: struct.int_pair* nocapture {{.*}} byval
 // CHECK: i32* nocapture %output
  output[0] = (int)input.a;
  output[1] = (int)input.b;
@@ -44,7 +44,7 @@
 kernel void test_kernel(test_struct input, global int* output) {
 // CHECK: spir_kernel
 // AMDGCN: define amdgpu_kernel void @test_kernel
-// CHECK: struct.test_struct* byval nocapture
+// CHECK: struct.test_struct* nocapture {{.*}} byval
 // CHECK: i32* nocapture %output
  output[0] = input.elementA;
  output[1] = input.elementB;