[AMDGPU] Restructure code object metadata creation

  - Rename runtime metadata -> code object metadata
  - Make metadata not flow
  - Switch enums to use ScalarEnumerationTraits
  - Cleanup and move AMDGPUCodeObjectMetadata.h to AMDGPU/MCTargetDesc
  - Introduce in-memory representation for attributes
  - Code object metadata streamer
  - Create metadata for isa and printf during EmitStartOfAsmFile
  - Create metadata for kernel during EmitFunctionBodyStart
  - Finalize and emit metadata to .note during EmitEndOfAsmFile
  - Other minor improvements/bug fixes

Differential Revision: https://reviews.llvm.org/D29948

llvm-svn: 298552

8 files changed, 295 insertions, 202 deletions

diff --git a/llvm/test/MC/AMDGPU/code-object-metadata-isa.s b/llvm/test/MC/AMDGPU/code-object-metadata-isa.s
new file mode 100644
index 00000000000..51d3a2b5559
--- /dev/null
+++ b/llvm/test/MC/AMDGPU/code-object-metadata-isa.s
@@ -0,0 +1,98 @@
+// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX700 %s
+// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX800 %s
+// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX900 %s
+
+// CHECK:  .amdgpu_code_object_metadata
+// CHECK:    Version: [ 1, 0 ]
+// CHECK:    Isa:
+// CHECK:      WavefrontSize:        64
+// CHECK:      LocalMemorySize:      65536
+// CHECK:      EUsPerCU:             4
+// CHECK:      MaxWavesPerEU:        10
+// CHECK:      MaxFlatWorkGroupSize: 2048
+// GFX700:     SGPRAllocGranule:     8
+// GFX800:     SGPRAllocGranule:     16
+// GFX900:     SGPRAllocGranule:     16
+// GFX700:     TotalNumSGPRs:        512
+// GFX800:     TotalNumSGPRs:        800
+// GFX900:     TotalNumSGPRs:        800
+// GFX700:     AddressableNumSGPRs:  104
+// GFX800:     AddressableNumSGPRs:  96
+// GFX900:     AddressableNumSGPRs:  102
+// CHECK:      VGPRAllocGranule:     4
+// CHECK:      TotalNumVGPRs:        256
+// CHECK:      AddressableNumVGPRs:  256
+// CHECK:    Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
+// CHECK:    Kernels:
+// CHECK:      - Name:            test_kernel
+// CHECK:        Language:        OpenCL C
+// CHECK:        LanguageVersion: [ 2, 0 ]
+// CHECK:        Args:
+// CHECK:          - Size:          1
+// CHECK:            Align:         1
+// CHECK:            Kind:          ByValue
+// CHECK:            ValueType:     I8
+// CHECK:            AccQual:       Default
+// CHECK:            TypeName:      char
+// CHECK:          - Size:          8
+// CHECK:            Align:         8
+// CHECK:            Kind:          HiddenGlobalOffsetX
+// CHECK:            ValueType:     I64
+// CHECK:          - Size:          8
+// CHECK:            Align:         8
+// CHECK:            Kind:          HiddenGlobalOffsetY
+// CHECK:            ValueType:     I64
+// CHECK:          - Size:          8
+// CHECK:            Align:         8
+// CHECK:            Kind:          HiddenGlobalOffsetZ
+// CHECK:            ValueType:     I64
+// CHECK:          - Size:          8
+// CHECK:            Align:         8
+// CHECK:            Kind:          HiddenPrintfBuffer
+// CHECK:            ValueType:     I8
+// CHECK:            AddrSpaceQual: Global
+// CHECK:  .end_amdgpu_code_object_metadata
+.amdgpu_code_object_metadata
+  Version: [ 1, 0 ]
+  Isa:
+    WavefrontSize:        1
+    LocalMemorySize:      1
+    EUsPerCU:             1
+    MaxWavesPerEU:        1
+    MaxFlatWorkGroupSize: 1
+    SGPRAllocGranule:     1
+    TotalNumSGPRs:        1
+    AddressableNumSGPRs:  1
+    VGPRAllocGranule:     1
+    TotalNumVGPRs:        1
+    AddressableNumVGPRs:  1
+  Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
+  Kernels:
+    - Name:            test_kernel
+      Language:        OpenCL C
+      LanguageVersion: [ 2, 0 ]
+      Args:
+        - Size:          1
+          Align:         1
+          Kind:          ByValue
+          ValueType:     I8
+          AccQual:       Default
+          TypeName:      char
+        - Size:          8
+          Align:         8
+          Kind:          HiddenGlobalOffsetX
+          ValueType:     I64
+        - Size:          8
+          Align:         8
+          Kind:          HiddenGlobalOffsetY
+          ValueType:     I64
+        - Size:          8
+          Align:         8
+          Kind:          HiddenGlobalOffsetZ
+          ValueType:     I64
+        - Size:          8
+          Align:         8
+          Kind:          HiddenPrintfBuffer
+          ValueType:     I8
+          AddrSpaceQual: Global
+.end_amdgpu_code_object_metadata
diff --git a/llvm/test/MC/AMDGPU/code-object-metadata-kernel-args.s b/llvm/test/MC/AMDGPU/code-object-metadata-kernel-args.s
new file mode 100644
index 00000000000..3f3a7f4d172
--- /dev/null
+++ b/llvm/test/MC/AMDGPU/code-object-metadata-kernel-args.s
@@ -0,0 +1,86 @@
+// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX700 %s
+// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX800 %s
+// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX900 %s
+
+// CHECK:  .amdgpu_code_object_metadata
+// CHECK:    Version: [ 1, 0 ]
+// CHECK:    Isa:
+// CHECK:      WavefrontSize:        64
+// CHECK:      LocalMemorySize:      65536
+// CHECK:      EUsPerCU:             4
+// CHECK:      MaxWavesPerEU:        10
+// CHECK:      MaxFlatWorkGroupSize: 2048
+// GFX700:     SGPRAllocGranule:     8
+// GFX800:     SGPRAllocGranule:     16
+// GFX900:     SGPRAllocGranule:     16
+// GFX700:     TotalNumSGPRs:        512
+// GFX800:     TotalNumSGPRs:        800
+// GFX900:     TotalNumSGPRs:        800
+// GFX700:     AddressableNumSGPRs:  104
+// GFX800:     AddressableNumSGPRs:  96
+// GFX900:     AddressableNumSGPRs:  102
+// CHECK:      VGPRAllocGranule:     4
+// CHECK:      TotalNumVGPRs:        256
+// CHECK:      AddressableNumVGPRs:  256
+// CHECK:    Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
+// CHECK:    Kernels:
+// CHECK:      - Name:            test_kernel
+// CHECK:        Language:        OpenCL C
+// CHECK:        LanguageVersion: [ 2, 0 ]
+// CHECK:        Args:
+// CHECK:          - Size:          1
+// CHECK:            Align:         1
+// CHECK:            Kind:          ByValue
+// CHECK:            ValueType:     I8
+// CHECK:            AccQual:       Default
+// CHECK:            TypeName:      char
+// CHECK:          - Size:          8
+// CHECK:            Align:         8
+// CHECK:            Kind:          HiddenGlobalOffsetX
+// CHECK:            ValueType:     I64
+// CHECK:          - Size:          8
+// CHECK:            Align:         8
+// CHECK:            Kind:          HiddenGlobalOffsetY
+// CHECK:            ValueType:     I64
+// CHECK:          - Size:          8
+// CHECK:            Align:         8
+// CHECK:            Kind:          HiddenGlobalOffsetZ
+// CHECK:            ValueType:     I64
+// CHECK:          - Size:          8
+// CHECK:            Align:         8
+// CHECK:            Kind:          HiddenPrintfBuffer
+// CHECK:            ValueType:     I8
+// CHECK:            AddrSpaceQual: Global
+// CHECK:  .end_amdgpu_code_object_metadata
+.amdgpu_code_object_metadata
+  Version: [ 1, 0 ]
+  Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
+  Kernels:
+    - Name:            test_kernel
+      Language:        OpenCL C
+      LanguageVersion: [ 2, 0 ]
+      Args:
+        - Size:          1
+          Align:         1
+          Kind:          ByValue
+          ValueType:     I8
+          AccQual:       Default
+          TypeName:      char
+        - Size:          8
+          Align:         8
+          Kind:          HiddenGlobalOffsetX
+          ValueType:     I64
+        - Size:          8
+          Align:         8
+          Kind:          HiddenGlobalOffsetY
+          ValueType:     I64
+        - Size:          8
+          Align:         8
+          Kind:          HiddenGlobalOffsetZ
+          ValueType:     I64
+        - Size:          8
+          Align:         8
+          Kind:          HiddenPrintfBuffer
+          ValueType:     I8
+          AddrSpaceQual: Global
+.end_amdgpu_code_object_metadata
diff --git a/llvm/test/MC/AMDGPU/code-object-metadata-kernel-attrs.s b/llvm/test/MC/AMDGPU/code-object-metadata-kernel-attrs.s
new file mode 100644
index 00000000000..247012b1c14
--- /dev/null
+++ b/llvm/test/MC/AMDGPU/code-object-metadata-kernel-attrs.s
@@ -0,0 +1,46 @@
+// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX700 %s
+// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX800 %s
+// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 -show-encoding %s | FileCheck --check-prefix=CHECK --check-prefix=GFX900 %s
+
+// CHECK:  .amdgpu_code_object_metadata
+// CHECK:    Version: [ 1, 0 ]
+// CHECK:    Isa:
+// CHECK:      WavefrontSize:        64
+// CHECK:      LocalMemorySize:      65536
+// CHECK:      EUsPerCU:             4
+// CHECK:      MaxWavesPerEU:        10
+// CHECK:      MaxFlatWorkGroupSize: 2048
+// GFX700:     SGPRAllocGranule:     8
+// GFX800:     SGPRAllocGranule:     16
+// GFX900:     SGPRAllocGranule:     16
+// GFX700:     TotalNumSGPRs:        512
+// GFX800:     TotalNumSGPRs:        800
+// GFX900:     TotalNumSGPRs:        800
+// GFX700:     AddressableNumSGPRs:  104
+// GFX800:     AddressableNumSGPRs:  96
+// GFX900:     AddressableNumSGPRs:  102
+// CHECK:      VGPRAllocGranule:     4
+// CHECK:      TotalNumVGPRs:        256
+// CHECK:      AddressableNumVGPRs:  256
+// CHECK:    Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
+// CHECK:    Kernels:
+// CHECK:      - Name:            test_kernel
+// CHECK:        Language:        OpenCL C
+// CHECK:        LanguageVersion: [ 2, 0 ]
+// CHECK:    Attrs:
+// CHECK:        ReqdWorkGroupSize: [ 1, 2, 4 ]
+// CHECK:        WorkGroupSizeHint: [ 8, 16, 32 ]
+// CHECK:        VecTypeHint:       int
+// CHECK: .end_amdgpu_code_object_metadata
+.amdgpu_code_object_metadata
+  Version: [ 1, 0 ]
+  Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
+  Kernels:
+    - Name:            test_kernel
+      Language:        OpenCL C
+      LanguageVersion: [ 2, 0 ]
+      Attrs:
+        ReqdWorkGroupSize: [ 1, 2, 4 ]
+        WorkGroupSizeHint: [ 8, 16, 32 ]
+        VecTypeHint:       int
+.end_amdgpu_code_object_metadata
diff --git a/llvm/test/MC/AMDGPU/code-object-metadata-unknown-key.s b/llvm/test/MC/AMDGPU/code-object-metadata-unknown-key.s
new file mode 100644
index 00000000000..c1062363bbc
--- /dev/null
+++ b/llvm/test/MC/AMDGPU/code-object-metadata-unknown-key.s
@@ -0,0 +1,41 @@
+// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 %s 2>&1 | FileCheck %s
+// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 %s 2>&1 | FileCheck %s
+// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 %s 2>&1 | FileCheck %s
+// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 -filetype=obj %s 2>&1 | FileCheck %s
+// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 -filetype=obj %s 2>&1 | FileCheck %s
+// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=obj %s 2>&1 | FileCheck %s
+
+// CHECK: error: unknown key 'UnknownKey'
+.amdgpu_code_object_metadata
+  UnknownKey: [ 2, 0 ]
+  Version: [ 1, 0 ]
+  Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
+  Kernels:
+    - Name:            test_kernel
+      Language:        OpenCL C
+      LanguageVersion: [ 2, 0 ]
+      Args:
+        - Size:          1
+          Align:         1
+          Kind:          ByValue
+          ValueType:     I8
+          AccQual:       Default
+          TypeName:      char
+        - Size:          8
+          Align:         8
+          Kind:          HiddenGlobalOffsetX
+          ValueType:     I64
+        - Size:          8
+          Align:         8
+          Kind:          HiddenGlobalOffsetY
+          ValueType:     I64
+        - Size:          8
+          Align:         8
+          Kind:          HiddenGlobalOffsetZ
+          ValueType:     I64
+        - Size:          8
+          Align:         8
+          Kind:          HiddenPrintfBuffer
+          ValueType:     I8
+          AddrSpaceQual: Global
+.end_amdgpu_code_object_metadata
diff --git a/llvm/test/MC/AMDGPU/hsa.s b/llvm/test/MC/AMDGPU/hsa.s
index cd15ec830c3..dd60f3e9763 100644
--- a/llvm/test/MC/AMDGPU/hsa.s
+++ b/llvm/test/MC/AMDGPU/hsa.s
@@ -37,25 +37,31 @@
 .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
 // ASM: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
 
-.amdgpu_runtime_metadata
-    {
-        amd.MDVersion: [ 2, 0 ]
-        amd.Kernels: [
-            { amd.KernelName: amd_kernel_code_t_test_all },
-            { amd.KernelName: amd_kernel_code_t_minimal }
-        ]
-    }
-.end_amdgpu_runtime_metadata
+.amdgpu_code_object_metadata
+  Version: [ 3, 0 ]
+  Kernels:
+    - Name: amd_kernel_code_t_test_all
+    - Name: amd_kernel_code_t_minimal
+.end_amdgpu_code_object_metadata
 
-// ASM: .amdgpu_runtime_metadata
-// ASM:  {
-// ASM:    amd.MDVersion: [ 2, 0 ]
-// ASM:    amd.IsaInfo: { amd.IsaInfoWavefrontSize: 64, amd.IsaInfoLocalMemorySize: 65536, amd.IsaInfoEUsPerCU: 4, amd.IsaInfoMaxWavesPerEU: 10, amd.IsaInfoMaxFlatWorkGroupSize: 2048, amd.IsaInfoSGPRAllocGranule: 8, amd.IsaInfoTotalNumSGPRs: 512, amd.IsaInfoAddressableNumSGPRs: 104, amd.IsaInfoVGPRAllocGranule: 4, amd.IsaInfoTotalNumVGPRs: 256, amd.IsaInfoAddressableNumVGPRs: 256 },
-// ASM:    amd.Kernels:
-// ASM:      - { amd.KernelName: amd_kernel_code_t_test_all }
-// ASM:      - { amd.KernelName: amd_kernel_code_t_minimal }
-// ASM:  }
-// ASM: .end_amdgpu_runtime_metadata
+// ASM: .amdgpu_code_object_metadata
+// ASM:    Version: [ 3, 0 ]
+// ASM:    Isa:
+// ASM:      WavefrontSize:        64
+// ASM:      LocalMemorySize:      65536
+// ASM:      EUsPerCU:             4
+// ASM:      MaxWavesPerEU:        10
+// ASM:      MaxFlatWorkGroupSize: 2048
+// ASM:      SGPRAllocGranule:     8
+// ASM:      TotalNumSGPRs:        512
+// ASM:      AddressableNumSGPRs:  104
+// ASM:      VGPRAllocGranule:     4
+// ASM:      TotalNumVGPRs:        256
+// ASM:      AddressableNumVGPRs:  256
+// ASM:    Kernels:
+// ASM:      - Name: amd_kernel_code_t_test_all
+// ASM:      - Name: amd_kernel_code_t_minimal
+// ASM: .end_amdgpu_code_object_metadata
 
 .amdgpu_hsa_kernel amd_kernel_code_t_test_all
 .amdgpu_hsa_kernel amd_kernel_code_t_minimal
diff --git a/llvm/test/MC/AMDGPU/runtime-metadata-1.s b/llvm/test/MC/AMDGPU/runtime-metadata-1.s
deleted file mode 100644
index 6e371a8a978..00000000000
--- a/llvm/test/MC/AMDGPU/runtime-metadata-1.s
+++ /dev/null
@@ -1,39 +0,0 @@
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 -show-encoding %s | FileCheck %s --check-prefix=GCN --check-prefix=GFX700
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 -show-encoding %s | FileCheck %s --check-prefix=GCN --check-prefix=GFX800
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 -show-encoding %s | FileCheck %s --check-prefix=GCN --check-prefix=GFX900
-
-.amdgpu_runtime_metadata
-  { amd.MDVersion: [ 2, 1 ], amd.PrintfInfo: [ '1:1:4:%d\n', '2:1:8:%g\n' ], amd.Kernels:
-    - { amd.KernelName: test_char, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args:
-        - { amd.ArgSize: 1, amd.ArgAlign: 1, amd.ArgKind: 0, amd.ArgValueType: 1, amd.ArgTypeName: char, amd.ArgAccQual: 0 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
-    - { amd.KernelName: test_ushort2, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args:
-        - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 4, amd.ArgTypeName: ushort2, amd.ArgAccQual: 0 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
-  }
-.end_amdgpu_runtime_metadata
-
-// GFX700: { amd.MDVersion: [ 2, 1 ], amd.IsaInfo: { amd.IsaInfoWavefrontSize: 64, amd.IsaInfoLocalMemorySize: 65536, amd.IsaInfoEUsPerCU: 4, amd.IsaInfoMaxWavesPerEU: 10, amd.IsaInfoMaxFlatWorkGroupSize: 2048, amd.IsaInfoSGPRAllocGranule: 8, amd.IsaInfoTotalNumSGPRs: 512, amd.IsaInfoAddressableNumSGPRs: 104, amd.IsaInfoVGPRAllocGranule: 4, amd.IsaInfoTotalNumVGPRs: 256, amd.IsaInfoAddressableNumVGPRs: 256 }, amd.PrintfInfo: [ '1:1:4:%d\n', '2:1:8:%g\n' ], amd.Kernels:
-
-// GFX800: { amd.MDVersion: [ 2, 1 ], amd.IsaInfo: { amd.IsaInfoWavefrontSize: 64, amd.IsaInfoLocalMemorySize: 65536, amd.IsaInfoEUsPerCU: 4, amd.IsaInfoMaxWavesPerEU: 10, amd.IsaInfoMaxFlatWorkGroupSize: 2048, amd.IsaInfoSGPRAllocGranule: 16, amd.IsaInfoTotalNumSGPRs: 800, amd.IsaInfoAddressableNumSGPRs: 96, amd.IsaInfoVGPRAllocGranule: 4, amd.IsaInfoTotalNumVGPRs: 256, amd.IsaInfoAddressableNumVGPRs: 256 }, amd.PrintfInfo: [ '1:1:4:%d\n', '2:1:8:%g\n' ], amd.Kernels:
-
-// GFX900: { amd.MDVersion: [ 2, 1 ], amd.IsaInfo: { amd.IsaInfoWavefrontSize: 64, amd.IsaInfoLocalMemorySize: 65536, amd.IsaInfoEUsPerCU: 4, amd.IsaInfoMaxWavesPerEU: 10, amd.IsaInfoMaxFlatWorkGroupSize: 2048, amd.IsaInfoSGPRAllocGranule: 16, amd.IsaInfoTotalNumSGPRs: 800, amd.IsaInfoAddressableNumSGPRs: 102, amd.IsaInfoVGPRAllocGranule: 4, amd.IsaInfoTotalNumVGPRs: 256, amd.IsaInfoAddressableNumVGPRs: 256 }, amd.PrintfInfo: [ '1:1:4:%d\n', '2:1:8:%g\n' ], amd.Kernels:
-
-// GCN:      - { amd.KernelName: test_char, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args:
-// GCN-NEXT:     - { amd.ArgSize: 1, amd.ArgAlign: 1, amd.ArgKind: 0, amd.ArgValueType: 1, amd.ArgTypeName: char, amd.ArgAccQual: 0 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
-// GCN-NEXT: - { amd.KernelName: test_ushort2, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args:
-// GCN-NEXT:     - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 4, amd.ArgTypeName: ushort2, amd.ArgAccQual: 0 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } } }
diff --git a/llvm/test/MC/AMDGPU/runtime-metadata-2.s b/llvm/test/MC/AMDGPU/runtime-metadata-2.s
deleted file mode 100644
index 569ddd5e61b..00000000000
--- a/llvm/test/MC/AMDGPU/runtime-metadata-2.s
+++ /dev/null
@@ -1,39 +0,0 @@
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 -show-encoding %s | FileCheck %s --check-prefix=GCN --check-prefix=GFX700
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 -show-encoding %s | FileCheck %s --check-prefix=GCN --check-prefix=GFX800
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 -show-encoding %s | FileCheck %s --check-prefix=GCN --check-prefix=GFX900
-
-.amdgpu_runtime_metadata
-  { amd.MDVersion: [ 2, 1 ], amd.IsaInfo: { amd.IsaInfoWavefrontSize: 64, amd.IsaInfoLocalMemorySize: 65536, amd.IsaInfoEUsPerCU: 4, amd.IsaInfoMaxWavesPerEU: 10, amd.IsaInfoMaxFlatWorkGroupSize: 2048, amd.IsaInfoSGPRAllocGranule: 8, amd.IsaInfoTotalNumSGPRs: 512, amd.IsaInfoAddressableNumSGPRs: 104, amd.IsaInfoVGPRAllocGranule: 4, amd.IsaInfoTotalNumVGPRs: 256, amd.IsaInfoAddressableNumVGPRs: 256 }, amd.PrintfInfo: [ '1:1:4:%d\n', '2:1:8:%g\n' ], amd.Kernels:
-    - { amd.KernelName: test_char, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args:
-        - { amd.ArgSize: 1, amd.ArgAlign: 1, amd.ArgKind: 0, amd.ArgValueType: 1, amd.ArgTypeName: char, amd.ArgAccQual: 0 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
-    - { amd.KernelName: test_ushort2, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args:
-        - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 4, amd.ArgTypeName: ushort2, amd.ArgAccQual: 0 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
-        - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
-  }
-.end_amdgpu_runtime_metadata
-
-// GFX700: { amd.MDVersion: [ 2, 1 ], amd.IsaInfo: { amd.IsaInfoWavefrontSize: 64, amd.IsaInfoLocalMemorySize: 65536, amd.IsaInfoEUsPerCU: 4, amd.IsaInfoMaxWavesPerEU: 10, amd.IsaInfoMaxFlatWorkGroupSize: 2048, amd.IsaInfoSGPRAllocGranule: 8, amd.IsaInfoTotalNumSGPRs: 512, amd.IsaInfoAddressableNumSGPRs: 104, amd.IsaInfoVGPRAllocGranule: 4, amd.IsaInfoTotalNumVGPRs: 256, amd.IsaInfoAddressableNumVGPRs: 256 }, amd.PrintfInfo: [ '1:1:4:%d\n', '2:1:8:%g\n' ], amd.Kernels:
-
-// GFX800: { amd.MDVersion: [ 2, 1 ], amd.IsaInfo: { amd.IsaInfoWavefrontSize: 64, amd.IsaInfoLocalMemorySize: 65536, amd.IsaInfoEUsPerCU: 4, amd.IsaInfoMaxWavesPerEU: 10, amd.IsaInfoMaxFlatWorkGroupSize: 2048, amd.IsaInfoSGPRAllocGranule: 16, amd.IsaInfoTotalNumSGPRs: 800, amd.IsaInfoAddressableNumSGPRs: 96, amd.IsaInfoVGPRAllocGranule: 4, amd.IsaInfoTotalNumVGPRs: 256, amd.IsaInfoAddressableNumVGPRs: 256 }, amd.PrintfInfo: [ '1:1:4:%d\n', '2:1:8:%g\n' ], amd.Kernels:
-
-// GFX900: { amd.MDVersion: [ 2, 1 ], amd.IsaInfo: { amd.IsaInfoWavefrontSize: 64, amd.IsaInfoLocalMemorySize: 65536, amd.IsaInfoEUsPerCU: 4, amd.IsaInfoMaxWavesPerEU: 10, amd.IsaInfoMaxFlatWorkGroupSize: 2048, amd.IsaInfoSGPRAllocGranule: 16, amd.IsaInfoTotalNumSGPRs: 800, amd.IsaInfoAddressableNumSGPRs: 102, amd.IsaInfoVGPRAllocGranule: 4, amd.IsaInfoTotalNumVGPRs: 256, amd.IsaInfoAddressableNumVGPRs: 256 }, amd.PrintfInfo: [ '1:1:4:%d\n', '2:1:8:%g\n' ], amd.Kernels:
-
-// GCN:      - { amd.KernelName: test_char, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args:
-// GCN-NEXT:     - { amd.ArgSize: 1, amd.ArgAlign: 1, amd.ArgKind: 0, amd.ArgValueType: 1, amd.ArgTypeName: char, amd.ArgAccQual: 0 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } }
-// GCN-NEXT: - { amd.KernelName: test_ushort2, amd.Language: OpenCL C, amd.LanguageVersion: [ 2, 0 ], amd.Args:
-// GCN-NEXT:     - { amd.ArgSize: 4, amd.ArgAlign: 4, amd.ArgKind: 0, amd.ArgValueType: 4, amd.ArgTypeName: ushort2, amd.ArgAccQual: 0 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 }
-// GCN-NEXT:     - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 11, amd.ArgValueType: 1, amd.ArgAddrQual: 1 } } }
diff --git a/llvm/test/MC/AMDGPU/runtime-metadata-invalid-1.s b/llvm/test/MC/AMDGPU/runtime-metadata-invalid-1.s
deleted file mode 100644
index 66bbbd7600a..00000000000
--- a/llvm/test/MC/AMDGPU/runtime-metadata-invalid-1.s
+++ /dev/null
@@ -1,106 +0,0 @@
-; RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 %s 2>&1 | FileCheck %s
-; RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 -filetype=obj %s 2>&1 | FileCheck %s
-; RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 %s 2>&1 | FileCheck %s
-; RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 -filetype=obj %s 2>&1 | FileCheck %s
-; RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 %s 2>&1 | FileCheck %s
-; RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=obj %s 2>&1 | FileCheck %s
-
-; CHECK: error: unknown key 'amd.RandomUnknownKey'
-
-	.text
-	.hsa_code_object_version 2,1
-	.hsa_code_object_isa 8,0,3,"AMD","AMDGPU"
-	.amdgpu_runtime_metadata
----
-{ amd.MDVersion: [ 2, 1 ], amd.RandomUnknownKey, amd.IsaInfo: { amd.IsaInfoWavefrontSize: 64, amd.IsaInfoLocalMemorySize: 65536, amd.IsaInfoEUsPerCU: 4, amd.IsaInfoMaxWavesPerEU: 10, amd.IsaInfoMaxFlatWorkGroupSize: 2048, amd.IsaInfoSGPRAllocGranule: 16, amd.IsaInfoTotalNumSGPRs: 800, amd.IsaInfoAddressableNumSGPRs: 102, amd.IsaInfoVGPRAllocGranule: 4, amd.IsaInfoTotalNumVGPRs: 256, amd.IsaInfoAddressableNumVGPRs: 256 }, amd.Kernels:
-  - { amd.KernelName: test, amd.Language: OpenCL C, amd.LanguageVersion: [ 1, 0 ], amd.Args:
-      - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 1, amd.ArgValueType: 6, amd.ArgTypeName: 'int*', amd.ArgAddrQual: 1, amd.ArgAccQual: 0 }
-      - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 7, amd.ArgValueType: 9 }
-      - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 8, amd.ArgValueType: 9 }
-      - { amd.ArgSize: 8, amd.ArgAlign: 8, amd.ArgKind: 9, amd.ArgValueType: 9 } } }
-...
-
-	.end_amdgpu_runtime_metadata
-	.globl	test
-	.p2align	8
-	.type	test,@function
-	.amdgpu_hsa_kernel test
-test:                                   ; @test
-	.amd_kernel_code_t
-		amd_code_version_major = 1
-		amd_code_version_minor = 0
-		amd_machine_kind = 1
-		amd_machine_version_major = 8
-		amd_machine_version_minor = 0
-		amd_machine_version_stepping = 3
-		kernel_code_entry_byte_offset = 256
-		kernel_code_prefetch_byte_size = 0
-		max_scratch_backing_memory_byte_size = 0
-		granulated_workitem_vgpr_count = 0
-		granulated_wavefront_sgpr_count = 0
-		priority = 0
-		float_mode = 192
-		priv = 0
-		enable_dx10_clamp = 1
-		debug_mode = 0
-		enable_ieee_mode = 1
-		enable_sgpr_private_segment_wave_byte_offset = 0
-		user_sgpr_count = 6
-		enable_trap_handler = 1
-		enable_sgpr_workgroup_id_x = 1
-		enable_sgpr_workgroup_id_y = 0
-		enable_sgpr_workgroup_id_z = 0
-		enable_sgpr_workgroup_info = 0
-		enable_vgpr_workitem_id = 0
-		enable_exception_msb = 0
-		granulated_lds_size = 0
-		enable_exception = 0
-		enable_sgpr_private_segment_buffer = 1
-		enable_sgpr_dispatch_ptr = 0
-		enable_sgpr_queue_ptr = 0
-		enable_sgpr_kernarg_segment_ptr = 1
-		enable_sgpr_dispatch_id = 0
-		enable_sgpr_flat_scratch_init = 0
-		enable_sgpr_private_segment_size = 0
-		enable_sgpr_grid_workgroup_count_x = 0
-		enable_sgpr_grid_workgroup_count_y = 0
-		enable_sgpr_grid_workgroup_count_z = 0
-		enable_ordered_append_gds = 0
-		private_element_size = 1
-		is_ptr64 = 1
-		is_dynamic_callstack = 0
-		is_debug_enabled = 0
-		is_xnack_enabled = 0
-		workitem_private_segment_byte_size = 0
-		workgroup_group_segment_byte_size = 0
-		gds_segment_byte_size = 0
-		kernarg_segment_byte_size = 8
-		workgroup_fbarrier_count = 0
-		wavefront_sgpr_count = 6
-		workitem_vgpr_count = 3
-		reserved_vgpr_first = 0
-		reserved_vgpr_count = 0
-		reserved_sgpr_first = 0
-		reserved_sgpr_count = 0
-		debug_wavefront_private_segment_offset_sgpr = 0
-		debug_private_segment_buffer_sgpr = 0
-		kernarg_segment_alignment = 4
-		group_segment_alignment = 4
-		private_segment_alignment = 4
-		wavefront_size = 6
-		call_convention = -1
-		runtime_loader_kernel_symbol = 0
-	.end_amd_kernel_code_t
-; BB#0:                                 ; %entry
-	s_load_dwordx2 s[0:1], s[4:5], 0x0
-	v_mov_b32_e32 v2, 0x309
-	s_waitcnt lgkmcnt(0)
-	v_mov_b32_e32 v0, s0
-	v_mov_b32_e32 v1, s1
-	flat_store_dword v[0:1], v2
-	s_endpgm
-.Lfunc_end0:
-	.size	test, .Lfunc_end0-test
-
-	.ident	""
-	.section	".note.GNU-stack"