AMDGPU: Emit runtime metadata version 2 as YAML

Differential Revision: https://reviews.llvm.org/D25046

llvm-svn: 289674

4 files changed, 214 insertions, 2303 deletions

diff --git a/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata1.ll b/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata1.ll
index 960368e4ab1..49c314fbc5d 100644
--- a/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata1.ll
+++ b/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata1.ll
@@ -1,10 +1,6 @@
-; RUN: llc -mtriple=amdgcn--amdhsa < %s | FileCheck %s
+; RUN: llc -mtriple=amdgcn--amdhsa -filetype=obj -o - < %s | llvm-readobj -amdgpu-runtime-metadata | FileCheck %s
 ; check llc does not crash for invalid opencl version metadata
 
-; CHECK: .section        .note,#alloc
-; CHECK-NEXT: .long   4
-; CHECK-NEXT: .long   {{.+}}
-; CHECK-NEXT: .long   7
-; CHECK-NEXT: .asciz  "AMD"
+; CHECK: { amd.MDVersion: [ 2, 0 ] }
 
 !opencl.ocl.version = !{}
diff --git a/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata2.ll b/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata2.ll
index 04326699fbf..1f5e8be531d 100644
--- a/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata2.ll
+++ b/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata2.ll
@@ -1,11 +1,7 @@
-; RUN: llc -mtriple=amdgcn--amdhsa < %s | FileCheck %s
+; RUN: llc -mtriple=amdgcn--amdhsa -filetype=obj -o - < %s | llvm-readobj -amdgpu-runtime-metadata | FileCheck %s
 ; check llc does not crash for invalid opencl version metadata
 
-; CHECK: .section        .note,#alloc
-; CHECK-NEXT: .long   4
-; CHECK-NEXT: .long   {{.+}}
-; CHECK-NEXT: .long   7
-; CHECK-NEXT: .asciz  "AMD"
+; CHECK: { amd.MDVersion: [ 2, 0 ] }
 
 !opencl.ocl.version = !{!0}
 !0 = !{}
diff --git a/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata3.ll b/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata3.ll
index fb5533706a9..b77551e268a 100644
--- a/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata3.ll
+++ b/llvm/test/CodeGen/AMDGPU/invalid-opencl-version-metadata3.ll
@@ -1,11 +1,7 @@
-; RUN: llc -mtriple=amdgcn--amdhsa < %s | FileCheck %s
+; RUN: llc -mtriple=amdgcn--amdhsa -filetype=obj -o - < %s | llvm-readobj -amdgpu-runtime-metadata | FileCheck %s
 ; check llc does not crash for invalid opencl version metadata
 
-; CHECK: .section        .note,#alloc
-; CHECK-NEXT: .long   4
-; CHECK-NEXT: .long   {{.+}}
-; CHECK-NEXT: .long   7
-; CHECK-NEXT: .asciz  "AMD"
+; CHECK: { amd.MDVersion: [ 2, 0 ] }
 
 !opencl.ocl.version = !{!0}
 !0 = !{i32 1}
diff --git a/llvm/test/CodeGen/AMDGPU/runtime-metadata.ll b/llvm/test/CodeGen/AMDGPU/runtime-metadata.ll
index 651ccaa2bba..6c67f8cb2fb 100644
--- a/llvm/test/CodeGen/AMDGPU/runtime-metadata.ll
+++ b/llvm/test/CodeGen/AMDGPU/runtime-metadata.ll
@@ -1,4 +1,5 @@
-; RUN: llc -mtriple=amdgcn--amdhsa < %s | FileCheck %s
+; RUN: llc -mtriple=amdgcn--amdhsa -filetype=obj -o - < %s | llvm-readobj -amdgpu-runtime-metadata | FileCheck %s
+; RUN: llc -mtriple=amdgcn--amdhsa -filetype=obj -amdgpu-dump-rtmd -amdgpu-check-rtmd-parser %s 2>&1 | FileCheck --check-prefix=CHECK --check-prefix=PARSER %s
 
 %struct.A = type { i8, float }
 %opencl.image1d_t = type opaque
@@ -9,2414 +10,336 @@
 %struct.B = type { i32 addrspace(1)*}
 %opencl.clk_event_t = type opaque
 
-; CHECK: .section        .note,#alloc
-; CHECK-NEXT: .long   4
-; CHECK-NEXT: .long   [[Ltmp1:.+]]-[[Ltmp0:.+]]
-; CHECK-NEXT: .long   7
-; CHECK-NEXT: .asciz  "AMD"
-; CHECK-NEXT: .p2align        2
-; CHECK-NEXT: [[Ltmp0]]:
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .short	256
-; CHECK-NEXT: .byte	2
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	3
-; CHECK-NEXT: .short	200
-; CHECK-NEXT: .byte	30
-; CHECK-NEXT: .long	10
-; CHECK-NEXT: .ascii	"1:1:4:%d\\n"
-; CHECK-NEXT: .byte	30
-; CHECK-NEXT: .long	10
-; CHECK-NEXT: .ascii	"2:1:8:%g\\n"
-
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	9
-; CHECK-NEXT: .ascii	"test_char"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	1
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	1
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .ascii	"char"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
+; CHECK: ---
+; CHECK-NEXT: { amd.MDVersion: [ 2, 0 ], amd.PrintfInfo: [ '1:1:4:%d\n', '2:1:8:%g\n' ], amd.Kernels: 
 
+; CHECK-NEXT:   - { amd.KernelName: test_char, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 1, amd.ArgAlign: 1, amd.ArgKind: 0, amd.ArgValueType: 1, amd.ArgTypeName: char, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_char(i8 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !9 !kernel_arg_base_type !9 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	12
-; CHECK-NEXT: .ascii	"test_ushort2"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	7
-; CHECK-NEXT: .ascii	"ushort2"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	4
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_ushort2, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 4, amd.ArgTypeName: ushort2, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_ushort2(<2 x i16> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !10 !kernel_arg_base_type !10 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	9
-; CHECK-NEXT: .ascii	"test_int3"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	16
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	16
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .ascii	"int3"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_int3, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 16, amd.ArgAlign: 16, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: int3, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_int3(<3 x i32> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !11 !kernel_arg_base_type !11 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	11
-; CHECK-NEXT: .ascii	"test_ulong4"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	32
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	32
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	6
-; CHECK-NEXT: .ascii	"ulong4"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	10
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_ulong4, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 32, amd.ArgAlign: 32, amd.ArgKind: 0, amd.ArgValueType: 10, amd.ArgTypeName: ulong4, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_ulong4(<4 x i64> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !12 !kernel_arg_base_type !12 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	10
-; CHECK-NEXT: .ascii	"test_half8"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	16
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	16
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"half8"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	5
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_half8, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 16, amd.ArgAlign: 16, amd.ArgKind: 0, amd.ArgValueType: 5, amd.ArgTypeName: half8, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_half8(<8 x half> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !13 !kernel_arg_base_type !13 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	12
-; CHECK-NEXT: .ascii	"test_float16"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	64
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	64
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	7
-; CHECK-NEXT: .ascii	"float16"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	8
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_float16, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 64, amd.ArgAlign: 64, amd.ArgKind: 0, amd.ArgValueType: 8, amd.ArgTypeName: float16, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_float16(<16 x float> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !14 !kernel_arg_base_type !14 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	13
-; CHECK-NEXT: .ascii	"test_double16"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	128
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	128
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .ascii	"double16"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	11
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_double16, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 128, amd.ArgAlign: 128, amd.ArgKind: 0, amd.ArgValueType: 11, amd.ArgTypeName: double16, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_double16(<16 x double> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !15 !kernel_arg_base_type !15 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	12
-; CHECK-NEXT: .ascii	"test_pointer"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"int *"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_pointer, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 1, amd.ArgValueType: 6, amd.ArgTypeName: 'int *', amd.ArgAddrQual: 1, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_pointer(i32 addrspace(1)* %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !16 !kernel_arg_base_type !16 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	10
-; CHECK-NEXT: .ascii	"test_image"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	9
-; CHECK-NEXT: .ascii	"image2d_t"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	0
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_image, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 4, amd.ArgValueType: 0, amd.ArgTypeName: image2d_t, amd.ArgAddrQual: 1, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_image(%opencl.image2d_t addrspace(1)* %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !17 !kernel_arg_base_type !17 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	12
-; CHECK-NEXT: .ascii	"test_sampler"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	9
-; CHECK-NEXT: .ascii	"sampler_t"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	3
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_sampler, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 3, amd.ArgValueType: 6, amd.ArgTypeName: sampler_t, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_sampler(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !18 !kernel_arg_base_type !18 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	10
-; CHECK-NEXT: .ascii	"test_queue"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	7
-; CHECK-NEXT: .ascii	"queue_t"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	0
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_queue, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 6, amd.ArgValueType: 0, amd.ArgTypeName: queue_t, amd.ArgAddrQual: 1, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_queue(%opencl.queue_t addrspace(1)* %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !19 !kernel_arg_base_type !19 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	11
-; CHECK-NEXT: .ascii	"test_struct"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .ascii	"struct A"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	0
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_struct, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 1, amd.ArgValueType: 0, amd.ArgTypeName: struct A, amd.ArgAddrQual: 0, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_struct(%struct.A* byval %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !20 !kernel_arg_base_type !20 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	9
-; CHECK-NEXT: .ascii	"test_i128"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	16
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .ascii	"i128"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	0
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_i128, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 16, amd.ArgAlign: 8, amd.ArgKind: 0, amd.ArgValueType: 0, amd.ArgTypeName: i128, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_i128(i128 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !21 !kernel_arg_base_type !21 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	14
-; CHECK-NEXT: .ascii	"test_multi_arg"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	3
-; CHECK-NEXT: .ascii	"int"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	6
-; CHECK-NEXT: .ascii	"short2"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	3
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"char3"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_multi_arg, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: int, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 3, amd.ArgTypeName: short2, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 1, amd.ArgTypeName: char3, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_multi_arg(i32 %a, <2 x i16> %b, <3 x i8> %c) !kernel_arg_addr_space !22 !kernel_arg_access_qual !23 !kernel_arg_type !24 !kernel_arg_base_type !24 !kernel_arg_type_qual !25 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	15
-; CHECK-NEXT: .ascii	"test_addr_space"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"int *"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"int *"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	2
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	32
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"int *"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	2
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	3
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_addr_space, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 1, amd.ArgValueType: 6, amd.ArgTypeName: 'int *', amd.ArgAddrQual: 1, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 1, amd.ArgValueType: 6, amd.ArgTypeName: 'int *', amd.ArgAddrQual: 2, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgPointeeAlign: 4, amd.ArgKind: 2, amd.ArgValueType: 6, amd.ArgTypeName: 'int *', amd.ArgAddrQual: 3, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_addr_space(i32 addrspace(1)* %g, i32 addrspace(2)* %c, i32 addrspace(3)* %l) !kernel_arg_addr_space !50 !kernel_arg_access_qual !23 !kernel_arg_type !51 !kernel_arg_base_type !51 !kernel_arg_type_qual !25 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	14
-; CHECK-NEXT: .ascii	"test_type_qual"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"int *"
-; CHECK-NEXT: .byte	19
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"int *"
-; CHECK-NEXT: .byte	17
-; CHECK-NEXT: .byte	18
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"int *"
-; CHECK-NEXT: .byte	20
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	5
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	0
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_type_qual, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 1, amd.ArgValueType: 6, amd.ArgTypeName: 'int *', amd.ArgAddrQual: 1, amd.ArgAccQual: 0, amd.ArgIsVolatile: 1 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 1, amd.ArgValueType: 6, amd.ArgTypeName: 'int *', amd.ArgAddrQual: 1, amd.ArgAccQual: 0, amd.ArgIsConst: 1, amd.ArgIsRestrict: 1 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 5, amd.ArgValueType: 0, amd.ArgTypeName: 'int *', amd.ArgAddrQual: 1, amd.ArgAccQual: 0, amd.ArgIsPipe: 1 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_type_qual(i32 addrspace(1)* %a, i32 addrspace(1)* %b, %opencl.pipe_t addrspace(1)* %c) !kernel_arg_addr_space !22 !kernel_arg_access_qual !23 !kernel_arg_type !51 !kernel_arg_base_type !51 !kernel_arg_type_qual !70 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	16
-; CHECK-NEXT: .ascii	"test_access_qual"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	9
-; CHECK-NEXT: .ascii	"image1d_t"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	0
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	9
-; CHECK-NEXT: .ascii	"image2d_t"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	0
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	2
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	9
-; CHECK-NEXT: .ascii	"image3d_t"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	0
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	3
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_access_qual, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 4, amd.ArgValueType: 0, amd.ArgTypeName: image1d_t, amd.ArgAddrQual: 1, amd.ArgAccQual: 1 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 4, amd.ArgValueType: 0, amd.ArgTypeName: image2d_t, amd.ArgAddrQual: 1, amd.ArgAccQual: 2 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 4, amd.ArgValueType: 0, amd.ArgTypeName: image3d_t, amd.ArgAddrQual: 1, amd.ArgAccQual: 3 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_access_qual(%opencl.image1d_t addrspace(1)* %ro, %opencl.image2d_t addrspace(1)* %wo, %opencl.image3d_t addrspace(1)* %rw) !kernel_arg_addr_space !60 !kernel_arg_access_qual !61 !kernel_arg_type !62 !kernel_arg_base_type !62 !kernel_arg_type_qual !25 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	23
-; CHECK-NEXT: .ascii	"test_vec_type_hint_half"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	3
-; CHECK-NEXT: .ascii	"int"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	23
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .ascii	"half"
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_vec_type_hint_half, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.VecTypeHint: half, amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: int, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_vec_type_hint_half(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !26 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	24
-; CHECK-NEXT: .ascii	"test_vec_type_hint_float"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	3
-; CHECK-NEXT: .ascii	"int"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	23
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"float"
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_vec_type_hint_float, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.VecTypeHint: float, amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: int, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_vec_type_hint_float(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !27 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	25
-; CHECK-NEXT: .ascii	"test_vec_type_hint_double"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	3
-; CHECK-NEXT: .ascii	"int"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	23
-; CHECK-NEXT: .long	6
-; CHECK-NEXT: .ascii	"double"
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_vec_type_hint_double, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.VecTypeHint: double, amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: int, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_vec_type_hint_double(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !28 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	23
-; CHECK-NEXT: .ascii	"test_vec_type_hint_char"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	3
-; CHECK-NEXT: .ascii	"int"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	23
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .ascii	"char"
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_vec_type_hint_char, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.VecTypeHint: char, amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: int, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_vec_type_hint_char(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !29 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	24
-; CHECK-NEXT: .ascii	"test_vec_type_hint_short"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	3
-; CHECK-NEXT: .ascii	"int"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	23
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"short"
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_vec_type_hint_short, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.VecTypeHint: short, amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: int, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_vec_type_hint_short(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !30 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	23
-; CHECK-NEXT: .ascii	"test_vec_type_hint_long"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	3
-; CHECK-NEXT: .ascii	"int"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	23
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .ascii	"long"
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_vec_type_hint_long, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.VecTypeHint: long, amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: int, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_vec_type_hint_long(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !31 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	26
-; CHECK-NEXT: .ascii	"test_vec_type_hint_unknown"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	3
-; CHECK-NEXT: .ascii	"int"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	23
-; CHECK-NEXT: .long	7
-; CHECK-NEXT: .ascii	"unknown"
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_vec_type_hint_unknown, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.VecTypeHint: unknown, amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: int, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_vec_type_hint_unknown(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !32 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	27
-; CHECK-NEXT: .ascii	"test_reqd_wgs_vec_type_hint"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	3
-; CHECK-NEXT: .ascii	"int"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	21
-; CHECK-NEXT: .long	1
-; CHECK-NEXT: .long	2
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	23
-; CHECK-NEXT: .long	3
-; CHECK-NEXT: .ascii	"int"
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_reqd_wgs_vec_type_hint, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.ReqdWorkGroupSize: [ 1, 2, 4 ], amd.VecTypeHint: int, amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: int, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_reqd_wgs_vec_type_hint(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !5 !reqd_work_group_size !6 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	27
-; CHECK-NEXT: .ascii	"test_wgs_hint_vec_type_hint"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	3
-; CHECK-NEXT: .ascii	"int"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	22
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .long	16
-; CHECK-NEXT: .long	32
-; CHECK-NEXT: .byte	23
-; CHECK-NEXT: .long	5
-; CHECK-NEXT: .ascii	"uint4"
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_wgs_hint_vec_type_hint, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.WorkGroupSizeHint: [ 8, 16, 32 ], amd.VecTypeHint: uint4, amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: int, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_wgs_hint_vec_type_hint(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !7 !work_group_size_hint !8 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	19
-; CHECK-NEXT: .ascii	"test_arg_ptr_to_ptr"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	6
-; CHECK-NEXT: .ascii	"int **"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_arg_ptr_to_ptr, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 1, amd.ArgValueType: 6, amd.ArgTypeName: 'int **', amd.ArgAddrQual: 1, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_arg_ptr_to_ptr(i32 * addrspace(1)* %a) !kernel_arg_addr_space !81 !kernel_arg_access_qual !2 !kernel_arg_type !80 !kernel_arg_base_type !80 !kernel_arg_type_qual !4 {
   ret void
 }
-
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	28
-; CHECK-NEXT: .ascii	"test_arg_struct_contains_ptr"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .ascii	"struct B"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	0
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_arg_struct_contains_ptr, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 1, amd.ArgValueType: 0, amd.ArgTypeName: struct B, amd.ArgAddrQual: 0, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_arg_struct_contains_ptr(%struct.B * byval %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !82 !kernel_arg_base_type !82 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	22
-; CHECK-NEXT: .ascii	"test_arg_vector_of_ptr"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	16
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	16
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	47
-; CHECK-NEXT: .ascii	"global int* __attribute__((ext_vector_type(2)))"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	6
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_arg_vector_of_ptr, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 16, amd.ArgAlign: 16, amd.ArgKind: 0, amd.ArgValueType: 6, amd.ArgTypeName: 'global int* __attribute__((ext_vector_type(2)))', amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_arg_vector_of_ptr(<2 x i32 addrspace(1)*> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !83 !kernel_arg_base_type !83 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	29
-; CHECK-NEXT: .ascii	"test_arg_unknown_builtin_type"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	11
-; CHECK-NEXT: .ascii	"clk_event_t"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	0
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
 
+; CHECK-NEXT:   - { amd.KernelName: test_arg_unknown_builtin_type, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 1, amd.ArgValueType: 0, amd.ArgTypeName: clk_event_t, amd.ArgAddrQual: 1, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
 define amdgpu_kernel void @test_arg_unknown_builtin_type(%opencl.clk_event_t addrspace(1)* %a) !kernel_arg_addr_space !81 !kernel_arg_access_qual !2 !kernel_arg_type !84 !kernel_arg_base_type !84 !kernel_arg_type_qual !4 {
   ret void
 }
 
-; CHECK-NEXT: .byte	4
-; CHECK-NEXT: .byte	6
-; CHECK-NEXT: .long	18
-; CHECK-NEXT: .ascii	"test_pointee_align"
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	6
-; CHECK-NEXT: .ascii	"long *"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	32
-; CHECK-NEXT: .long	1
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	6
-; CHECK-NEXT: .ascii	"char *"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	2
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	3
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	32
-; CHECK-NEXT: .long	2
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	7
-; CHECK-NEXT: .ascii	"char2 *"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	2
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	3
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	32
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	7
-; CHECK-NEXT: .ascii	"char3 *"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	2
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	3
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	32
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	7
-; CHECK-NEXT: .ascii	"char4 *"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	2
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	3
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	32
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	7
-; CHECK-NEXT: .ascii	"char8 *"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	2
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	3
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	4
-; CHECK-NEXT: .byte	32
-; CHECK-NEXT: .long	16
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .ascii	"char16 *"
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	2
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	16
-; CHECK-NEXT: .byte	0
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	3
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	9
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	7
-; CHECK-NEXT: .byte	9
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	10
-; CHECK-NEXT: .long	8
-; CHECK-NEXT: .byte	13
-; CHECK-NEXT: .byte	11
-; CHECK-NEXT: .byte	14
-; CHECK-NEXT: .short	1
-; CHECK-NEXT: .byte	15
-; CHECK-NEXT: .byte	1
-; CHECK-NEXT: .byte	8
-; CHECK-NEXT: .byte	5
-
+; CHECK-NEXT:   - { amd.KernelName: test_pointee_align, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args: 
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 1, amd.ArgValueType: 9, amd.ArgTypeName: 'long *', amd.ArgAddrQual: 1, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgPointeeAlign: 1, amd.ArgKind: 2, amd.ArgValueType: 1, amd.ArgTypeName: 'char *', amd.ArgAddrQual: 3, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgPointeeAlign: 2, amd.ArgKind: 2, amd.ArgValueType: 1, amd.ArgTypeName: 'char2 *', amd.ArgAddrQual: 3, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgPointeeAlign: 4, amd.ArgKind: 2, amd.ArgValueType: 1, amd.ArgTypeName: 'char3 *', amd.ArgAddrQual: 3, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgPointeeAlign: 4, amd.ArgKind: 2, amd.ArgValueType: 1, amd.ArgTypeName: 'char4 *', amd.ArgAddrQual: 3, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgPointeeAlign: 8, amd.ArgKind: 2, amd.ArgValueType: 1, amd.ArgTypeName: 'char8 *', amd.ArgAddrQual: 3, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgPointeeAlign: 16, amd.ArgKind: 2, amd.ArgValueType: 1, amd.ArgTypeName: 'char16 *', amd.ArgAddrQual: 3, amd.ArgAccQual: 0 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
+; CHECK-NEXT:       - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } } }
 define amdgpu_kernel void @test_pointee_align(i64 addrspace(1)* %a, i8 addrspace(3)* %b, <2 x i8> addrspace(3)* %c, <3 x i8> addrspace(3)* %d, <4 x i8> addrspace(3)* %e, <8 x i8> addrspace(3)* %f, <16 x i8> addrspace(3)* %g) !kernel_arg_addr_space !91 !kernel_arg_access_qual !92 !kernel_arg_type !93 !kernel_arg_base_type !93 !kernel_arg_type_qual !94 {
   ret void
 }
-; CHECK-NEXT: [[Ltmp1]]:
-; CHECK-NEXT: .p2align        2
+
+; CHECK-NEXT:...
+
+; PARSER: AMDGPU runtime metadata parser test passes.
 
 !llvm.printf.fmts = !{!100, !101}