[AMDGPU] Remove Code Object V2

[Pierre-vh]

Summary

Code Object V2 has been deprecated for more than a year now. We can safely remove it from LLVM.

• [clang] Remove support for the -mcode-object-version=2 option.
• [lld] Remove/refactor tests that were still using COV2
• [llvm] Update AMDGPUUsage.rst
  • Code Object V2 docs are left for informational purposes because those code objects may still be supported by the runtime/loaders for a while.
• [AMDGPU] Remove COV2 emission capabilities.
• [AMDGPU] Remove MetadataStreamerYamlV2 which was only used by COV2
• [AMDGPU] Update all tests that were still using COV2
  • They are either deleted or ported directly to code object v4 (as v3 is also planned to be removed soon).

Depends on D145671

[kzhuravl]

llvm/docs/AMDGPUUsage.rst

1379

emission->generation?

2647

emission->generation?

14597

ditto

llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp

749–750

Nice to see this finally go

[yaxunl]

LGTM on clang side.

[arsenm]

Is clover still relying on the cov2 support?

clang/include/clang/Basic/TargetOptions.h

85

I wouldn't remove the enum field, just add a comment that emission is unsupported or something

llvm/test/MC/AMDGPU/hsa-gfx10.s

3

I thought we were still going to be able to read old objects

llvm/tools/llvm-readobj/ELFDumper.cpp

5437–5440

This looks like a separate change?

[Pierre-vh]

Address comments, split some change in D146119

llvm/test/MC/AMDGPU/hsa-gfx10.s

3

I think llvm-readobj uses all of the MC/Target infrastructure so if we remove emission, we also remove reading, no?

I'm actually not sure if we plan to let readobj/readelf read COV2 object files, it's an interesting question

llvm/tools/llvm-readobj/ELFDumper.cpp

5437–5440

Moved to D146119

[Pierre-vh]

Rebase

[Pierre-vh]

Rebase

[Pierre-vh]

ping

[Pierre-vh]

ping

[scott.linder]

llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp

522–524

I don't follow this change; was the assert just incorrect previously?

llvm/test/MC/AMDGPU/hsa-gfx10.s

3

I think this is my biggest concern. Do we incur a huge maintenance burden that warrants dropping read support? How much code do we really need to maintain to keep the readobj/objdump like tools universal?

@t-tye do you have any thoughts on whether we should maintain backwards compatibility in the LLVM tooling, even if we drop generation support?

[Pierre-vh]

llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp

522–524

It's for CodeGen/AMDGPU/no-hsa-graphics-shaders.ll, it crashes otherwise.

An alternative can be to change this:

if (STM.isAmdHsaOS())
  HSAMetadataStream->emitKernel(*MF, CurrentProgramInfo);

So it checks the CC and doesn't call the function if the CC is incorrect. I don't mind either solution

llvm/test/MC/AMDGPU/hsa-gfx10.s

3

It's been a while since I wrote this but IIRC there was a discussion about it and it was fine to remove read support. An alternative may be to still identify code object V2, but not read the metadata and instead print a warning about the file format being deprecated?

Or I think it's YAML, maybe we can just raw dump the MD and print a warning?

Most of the maintenance cost would be in the MD mapper which is almost 500 lines of code that'd just be there for the sake of "maybe some needs to read MD"

If we go with one of the above suggestions I can just add a test using yml2obj that emits a V2 file

[Pierre-vh]

Rebase

[scott.linder]

llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp

522–524

OK, makes sense. I don't have a particularly strong preference, but whatever the solution is I would prefer it be split into another patch. It isn't actually a result of dropping v2 support, as the bug is present in HEAD as-is.

llvm/test/MC/AMDGPU/hsa-gfx10.s

3

Ah, alright; apologies if I was part of the discussions and am still re-litigating now :)

I don't have particularly strong feelings, especially if there is some consensus that dropping is OK. Or if it isn't too onerous the "best effort" support of dumping things as-is for the old versions sounds good to me!

[Pierre-vh]

Rebase on D152432

[Pierre-vh]

Rebase

[Pierre-vh]

llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp

5583 ↗

(On Diff #545938)

This is an issue with amdpal-elf.ll, the run line with llvm-mc fails because it can't parse amd_amdgpu_isa.
Not sure how to fix this. Should we be able to read that directive, or should we just never emit it?
Some tests use it, and stg also emits it in the same test, so it's not new. It's just no longer parse-able after isHsaAbiVersion3AndAbove was removed - I suspect that function returned false for non-HSA OSes and was mistakenly used here to check for != AMDHSA?

[Pierre-vh]

Fix non-HSA

[cfang]

llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp

5598 ↗

(On Diff #546714)

Are you sure Non-HSA does not have the four directives you deleted?

llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp

104

It is fine now. But I think STI could never be null.

llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h

46

Should we keep this field, and just mention "unsupported"?

59

Are all these "isHsaAbiVersionX" no longer needed?

[Pierre-vh]

Fix tests, address comments

[Pierre-vh]

Simplify ParseDirectiveHSAMetadata as it's now HSA only

llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp

5598 ↗

(On Diff #546714)

I'm really not sure, I saw hsa in the name and I thought it only applied to HSA, but some tests are failing.
I'll leave them in until someone can answer for sure.

llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h

46

I'm not sure about that, I assume that we're removing as many traces of V2 as possible from the backend. No point in keeping an unused enum entry IMO, but I'm okay with keeping it if there's a good reason to

59

Yes they're needed because they implicitly check for HSA as well

[Pierre-vh]

ping

[Pierre-vh]

https://github.com/llvm/llvm-project/pull/65715

clang/include/clang/Basic/TargetOptions.h

public:
 
   /// \brief If enabled, allow AMDGPU unsafe floating point atomics.
   bool AllowAMDGPUUnsafeFPAtomics = false;
 
   /// \brief Enumeration value for AMDGPU code object version, which is the
   /// code object version times 100.
   enum CodeObjectVersionKind {
     COV_None,
-    COV_2 = 200,
     COV_3 = 300,
     COV_4 = 400,
     COV_5 = 500,
   };
   /// \brief Code object version for AMDGPU.
   CodeObjectVersionKind CodeObjectVersion;
 
   // The code model to be used as specified by the user. Corresponds to

clang/include/clang/Driver/Options.td

defm amdgpu_ieee : BoolOption<"m", "amdgpu-ieee",
   " mode register. Floating point opcodes that support exception flag "
   "gathering quiet and propagate signaling NaN inputs per IEEE 754-2008. "
   "This option changes the ABI. (AMDGPU only)">,
   NegFlag<SetFalse, [CC1Option]>>, Group<m_Group>;
 
 def mcode_object_version_EQ : Joined<["-"], "mcode-object-version=">, Group<m_Group>,
   HelpText<"Specify code object ABI version. Defaults to 4. (AMDGPU only)">,
   Flags<[CC1Option]>,
-  Values<"none,2,3,4,5">,
+  Values<"none,3,4,5">,
   NormalizedValuesScope<"TargetOptions">,
-  NormalizedValues<["COV_None", "COV_2", "COV_3", "COV_4", "COV_5"]>,
+  NormalizedValues<["COV_None", "COV_3", "COV_4", "COV_5"]>,
   MarshallingInfoEnum<TargetOpts<"CodeObjectVersion">, "COV_4">;
 
 defm cumode : SimpleMFlag<"cumode",
   "Specify CU wavefront", "Specify WGP wavefront",
   " execution mode (AMDGPU only)", m_amdgpu_Features_Group>;
 defm tgsplit : SimpleMFlag<"tgsplit", "Enable", "Disable",
   " threadgroup split execution mode (AMDGPU only)", m_amdgpu_Features_Group>;
 defm wavefrontsize64 : SimpleMFlag<"wavefrontsize64",

clang/lib/Driver/ToolChains/CommonArgs.cpp

 
 static llvm::opt::Arg *
 getAMDGPUCodeObjectArgument(const Driver &D, const llvm::opt::ArgList &Args) {
   return Args.getLastArg(options::OPT_mcode_object_version_EQ);
 }
 
 void tools::checkAMDGPUCodeObjectVersion(const Driver &D,
                                          const llvm::opt::ArgList &Args) {
-  const unsigned MinCodeObjVer = 2;
+  const unsigned MinCodeObjVer = 3;
   const unsigned MaxCodeObjVer = 5;
 
   if (auto *CodeObjArg = getAMDGPUCodeObjectArgument(D, Args)) {
     if (CodeObjArg->getOption().getID() ==
         options::OPT_mcode_object_version_EQ) {
       unsigned CodeObjVer = MaxCodeObjVer;
       auto Remnant =
           StringRef(CodeObjArg->getValue()).getAsInteger(0, CodeObjVer);

clang/test/CodeGenCUDA/amdgpu-code-object-version.cu

 // Create module flag for code object version.
 
 // RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
 // RUN:   -o - %s | FileCheck %s -check-prefix=V4
 
 // RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
-// RUN:   -mcode-object-version=2 -o - %s | FileCheck -check-prefix=V2 %s
-
-// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
 // RUN:   -mcode-object-version=3 -o - %s | FileCheck -check-prefix=V3 %s
 
 // RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
 // RUN:   -mcode-object-version=4 -o - %s | FileCheck -check-prefix=V4 %s
 
 // RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
 // RUN:   -mcode-object-version=5 -o - %s | FileCheck -check-prefix=V5 %s
 
 // RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
 // RUN:   -mcode-object-version=none -o - %s | FileCheck %s -check-prefix=NONE
 
 // RUN: not %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
 // RUN:   -mcode-object-version=4.1 -o - %s 2>&1| FileCheck %s -check-prefix=INV
 
-// V2: !{{.*}} = !{i32 1, !"amdgpu_code_object_version", i32 200}
 // V3: !{{.*}} = !{i32 1, !"amdgpu_code_object_version", i32 300}
 // V4: !{{.*}} = !{i32 1, !"amdgpu_code_object_version", i32 400}
 // V5: !{{.*}} = !{i32 1, !"amdgpu_code_object_version", i32 500}
 // NONE-NOT: !{{.*}} = !{i32 1, !"amdgpu_code_object_version",
 // INV: error: invalid value '4.1' in '-mcode-object-version=4.1'

clang/test/Driver/hip-code-object-version.hip

 // REQUIRES: amdgpu-registered-target
 
-// Check bundle ID for code object v2.
-
-// RUN: %clang -### --target=x86_64-linux-gnu \
-// RUN:   -mcode-object-version=2 \
-// RUN:   --offload-arch=gfx906 -nogpulib \
-// RUN:   %s 2>&1 | FileCheck -check-prefix=V2 %s
-
-// V2: "-mllvm" "--amdhsa-code-object-version=2"
-// V2: "-targets=host-x86_64-unknown-linux,hip-amdgcn-amd-amdhsa--gfx906"
-
 // Check bundle ID for code object v3.
 
 // RUN: %clang -### --target=x86_64-linux-gnu \
 // RUN:   -mcode-object-version=3 \
 // RUN:   --offload-arch=gfx906 -nogpulib \
 // RUN:   %s 2>&1 | FileCheck -check-prefix=V3 %s
 
 // RUN: %clang -### --target=x86_64-linux-gnu \

 
 // VD: "-targets=host-x86_64-unknown-linux,hipv4-amdgcn-amd-amdhsa--gfx906"
 
 // Check invalid code object version option.
 
 // RUN: %clang -### --target=x86_64-linux-gnu \
 // RUN:   -mcode-object-version=1 \
 // RUN:   --offload-arch=gfx906 -nogpulib \
-// RUN:   %s 2>&1 | FileCheck -check-prefix=INVALID %s
-// INVALID: error: invalid integral value '1' in '-mcode-object-version=1'
-// INVALID-NOT: error: invalid integral value
+// RUN:   %s 2>&1 | FileCheck -check-prefix=INVALID_1 %s
+// INVALID_1: error: invalid integral value '1' in '-mcode-object-version=1'
+// INVALID_1-NOT: error: invalid integral value
+
+// RUN: %clang -### --target=x86_64-linux-gnu \
+// RUN:   -mcode-object-version=2 \
+// RUN:   --offload-arch=gfx906 -nogpulib \
+// RUN:   %s 2>&1 | FileCheck -check-prefix=INVALID_2 %s
+// INVALID_2: error: invalid integral value '2' in '-mcode-object-version=2'
+// INVALID_2-NOT: error: invalid integral value
 
 // Check LLVM code object version option --amdhsa-code-object-version
 // is passed to -cc1 and -cc1as, and -mcode-object-version is passed
 // to -cc1 but not -cc1as.
 
 // RUN: %clang -### --target=x86_64-linux-gnu \
 // RUN:   -mcode-object-version=5 \
 // RUN:   --offload-arch=gfx906 -nogpulib -save-temps \

lld/test/ELF/Inputs/amdgpu-kernel-0.s

 .text
 .globl kernel_0
 .align 64
-.amdgpu_hsa_kernel kernel_0
 kernel_0:
   s_endpgm

lld/test/ELF/Inputs/amdgpu-kernel-1.s

 .text
 .globl kernel_1
 .align 64
-.amdgpu_hsa_kernel kernel_1
 kernel_1:
   s_endpgm

lld/test/ELF/amdgpu-abi-version-err.s

 # REQUIRES: amdgpu
-# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=obj %s -o %t-0.o
-# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=2 -filetype=obj %s -o %t-1.o
+# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=4 -filetype=obj %s -o %t-0.o
+# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=5 -filetype=obj %s -o %t-1.o
 # RUN: not ld.lld -shared %t-0.o %t-1.o -o /dev/null 2>&1 | FileCheck %s
 
 # CHECK: ld.lld: error: incompatible ABI version: {{.*}}-1.o
 
 .text
   s_nop 0x0
   s_endpgm

lld/test/ELF/amdgpu-elf-flags-err.s

 # REQUIRES: amdgpu
-# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx802 --amdhsa-code-object-version=2 -filetype=obj %S/Inputs/amdgpu-kernel-0.s -o %t-0.o
-# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx803 --amdhsa-code-object-version=2 -filetype=obj %S/Inputs/amdgpu-kernel-1.s -o %t-1.o
+# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx802 --amdhsa-code-object-version=4 -filetype=obj %S/Inputs/amdgpu-kernel-0.s -o %t-0.o
+# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx803 --amdhsa-code-object-version=4 -filetype=obj %S/Inputs/amdgpu-kernel-1.s -o %t-1.o
 # RUN: not ld.lld -shared %t-0.o %t-1.o -o /dev/null 2>&1 | FileCheck %s
 
-# CHECK: error: incompatible e_flags: {{.*}}-1.o
+# CHECK: error: incompatible mach: {{.*}}-1.o

lld/test/ELF/amdgpu-elf-flags.s

 # REQUIRES: amdgpu
-# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx803 --amdhsa-code-object-version=2 -filetype=obj %S/Inputs/amdgpu-kernel-0.s -o %t-0.o
-# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx803 --amdhsa-code-object-version=2 -filetype=obj %S/Inputs/amdgpu-kernel-1.s -o %t-1.o
+# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx803 --amdhsa-code-object-version=4 -filetype=obj %S/Inputs/amdgpu-kernel-0.s -o %t-0.o
+# RUN: llvm-mc -triple amdgcn-amd-amdhsa -mcpu=gfx803 --amdhsa-code-object-version=4 -filetype=obj %S/Inputs/amdgpu-kernel-1.s -o %t-1.o
 # RUN: ld.lld -shared %t-0.o %t-1.o -o %t.so
 # RUN: llvm-readobj --file-headers %t.so | FileCheck --check-prefix=FIRSTLINK %s
 
 ## Try to link again where there are no object file inputs, only a shared library. Issue 47690
 # RUN: ld.lld -shared %t.so -o - | llvm-readobj -h - | FileCheck --check-prefix=SECONDLINK %s
 
 
 # FIRSTLINK:      Flags [
 # FIRSTLINK-NEXT:   EF_AMDGPU_MACH_AMDGCN_GFX803 (0x2A)
 # FIRSTLINK-NEXT: ]
 
 # SECONDLINK:      Flags [ (0x0)
 # SECONDLINK-NEXT: ]

lld/test/ELF/amdgpu-kernels.s

-# REQUIRES: amdgpu
-# RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=2 %s -o %t.o
-# RUN: ld.lld -shared %t.o -o %t
-# RUN: llvm-readobj --sections --symbols -l %t | FileCheck %s
-
-.hsa_code_object_version 1,0
-.hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-
-.text
-.globl kernel0
-.align 256
-.amdgpu_hsa_kernel kernel0
-kernel0:
-  s_endpgm
-.Lfunc_end0:
-  .size kernel0, .Lfunc_end0-kernel0
-
-.globl kernel1
-.align 256
-.amdgpu_hsa_kernel kernel1
-kernel1:
-  s_endpgm
-  s_endpgm
-.Lfunc_end1:
-  .size kernel1, .Lfunc_end1-kernel1
-
-
-# CHECK: Section {
-# CHECK: Name: .text
-# CHECK: Type: SHT_PROGBITS
-# CHECK: Flags [ (0x6)
-# CHECK: SHF_ALLOC (0x2)
-# CHECK: SHF_EXECINSTR (0x4)
-# CHECK: ]
-# CHECK: }
-
-# CHECK: ProgramHeader {
-# CHECK:   Type: PT_LOAD
-
-# CHECK: Symbol {
-# CHECK: Name: kernel0
-# CHECK: Value:
-# CHECK: Size: 4
-# CHECK: Binding: Global
-# CHECK: Type: AMDGPU_HSA_KERNEL
-# CHECK: Section: .text
-# CHECK: }
-
-# CHECK: Symbol {
-# CHECK: Name: kernel1
-# CHECK: Value:
-# CHECK: Size: 8
-# CHECK: Binding: Global
-# CHECK: Type: AMDGPU_HSA_KERNEL
-# CHECK: Section: .text
-# CHECK: }

llvm/docs/AMDGPUUsage.rst

 alignment.
 
 .. _amdgpu-note-records-v2:
 
 Code Object V2 Note Records
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. warning::
-  Code object V2 is not the default code object version emitted by
-  this version of LLVM.
+  Code object V2 emission is no longer supported by this version of LLVM.
 
 The AMDGPU backend code object uses the following ELF note record in the
 ``.note`` section when compiling for code object V2.
 
 The note record vendor field is "AMD".
 
 Additional note records may be present, but any which are not documented here
 are deprecated and should not be used.

 example, the AMD OpenCL runtime records kernel argument information.
 
 .. _amdgpu-amdhsa-code-object-metadata-v2:
 
 Code Object V2 Metadata
 +++++++++++++++++++++++
 
 .. warning::
-  Code object V2 is not the default code object version emitted by this version
-  of LLVM.
+  Code object V2 emission is no longer supported by this version of LLVM.
 
 Code object V2 metadata is specified by the ``NT_AMD_HSA_METADATA`` note record
 (see :ref:`amdgpu-note-records-v2`).
 
 The metadata is specified as a YAML formatted string (see [YAML]_ and
 :doc:`YamlIO`).
 
 .. TODO::

 For full list of supported instructions, refer to "Vector ALU instructions".
 
 .. _amdgpu-amdhsa-assembler-predefined-symbols-v2:
 
 Code Object V2 Predefined Symbols
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. warning::
-  Code object V2 is not the default code object version emitted by
-  this version of LLVM.
+  Code object V2 emission is no longer supported by this version of LLVM.
 
 The AMDGPU assembler defines and updates some symbols automatically. These
 symbols do not affect code generation.
 
 .option.machine_version_major
 +++++++++++++++++++++++++++++
 
 Set to the GFX major generation number of the target being assembled for. For

 one.
 
 .. _amdgpu-amdhsa-assembler-directives-v2:
 
 Code Object V2 Directives
 ~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. warning::
-  Code object V2 is not the default code object version emitted by
-  this version of LLVM.
+  Code object V2 emission is no longer supported by this version of LLVM.
 
 AMDGPU ABI defines auxiliary data in output code object. In assembly source,
 one can specify them with assembler directives.
 
 .hsa_code_object_version major, minor
 +++++++++++++++++++++++++++++++++++++
 
 *major* and *minor* are integers that specify the version of the HSA code

 comments in lib/Target/AMDGPU/AmdKernelCodeT.h and test/CodeGen/AMDGPU/hsa.s.
 
 .. _amdgpu-amdhsa-assembler-example-v2:
 
 Code Object V2 Example Source Code
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 .. warning::
-  Code Object V2 is not the default code object version emitted by
-  this version of LLVM.
+  Code object V2 emission is no longer supported by this version of LLVM.
 
 Here is an example of a minimal assembly source file, defining one HSA kernel:
 
 .. code::
    :number-lines:
 
    .hsa_code_object_version 1,0
    .hsa_code_object_isa

llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp

void AMDGPUAsmPrinter::initTargetStreamer(Module &M) {
   if (CodeObjectVersion >= AMDGPU::AMDHSA_COV3)
     getTargetStreamer()->EmitDirectiveAMDGCNTarget();
 
   if (TM.getTargetTriple().getOS() == Triple::AMDHSA)
     HSAMetadataStream->begin(M, *getTargetStreamer()->getTargetID());
 
   if (TM.getTargetTriple().getOS() == Triple::AMDPAL)
     getTargetStreamer()->getPALMetadata()->readFromIR(M);
-
-  if (CodeObjectVersion >= AMDGPU::AMDHSA_COV3)
-    return;
-
-  // HSA emits NT_AMD_HSA_CODE_OBJECT_VERSION for code objects v2.
-  if (TM.getTargetTriple().getOS() == Triple::AMDHSA)
-    getTargetStreamer()->EmitDirectiveHSACodeObjectVersion(2, 1);
-
-  // HSA and PAL emit NT_AMD_HSA_ISA_VERSION for code objects v2.
-  IsaVersion Version = getIsaVersion(getGlobalSTI()->getCPU());
-  getTargetStreamer()->EmitDirectiveHSACodeObjectISAV2(
-      Version.Major, Version.Minor, Version.Stepping, "AMD", "AMDGPU");
 }
 
 void AMDGPUAsmPrinter::emitEndOfAsmFile(Module &M) {
   // Init target streamer if it has not yet happened
   if (!IsTargetStreamerInitialized)
     initTargetStreamer(M);
 
-  if (TM.getTargetTriple().getOS() != Triple::AMDHSA ||
-      CodeObjectVersion == AMDGPU::AMDHSA_COV2)
+  if (TM.getTargetTriple().getOS() != Triple::AMDHSA)
     getTargetStreamer()->EmitISAVersion();
 
   // Emit HSA Metadata (NT_AMD_AMDGPU_HSA_METADATA).
   // Emit HSA Metadata (NT_AMD_HSA_METADATA).
   if (TM.getTargetTriple().getOS() == Triple::AMDHSA) {
     HSAMetadataStream->end();
     bool Success = HSAMetadataStream->emitTo(*getTargetStreamer());
     (void)Success;
if (FunctionTargetID.isSramEccSupported() &&
     OutContext.reportError({}, "sramecc setting of '" + Twine(MF->getName()) +
                            "' function does not match module sramecc setting");
     return;
   }
 
   if (!MFI.isEntryFunction())
     return;
 
-  if ((STM.isMesaKernel(F) || CodeObjectVersion == AMDGPU::AMDHSA_COV2) &&
+  if (STM.isMesaKernel(F) &&
       (F.getCallingConv() == CallingConv::AMDGPU_KERNEL ||
        F.getCallingConv() == CallingConv::SPIR_KERNEL)) {
     amd_kernel_code_t KernelCode;
     getAmdKernelCode(KernelCode, CurrentProgramInfo, *MF);
     getTargetStreamer()->EmitAMDKernelCodeT(KernelCode);
   }
 
   if (STM.isAmdHsaOS())
     HSAMetadataStream->emitKernel(*MF, CurrentProgramInfo);
 }
 
 void AMDGPUAsmPrinter::emitFunctionBodyEnd() {
   const SIMachineFunctionInfo &MFI = *MF->getInfo<SIMachineFunctionInfo>();
   if (!MFI.isEntryFunction())
     return;
 
-  if (TM.getTargetTriple().getOS() != Triple::AMDHSA ||
-      CodeObjectVersion == AMDGPU::AMDHSA_COV2)
+  if (TM.getTargetTriple().getOS() != Triple::AMDHSA)
     return;
 
   auto &Streamer = getTargetStreamer()->getStreamer();
   auto &Context = Streamer.getContext();
   auto &ObjectFileInfo = *Context.getObjectFileInfo();
   auto &ReadOnlySection = *ObjectFileInfo.getReadOnlySection();
 
   Streamer.pushSection();
void AMDGPUAsmPrinter::emitGlobalVariable(const GlobalVariable *GV) {
   AsmPrinter::emitGlobalVariable(GV);
 }
 
 bool AMDGPUAsmPrinter::doInitialization(Module &M) {
   CodeObjectVersion = AMDGPU::getCodeObjectVersion(M);
 
   if (TM.getTargetTriple().getOS() == Triple::AMDHSA) {
     switch (CodeObjectVersion) {
-    case AMDGPU::AMDHSA_COV2:
-      HSAMetadataStream.reset(new HSAMD::MetadataStreamerYamlV2());
-      break;
     case AMDGPU::AMDHSA_COV3:
       HSAMetadataStream.reset(new HSAMD::MetadataStreamerMsgPackV3());
       break;
     case AMDGPU::AMDHSA_COV4:
       HSAMetadataStream.reset(new HSAMD::MetadataStreamerMsgPackV4());
       break;
     case AMDGPU::AMDHSA_COV5:
       HSAMetadataStream.reset(new HSAMD::MetadataStreamerMsgPackV5());

llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.h

void emitHiddenKernelArgs(const MachineFunction &MF, unsigned &Offset,
                             msgpack::ArrayDocNode Args) override;
   void emitKernelAttrs(const Function &Func, msgpack::MapDocNode Kern) override;
 
 public:
   MetadataStreamerMsgPackV5() = default;
   ~MetadataStreamerMsgPackV5() = default;
 };
 
-// TODO: Rename MetadataStreamerV2 -> MetadataStreamerYamlV2.
-class MetadataStreamerYamlV2 final : public MetadataStreamer {
-private:
-  Metadata HSAMetadata;
-
-  void dump(StringRef HSAMetadataString) const;
-
-  void verify(StringRef HSAMetadataString) const;
-
-  AccessQualifier getAccessQualifier(StringRef AccQual) const;
-
-  AddressSpaceQualifier getAddressSpaceQualifier(unsigned AddressSpace) const;
-
-  ValueKind getValueKind(Type *Ty, StringRef TypeQual,
-                         StringRef BaseTypeName) const;
-
-  std::string getTypeName(Type *Ty, bool Signed) const;
-
-  std::vector<uint32_t> getWorkGroupDimensions(MDNode *Node) const;
-
-  Kernel::CodeProps::Metadata getHSACodeProps(
-      const MachineFunction &MF,
-      const SIProgramInfo &ProgramInfo) const;
-  Kernel::DebugProps::Metadata getHSADebugProps(
-      const MachineFunction &MF,
-      const SIProgramInfo &ProgramInfo) const;
-
-  void emitPrintf(const Module &Mod);
-
-  void emitKernelLanguage(const Function &Func);
-
-  void emitKernelAttrs(const Function &Func);
-
-  void emitKernelArgs(const Function &Func, const GCNSubtarget &ST);
-
-  void emitKernelArg(const Argument &Arg);
-
-  void emitKernelArg(const DataLayout &DL, Type *Ty, Align Alignment,
-                     ValueKind ValueKind,
-                     MaybeAlign PointeeAlign = std::nullopt,
-                     StringRef Name = "", StringRef TypeName = "",
-                     StringRef BaseTypeName = "", StringRef AccQual = "",
-                     StringRef TypeQual = "");
-
-  void emitHiddenKernelArgs(const Function &Func, const GCNSubtarget &ST);
-
-  const Metadata &getHSAMetadata() const {
-    return HSAMetadata;
-  }
-
-protected:
-  void emitVersion() override;
-  void emitHiddenKernelArgs(const MachineFunction &MF, unsigned &Offset,
-                            msgpack::ArrayDocNode Args) override {
-    llvm_unreachable("Dummy override should not be invoked!");
-  }
-  void emitKernelAttrs(const Function &Func,
-                       msgpack::MapDocNode Kern) override {
-    llvm_unreachable("Dummy override should not be invoked!");
-  }
-
-public:
-  MetadataStreamerYamlV2() = default;
-  ~MetadataStreamerYamlV2() = default;
-
-  bool emitTo(AMDGPUTargetStreamer &TargetStreamer) override;
-
-  void begin(const Module &Mod,
-             const IsaInfo::AMDGPUTargetID &TargetID) override;
-
-  void end() override;
-
-  void emitKernel(const MachineFunction &MF,
-                  const SIProgramInfo &ProgramInfo) override;
-};
-
 } // end namespace HSAMD
 } // end namespace AMDGPU
 } // end namespace llvm
 
 #endif // LLVM_LIB_TARGET_AMDGPU_MCTARGETDESC_AMDGPUHSAMETADATASTREAMER_H

llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp

 static cl::opt<bool> VerifyHSAMetadata(
     "amdgpu-verify-hsa-metadata",
     cl::desc("Verify AMDGPU HSA Metadata"));
 
 namespace AMDGPU {
 namespace HSAMD {
 
 //===----------------------------------------------------------------------===//
-// HSAMetadataStreamerV2
-//===----------------------------------------------------------------------===//
-void MetadataStreamerYamlV2::dump(StringRef HSAMetadataString) const {
-  errs() << "AMDGPU HSA Metadata:\n" << HSAMetadataString << '\n';
-}
-
-void MetadataStreamerYamlV2::verify(StringRef HSAMetadataString) const {
-  errs() << "AMDGPU HSA Metadata Parser Test: ";
-
-  HSAMD::Metadata FromHSAMetadataString;
-  if (fromString(HSAMetadataString, FromHSAMetadataString)) {
-    errs() << "FAIL\n";
-    return;
-  }
-
-  std::string ToHSAMetadataString;
-  if (toString(FromHSAMetadataString, ToHSAMetadataString)) {
-    errs() << "FAIL\n";
-    return;
-  }
-
-  errs() << (HSAMetadataString == ToHSAMetadataString ? "PASS" : "FAIL")
-         << '\n';
-  if (HSAMetadataString != ToHSAMetadataString) {
-    errs() << "Original input: " << HSAMetadataString << '\n'
-           << "Produced output: " << ToHSAMetadataString << '\n';
-  }
-}
-
-AccessQualifier
-MetadataStreamerYamlV2::getAccessQualifier(StringRef AccQual) const {
-  if (AccQual.empty())
-    return AccessQualifier::Unknown;
-
-  return StringSwitch<AccessQualifier>(AccQual)
-             .Case("read_only",  AccessQualifier::ReadOnly)
-             .Case("write_only", AccessQualifier::WriteOnly)
-             .Case("read_write", AccessQualifier::ReadWrite)
-             .Default(AccessQualifier::Default);
-}
-
-AddressSpaceQualifier
-MetadataStreamerYamlV2::getAddressSpaceQualifier(unsigned AddressSpace) const {
-  switch (AddressSpace) {
-  case AMDGPUAS::PRIVATE_ADDRESS:
-    return AddressSpaceQualifier::Private;
-  case AMDGPUAS::GLOBAL_ADDRESS:
-    return AddressSpaceQualifier::Global;
-  case AMDGPUAS::CONSTANT_ADDRESS:
-    return AddressSpaceQualifier::Constant;
-  case AMDGPUAS::LOCAL_ADDRESS:
-    return AddressSpaceQualifier::Local;
-  case AMDGPUAS::FLAT_ADDRESS:
-    return AddressSpaceQualifier::Generic;
-  case AMDGPUAS::REGION_ADDRESS:
-    return AddressSpaceQualifier::Region;
-  default:
-    return AddressSpaceQualifier::Unknown;
-  }
-}
-
-ValueKind MetadataStreamerYamlV2::getValueKind(Type *Ty, StringRef TypeQual,
-                                               StringRef BaseTypeName) const {
-  if (TypeQual.contains("pipe"))
-    return ValueKind::Pipe;
-
-  return StringSwitch<ValueKind>(BaseTypeName)
-             .Case("image1d_t", ValueKind::Image)
-             .Case("image1d_array_t", ValueKind::Image)
-             .Case("image1d_buffer_t", ValueKind::Image)
-             .Case("image2d_t", ValueKind::Image)
-             .Case("image2d_array_t", ValueKind::Image)
-             .Case("image2d_array_depth_t", ValueKind::Image)
-             .Case("image2d_array_msaa_t", ValueKind::Image)
-             .Case("image2d_array_msaa_depth_t", ValueKind::Image)
-             .Case("image2d_depth_t", ValueKind::Image)
-             .Case("image2d_msaa_t", ValueKind::Image)
-             .Case("image2d_msaa_depth_t", ValueKind::Image)
-             .Case("image3d_t", ValueKind::Image)
-             .Case("sampler_t", ValueKind::Sampler)
-             .Case("queue_t", ValueKind::Queue)
-             .Default(isa<PointerType>(Ty) ?
-                          (Ty->getPointerAddressSpace() ==
-                           AMDGPUAS::LOCAL_ADDRESS ?
-                           ValueKind::DynamicSharedPointer :
-                           ValueKind::GlobalBuffer) :
-                      ValueKind::ByValue);
-}
-
-std::string MetadataStreamerYamlV2::getTypeName(Type *Ty, bool Signed) const {
-  switch (Ty->getTypeID()) {
-  case Type::IntegerTyID: {
-    if (!Signed)
-      return (Twine('u') + getTypeName(Ty, true)).str();
-
-    auto BitWidth = Ty->getIntegerBitWidth();
-    switch (BitWidth) {
-    case 8:
-      return "char";
-    case 16:
-      return "short";
-    case 32:
-      return "int";
-    case 64:
-      return "long";
-    default:
-      return (Twine('i') + Twine(BitWidth)).str();
-    }
-  }
-  case Type::HalfTyID:
-    return "half";
-  case Type::FloatTyID:
-    return "float";
-  case Type::DoubleTyID:
-    return "double";
-  case Type::FixedVectorTyID: {
-    auto VecTy = cast<FixedVectorType>(Ty);
-    auto ElTy = VecTy->getElementType();
-    auto NumElements = VecTy->getNumElements();
-    return (Twine(getTypeName(ElTy, Signed)) + Twine(NumElements)).str();
-  }
-  default:
-    return "unknown";
-  }
-}
-
-std::vector<uint32_t>
-MetadataStreamerYamlV2::getWorkGroupDimensions(MDNode *Node) const {
-  std::vector<uint32_t> Dims;
-  if (Node->getNumOperands() != 3)
-    return Dims;
-
-  for (auto &Op : Node->operands())
-    Dims.push_back(mdconst::extract<ConstantInt>(Op)->getZExtValue());
-  return Dims;
-}
-
-Kernel::CodeProps::Metadata MetadataStreamerYamlV2::getHSACodeProps(
-    const MachineFunction &MF, const SIProgramInfo &ProgramInfo) const {
-  const GCNSubtarget &STM = MF.getSubtarget<GCNSubtarget>();
-  const SIMachineFunctionInfo &MFI = *MF.getInfo<SIMachineFunctionInfo>();
-  HSAMD::Kernel::CodeProps::Metadata HSACodeProps;
-  const Function &F = MF.getFunction();
-
-  assert(F.getCallingConv() == CallingConv::AMDGPU_KERNEL ||
-         F.getCallingConv() == CallingConv::SPIR_KERNEL);
-
-  Align MaxKernArgAlign;
-  HSACodeProps.mKernargSegmentSize = STM.getKernArgSegmentSize(F,
-                                                               MaxKernArgAlign);
-  HSACodeProps.mKernargSegmentAlign =
-    std::max(MaxKernArgAlign, Align(4)).value();
-
-  HSACodeProps.mGroupSegmentFixedSize = ProgramInfo.LDSSize;
-  HSACodeProps.mPrivateSegmentFixedSize = ProgramInfo.ScratchSize;
-  HSACodeProps.mWavefrontSize = STM.getWavefrontSize();
-  HSACodeProps.mNumSGPRs = ProgramInfo.NumSGPR;
-  HSACodeProps.mNumVGPRs = ProgramInfo.NumVGPR;
-  HSACodeProps.mMaxFlatWorkGroupSize = MFI.getMaxFlatWorkGroupSize();
-  HSACodeProps.mIsDynamicCallStack = ProgramInfo.DynamicCallStack;
-  HSACodeProps.mIsXNACKEnabled = STM.isXNACKEnabled();
-  HSACodeProps.mNumSpilledSGPRs = MFI.getNumSpilledSGPRs();
-  HSACodeProps.mNumSpilledVGPRs = MFI.getNumSpilledVGPRs();
-
-  return HSACodeProps;
-}
-
-Kernel::DebugProps::Metadata MetadataStreamerYamlV2::getHSADebugProps(
-    const MachineFunction &MF, const SIProgramInfo &ProgramInfo) const {
-  return HSAMD::Kernel::DebugProps::Metadata();
-}
-
-void MetadataStreamerYamlV2::emitVersion() {
-  auto &Version = HSAMetadata.mVersion;
-
-  Version.push_back(VersionMajorV2);
-  Version.push_back(VersionMinorV2);
-}
-
-void MetadataStreamerYamlV2::emitPrintf(const Module &Mod) {
-  auto &Printf = HSAMetadata.mPrintf;
-
-  auto Node = Mod.getNamedMetadata("llvm.printf.fmts");
-  if (!Node)
-    return;
-
-  for (auto *Op : Node->operands())
-    if (Op->getNumOperands())
-      Printf.push_back(
-          std::string(cast<MDString>(Op->getOperand(0))->getString()));
-}
-
-void MetadataStreamerYamlV2::emitKernelLanguage(const Function &Func) {
-  auto &Kernel = HSAMetadata.mKernels.back();
-
-  // TODO: What about other languages?
-  auto Node = Func.getParent()->getNamedMetadata("opencl.ocl.version");
-  if (!Node || !Node->getNumOperands())
-    return;
-  auto Op0 = Node->getOperand(0);
-  if (Op0->getNumOperands() <= 1)
-    return;
-
-  Kernel.mLanguage = "OpenCL C";
-  Kernel.mLanguageVersion.push_back(
-      mdconst::extract<ConstantInt>(Op0->getOperand(0))->getZExtValue());
-  Kernel.mLanguageVersion.push_back(
-      mdconst::extract<ConstantInt>(Op0->getOperand(1))->getZExtValue());
-}
-
-void MetadataStreamerYamlV2::emitKernelAttrs(const Function &Func) {
-  auto &Attrs = HSAMetadata.mKernels.back().mAttrs;
-
-  if (auto Node = Func.getMetadata("reqd_work_group_size"))
-    Attrs.mReqdWorkGroupSize = getWorkGroupDimensions(Node);
-  if (auto Node = Func.getMetadata("work_group_size_hint"))
-    Attrs.mWorkGroupSizeHint = getWorkGroupDimensions(Node);
-  if (auto Node = Func.getMetadata("vec_type_hint")) {
-    Attrs.mVecTypeHint = getTypeName(
-        cast<ValueAsMetadata>(Node->getOperand(0))->getType(),
-        mdconst::extract<ConstantInt>(Node->getOperand(1))->getZExtValue());
-  }
-  if (Func.hasFnAttribute("runtime-handle")) {
-    Attrs.mRuntimeHandle =
-        Func.getFnAttribute("runtime-handle").getValueAsString().str();
-  }
-}
-
-void MetadataStreamerYamlV2::emitKernelArgs(const Function &Func,
-                                            const GCNSubtarget &ST) {
-  for (auto &Arg : Func.args())
-    emitKernelArg(Arg);
-
-  emitHiddenKernelArgs(Func, ST);
-}
-
-void MetadataStreamerYamlV2::emitKernelArg(const Argument &Arg) {
-  auto Func = Arg.getParent();
-  auto ArgNo = Arg.getArgNo();
-  const MDNode *Node;
-
-  StringRef Name;
-  Node = Func->getMetadata("kernel_arg_name");
-  if (Node && ArgNo < Node->getNumOperands())
-    Name = cast<MDString>(Node->getOperand(ArgNo))->getString();
-  else if (Arg.hasName())
-    Name = Arg.getName();
-
-  StringRef TypeName;
-  Node = Func->getMetadata("kernel_arg_type");
-  if (Node && ArgNo < Node->getNumOperands())
-    TypeName = cast<MDString>(Node->getOperand(ArgNo))->getString();
-
-  StringRef BaseTypeName;
-  Node = Func->getMetadata("kernel_arg_base_type");
-  if (Node && ArgNo < Node->getNumOperands())
-    BaseTypeName = cast<MDString>(Node->getOperand(ArgNo))->getString();
-
-  StringRef AccQual;
-  if (Arg.getType()->isPointerTy() && Arg.onlyReadsMemory() &&
-      Arg.hasNoAliasAttr()) {
-    AccQual = "read_only";
-  } else {
-    Node = Func->getMetadata("kernel_arg_access_qual");
-    if (Node && ArgNo < Node->getNumOperands())
-      AccQual = cast<MDString>(Node->getOperand(ArgNo))->getString();
-  }
-
-  StringRef TypeQual;
-  Node = Func->getMetadata("kernel_arg_type_qual");
-  if (Node && ArgNo < Node->getNumOperands())
-    TypeQual = cast<MDString>(Node->getOperand(ArgNo))->getString();
-
-  const DataLayout &DL = Func->getParent()->getDataLayout();
-
-  MaybeAlign PointeeAlign;
-  if (auto PtrTy = dyn_cast<PointerType>(Arg.getType())) {
-    if (PtrTy->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS) {
-      // FIXME: Should report this for all address spaces
-      PointeeAlign = Arg.getParamAlign().valueOrOne();
-    }
-  }
-
-  Type *ArgTy;
-  Align ArgAlign;
-  std::tie(ArgTy, ArgAlign) = getArgumentTypeAlign(Arg, DL);
-
-  emitKernelArg(DL, ArgTy, ArgAlign,
-                getValueKind(ArgTy, TypeQual, BaseTypeName), PointeeAlign, Name,
-                TypeName, BaseTypeName, AccQual, TypeQual);
-}
-
-void MetadataStreamerYamlV2::emitKernelArg(
-    const DataLayout &DL, Type *Ty, Align Alignment, ValueKind ValueKind,
-    MaybeAlign PointeeAlign, StringRef Name, StringRef TypeName,
-    StringRef BaseTypeName, StringRef AccQual, StringRef TypeQual) {
-  HSAMetadata.mKernels.back().mArgs.push_back(Kernel::Arg::Metadata());
-  auto &Arg = HSAMetadata.mKernels.back().mArgs.back();
-
-  Arg.mName = std::string(Name);
-  Arg.mTypeName = std::string(TypeName);
-  Arg.mSize = DL.getTypeAllocSize(Ty);
-  Arg.mAlign = Alignment.value();
-  Arg.mValueKind = ValueKind;
-  Arg.mPointeeAlign = PointeeAlign ? PointeeAlign->value() : 0;
-
-  if (auto PtrTy = dyn_cast<PointerType>(Ty))
-    Arg.mAddrSpaceQual = getAddressSpaceQualifier(PtrTy->getAddressSpace());
-
-  Arg.mAccQual = getAccessQualifier(AccQual);
-
-  // TODO: Emit Arg.mActualAccQual.
-
-  SmallVector<StringRef, 1> SplitTypeQuals;
-  TypeQual.split(SplitTypeQuals, " ", -1, false);
-  for (StringRef Key : SplitTypeQuals) {
-    auto P = StringSwitch<bool*>(Key)
-                 .Case("const",    &Arg.mIsConst)
-                 .Case("restrict", &Arg.mIsRestrict)
-                 .Case("volatile", &Arg.mIsVolatile)
-                 .Case("pipe",     &Arg.mIsPipe)
-                 .Default(nullptr);
-    if (P)
-      *P = true;
-  }
-}
-
-void MetadataStreamerYamlV2::emitHiddenKernelArgs(const Function &Func,
-                                                  const GCNSubtarget &ST) {
-  unsigned HiddenArgNumBytes = ST.getImplicitArgNumBytes(Func);
-  if (!HiddenArgNumBytes)
-    return;
-
-  auto &DL = Func.getParent()->getDataLayout();
-  auto Int64Ty = Type::getInt64Ty(Func.getContext());
-
-  if (HiddenArgNumBytes >= 8)
-    emitKernelArg(DL, Int64Ty, Align(8), ValueKind::HiddenGlobalOffsetX);
-  if (HiddenArgNumBytes >= 16)
-    emitKernelArg(DL, Int64Ty, Align(8), ValueKind::HiddenGlobalOffsetY);
-  if (HiddenArgNumBytes >= 24)
-    emitKernelArg(DL, Int64Ty, Align(8), ValueKind::HiddenGlobalOffsetZ);
-
-  auto Int8PtrTy = Type::getInt8PtrTy(Func.getContext(),
-                                      AMDGPUAS::GLOBAL_ADDRESS);
-
-  if (HiddenArgNumBytes >= 32) {
-    // We forbid the use of features requiring hostcall when compiling OpenCL
-    // before code object V5, which makes the mutual exclusion between the
-    // "printf buffer" and "hostcall buffer" here sound.
-    if (Func.getParent()->getNamedMetadata("llvm.printf.fmts"))
-      emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenPrintfBuffer);
-    else if (!Func.hasFnAttribute("amdgpu-no-hostcall-ptr"))
-      emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenHostcallBuffer);
-    else
-      emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenNone);
-  }
-
-  // Emit "default queue" and "completion action" arguments if enqueue kernel is
-  // used, otherwise emit dummy "none" arguments.
-  if (HiddenArgNumBytes >= 40) {
-    if (!Func.hasFnAttribute("amdgpu-no-default-queue")) {
-      emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenDefaultQueue);
-    } else {
-      emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenNone);
-    }
-  }
-
-  if (HiddenArgNumBytes >= 48) {
-    if (!Func.hasFnAttribute("amdgpu-no-completion-action") &&
-        // FIXME: Hack for runtime bug if we fail to optimize this out
-        Func.hasFnAttribute("calls-enqueue-kernel")) {
-      emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenCompletionAction);
-    } else {
-      emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenNone);
-    }
-  }
-
-  // Emit the pointer argument for multi-grid object.
-  if (HiddenArgNumBytes >= 56) {
-    if (!Func.hasFnAttribute("amdgpu-no-multigrid-sync-arg"))
-      emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenMultiGridSyncArg);
-    else
-      emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenNone);
-  }
-}
-
-bool MetadataStreamerYamlV2::emitTo(AMDGPUTargetStreamer &TargetStreamer) {
-  return TargetStreamer.EmitHSAMetadata(getHSAMetadata());
-}
-
-void MetadataStreamerYamlV2::begin(const Module &Mod,
-                                   const IsaInfo::AMDGPUTargetID &TargetID) {
-  emitVersion();
-  emitPrintf(Mod);
-}
-
-void MetadataStreamerYamlV2::end() {
-  std::string HSAMetadataString;
-  if (toString(HSAMetadata, HSAMetadataString))
-    return;
-
-  if (DumpHSAMetadata)
-    dump(HSAMetadataString);
-  if (VerifyHSAMetadata)
-    verify(HSAMetadataString);
-}
-
-void MetadataStreamerYamlV2::emitKernel(const MachineFunction &MF,
-                                        const SIProgramInfo &ProgramInfo) {
-  auto &Func = MF.getFunction();
-  if (Func.getCallingConv() != CallingConv::AMDGPU_KERNEL)
-    return;
-
-  auto CodeProps = getHSACodeProps(MF, ProgramInfo);
-  auto DebugProps = getHSADebugProps(MF, ProgramInfo);
-
-  HSAMetadata.mKernels.push_back(Kernel::Metadata());
-  auto &Kernel = HSAMetadata.mKernels.back();
-
-  const GCNSubtarget &ST = MF.getSubtarget<GCNSubtarget>();
-  Kernel.mName = std::string(Func.getName());
-  Kernel.mSymbolName = (Twine(Func.getName()) + Twine("@kd")).str();
-  emitKernelLanguage(Func);
-  emitKernelAttrs(Func);
-  emitKernelArgs(Func, ST);
-  HSAMetadata.mKernels.back().mCodeProps = CodeProps;
-  HSAMetadata.mKernels.back().mDebugProps = DebugProps;
-}
-
-//===----------------------------------------------------------------------===//
 // HSAMetadataStreamerV3
 //===----------------------------------------------------------------------===//
 
 void MetadataStreamerMsgPackV3::dump(StringRef HSAMetadataString) const {
   errs() << "AMDGPU HSA Metadata:\n" << HSAMetadataString << '\n';
 }
 
 void MetadataStreamerMsgPackV3::verify(StringRef HSAMetadataString) const {

 }
 
 void MetadataStreamerMsgPackV3::emitKernel(const MachineFunction &MF,
                                            const SIProgramInfo &ProgramInfo) {
   auto &Func = MF.getFunction();
   auto CodeObjectVersion = AMDGPU::getCodeObjectVersion(*Func.getParent());
   auto Kern = getHSAKernelProps(MF, ProgramInfo, CodeObjectVersion);
 
-  assert(Func.getCallingConv() == CallingConv::AMDGPU_KERNEL ||
-         Func.getCallingConv() == CallingConv::SPIR_KERNEL);
+  if (Func.getCallingConv() != CallingConv::AMDGPU_KERNEL &&
+      Func.getCallingConv() != CallingConv::SPIR_KERNEL)
+    return;
 
   auto Kernels =
       getRootMetadata("amdhsa.kernels").getArray(/*Convert=*/true);
 
   {
     Kern[".name"] = Kern.getDocument()->getNode(Func.getName());
     Kern[".symbol"] = Kern.getDocument()->getNode(
         (Twine(Func.getName()) + Twine(".kd")).str(), /*Copy=*/true);

llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp

for (const Argument &Arg : F.args()) {
     MaxAlign = std::max(MaxAlign, Alignment);
   }
 
   return ExplicitArgBytes;
 }
 
 unsigned AMDGPUSubtarget::getKernArgSegmentSize(const Function &F,
                                                 Align &MaxAlign) const {
+  if (F.getCallingConv() != CallingConv::AMDGPU_KERNEL &&
+      F.getCallingConv() != CallingConv::SPIR_KERNEL)
+    return 0;
+
   uint64_t ExplicitArgBytes = getExplicitKernArgSize(F, MaxAlign);
 
   unsigned ExplicitOffset = getExplicitKernelArgOffset(F);
 
   uint64_t TotalSize = ExplicitOffset + ExplicitArgBytes;
   unsigned ImplicitBytes = getImplicitArgNumBytes(F);
   if (ImplicitBytes != 0) {
     const Align Alignment = getAlignmentForImplicitArgPtr();

llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp

#define PRINT_FIELD(STREAM, DIRECTIVE, KERNEL_DESC, MEMBER_NAME, FIELD_NAME)   \
   if (!ReserveVCC)
     OS << "\t\t.amdhsa_reserve_vcc " << ReserveVCC << '\n';
   if (IVersion.Major >= 7 && !ReserveFlatScr && !hasArchitectedFlatScratch(STI))
     OS << "\t\t.amdhsa_reserve_flat_scratch " << ReserveFlatScr << '\n';
 
   switch (CodeObjectVersion) {
   default:
     break;
-  case AMDGPU::AMDHSA_COV2:
-    break;
   case AMDGPU::AMDHSA_COV3:
   case AMDGPU::AMDHSA_COV4:
   case AMDGPU::AMDHSA_COV5:
     if (getTargetID()->isXnackSupported())
       OS << "\t\t.amdhsa_reserve_xnack_mask " << getTargetID()->isXnackOnOrAny() << '\n';
     break;
   }
 
unsigned AMDGPUTargetELFStreamer::getEFlagsUnknownOS() {
   return getEFlagsV3();
 }
 
 unsigned AMDGPUTargetELFStreamer::getEFlagsAMDHSA() {
   assert(STI.getTargetTriple().getOS() == Triple::AMDHSA);
 
   if (std::optional<uint8_t> HsaAbiVer = getHsaAbiVersion(&STI)) {
     switch (*HsaAbiVer) {
-    case ELF::ELFABIVERSION_AMDGPU_HSA_V2:
     case ELF::ELFABIVERSION_AMDGPU_HSA_V3:
       return getEFlagsV3();
     case ELF::ELFABIVERSION_AMDGPU_HSA_V4:
     case ELF::ELFABIVERSION_AMDGPU_HSA_V5:
       return getEFlagsV4();
     }
   }
 

llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h

 struct kernel_descriptor_t;
 }
 
 namespace AMDGPU {
 
 struct IsaVersion;
 
 enum {
-  AMDHSA_COV2 = 2,
   AMDHSA_COV3 = 3,
   AMDHSA_COV4 = 4,
   AMDHSA_COV5 = 5
 };
 
 /// \returns HSA OS ABI Version identification.
 std::optional<uint8_t> getHsaAbiVersion(const MCSubtargetInfo *STI);
-/// \returns True if HSA OS ABI Version identification is 2,
-/// false otherwise.
-bool isHsaAbiVersion2(const MCSubtargetInfo *STI);
 /// \returns True if HSA OS ABI Version identification is 3,
 /// false otherwise.
 bool isHsaAbiVersion3(const MCSubtargetInfo *STI);
 /// \returns True if HSA OS ABI Version identification is 4,
 /// false otherwise.
 bool isHsaAbiVersion4(const MCSubtargetInfo *STI);
 /// \returns True if HSA OS ABI Version identification is 5,
 /// false otherwise.
 bool isHsaAbiVersion5(const MCSubtargetInfo *STI);
 /// \returns True if HSA OS ABI Version identification is 3 and above,
 /// false otherwise.

llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp

 
 } // end namespace anonymous
 
 namespace llvm {
 
 namespace AMDGPU {
 
 std::optional<uint8_t> getHsaAbiVersion(const MCSubtargetInfo *STI) {
   if (STI && STI->getTargetTriple().getOS() != Triple::AMDHSA)
     return std::nullopt;
 
   switch (AmdhsaCodeObjectVersion) {
-  case 2:
-    return ELF::ELFABIVERSION_AMDGPU_HSA_V2;
   case 3:
     return ELF::ELFABIVERSION_AMDGPU_HSA_V3;
   case 4:
     return ELF::ELFABIVERSION_AMDGPU_HSA_V4;
   case 5:
     return ELF::ELFABIVERSION_AMDGPU_HSA_V5;
   default:
     report_fatal_error(Twine("Unsupported AMDHSA Code Object Version ") +
                        Twine(AmdhsaCodeObjectVersion));
   }
 }
 
-bool isHsaAbiVersion2(const MCSubtargetInfo *STI) {
-  if (std::optional<uint8_t> HsaAbiVer = getHsaAbiVersion(STI))
-    return *HsaAbiVer == ELF::ELFABIVERSION_AMDGPU_HSA_V2;
-  return false;
-}
-
 bool isHsaAbiVersion3(const MCSubtargetInfo *STI) {
   if (std::optional<uint8_t> HsaAbiVer = getHsaAbiVersion(STI))
     return *HsaAbiVer == ELF::ELFABIVERSION_AMDGPU_HSA_V3;
   return false;
 }
 
 bool isHsaAbiVersion4(const MCSubtargetInfo *STI) {
   if (std::optional<uint8_t> HsaAbiVer = getHsaAbiVersion(STI))
unsigned getCodeObjectVersion(const Module &M) {
   }
 
   // Default code object version.
   return AMDHSA_COV4;
 }
 
 unsigned getMultigridSyncArgImplicitArgPosition(unsigned CodeObjectVersion) {
   switch (CodeObjectVersion) {
-  case AMDHSA_COV2:
   case AMDHSA_COV3:
   case AMDHSA_COV4:
     return 48;
   case AMDHSA_COV5:
   default:
     return AMDGPU::ImplicitArg::MULTIGRID_SYNC_ARG_OFFSET;
   }
 }
 
 
 // FIXME: All such magic numbers about the ABI should be in a
 // central TD file.
 unsigned getHostcallImplicitArgPosition(unsigned CodeObjectVersion) {
   switch (CodeObjectVersion) {
-  case AMDHSA_COV2:
   case AMDHSA_COV3:
   case AMDHSA_COV4:
     return 24;
   case AMDHSA_COV5:
   default:
     return AMDGPU::ImplicitArg::HOSTCALL_PTR_OFFSET;
   }
 }
 
 unsigned getDefaultQueueImplicitArgPosition(unsigned CodeObjectVersion) {
   switch (CodeObjectVersion) {
-  case AMDHSA_COV2:
   case AMDHSA_COV3:
   case AMDHSA_COV4:
     return 32;
   case AMDHSA_COV5:
   default:
     return AMDGPU::ImplicitArg::DEFAULT_QUEUE_OFFSET;
   }
 }
 
 unsigned getCompletionActionImplicitArgPosition(unsigned CodeObjectVersion) {
   switch (CodeObjectVersion) {
-  case AMDHSA_COV2:
   case AMDHSA_COV3:
   case AMDHSA_COV4:
     return 40;
   case AMDHSA_COV5:
   default:
     return AMDGPU::ImplicitArg::COMPLETION_ACTION_OFFSET;
   }
 }
std::string AMDGPUTargetID::toString() const {
   else
     Processor = (Twine("gfx") + Twine(Version.Major) + Twine(Version.Minor) +
                  Twine(Version.Stepping))
                     .str();
 
   std::string Features;
   if (STI.getTargetTriple().getOS() == Triple::AMDHSA) {
     switch (CodeObjectVersion) {
-    case AMDGPU::AMDHSA_COV2:
-      // Code object V2 only supported specific processors and had fixed
-      // settings for the XNACK.
-      if (Processor == "gfx600") {
-      } else if (Processor == "gfx601") {
-      } else if (Processor == "gfx602") {
-      } else if (Processor == "gfx700") {
-      } else if (Processor == "gfx701") {
-      } else if (Processor == "gfx702") {
-      } else if (Processor == "gfx703") {
-      } else if (Processor == "gfx704") {
-      } else if (Processor == "gfx705") {
-      } else if (Processor == "gfx801") {
-        if (!isXnackOnOrAny())
-          report_fatal_error(
-              "AMD GPU code object V2 does not support processor " +
-              Twine(Processor) + " without XNACK");
-      } else if (Processor == "gfx802") {
-      } else if (Processor == "gfx803") {
-      } else if (Processor == "gfx805") {
-      } else if (Processor == "gfx810") {
-        if (!isXnackOnOrAny())
-          report_fatal_error(
-              "AMD GPU code object V2 does not support processor " +
-              Twine(Processor) + " without XNACK");
-      } else if (Processor == "gfx900") {
-        if (isXnackOnOrAny())
-          Processor = "gfx901";
-      } else if (Processor == "gfx902") {
-        if (isXnackOnOrAny())
-          Processor = "gfx903";
-      } else if (Processor == "gfx904") {
-        if (isXnackOnOrAny())
-          Processor = "gfx905";
-      } else if (Processor == "gfx906") {
-        if (isXnackOnOrAny())
-          Processor = "gfx907";
-      } else if (Processor == "gfx90c") {
-        if (isXnackOnOrAny())
-          report_fatal_error(
-              "AMD GPU code object V2 does not support processor " +
-              Twine(Processor) + " with XNACK being ON or ANY");
-      } else {
-        report_fatal_error(
-            "AMD GPU code object V2 does not support processor " +
-            Twine(Processor));
-      }
-      break;
     case AMDGPU::AMDHSA_COV3:
       // xnack.
       if (isXnackOnOrAny())
         Features += "+xnack";
       // In code object v2 and v3, "sramecc" feature was spelled with a
       // hyphen ("sram-ecc").
       if (isSramEccOnOrAny())
         Features += "+sram-ecc";

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.dispatch.id.ll

 ; RUN: llc -global-isel -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 declare i64 @llvm.amdgcn.dispatch.id() #1
 
 ; GCN-LABEL: {{^}}dispatch_id:
-; GCN: .amd_kernel_code_t
-; GCN: enable_sgpr_dispatch_id = 1
-
 ; GCN-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], s6
 ; GCN-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], s7
 ; GCN: flat_store_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v[[[LO]]:[[HI]]]
+; GCN: .amdhsa_user_sgpr_dispatch_id 1
 define amdgpu_kernel void @dispatch_id(ptr addrspace(1) %out) #0 {
   %tmp0 = call i64 @llvm.amdgcn.dispatch.id()
   store i64 %tmp0, ptr addrspace(1) %out
   ret void
 }
 
 attributes #0 = { nounwind }
 attributes #1 = { nounwind readnone }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.dispatch.ptr.ll

 ; RUN: llc -global-isel -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 ; FIXME: Error on non-HSA target
 
 ; GCN-LABEL: {{^}}test:
-; GCN: enable_sgpr_dispatch_ptr = 1
 ; GCN: s_load_dword s{{[0-9]+}}, s[4:5], 0x0
+; GCN: .amdhsa_user_sgpr_dispatch_ptr 1
 define amdgpu_kernel void @test(ptr addrspace(1) %out) {
   %dispatch_ptr = call noalias ptr addrspace(4) @llvm.amdgcn.dispatch.ptr() #0
   %value = load i32, ptr addrspace(4) %dispatch_ptr
   store i32 %value, ptr addrspace(1) %out
   ret void
 }
 
 declare noalias ptr addrspace(4) @llvm.amdgcn.dispatch.ptr() #0
 
 attributes #0 = { readnone }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.kernarg.segment.ptr.ll

-; RUN: llc -global-isel -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V2,HSA,ALL %s
-; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=hawaii -mattr=+flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V2,OS-MESA3D,ALL %s
+; RUN: llc -global-isel -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V4,HSA,ALL %s
+; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=hawaii -mattr=+flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V4,OS-MESA3D,ALL %s
 ; RUN: llc -global-isel -mtriple=amdgcn-mesa-unknown -mcpu=hawaii -mattr=+flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=OS-UNKNOWN,ALL %s
 
 ; ALL-LABEL: {{^}}test:
-; CO-V2: enable_sgpr_kernarg_segment_ptr = 1
-; HSA: kernarg_segment_byte_size = 8
-; HSA: kernarg_segment_alignment = 4
-
-; CO-V2: s_load_dword s{{[0-9]+}}, s[4:5], 0xa
+; OS-MESA3D: enable_sgpr_kernarg_segment_ptr = 1
+; CO-V4: s_load_dword s{{[0-9]+}}, s[4:5], 0xa
 
 ; OS-UNKNOWN: s_load_dword s{{[0-9]+}}, s[0:1], 0xa
+
+; HSA: .amdhsa_kernarg_size 8
+; HSA: .amdhsa_user_sgpr_kernarg_segment_ptr 1
 define amdgpu_kernel void @test(ptr addrspace(1) %out) #1 {
   %kernarg.segment.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
   %gep = getelementptr i32, ptr addrspace(4) %kernarg.segment.ptr, i64 10
   %value = load i32, ptr addrspace(4) %gep
   store i32 %value, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_implicit:
-; HSA: kernarg_segment_byte_size = 8
 ; OS-MESA3D: kernarg_segment_byte_size = 24
-; CO-V2: kernarg_segment_alignment = 4
+; OS-MESA3D: kernarg_segment_alignment = 4
 
 ; 10 + 9 (36 prepended implicit bytes) + 2(out pointer) = 21 = 0x15
 
 ; OS-UNKNOWN: s_load_dword s{{[0-9]+}}, s{{\[[0-9]+:[0-9]+\]}}, 0x15
+
+; HSA:        .amdhsa_kernarg_size 8
 define amdgpu_kernel void @test_implicit(ptr addrspace(1) %out) #1 {
   %implicitarg.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %gep = getelementptr i32, ptr addrspace(4) %implicitarg.ptr, i64 10
   %value = load i32, ptr addrspace(4) %gep
   store i32 %value, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_implicit_alignment:
-; HSA: kernarg_segment_byte_size = 12
 ; OS-MESA3D: kernarg_segment_byte_size = 28
-; CO-V2: kernarg_segment_alignment = 4
-
+; OS-MESA3D: kernarg_segment_alignment = 4
 
 ; OS-UNKNOWN: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0xc
 ; HSA: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x4
 ; OS-MESA3D: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x3
 ; ALL: v_mov_b32_e32 [[V_VAL:v[0-9]+]], [[VAL]]
 ; ALL: flat_store_dword v[{{[0-9]+:[0-9]+}}], [[V_VAL]]
+
+; HSA:        .amdhsa_kernarg_size 12
 define amdgpu_kernel void @test_implicit_alignment(ptr addrspace(1) %out, <2 x i8> %in) #1 {
   %implicitarg.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %val = load i32, ptr addrspace(4) %implicitarg.ptr
   store i32 %val, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}opencl_test_implicit_alignment
-; HSA: kernarg_segment_byte_size = 64
 ; OS-MESA3D: kernarg_segment_byte_size = 28
-; CO-V2: kernarg_segment_alignment = 4
-
+; OS-MESA3D: kernarg_segment_alignment = 4
 
 ; OS-UNKNOWN: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0xc
 ; HSA: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x4
 ; OS-MESA3D: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x3
 ; ALL: v_mov_b32_e32 [[V_VAL:v[0-9]+]], [[VAL]]
 ; ALL: flat_store_dword v[{{[0-9]+:[0-9]+}}], [[V_VAL]]
+
+; HSA:        .amdhsa_kernarg_size 64
 define amdgpu_kernel void @opencl_test_implicit_alignment(ptr addrspace(1) %out, <2 x i8> %in) #2 {
   %implicitarg.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %val = load i32, ptr addrspace(4) %implicitarg.ptr
   store i32 %val, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_no_kernargs:
-; CO-V2: enable_sgpr_kernarg_segment_ptr = 0
-; CO-V2: kernarg_segment_byte_size = 0
-; CO-V2: kernarg_segment_alignment = 4
+; OS-MESA3D: enable_sgpr_kernarg_segment_ptr = 0
+; OS-MESA3D: kernarg_segment_byte_size = 0
+; OS-MESA3D: kernarg_segment_alignment = 4
 
 ; HSA: s_mov_b64 [[OFFSET_NULL:s\[[0-9]+:[0-9]+\]]], 40{{$}}
 ; HSA: s_load_dword s{{[0-9]+}}, [[OFFSET_NULL]]
+
+; HSA: .amdhsa_kernarg_size 0
+; HSA: .amdhsa_user_sgpr_kernarg_segment_ptr 0
 define amdgpu_kernel void @test_no_kernargs() #1 {
   %kernarg.segment.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
   %gep = getelementptr i32, ptr addrspace(4) %kernarg.segment.ptr, i64 10
   %value = load i32, ptr addrspace(4) %gep
   store volatile i32 %value, ptr addrspace(1) undef
   ret void
 }
 
 ; ALL-LABEL: {{^}}opencl_test_implicit_alignment_no_explicit_kernargs:
-; HSA: kernarg_segment_byte_size = 48
 ; OS-MESA3D: kernarg_segment_byte_size = 16
-; CO-V2: kernarg_segment_alignment = 4
+; OS-MESA3D: kernarg_segment_alignment = 4
+; HSA:        .amdhsa_kernarg_size 48
 define amdgpu_kernel void @opencl_test_implicit_alignment_no_explicit_kernargs() #2 {
   %implicitarg.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %val = load volatile i32, ptr addrspace(4) %implicitarg.ptr
   store volatile i32 %val, ptr addrspace(1) null
   ret void
 }
 
 ; ALL-LABEL: {{^}}opencl_test_implicit_alignment_no_explicit_kernargs_round_up:
-; HSA: kernarg_segment_byte_size = 40
 ; OS-MESA3D: kernarg_segment_byte_size = 16
-; CO-V2: kernarg_segment_alignment = 4
+; OS-MESA3D: kernarg_segment_alignment = 4
+; HSA:        .amdhsa_kernarg_size 40
 define amdgpu_kernel void @opencl_test_implicit_alignment_no_explicit_kernargs_round_up() #3 {
   %implicitarg.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %val = load volatile i32, ptr addrspace(4) %implicitarg.ptr
   store volatile i32 %val, ptr addrspace(1) null
   ret void
 }
 
 ; ALL-LABEL: {{^}}func_kernarg_segment_ptr:
 ; ALL: v_mov_b32_e32 v0, 0{{$}}
 ; ALL: v_mov_b32_e32 v1, 0{{$}}
 define ptr addrspace(4) @func_kernarg_segment_ptr() {
   %ptr = call ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
   ret ptr addrspace(4) %ptr
 }
 
 declare ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr() #0
 declare ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr() #0
 
 attributes #0 = { nounwind readnone }
 attributes #1 = { nounwind "amdgpu-implicitarg-num-bytes"="0" }
 attributes #2 = { nounwind "amdgpu-implicitarg-num-bytes"="48" }
 attributes #3 = { nounwind "amdgpu-implicitarg-num-bytes"="38" }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.queue.ptr.ll

 ; RUN: llc -global-isel -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 ; FIXME: Error on non-hsa target
 
 ; GCN-LABEL: {{^}}test:
-; GCN: enable_sgpr_queue_ptr = 1
 ; GCN: s_load_dword s{{[0-9]+}}, s[4:5], 0x0
+; GCN: .amdhsa_user_sgpr_queue_ptr 1
 define amdgpu_kernel void @test(ptr addrspace(1) %out) {
   %queue_ptr = call noalias ptr addrspace(4) @llvm.amdgcn.queue.ptr() #0
   %value = load i32, ptr addrspace(4) %queue_ptr
   store i32 %value, ptr addrspace(1) %out
   ret void
 }
 
 declare noalias ptr addrspace(4) @llvm.amdgcn.queue.ptr() #0
 
 attributes #0 = { nounwind readnone }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.workgroup.id.ll

-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -global-isel -mtriple=amdgcn-unknown-amdhsa -mcpu=kaveri -verify-machineinstrs | FileCheck --check-prefixes=ALL,CO-V2  %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -global-isel -mtriple=amdgcn-unknown-amdhsa -mcpu=carrizo -verify-machineinstrs | FileCheck --check-prefixes=ALL,CO-V2  %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -global-isel -mtriple=amdgcn-- -mcpu=hawaii -verify-machineinstrs | FileCheck --check-prefixes=ALL,UNKNOWN-OS %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -global-isel -mtriple=amdgcn-- -mcpu=tonga -verify-machineinstrs | FileCheck --check-prefixes=ALL,UNKNOWN-OS %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -global-isel -mtriple=amdgcn-unknown-mesa3d -mcpu=hawaii -verify-machineinstrs | FileCheck -check-prefixes=ALL,CO-V2 %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -global-isel -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefixes=ALL,CO-V2 %s
+; RUN: llc -global-isel -mtriple=amdgcn-- -mcpu=hawaii -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,UNKNOWN-OS %s
+; RUN: llc -global-isel -mtriple=amdgcn-- -mcpu=tonga -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,UNKNOWN-OS %s
+; RUN: llc -global-isel -mtriple=amdgcn-unknown-mesa3d -mcpu=hawaii -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,MESA3D %s
+; RUN: llc -global-isel -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,MESA3D %s
 
 declare i32 @llvm.amdgcn.workgroup.id.x() #0
 declare i32 @llvm.amdgcn.workgroup.id.y() #0
 declare i32 @llvm.amdgcn.workgroup.id.z() #0
 
 ; ALL-LABEL: {{^}}test_workgroup_id_x:
 
-; CO-V2: .amd_kernel_code_t
-; CO-V2: user_sgpr_count = 6
-; CO-V2: enable_sgpr_workgroup_id_x = 1
-; CO-V2: enable_sgpr_workgroup_id_y = 0
-; CO-V2: enable_sgpr_workgroup_id_z = 0
-; CO-V2: enable_sgpr_workgroup_info = 0
-; CO-V2: enable_vgpr_workitem_id = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_x = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_y = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_z = 0
-; CO-V2: .end_amd_kernel_code_t
+; MESA3D: .amd_kernel_code_t
+; MESA3D: user_sgpr_count = 6
+; MESA3D: enable_sgpr_workgroup_id_x = 1
+; MESA3D: enable_sgpr_workgroup_id_y = 0
+; MESA3D: enable_sgpr_workgroup_id_z = 0
+; MESA3D: enable_sgpr_workgroup_info = 0
+; MESA3D: enable_vgpr_workitem_id = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_x = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_y = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_z = 0
+; MESA3D: .end_amd_kernel_code_t
 
 ; UNKNOWN-OS: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s2{{$}}
-; CO-V2: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s6{{$}}
+; MESA3D: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s6{{$}}
 
 ; ALL: {{buffer|flat}}_store_dword {{.*}}[[VCOPY]]
 
-; CO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 6
-; ALL-NOCO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 2
+; MESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 6
+; ALL-NOMESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 2
 ; ALL: COMPUTE_PGM_RSRC2:TGID_X_EN: 1
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Y_EN: 0
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Z_EN: 0
 ; ALL: COMPUTE_PGM_RSRC2:TIDIG_COMP_CNT: 0
 define amdgpu_kernel void @test_workgroup_id_x(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workgroup.id.x()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_workgroup_id_y:
-; CO-V2: user_sgpr_count = 6
-; CO-V2: enable_sgpr_workgroup_id_x = 1
-; CO-V2: enable_sgpr_workgroup_id_y = 1
-; CO-V2: enable_sgpr_workgroup_id_z = 0
-; CO-V2: enable_sgpr_workgroup_info = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_x = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_y = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_z = 0
+; MESA3D: user_sgpr_count = 6
+; MESA3D: enable_sgpr_workgroup_id_x = 1
+; MESA3D: enable_sgpr_workgroup_id_y = 1
+; MESA3D: enable_sgpr_workgroup_id_z = 0
+; MESA3D: enable_sgpr_workgroup_info = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_x = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_y = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_z = 0
 
 ; UNKNOWN-OS: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s3{{$}}
 ; HSA: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s7{{$}}
 
 ; ALL: {{buffer|flat}}_store_dword {{.*}}[[VCOPY]]
 
-; CO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 6
-; ALL-NOCO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 2
+; MESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 6
+; ALL-NOMESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 2
 ; ALL: COMPUTE_PGM_RSRC2:TGID_X_EN: 1
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Y_EN: 1
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Z_EN: 0
 ; ALL: COMPUTE_PGM_RSRC2:TIDIG_COMP_CNT: 0
 define amdgpu_kernel void @test_workgroup_id_y(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workgroup.id.y()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_workgroup_id_z:
-; CO-V2: user_sgpr_count = 6
-; CO-V2: enable_sgpr_workgroup_id_x = 1
-; CO-V2: enable_sgpr_workgroup_id_y = 0
-; CO-V2: enable_sgpr_workgroup_id_z = 1
-; CO-V2: enable_sgpr_workgroup_info = 0
-; CO-V2: enable_vgpr_workitem_id = 0
-; CO-V2: enable_sgpr_private_segment_buffer = 1
-; CO-V2: enable_sgpr_dispatch_ptr = 0
-; CO-V2: enable_sgpr_queue_ptr = 0
-; CO-V2: enable_sgpr_kernarg_segment_ptr = 1
-; CO-V2: enable_sgpr_dispatch_id = 0
-; CO-V2: enable_sgpr_flat_scratch_init = 0
-; CO-V2: enable_sgpr_private_segment_size = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_x = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_y = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_z = 0
+; MESA3D: user_sgpr_count = 6
+; MESA3D: enable_sgpr_workgroup_id_x = 1
+; MESA3D: enable_sgpr_workgroup_id_y = 0
+; MESA3D: enable_sgpr_workgroup_id_z = 1
+; MESA3D: enable_sgpr_workgroup_info = 0
+; MESA3D: enable_vgpr_workitem_id = 0
+; MESA3D: enable_sgpr_private_segment_buffer = 1
+; MESA3D: enable_sgpr_dispatch_ptr = 0
+; MESA3D: enable_sgpr_queue_ptr = 0
+; MESA3D: enable_sgpr_kernarg_segment_ptr = 1
+; MESA3D: enable_sgpr_dispatch_id = 0
+; MESA3D: enable_sgpr_flat_scratch_init = 0
+; MESA3D: enable_sgpr_private_segment_size = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_x = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_y = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_z = 0
 
 ; UNKNOWN-OS: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s3{{$}}
 ; HSA: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s7{{$}}
 
 ; ALL: {{buffer|flat}}_store_dword {{.*}}[[VCOPY]]
 
-; CO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 6
-; ALL-NOCO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 2
+; MESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 6
+; ALL-NOMESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 2
 ; ALL: COMPUTE_PGM_RSRC2:TGID_X_EN: 1
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Y_EN: 0
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Z_EN: 1
 ; ALL: COMPUTE_PGM_RSRC2:TIDIG_COMP_CNT: 0
 define amdgpu_kernel void @test_workgroup_id_z(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workgroup.id.z()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 attributes #0 = { nounwind readnone }
 attributes #1 = { nounwind }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 CODE_OBJECT_VERSION}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.workitem.id.ll

-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -global-isel -mtriple=amdgcn-unknown-amdhsa -mcpu=kaveri -verify-machineinstrs | FileCheck --check-prefixes=ALL,HSA,CO-V2,UNPACKED  %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -global-isel -mtriple=amdgcn-unknown-amdhsa -mcpu=carrizo -verify-machineinstrs | FileCheck --check-prefixes=ALL,HSA,CO-V2,UNPACKED  %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -global-isel -mtriple=amdgcn-- -mcpu=hawaii -mattr=+flat-for-global -verify-machineinstrs | FileCheck --check-prefixes=ALL,MESA,UNPACKED %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -global-isel -mtriple=amdgcn-- -mcpu=tonga -mattr=+flat-for-global -verify-machineinstrs | FileCheck --check-prefixes=ALL,MESA,UNPACKED %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -global-isel -mtriple=amdgcn-unknown-mesa3d -mattr=+flat-for-global -mcpu=hawaii -verify-machineinstrs | FileCheck -check-prefixes=ALL,CO-V2,UNPACKED %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -global-isel -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefixes=ALL,CO-V2,UNPACKED %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -global-isel -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a -verify-machineinstrs | FileCheck -check-prefixes=ALL,PACKED-TID %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -global-isel -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1100 -verify-machineinstrs -amdgpu-enable-vopd=0 | FileCheck -check-prefixes=ALL,PACKED-TID %s
+; RUN: llc -global-isel -mtriple=amdgcn-- -mcpu=hawaii -mattr=+flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,MESA,UNPACKED %s
+; RUN: llc -global-isel -mtriple=amdgcn-- -mcpu=tonga -mattr=+flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,MESA,UNPACKED %s
+; RUN: llc -global-isel -mtriple=amdgcn-unknown-mesa3d -mattr=+flat-for-global -mcpu=hawaii -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,MESA3D,UNPACKED %s
+; RUN: llc -global-isel -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,MESA3D,UNPACKED %s
+; RUN: llc -global-isel -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,PACKED-TID %s
+; RUN: llc -global-isel -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1100 -verify-machineinstrs -amdgpu-enable-vopd=0 < %s | FileCheck -check-prefixes=ALL,PACKED-TID %s
 
 declare i32 @llvm.amdgcn.workitem.id.x() #0
 declare i32 @llvm.amdgcn.workitem.id.y() #0
 declare i32 @llvm.amdgcn.workitem.id.z() #0
 
 ; MESA: .section .AMDGPU.config
 ; MESA: .long 47180
 ; MESA-NEXT: .long 132{{$}}
 
 ; ALL-LABEL: {{^}}test_workitem_id_x:
-; CO-V2: enable_vgpr_workitem_id = 0
+; MESA3D: enable_vgpr_workitem_id = 0
 
 ; ALL-NOT: v0
 ; ALL: {{buffer|flat|global}}_store_{{dword|b32}} {{.*}}v0
 
 ; PACKED-TID: .amdhsa_system_vgpr_workitem_id 0
 define amdgpu_kernel void @test_workitem_id_x(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workitem.id.x()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 ; MESA: .section .AMDGPU.config
 ; MESA: .long 47180
 ; MESA-NEXT: .long 2180{{$}}
 
 ; ALL-LABEL: {{^}}test_workitem_id_y:
-; CO-V2: enable_vgpr_workitem_id = 1
-; CO-V2-NOT: v1
-; CO-V2: {{buffer|flat}}_store_dword {{.*}}v1
+; MESA3D: enable_vgpr_workitem_id = 1
+; MESA3D-NOT: v1
+; MESA3D: {{buffer|flat}}_store_dword {{.*}}v1
 
 ; PACKED-TID: v_bfe_u32 [[ID:v[0-9]+]], v0, 10, 10
 ; PACKED-TID: {{buffer|flat|global}}_store_{{dword|b32}} {{.*}}[[ID]]
 ; PACKED-TID: .amdhsa_system_vgpr_workitem_id 1
 define amdgpu_kernel void @test_workitem_id_y(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workitem.id.y()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 ; MESA: .section .AMDGPU.config
 ; MESA: .long 47180
 ; MESA-NEXT: .long 4228{{$}}
 
 ; ALL-LABEL: {{^}}test_workitem_id_z:
-; CO-V2: enable_vgpr_workitem_id = 2
-; CO-V2-NOT: v2
-; CO-V2: {{buffer|flat}}_store_dword {{.*}}v2
+; MESA3D: enable_vgpr_workitem_id = 2
+; MESA3D-NOT: v2
+; MESA3D: {{buffer|flat}}_store_dword {{.*}}v2
 
 ; PACKED-TID: v_bfe_u32 [[ID:v[0-9]+]], v0, 20, 10
 ; PACKED-TID: {{buffer|flat|global}}_store_{{dword|b32}} {{.*}}[[ID]]
 ; PACKED-TID: .amdhsa_system_vgpr_workitem_id 2
 define amdgpu_kernel void @test_workitem_id_z(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workitem.id.z()
   store i32 %id, ptr addrspace(1) %out
   ret void
define void @test_workitem_id_z_func(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workitem.id.z()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 ; FIXME: Should be able to avoid enabling in kernel inputs
 ; FIXME: Packed tid should avoid the and
 ; ALL-LABEL: {{^}}test_reqd_workgroup_size_x_only:
-; CO-V2: enable_vgpr_workitem_id = 0
+; MESA3D: enable_vgpr_workitem_id = 0
 
 ; ALL-DAG: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
 ; UNPACKED-DAG: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
 
 ; PACKED: v_and_b32_e32 [[MASKED:v[0-9]+]], 0x3ff, v0
 ; PACKED: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[MASKED]]
 
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 define amdgpu_kernel void @test_reqd_workgroup_size_x_only(ptr %out) !reqd_work_group_size !0 {
   %id.x = call i32 @llvm.amdgcn.workitem.id.x()
   %id.y = call i32 @llvm.amdgcn.workitem.id.y()
   %id.z = call i32 @llvm.amdgcn.workitem.id.z()
   store volatile i32 %id.x, ptr %out
   store volatile i32 %id.y, ptr %out
   store volatile i32 %id.z, ptr %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_reqd_workgroup_size_y_only:
-; CO-V2: enable_vgpr_workitem_id = 1
+; MESA3D: enable_vgpr_workitem_id = 1
 
 ; ALL: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 
 ; UNPACKED: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v1
 
 ; PACKED: v_bfe_u32 [[MASKED:v[0-9]+]], v0, 10, 10
 ; PACKED: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[MASKED]]
 
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 define amdgpu_kernel void @test_reqd_workgroup_size_y_only(ptr %out) !reqd_work_group_size !1 {
   %id.x = call i32 @llvm.amdgcn.workitem.id.x()
   %id.y = call i32 @llvm.amdgcn.workitem.id.y()
   %id.z = call i32 @llvm.amdgcn.workitem.id.z()
   store volatile i32 %id.x, ptr %out
   store volatile i32 %id.y, ptr %out
   store volatile i32 %id.z, ptr %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_reqd_workgroup_size_z_only:
-; CO-V2: enable_vgpr_workitem_id = 2
+; MESA3D: enable_vgpr_workitem_id = 2
 
 ; ALL: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 
 ; UNPACKED: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v2
 
 ; PACKED: v_bfe_u32 [[MASKED:v[0-9]+]], v0, 10, 20

 attributes #0 = { nounwind readnone }
 attributes #1 = { nounwind }
 
 !0 = !{i32 64, i32 1, i32 1}
 !1 = !{i32 1, i32 64, i32 1}
 !2 = !{i32 1, i32 1, i32 64}
 
 !llvm.module.flags = !{!99}
-!99 = !{i32 1, !"amdgpu_code_object_version", i32 CODE_OBJECT_VERSION}
+!99 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/addrspacecast.ll

 ; RUN: llc -march=amdgcn -mtriple=amdgcn-amd-amdhsa -mcpu=kaveri -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=HSA -check-prefix=CI %s
 ; RUN: llc -march=amdgcn -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-promote-alloca -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=HSA -check-prefix=GFX9 %s
 
 ; HSA-LABEL: {{^}}use_group_to_flat_addrspacecast:
-; HSA: enable_sgpr_private_segment_buffer = 1
-; HSA: enable_sgpr_dispatch_ptr = 0
-; CI: enable_sgpr_queue_ptr = 1
-; GFX9: enable_sgpr_queue_ptr = 0
 
 ; CI-DAG: s_load_dword [[PTR:s[0-9]+]], s[6:7], 0x0{{$}}
 ; CI-DAG: s_load_dword [[APERTURE:s[0-9]+]], s[4:5], 0x10{{$}}
 ; CI-DAG: s_cmp_lg_u32 [[PTR]], -1
 ; CI-DAG: s_cselect_b32 s[[HI:[0-9]+]], [[APERTURE]], 0
 ; CI-DAG: s_cselect_b32 s[[LO:[0-9]+]], [[PTR]], 0
 
 ; GFX9-DAG: s_mov_b64 s[{{[0-9]+}}:[[HIBASE:[0-9]+]]], src_shared_base
 
 ; HSA-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
 ; GFX9-DAG: s_load_dword [[PTR:s[0-9]+]], s[4:5], 0x0{{$}}
 
 ; GFX9: s_cmp_lg_u32 [[PTR]], -1
 ; GFX9-DAG: s_cselect_b32 s[[LO:[0-9]+]], s[[HIBASE]], 0
 ; GFX9-DAG: s_cselect_b32 s[[HI:[0-9]+]], [[PTR]], 0
 
 ; HSA: flat_store_dword v[[[LO]]:[[HI]]], [[K]]
 
+; HSA:  .amdhsa_user_sgpr_private_segment_buffer 1
+; HSA:  .amdhsa_user_sgpr_dispatch_ptr 0
+; CI:   .amdhsa_user_sgpr_queue_ptr 1
+; GFX9: .amdhsa_user_sgpr_queue_ptr 0
+
 ; At most 2 digits. Make sure src_shared_base is not counted as a high
 ; number SGPR.
 
 ; HSA: NumSgprs: {{[0-9]+}}
 define amdgpu_kernel void @use_group_to_flat_addrspacecast(ptr addrspace(3) %ptr) #0 {
   %stof = addrspacecast ptr addrspace(3) %ptr to ptr
   store volatile i32 7, ptr %stof
   ret void

 ; HSA: flat_store_dword v[[[LO]]:[[HI]]], [[K]]
 define void @use_group_to_flat_addrspacecast_func(ptr addrspace(3) %ptr) #0 {
   %stof = addrspacecast ptr addrspace(3) %ptr to ptr
   store volatile i32 7, ptr %stof
   ret void
 }
 
 ; HSA-LABEL: {{^}}use_private_to_flat_addrspacecast:
-; HSA: enable_sgpr_private_segment_buffer = 1
-; HSA: enable_sgpr_dispatch_ptr = 0
-; CI: enable_sgpr_queue_ptr = 1
-; GFX9: enable_sgpr_queue_ptr = 0
 
 ; CI-DAG: s_load_dword [[PTR:s[0-9]+]], s[6:7], 0x0{{$}}
 ; CI-DAG: s_load_dword [[APERTURE:s[0-9]+]], s[4:5], 0x11{{$}}
 
 ; CI-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
 ; CI-DAG: s_cmp_lg_u32 [[PTR]], -1
 ; CI-DAG: s_cselect_b32 s[[HI:[0-9]+]], [[APERTURE]], 0
 ; CI-DAG: s_cselect_b32 s[[LO:[0-9]+]], [[PTR]], 0
 
 ; GFX9-DAG: s_load_dword [[PTR:s[0-9]+]], s[4:5], 0x0{{$}}
 ; GFX9-DAG: s_mov_b64 s[{{[0-9]+}}:[[HIBASE:[0-9]+]]], src_private_base
 
 ; GFX9-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
 ; GFX9: s_cmp_lg_u32 [[PTR]], -1
 ; GFX9: s_cselect_b32 s[[LO:[0-9]+]], s[[HIBASE]], 0
 ; GFX9: s_cselect_b32 s[[HI:[0-9]+]], [[PTR]], 0
 
 ; HSA: flat_store_dword v[[[LO]]:[[HI]]], [[K]]
 
+; HSA:  .amdhsa_user_sgpr_private_segment_buffer 1
+; HSA:  .amdhsa_user_sgpr_dispatch_ptr 0
+; CI:   .amdhsa_user_sgpr_queue_ptr 1
+; GFX9: .amdhsa_user_sgpr_queue_ptr 0
+
 ; HSA: NumSgprs: {{[0-9]+}}
 define amdgpu_kernel void @use_private_to_flat_addrspacecast(ptr addrspace(5) %ptr) #0 {
   %stof = addrspacecast ptr addrspace(5) %ptr to ptr
   store volatile i32 7, ptr %stof
   ret void
 }
 
 ; no-op
 ; HSA-LABEL: {{^}}use_global_to_flat_addrspacecast:
-; HSA: enable_sgpr_queue_ptr = 0
 
 ; HSA: s_load_dwordx2 s[[[PTRLO:[0-9]+]]:[[PTRHI:[0-9]+]]]
 ; HSA-DAG: v_mov_b32_e32 v[[VPTRLO:[0-9]+]], s[[PTRLO]]
 ; HSA-DAG: v_mov_b32_e32 v[[VPTRHI:[0-9]+]], s[[PTRHI]]
 ; HSA-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 7
 ; HSA: flat_store_dword v[[[VPTRLO]]:[[VPTRHI]]], [[K]]
+
+; HSA:  .amdhsa_user_sgpr_queue_ptr 0
 define amdgpu_kernel void @use_global_to_flat_addrspacecast(ptr addrspace(1) %ptr) #0 {
   %stof = addrspacecast ptr addrspace(1) %ptr to ptr
   store volatile i32 7, ptr %stof
   ret void
 }
 
 ; no-op
 ; HSA-LABEl: {{^}}use_constant_to_flat_addrspacecast:

 ; GFX9: global_load_dword v{{[0-9]+}}, [[ZERO:v[0-9]+]], s[[[PTRLO]]:[[PTRHI]]]
 define amdgpu_kernel void @use_constant_to_global_addrspacecast(ptr addrspace(4) %ptr) #0 {
   %stof = addrspacecast ptr addrspace(4) %ptr to ptr addrspace(1)
   %ld = load volatile i32, ptr addrspace(1) %stof
   ret void
 }
 
 ; HSA-LABEL: {{^}}use_flat_to_group_addrspacecast:
-; HSA: enable_sgpr_private_segment_buffer = 1
-; HSA: enable_sgpr_dispatch_ptr = 0
-; HSA: enable_sgpr_queue_ptr = 0
 
 ; HSA: s_load_dwordx2 s[[[PTR_LO:[0-9]+]]:[[PTR_HI:[0-9]+]]]
 ; CI-DAG: v_cmp_ne_u64_e64 s[[[CMP_LO:[0-9]+]]:[[CMP_HI:[0-9]+]]], s[[[PTR_LO]]:[[PTR_HI]]], 0{{$}}
 ; CI-DAG: s_and_b64 s{{[[0-9]+:[0-9]+]}}, s[[[CMP_LO]]:[[CMP_HI]]], exec
 ; CI-DAG: s_cselect_b32 [[CASTPTR:s[0-9]+]], s[[PTR_LO]], -1
 ; CI-DAG: v_mov_b32_e32 [[VCASTPTR:v[0-9]+]], [[CASTPTR]]
 ; HSA-DAG: v_mov_b32_e32 v[[K:[0-9]+]], 0{{$}}
 ; GFX9-DAG: s_cmp_lg_u64 s[[[CMP_LO:[0-9]+]]:[[CMP_HI:[0-9]+]]], 0
 ; GFX9-DAG: s_cselect_b32 s[[PTR_LO]], s[[PTR_LO]], -1
 ; GFX9-DAG: v_mov_b32_e32 [[CASTPTR:v[0-9]+]], s[[PTR_LO]]
 ; CI-DAG: ds_write_b32 [[VCASTPTR]], v[[K]]
 ; GFX9-DAG: ds_write_b32 [[CASTPTR]], v[[K]]
+
+; HSA:  .amdhsa_user_sgpr_private_segment_buffer 1
+; HSA:  .amdhsa_user_sgpr_dispatch_ptr 0
+; HSA:  .amdhsa_user_sgpr_queue_ptr 0
 define amdgpu_kernel void @use_flat_to_group_addrspacecast(ptr %ptr) #0 {
   %ftos = addrspacecast ptr %ptr to ptr addrspace(3)
   store volatile i32 0, ptr addrspace(3) %ftos
   ret void
 }
 
 ; HSA-LABEL: {{^}}use_flat_to_private_addrspacecast:
-; HSA: enable_sgpr_private_segment_buffer = 1
-; HSA: enable_sgpr_dispatch_ptr = 0
-; HSA: enable_sgpr_queue_ptr = 0
 
 ; HSA: s_load_dwordx2 s[[[PTR_LO:[0-9]+]]:[[PTR_HI:[0-9]+]]]
 ; CI-DAG v_cmp_ne_u64_e64 vcc, s[[[PTR_LO]]:[[PTR_HI]]], 0{{$}}
 ; CI-DAG v_mov_b32_e32 v[[VPTR_LO:[0-9]+]], s[[PTR_LO]]
 ; CI-DAG v_cndmask_b32_e32 [[CASTPTR:v[0-9]+]], -1, v[[VPTR_LO]]
 ; CI-DAG: v_cmp_ne_u64_e64 s[[[CMP_LO:[0-9]+]]:[[CMP_HI:[0-9]+]]], s[[[PTR_LO]]:[[PTR_HI]]], 0{{$}}
 ; CI-DAG: s_and_b64 s{{[[0-9]+:[0-9]+]}}, s[[[CMP_LO]]:[[CMP_HI]]], exec
 ; CI-DAG: s_cselect_b32 [[CASTPTR:s[0-9]+]], s[[PTR_LO]], -1
 ; CI-DAG: v_mov_b32_e32 [[VCASTPTR:v[0-9]+]], [[CASTPTR]]
 ; HSA-DAG: v_mov_b32_e32 v[[K:[0-9]+]], 0{{$}}
 ; GFX9-DAG: s_cmp_lg_u64 s[[[CMP_LO:[0-9]+]]:[[CMP_HI:[0-9]+]]], 0
 ; GFX9-DAG: s_cselect_b32 s[[PTR_LO]], s[[PTR_LO]], -1
 ; GFX9-DAG: v_mov_b32_e32 [[CASTPTR:v[0-9]+]], s[[PTR_LO]]
 ; CI: buffer_store_dword v[[K]], [[VCASTPTR]], s{{\[[0-9]+:[0-9]+\]}}, 0 offen{{$}}
 ; GFX9: buffer_store_dword v[[K]], [[CASTPTR]], s{{\[[0-9]+:[0-9]+\]}}, 0 offen{{$}}
+
+; HSA:  .amdhsa_user_sgpr_private_segment_buffer 1
+; HSA:  .amdhsa_user_sgpr_dispatch_ptr 0
+; HSA:  .amdhsa_user_sgpr_queue_ptr 0
 define amdgpu_kernel void @use_flat_to_private_addrspacecast(ptr %ptr) #0 {
   %ftos = addrspacecast ptr %ptr to ptr addrspace(5)
   store volatile i32 0, ptr addrspace(5) %ftos
   ret void
 }
 
 ; HSA-LABEL: {{^}}use_flat_to_global_addrspacecast:
-; HSA: enable_sgpr_queue_ptr = 0
 
 ; HSA: s_load_dwordx2 s[[[PTRLO:[0-9]+]]:[[PTRHI:[0-9]+]]], s[4:5], 0x0
 ; CI-DAG: v_mov_b32_e32 v[[VPTRLO:[0-9]+]], s[[PTRLO]]
 ; CI-DAG: v_mov_b32_e32 v[[VPTRHI:[0-9]+]], s[[PTRHI]]
 ; CI-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 0
 ; CI: flat_store_dword v[[[VPTRLO]]:[[VPTRHI]]], [[K]]
 
 ; GFX9: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0
 ; GFX9: global_store_dword [[ZERO]], [[ZERO]], s[[[PTRLO]]:[[PTRHI]]{{\]$}}
+
+; HSA:  .amdhsa_user_sgpr_queue_ptr 0
 define amdgpu_kernel void @use_flat_to_global_addrspacecast(ptr %ptr) #0 {
   %ftos = addrspacecast ptr %ptr to ptr addrspace(1)
   store volatile i32 0, ptr addrspace(1) %ftos
   ret void
 }
 
 ; HSA-LABEL: {{^}}use_flat_to_constant_addrspacecast:
-; HSA: enable_sgpr_queue_ptr = 0
 
 ; HSA: s_load_dwordx2 s[[[PTRLO:[0-9]+]]:[[PTRHI:[0-9]+]]], s[4:5], 0x0
 ; HSA: s_load_dword s{{[0-9]+}}, s[[[PTRLO]]:[[PTRHI]]], 0x0
+
+; HSA:  .amdhsa_user_sgpr_queue_ptr 0
 define amdgpu_kernel void @use_flat_to_constant_addrspacecast(ptr %ptr) #0 {
   %ftos = addrspacecast ptr %ptr to ptr addrspace(4)
   load volatile i32, ptr addrspace(4) %ftos
   ret void
 }
 
 ; HSA-LABEL: {{^}}cast_0_group_to_flat_addrspacecast:
 ; CI: s_load_dword [[APERTURE:s[0-9]+]], s[4:5], 0x10

 define amdgpu_kernel void @cast_0_flat_to_private_addrspacecast() #0 {
   %cast = addrspacecast ptr null to ptr addrspace(5)
   store volatile i32 7, ptr addrspace(5) %cast
   ret void
 }
 
 
 ; HSA-LABEL: {{^}}cast_neg1_private_to_flat_addrspacecast:
-; CI: enable_sgpr_queue_ptr = 1
-; GFX9: enable_sgpr_queue_ptr = 0
 
 ; HSA: v_mov_b32_e32 v[[LO:[0-9]+]], 0{{$}}
 ; HSA-DAG: v_mov_b32_e32 v[[K:[0-9]+]], 7{{$}}
 ; HSA-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], 0{{$}}
 ; HSA: {{flat|global}}_store_dword v[[[LO]]:[[HI]]], v[[K]]
+
+; CI:  .amdhsa_user_sgpr_queue_ptr 1
+; GFX9:  .amdhsa_user_sgpr_queue_ptr 0
 define amdgpu_kernel void @cast_neg1_private_to_flat_addrspacecast() #0 {
   %cast = addrspacecast ptr addrspace(5) inttoptr (i32 -1 to ptr addrspace(5)) to ptr
   store volatile i32 7, ptr %cast
   ret void
 }
 
 ; HSA-LABEL: {{^}}cast_neg1_flat_to_private_addrspacecast:
 ; HSA-DAG: v_mov_b32_e32 [[PTR:v[0-9]+]], -1{{$}}

 declare i32 @llvm.amdgcn.workitem.id.x() #2
 
 attributes #0 = { nounwind }
 attributes #1 = { nounwind convergent }
 attributes #2 = { nounwind readnone }
 attributes #3 = { nounwind "amdgpu-32bit-address-high-bits"="0xffff8000" }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll

-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -show-mc-encoding -mattr=+promote-alloca -disable-promote-alloca-to-vector -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -march=amdgcn | FileCheck -enable-var-scope -check-prefix=SI-PROMOTE -check-prefix=SI -check-prefix=FUNC %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -show-mc-encoding -mattr=+promote-alloca -disable-promote-alloca-to-vector -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-unaligned-access-mode | FileCheck -enable-var-scope -check-prefix=SI-PROMOTE -check-prefix=SI -check-prefix=FUNC -check-prefix=HSA-PROMOTE %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -show-mc-encoding -mattr=-promote-alloca -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -march=amdgcn | FileCheck %s -check-prefix=SI-ALLOCA -check-prefix=SI -check-prefix=FUNC
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -show-mc-encoding -mattr=-promote-alloca -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -mtriple=amdgcn-amdhsa -mcpu=kaveri -mattr=-unaligned-access-mode | FileCheck -enable-var-scope -check-prefix=SI-ALLOCA -check-prefix=SI -check-prefix=FUNC -check-prefix=HSA-ALLOCA %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -show-mc-encoding -mattr=+promote-alloca -disable-promote-alloca-to-vector -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -mtriple=amdgcn-amdhsa -march=amdgcn -mcpu=tonga -mattr=-unaligned-access-mode | FileCheck -enable-var-scope -check-prefix=SI-PROMOTE -check-prefix=SI -check-prefix=FUNC %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -show-mc-encoding -mattr=+promote-alloca -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -mtriple=amdgcn-amdhsa -march=amdgcn -mcpu=tonga -mattr=-unaligned-access-mode | FileCheck -enable-var-scope -check-prefix=SI-PROMOTE-VECT -check-prefix=SI -check-prefix=FUNC %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -show-mc-encoding -mattr=-promote-alloca -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -mtriple=amdgcn-amdhsa -march=amdgcn -mcpu=tonga -mattr=-unaligned-access-mode | FileCheck -enable-var-scope -check-prefix=SI-ALLOCA -check-prefix=SI -check-prefix=FUNC %s
+; RUN: llc < %s -show-mc-encoding -mattr=+promote-alloca -disable-promote-alloca-to-vector -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -march=amdgcn | FileCheck -enable-var-scope -check-prefix=SI-PROMOTE -check-prefix=SI -check-prefix=FUNC %s
+; RUN: llc < %s -show-mc-encoding -mattr=+promote-alloca -disable-promote-alloca-to-vector -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-unaligned-access-mode | FileCheck -enable-var-scope -check-prefix=SI-PROMOTE -check-prefix=SI -check-prefix=FUNC -check-prefix=HSA-PROMOTE %s
+; RUN: llc < %s -show-mc-encoding -mattr=-promote-alloca -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -march=amdgcn | FileCheck %s -check-prefix=SI-ALLOCA -check-prefix=SI -check-prefix=FUNC
+; RUN: llc < %s -show-mc-encoding -mattr=-promote-alloca -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -mtriple=amdgcn-amdhsa -mcpu=kaveri -mattr=-unaligned-access-mode | FileCheck -enable-var-scope -check-prefix=SI-ALLOCA -check-prefix=SI -check-prefix=FUNC -check-prefix=HSA-ALLOCA %s
+; RUN: llc < %s -show-mc-encoding -mattr=+promote-alloca -disable-promote-alloca-to-vector -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -mtriple=amdgcn-amdhsa -march=amdgcn -mcpu=tonga -mattr=-unaligned-access-mode | FileCheck -enable-var-scope -check-prefix=SI-PROMOTE -check-prefix=SI -check-prefix=FUNC %s
+; RUN: llc < %s -show-mc-encoding -mattr=+promote-alloca -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -mtriple=amdgcn-amdhsa -march=amdgcn -mcpu=tonga -mattr=-unaligned-access-mode | FileCheck -enable-var-scope -check-prefix=SI-PROMOTE-VECT -check-prefix=SI -check-prefix=FUNC %s
+; RUN: llc < %s -show-mc-encoding -mattr=-promote-alloca -amdgpu-load-store-vectorizer=0 -enable-amdgpu-aa=0 -verify-machineinstrs -mtriple=amdgcn-amdhsa -march=amdgcn -mcpu=tonga -mattr=-unaligned-access-mode | FileCheck -enable-var-scope -check-prefix=SI-ALLOCA -check-prefix=SI -check-prefix=FUNC %s
 
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | opt -S -mtriple=amdgcn-unknown-amdhsa -data-layout=A5 -mcpu=kaveri -passes=amdgpu-promote-alloca -disable-promote-alloca-to-vector | FileCheck -enable-var-scope -check-prefix=HSAOPT -check-prefix=OPT %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | opt -S -mtriple=amdgcn-unknown-unknown -data-layout=A5 -mcpu=kaveri -passes=amdgpu-promote-alloca -disable-promote-alloca-to-vector | FileCheck -enable-var-scope -check-prefix=NOHSAOPT -check-prefix=OPT %s
+; RUN: opt < %s -S -mtriple=amdgcn-unknown-amdhsa -data-layout=A5 -mcpu=kaveri -passes=amdgpu-promote-alloca -disable-promote-alloca-to-vector | FileCheck -enable-var-scope -check-prefix=HSAOPT -check-prefix=OPT %s
+; RUN: opt < %s -S -mtriple=amdgcn-unknown-unknown -data-layout=A5 -mcpu=kaveri -passes=amdgpu-promote-alloca -disable-promote-alloca-to-vector | FileCheck -enable-var-scope -check-prefix=NOHSAOPT -check-prefix=OPT %s
 
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=r600 -mcpu=cypress -disable-promote-alloca-to-vector | FileCheck %s -check-prefix=R600 -check-prefix=FUNC
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=r600 -mcpu=cypress | FileCheck %s -check-prefix=R600-VECT -check-prefix=FUNC
+; RUN: llc < %s -march=r600 -mcpu=cypress -disable-promote-alloca-to-vector | FileCheck %s -check-prefix=R600 -check-prefix=FUNC
+; RUN: llc < %s -march=r600 -mcpu=cypress | FileCheck %s -check-prefix=R600-VECT -check-prefix=FUNC
 
 ; HSAOPT: @mova_same_clause.stack = internal unnamed_addr addrspace(3) global [256 x [5 x i32]] poison, align 4
 ; HSAOPT: @high_alignment.stack = internal unnamed_addr addrspace(3) global [256 x [8 x i32]] poison, align 16
 
 
 ; FUNC-LABEL: {{^}}mova_same_clause:
 ; OPT-LABEL: @mova_same_clause(
 
 ; R600: LDS_WRITE
 ; R600: LDS_WRITE
 ; R600: LDS_READ
 ; R600: LDS_READ
 
-; HSA-PROMOTE: .amd_kernel_code_t
-; HSA-PROMOTE: workgroup_group_segment_byte_size = 5120
-; HSA-PROMOTE: .end_amd_kernel_code_t
+; HSA-PROMOTE: .amdhsa_group_segment_fixed_size 5120
 
 ; HSA-PROMOTE: s_load_dwordx2 s[{{[0-9:]+}}], s[4:5], 0x1
 
 ; SI-PROMOTE: ds_write_b32
 ; SI-PROMOTE: ds_write_b32
 ; SI-PROMOTE: ds_read_b32
 ; SI-PROMOTE: ds_read_b32
 
-; HSA-ALLOCA: .amd_kernel_code_t
 ; FIXME: Creating the emergency stack slots causes us to over-estimate scratch
 ; by 4 bytes.
-; HSA-ALLOCA: workitem_private_segment_byte_size = 24
-; HSA-ALLOCA: .end_amd_kernel_code_t
+; HSA-ALLOCA: .amdhsa_private_segment_fixed_size 24
 
-; HSA-ALLOCA: s_mov_b32 flat_scratch_lo, s7
 ; HSA-ALLOCA: s_add_i32 s6, s6, s9
+; HSA-ALLOCA: s_mov_b32 flat_scratch_lo, s7
 ; HSA-ALLOCA: s_lshr_b32 flat_scratch_hi, s6, 8
 
 ; SI-ALLOCA: buffer_store_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 offen ; encoding: [0x00,0x10,0x70,0xe0
 ; SI-ALLOCA: buffer_store_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 offen ; encoding: [0x00,0x10,0x70,0xe0
 
 
 ; HSAOPT: [[DISPATCH_PTR:%[0-9]+]] = call noalias nonnull dereferenceable(64) ptr addrspace(4) @llvm.amdgcn.dispatch.ptr()
 ; HSAOPT: [[GEP0:%[0-9]+]] = getelementptr inbounds i32, ptr addrspace(4) [[DISPATCH_PTR]], i64 1
entry:
   store [1 x i32] %load, ptr addrspace(1) %out
   ret void
 }
 
 attributes #0 = { nounwind "amdgpu-waves-per-eu"="1,2" "amdgpu-flat-work-group-size"="1,256" }
 attributes #1 = { nounwind "amdgpu-flat-work-group-size"="1,256" }
 
 !llvm.module.flags = !{!99}
-!99 = !{i32 1, !"amdgpu_code_object_version", i32 CODE_OBJECT_VERSION}
+!99 = !{i32 1, !"amdgpu_code_object_version", i32 400}
 
 ; HSAOPT: !1 = !{}
 ; HSAOPT: !2 = !{i32 0, i32 257}
 ; HSAOPT: !3 = !{i32 0, i32 256}
 
 ; NOHSAOPT: !1 = !{i32 0, i32 257}
 ; NOHSAOPT: !2 = !{i32 0, i32 256}

llvm/test/CodeGen/AMDGPU/attr-amdgpu-flat-work-group-size.ll

define amdgpu_kernel void @min_1024_max_1024() #3 {
   store volatile float %val39, ptr addrspace(1) @var
   store volatile float %val40, ptr addrspace(1) @var
 
   ret void
 }
 attributes #3 = {"amdgpu-flat-work-group-size"="1024,1024"}
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}
 
-; HSAMD: NT_AMD_HSA_METADATA (AMD HSA Metadata)
-; HSAMD: Version: [ 1, 0 ]
-; HSAMD: Kernels:
-; HSAMD: - Name:                 min_64_max_64
-; HSAMD:   MaxFlatWorkGroupSize: 64
-; HSAMD: - Name:                 min_64_max_128
-; HSAMD:   MaxFlatWorkGroupSize: 128
-; HSAMD: - Name:                 min_128_max_128
-; HSAMD:   MaxFlatWorkGroupSize: 128
-; HSAMD: - Name:                 min_1024_max_1024
-; HSAMD:   MaxFlatWorkGroupSize: 1024
+; HSAMD: amdhsa.kernels
+; HSAMD:  .max_flat_workgroup_size: 64
+; HSAMD:  .name: min_64_max_64
+; HSAMD:  .max_flat_workgroup_size: 128
+; HSAMD:  .name: min_64_max_128
+; HSAMD:  .max_flat_workgroup_size: 128
+; HSAMD:  .name: min_128_max_128
+; HSAMD:  .max_flat_workgroup_size: 1024
+; HSAMD:  .name: min_1024_max_1024

llvm/test/CodeGen/AMDGPU/call-graph-register-usage.ll

-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn-amd-amdhsa -enable-ipra=0 -verify-machineinstrs | FileCheck -check-prefixes=GCN,CI %s
+; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-amd-amdhsa -enable-ipra=0 -verify-machineinstrs | FileCheck -check-prefixes=GCN,CI %s
 ; RUN: sed 's/CODE_OBJECT_VERSION/500/g' %s | llc -mtriple=amdgcn-amd-amdhsa -enable-ipra=0 -verify-machineinstrs | FileCheck -check-prefixes=GCN-V5 %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -enable-ipra=0 -verify-machineinstrs | FileCheck -check-prefixes=GCN,VI,VI-NOBUG %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=iceland -enable-ipra=0 -verify-machineinstrs | FileCheck -check-prefixes=GCN,VI,VI-BUG %s
+; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -enable-ipra=0 -verify-machineinstrs | FileCheck -check-prefixes=GCN,VI,VI-NOBUG %s
+; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=iceland -enable-ipra=0 -verify-machineinstrs | FileCheck -check-prefixes=GCN,VI,VI-BUG %s
 
 ; Make sure to run a GPU with the SGPR allocation bug.
 
 ; GCN-LABEL: {{^}}use_vcc:
 ; GCN: ; NumSgprs: 34
 ; GCN: ; NumVgprs: 0
 define void @use_vcc() #1 {
   call void asm sideeffect "", "~{vcc}" () #0

 ; GCN: ; NumSgprs: 36
 ; GCN: ; NumVgprs: 42
 define void @indirect_use_vcc() #1 {
   call void @use_vcc()
   ret void
 }
 
 ; GCN-LABEL: {{^}}indirect_2level_use_vcc_kernel:
-; GCN: is_dynamic_callstack = 0
 ; CI: ; NumSgprs: 38
 ; VI-NOBUG: ; NumSgprs: 40
 ; VI-BUG: ; NumSgprs: 96
 ; GCN: ; NumVgprs: 42
 define amdgpu_kernel void @indirect_2level_use_vcc_kernel(ptr addrspace(1) %out) #0 {
   call void @indirect_use_vcc()
   ret void
 }

 ; VI: ; NumSgprs: 40
 ; GCN: ; NumVgprs: 42
 define void @indirect_use_flat_scratch() #1 {
   call void @use_flat_scratch()
   ret void
 }
 
 ; GCN-LABEL: {{^}}indirect_2level_use_flat_scratch_kernel:
-; GCN: is_dynamic_callstack = 0
 ; CI: ; NumSgprs: 38
 ; VI-NOBUG: ; NumSgprs: 40
 ; VI-BUG: ; NumSgprs: 96
 ; GCN: ; NumVgprs: 42
 define amdgpu_kernel void @indirect_2level_use_flat_scratch_kernel(ptr addrspace(1) %out) #0 {
   call void @indirect_use_flat_scratch()
   ret void
 }

 ; GCN-LABEL: {{^}}indirect_use_10_vgpr:
 ; GCN: ; NumVgprs: 42
 define void @indirect_use_10_vgpr() #0 {
   call void @use_10_vgpr()
   ret void
 }
 
 ; GCN-LABEL: {{^}}indirect_2_level_use_10_vgpr:
-; GCN: is_dynamic_callstack = 0
 ; GCN: ; NumVgprs: 42
 define amdgpu_kernel void @indirect_2_level_use_10_vgpr() #0 {
   call void @indirect_use_10_vgpr()
   ret void
 }
 
 ; GCN-LABEL: {{^}}use_50_vgpr:
 ; GCN: ; NumVgprs: 50

 ; GCN-LABEL: {{^}}indirect_use_80_sgpr:
 ; GCN: ; NumSgprs: 82
 define void @indirect_use_80_sgpr() #1 {
   call void @use_80_sgpr()
   ret void
 }
 
 ; GCN-LABEL: {{^}}indirect_2_level_use_80_sgpr:
-; GCN: is_dynamic_callstack = 0
 ; CI: ; NumSgprs: 84
 ; VI-NOBUG: ; NumSgprs: 86
 ; VI-BUG: ; NumSgprs: 96
 define amdgpu_kernel void @indirect_2_level_use_80_sgpr() #0 {
   call void @indirect_use_80_sgpr()
   ret void
 }
 

 define void @indirect_use_stack() #1 {
   %alloca = alloca [16 x i32], align 4, addrspace(5)
   call void asm sideeffect "; use $0", "v"(ptr addrspace(5) %alloca) #0
   call void @use_stack0()
   ret void
 }
 
 ; GCN-LABEL: {{^}}indirect_2_level_use_stack:
-; GCN: is_dynamic_callstack = 0
 ; GCN: ScratchSize: 2132
 define amdgpu_kernel void @indirect_2_level_use_stack() #0 {
   call void @indirect_use_stack()
   ret void
 }
 
 
 ; Should be maximum of callee usage
 ; GCN-LABEL: {{^}}multi_call_use_use_stack:
-; GCN: is_dynamic_callstack = 0
 ; GCN: ScratchSize: 2052
 define amdgpu_kernel void @multi_call_use_use_stack() #0 {
   call void @use_stack0()
   call void @use_stack1()
   ret void
 }
 
 
 declare void @external() #0
 
 ; GCN-LABEL: {{^}}usage_external:
-; GCN: is_dynamic_callstack = 1
 ; NumSgprs: 48
 ; NumVgprs: 24
 ; GCN: ScratchSize: 16384
 ;
 ; GCN-V5-LABEL: {{^}}usage_external:
 ; GCN-V5: ScratchSize: 0
 define amdgpu_kernel void @usage_external() #0 {
   call void @external()
   ret void
 }
 
 declare void @external_recurse() #2
 
 ; GCN-LABEL: {{^}}usage_external_recurse:
-; GCN: is_dynamic_callstack = 1
 ; NumSgprs: 48
 ; NumVgprs: 24
 ; GCN: ScratchSize: 16384
 ;
 ; GCN-V5-LABEL: {{^}}usage_external_recurse:
 ; GCN-V5: ScratchSize: 0
 define amdgpu_kernel void @usage_external_recurse() #0 {
   call void @external_recurse()
call:
   call void @direct_recursion_use_stack(i32 %val.sub1)
   br label %ret
 
 ret:
   ret void
 }
 
 ; GCN-LABEL: {{^}}usage_direct_recursion:
-; GCN: is_ptr64 = 1
-; GCN: is_dynamic_callstack = 1
-; GCN: workitem_private_segment_byte_size = 18448{{$}}
+; GCN: .amdhsa_private_segment_fixed_size 18448
 ;
 ; GCN-V5-LABEL: {{^}}usage_direct_recursion:
 ; GCN-V5: .amdhsa_private_segment_fixed_size 2064{{$}}
 define amdgpu_kernel void @usage_direct_recursion(i32 %n) #0 {
   call void @direct_recursion_use_stack(i32 %n)
   ret void
 }
 

llvm/test/CodeGen/AMDGPU/callee-special-input-vgprs.ll

define void @use_workitem_id_yz() #1 {
   %val0 = call i32 @llvm.amdgcn.workitem.id.y()
   %val1 = call i32 @llvm.amdgcn.workitem.id.z()
   store volatile i32 %val0, ptr addrspace(1) undef
   store volatile i32 %val1, ptr addrspace(1) undef
   ret void
 }
 
 ; GCN-LABEL: {{^}}kern_indirect_use_workitem_id_x:
-; GCN: enable_vgpr_workitem_id = 0
 
 ; FIXEDABI-NOT: v0
 ; FIXEDABI-NOT: v31
 ; FIXEDABI: v_mov_b32_e32 v31, v0{{$}}
 ; FIXEDABI-NOT: v0
 ; FIXEDABI-NOT: v31
 
 ; GCN: s_swappc_b64
+
+; GCN: .amdhsa_system_vgpr_workitem_id 0
 define amdgpu_kernel void @kern_indirect_use_workitem_id_x() #1 {
   call void @use_workitem_id_x()
   ret void
 }
 
 ; GCN-LABEL: {{^}}kern_indirect_use_workitem_id_y:
-; GCN: enable_vgpr_workitem_id = 1
 
 ; FIXEDABI-NOT: v0
 ; FIXEDABI-NOT: v1
 ; FIXEDABI-NOT: v2
 ; FIXEDABI: v_lshlrev_b32_e32 v31, 10, v1
 ; FIXEDABI-NOT: v0
 ; FIXEDABI-NOT: v1
 ; FIXEDABI-NOT: v2
 
 ; GCN: s_swappc_b64
+
+; GCN: .amdhsa_system_vgpr_workitem_id 1
 define amdgpu_kernel void @kern_indirect_use_workitem_id_y() #1 {
   call void @use_workitem_id_y()
   ret void
 }
 
 ; GCN-LABEL: {{^}}kern_indirect_use_workitem_id_z:
-; GCN: enable_vgpr_workitem_id = 2
 
 ; FIXEDABI-NOT: v0
 ; FIXEDABI-NOT: v1
 ; FIXEDABI: v_lshlrev_b32_e32 v31, 20, v2
 ; FIXEDABI-NOT: v0
 ; FIXEDABI-NOT: v1
 
 ; GCN: s_swappc_b64
+
+; GCN: .amdhsa_system_vgpr_workitem_id 2
 define amdgpu_kernel void @kern_indirect_use_workitem_id_z() #1 {
   call void @use_workitem_id_z()
   ret void
 }
 
 ; GCN-LABEL: {{^}}kern_indirect_use_workitem_id_xy:
 ; FIXEDABI-NOT: v0
 ; FIXEDABI-NOT: v1
define void @other_arg_use_workitem_id_z(i32 %arg0) #1 {
   %val = call i32 @llvm.amdgcn.workitem.id.z()
   store volatile i32 %arg0, ptr addrspace(1) undef
   store volatile i32 %val, ptr addrspace(1) undef
   ret void
 }
 
 
 ; GCN-LABEL: {{^}}kern_indirect_other_arg_use_workitem_id_x:
-; GCN: enable_vgpr_workitem_id = 0
 
 ; FIXEDABI-NOT: v0
 ; FIXEDABI: v_mov_b32_e32 v31, v0
 ; FIXEDABI: v_mov_b32_e32 v0, 0x22b
 
 ; GCN: s_swappc_b64
+
+; GCN: .amdhsa_system_vgpr_workitem_id 0
 define amdgpu_kernel void @kern_indirect_other_arg_use_workitem_id_x() #1 {
   call void @other_arg_use_workitem_id_x(i32 555)
   ret void
 }
 
 
 ; GCN-LABEL: {{^}}kern_indirect_other_arg_use_workitem_id_y:
-; GCN: enable_vgpr_workitem_id = 1
 
 ; FIXEDABI-NOT: v0
 ; FIXEDABI-NOT: v1
 ; FIXEDABI-NOT: v2
 ; FIXEDABI: v_lshlrev_b32_e32 v31, 10, v1
 ; FIXEDABI: v_mov_b32_e32 v0, 0x22b
+
+; GCN: .amdhsa_system_vgpr_workitem_id 1
 define amdgpu_kernel void @kern_indirect_other_arg_use_workitem_id_y() #1 {
   call void @other_arg_use_workitem_id_y(i32 555)
   ret void
 }
 
 ; GCN-LABEL: {{^}}kern_indirect_other_arg_use_workitem_id_z:
-; GCN: enable_vgpr_workitem_id = 2
 
 ; FIXEDABI-NOT: v0
 ; FIXEDABI-NOT: v1
 ; FIXEDABI-NOT: v2
 ; FIXEDABI: v_lshlrev_b32_e32 v31, 20, v2
 ; FIXEDABI: v_mov_b32_e32 v0, 0x22b
+
+; GCN: .amdhsa_system_vgpr_workitem_id 2
 define amdgpu_kernel void @kern_indirect_other_arg_use_workitem_id_z() #1 {
   call void @other_arg_use_workitem_id_z(i32 555)
   ret void
 }
 
 ; GCN-LABEL: {{^}}too_many_args_use_workitem_id_x:
 ; FIXEDABI: v_and_b32_e32 v31, 0x3ff, v31
 ; FIXEDABI: buffer_load_dword v{{[0-9]+}}, off, s[0:3], s32{{$}}
define void @too_many_args_use_workitem_id_x(
   store volatile i32 %arg29, ptr addrspace(1) undef
   store volatile i32 %arg30, ptr addrspace(1) undef
   store volatile i32 %arg31, ptr addrspace(1) undef
 
   ret void
 }
 
 ; GCN-LABEL: {{^}}kern_call_too_many_args_use_workitem_id_x:
-; GCN: enable_vgpr_workitem_id = 0
 
 ; FIXEDABI-NOT: v0
 ; FIXEDABI-NOT: v1
 ; FIXEDABI-NOT: v2
 ; FIXEDABI-DAG: s_mov_b32 s32, 0
 ; FIXEDABI-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 0x140{{$}}
 ; FIXEDABI-DAG: buffer_store_dword [[K]], off, s[0:3], s32{{$}}
 ; FIXEDABI-DAG: v_mov_b32_e32 v31, v0
 
 ; FIXEDABI: s_swappc_b64
+
+; GCN: .amdhsa_system_vgpr_workitem_id 0
 define amdgpu_kernel void @kern_call_too_many_args_use_workitem_id_x() #1 {
   call void @too_many_args_use_workitem_id_x(
     i32 10, i32 20, i32 30, i32 40,
     i32 50, i32 60, i32 70, i32 80,
     i32 90, i32 100, i32 110, i32 120,
     i32 130, i32 140, i32 150, i32 160,
     i32 170, i32 180, i32 190, i32 200,
     i32 210, i32 220, i32 230, i32 240,
define void @too_many_args_use_workitem_id_xyz(
   store volatile i32 %arg29, ptr addrspace(1) undef
   store volatile i32 %arg30, ptr addrspace(1) undef
   store volatile i32 %arg31, ptr addrspace(1) undef
 
   ret void
 }
 
 ; GCN-LABEL: {{^}}kern_call_too_many_args_use_workitem_id_xyz:
-; GCN: enable_vgpr_workitem_id = 2
 
 ; GCN-DAG: s_mov_b32 s32, 0
 
 ; GCN-DAG: v_lshlrev_b32_e32 [[TMP1:v[0-9]+]], 10, v1
 ; FIXEDABI-DAG: v_mov_b32_e32 [[K:v[0-9]+]], 0x140
 ; GCN-DAG: v_lshlrev_b32_e32 [[TMP0:v[0-9]+]], 20, v2
 ; GCN-DAG: v_or_b32_e32 [[TMP2:v[0-9]+]], v0, [[TMP1]]
 
 ; FIXEDABI: buffer_store_dword [[K]], off, s[0:3], s32{{$}}
 ; FIXEDABI-DAG: v_or_b32_e32 v31, [[TMP2]], [[TMP0]]
 
 ; GCN: s_swappc_b64
+
+; GCN: .amdhsa_system_vgpr_workitem_id 2
 define amdgpu_kernel void @kern_call_too_many_args_use_workitem_id_xyz() #1 {
   call void @too_many_args_use_workitem_id_xyz(
     i32 10, i32 20, i32 30, i32 40,
     i32 50, i32 60, i32 70, i32 80,
     i32 90, i32 100, i32 110, i32 120,
     i32 130, i32 140, i32 150, i32 160,
     i32 170, i32 180, i32 190, i32 200,
     i32 210, i32 220, i32 230, i32 240,
define void @too_many_args_use_workitem_id_x_stack_yz(
   store volatile i32 %arg28, ptr addrspace(1) undef
   store volatile i32 %arg29, ptr addrspace(1) undef
   store volatile i32 %arg30, ptr addrspace(1) undef
 
   ret void
 }
 
 ; GCN-LABEL: {{^}}kern_call_too_many_args_use_workitem_id_x_stack_yz:
-; GCN: enable_vgpr_workitem_id = 2
 
 ; GCN-NOT: v0
 ; GCN-DAG: v_lshlrev_b32_e32 v1, 10, v1
 ; GCN-DAG: v_or_b32_e32 v0, v0, v1
 ; GCN-DAG: v_lshlrev_b32_e32 v2, 20, v2
 ; GCN-DAG: v_or_b32_e32 v31, v0, v2
 
 ; GCN: s_mov_b32 s32, 0
 ; GCN: s_swappc_b64
+
+; GCN: .amdhsa_system_vgpr_workitem_id 2
 define amdgpu_kernel void @kern_call_too_many_args_use_workitem_id_x_stack_yz() #1 {
   call void @too_many_args_use_workitem_id_x_stack_yz(
     i32 10, i32 20, i32 30, i32 40,
     i32 50, i32 60, i32 70, i32 80,
     i32 90, i32 100, i32 110, i32 120,
     i32 130, i32 140, i32 150, i32 160,
     i32 170, i32 180, i32 190, i32 200,
     i32 210, i32 220, i32 230, i32 240,

 declare i32 @llvm.amdgcn.workitem.id.y() #0
 declare i32 @llvm.amdgcn.workitem.id.z() #0
 
 attributes #0 = { nounwind readnone speculatable }
 attributes #1 = { nounwind noinline }
 attributes #2 = { nounwind "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/control-flow-fastregalloc.ll

 ; RUN: llc -O0 -mtriple=amdgcn--amdhsa -march=amdgcn -amdgpu-spill-sgpr-to-vgpr=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=VMEM -check-prefix=GCN %s
 ; RUN: llc -O0 -mtriple=amdgcn--amdhsa -march=amdgcn -amdgpu-spill-sgpr-to-vgpr=1 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefix=VGPR -check-prefix=GCN %s
 
 ; Verify registers used for tracking exec mask changes when all
 ; registers are spilled at the end of the block. The SGPR spill
 ; placement relative to the exec modifications are important.
 
 ; FIXME: This checks with SGPR to VGPR spilling disabled, but this may
 ; not work correctly in cases where no workitems take a branch.
 
 
 ; GCN-LABEL: {{^}}divergent_if_endif:
-; VGPR: workitem_private_segment_byte_size = 12{{$}}
-
 
 ; GCN: {{^}}; %bb.0:
 ; GCN: s_mov_b32 m0, -1
 ; GCN: ds_read_b32 [[LOAD0:v[0-9]+]]
 
 ; Spill load
 ; GCN: buffer_store_dword [[LOAD0]], off, s[0:3], 0 offset:[[LOAD0_OFFSET:[0-9]+]] ; 4-byte Folded Spill
 ; GCN: v_cmp_eq_u32_e64 [[CMP0:s\[[0-9]+:[0-9]\]]], v0, s{{[0-9]+}}

 ; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC:[0-9]+]], off, s[0:3], 0 offset:[[V_EXEC_SPILL_OFFSET]] ; 4-byte Folded Reload
 ; VMEM: s_waitcnt vmcnt(0)
 ; VMEM: v_readlane_b32 s[[S_RELOAD_SAVEEXEC_LO:[0-9]+]], v[[V_RELOAD_SAVEEXEC]], 0
 ; VMEM: v_readlane_b32 s[[S_RELOAD_SAVEEXEC_HI:[0-9]+]], v[[V_RELOAD_SAVEEXEC]], 1
 
 ; GCN: s_or_b64 exec, exec, s[[[S_RELOAD_SAVEEXEC_LO]]:[[S_RELOAD_SAVEEXEC_HI]]]
 
 ; GCN: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[RELOAD_VAL]]
+
+; VGPR: .amdhsa_private_segment_fixed_size 12
 define amdgpu_kernel void @divergent_if_endif(ptr addrspace(1) %out) #0 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %load0 = load volatile i32, ptr addrspace(3) undef
   %cmp0 = icmp eq i32 %tid, 0
   br i1 %cmp0, label %if, label %endif
 
 if:
   %load1 = load volatile i32, ptr addrspace(3) undef
   %val = add i32 %load0, %load1
   br label %endif
 
 endif:
   %tmp4 = phi i32 [ %val, %if ], [ 0, %entry ]
   store i32 %tmp4, ptr addrspace(1) %out
   ret void
 }
 
 ; GCN-LABEL: {{^}}divergent_loop:
-; VGPR: workitem_private_segment_byte_size = 16{{$}}
 
 ; GCN: {{^}}; %bb.0:
 ; GCN-DAG: s_mov_b32 m0, -1
 ; GCN-DAG: v_mov_b32_e32 [[PTR0:v[0-9]+]], 0{{$}}
 ; GCN: ds_read_b32 [[LOAD0:v[0-9]+]], [[PTR0]]
 ; GCN: v_cmp_eq_u32_e64 [[CMP0:s\[[0-9]+:[0-9]+\]]], v0, s{{[0-9]+}}
 
 ; Spill load

 ; VMEM: buffer_load_dword v[[V_RELOAD_SAVEEXEC:[0-9]+]], off, s[0:3], 0 offset:[[V_EXEC_SPILL_OFFSET]] ; 4-byte Folded Reload
 ; VMEM: s_waitcnt vmcnt(0)
 ; VMEM: v_readlane_b32 s[[S_RELOAD_SAVEEXEC_LO:[0-9]+]], v[[V_RELOAD_SAVEEXEC]], 0
 ; VMEM: v_readlane_b32 s[[S_RELOAD_SAVEEXEC_HI:[0-9]+]], v[[V_RELOAD_SAVEEXEC]], 1
 
 ; GCN: s_or_b64 exec, exec, s[[[S_RELOAD_SAVEEXEC_LO]]:[[S_RELOAD_SAVEEXEC_HI]]]
 
 ; GCN: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v[[VAL_END]]
+
+; VGPR: .amdhsa_private_segment_fixed_size 16
 define amdgpu_kernel void @divergent_loop(ptr addrspace(1) %out) #0 {
 entry:
   %tid = call i32 @llvm.amdgcn.workitem.id.x()
   %load0 = load volatile i32, ptr addrspace(3) null
   %cmp0 = icmp eq i32 %tid, 0
   br i1 %cmp0, label %loop, label %end
 
 loop:

 }
 
 declare i32 @llvm.amdgcn.workitem.id.x() #1
 
 attributes #0 = { nounwind }
 attributes #1 = { nounwind readnone }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/elf-notes.ll

 ; OSABI-UNK-ELF: AMD HSA ISA Name:
 ; OSABI-UNK-ELF: amdgcn-amd-unknown--gfx802
 ; OSABI-UNK-ELF-NOT: Unknown note type
 ; OSABI-UNK-ELF-NOT: NT_AMD_HSA_METADATA (AMD HSA Metadata)
 ; OSABI-UNK-ELF-NOT: Unknown note type
 ; OSABI-UNK-ELF-NOT: NT_AMD_PAL_METADATA (AMD PAL Metadata)
 ; OSABI-UNK-ELF-NOT: Unknown note type
 
-; OSABI-HSA: .hsa_code_object_version
-; OSABI-HSA: .hsa_code_object_isa
-; OSABI-HSA: .amd_amdgpu_isa "amdgcn-amd-amdhsa--gfx802"
-; OSABI-HSA: .amd_amdgpu_hsa_metadata
+; OSABI-HSA: amdhsa.target:   amdgcn-amd-amdhsa--gfx802
+; OSABI-HSA: amdhsa.version:
+; OSABI-HSA: .end_amdgpu_metadata
 ; OSABI-HSA-NOT: .amd_amdgpu_pal_metadata
 
-; OSABI-HSA-ELF: NT_AMD_HSA_CODE_OBJECT_VERSION (AMD HSA Code Object Version)
-; OSABI-HSA-ELF: NT_AMD_HSA_ISA_VERSION (AMD HSA ISA Version)
-; OSABI-HSA-ELF: NT_AMD_HSA_ISA_NAME (AMD HSA ISA Name)
-; OSABI-HSA-ELF: AMD HSA ISA Name:
-; OSABI-HSA-ELF: amdgcn-amd-amdhsa--gfx802
-; OSABI-HSA-ELF: NT_AMD_HSA_METADATA (AMD HSA Metadata)
-; OSABI-HSA-ELF: HSA Metadata:
+; OSABI-HSA-ELF: NT_AMDGPU_METADATA (AMDGPU Metadata)
 ; OSABI-HSA-ELF: ---
-; OSABI-HSA-ELF: Version: [ 1, 0 ]
-; OSABI-HSA-ELF: Kernels:
-; OSABI-HSA-ELF:   - Name:       elf_notes
-; OSABI-HSA-ELF:     SymbolName: 'elf_notes@kd'
-; OSABI-HSA-ELF:     CodeProps:
-; OSABI-HSA-ELF:       KernargSegmentSize: 0
-; OSABI-HSA-ELF:       GroupSegmentFixedSize: 0
-; OSABI-HSA-ELF:       PrivateSegmentFixedSize: 0
-; OSABI-HSA-ELF:       KernargSegmentAlign: 4
-; OSABI-HSA-ELF:       WavefrontSize:   64
-; OSABI-HSA-ELF:       NumSGPRs:        96
+; OSABI-HSA-ELF: amdhsa.kernels:
+; OSABI-HSA-ELF:   - .args:           []
+; OSABI-HSA-ELF:     .group_segment_fixed_size: 0
+; OSABI-HSA-ELF:     .kernarg_segment_align: 4
+; OSABI-HSA-ELF:     .kernarg_segment_size: 0
+; OSABI-HSA-ELF:     .max_flat_workgroup_size: 1024
+; OSABI-HSA-ELF:     .name:           elf_notes
+; OSABI-HSA-ELF:     .private_segment_fixed_size: 0
+; OSABI-HSA-ELF:     .sgpr_count:     96
+; OSABI-HSA-ELF:     .sgpr_spill_count: 0
+; OSABI-HSA-ELF:     .symbol:         elf_notes.kd
+; OSABI-HSA-ELF:     .vgpr_count:     0
+; OSABI-HSA-ELF:     .vgpr_spill_count: 0
+; OSABI-HSA-ELF:     .wavefront_size: 64
+; OSABI-HSA-ELF: amdhsa.target:   amdgcn-amd-amdhsa--gfx802
+; OSABI-HSA-ELF: amdhsa.version:
+; OSABI-HSA-ELF:   - 1
+; OSABI-HSA-ELF:   - 1
 ; OSABI-HSA-ELF: ...
 ; OSABI-HSA-ELF-NOT: NT_AMD_PAL_METADATA (AMD PAL Metadata)
 
-; OSABI-PAL-NOT: .hsa_code_object_version
-; OSABI-PAL: .hsa_code_object_isa
-; OSABI-PAL: .amd_amdgpu_isa "amdgcn-amd-amdpal--gfx802"
+; OSABI-PAL: .amd_amdgpu_isa  "amdgcn-amd-amdpal--gfx802"
+; OSABI-PAL: .amdgpu_pal_metadata
 ; OSABI-PAL-NOT: .amd_amdgpu_hsa_metadata
 
-; OSABI-PAL-ELF: NT_AMD_HSA_ISA_VERSION (AMD HSA ISA Version)
 ; OSABI-PAL-ELF: NT_AMD_HSA_ISA_NAME (AMD HSA ISA Name)
 ; OSABI-PAL-ELF: AMD HSA ISA Name:
 ; OSABI-PAL-ELF: amdgcn-amd-amdpal--gfx802
 ; OSABI-PAL-ELF-NOT: NT_AMD_HSA_METADATA (AMD HSA Metadata)
 ; OSABI-PAL-ELF: NT_AMDGPU_METADATA (AMDGPU Metadata)
 ; OSABI-PAL-ELF: AMDGPU Metadata:
 ; OSABI-PAL-ELF: amdpal.pipelines:
 ; OSABI-PAL-ELF:   - .hardware_stages:
 ; OSABI-PAL-ELF:       .cs:
 ; OSABI-PAL-ELF:         .entry_point:    elf_notes
 ; OSABI-PAL-ELF:         .scratch_memory_size: 0
 ; OSABI-PAL-ELF:         .sgpr_count:     96
 ; OSABI-PAL-ELF:         .vgpr_count:     1
 ; OSABI-PAL-ELF:     .registers:
 ; OSABI-PAL-ELF:       11794:           11469504
 ; OSABI-PAL-ELF:       11795:           128
-; OSABI-PAL: amdpal.pipelines:
-; OSABI-PAL:   - .hardware_stages:
-; OSABI-PAL:       .cs:
-; OSABI-PAL:         .entry_point:    elf_notes
-; OSABI-PAL:         .scratch_memory_size: 0
-; OSABI-PAL:         .sgpr_count:     0x60
-; OSABI-PAL:         .vgpr_count:     0x1
-; OSABI-PAL:     .registers:
-; OSABI-PAL:       0x2e12 (COMPUTE_PGM_RSRC1): 0xaf02c0
-; OSABI-PAL:       0x2e13 (COMPUTE_PGM_RSRC2): 0x80
 
 ; R600-NOT: .hsa_code_object_version
 ; R600-NOT: .hsa_code_object_isa
 ; R600-NOT: .amd_amdgpu_isa
 ; R600-NOT: .amd_amdgpu_hsa_metadata
 ; R600-NOT: .amd_amdgpu_pal_metadata
 
 define amdgpu_kernel void @elf_notes() {
   ret void
 }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/flat-for-global-subtarget-feature.ll

-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=+flat-for-global | FileCheck -check-prefix=HSA -check-prefix=HSA-DEFAULT -check-prefix=ALL %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-flat-for-global | FileCheck -check-prefix=HSA -check-prefix=HSA-NODEFAULT -check-prefix=ALL %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-- -mcpu=tonga | FileCheck -check-prefix=HSA-NOADDR64 -check-prefix=ALL %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-- -mcpu=kaveri -mattr=-flat-for-global | FileCheck -check-prefix=NOHSA-DEFAULT -check-prefix=ALL %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-- -mcpu=kaveri -mattr=+flat-for-global | FileCheck -check-prefix=NOHSA-NODEFAULT -check-prefix=ALL %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-- -mcpu=tonga | FileCheck -check-prefix=NOHSA-NOADDR64 -check-prefix=ALL %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=+flat-for-global | FileCheck -check-prefix=HSA -check-prefix=HSA-DEFAULT -check-prefix=ALL %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-flat-for-global | FileCheck -check-prefix=HSA -check-prefix=HSA-NODEFAULT -check-prefix=ALL %s
+; RUN: llc < %s -mtriple=amdgcn-- -mcpu=tonga | FileCheck -check-prefix=HSA-NOADDR64 -check-prefix=ALL %s
+; RUN: llc < %s -mtriple=amdgcn-- -mcpu=kaveri -mattr=-flat-for-global | FileCheck -check-prefix=NOHSA-DEFAULT -check-prefix=ALL %s
+; RUN: llc < %s -mtriple=amdgcn-- -mcpu=kaveri -mattr=+flat-for-global | FileCheck -check-prefix=NOHSA-NODEFAULT -check-prefix=ALL %s
+; RUN: llc < %s -mtriple=amdgcn-- -mcpu=tonga | FileCheck -check-prefix=NOHSA-NOADDR64 -check-prefix=ALL %s
 
 
 ; There are no stack objects even though flat is used by default, so
 ; flat_scratch_init should be disabled.
 
 ; ALL-LABEL: {{^}}test:
-; HSA: .amd_kernel_code_t
-; HSA: enable_sgpr_flat_scratch_init = 0
-; HSA: .end_amd_kernel_code_t
 
 ; ALL-NOT: flat_scr
 
 ; HSA-DEFAULT: flat_store_dword
 ; HSA-NODEFAULT: buffer_store_dword
 ; HSA-NOADDR64: flat_store_dword
 
+; HSA: .amdhsa_user_sgpr_flat_scratch_init 0
+
 ; NOHSA-DEFAULT: buffer_store_dword
 ; NOHSA-NODEFAULT: flat_store_dword
 ; NOHSA-NOADDR64: flat_store_dword
 define amdgpu_kernel void @test(ptr addrspace(1) %out) {
 entry:
   store i32 0, ptr addrspace(1) %out
   ret void
 }
entry:
   %ld1 = load ptr addrspace(1), ptr addrspace(5) %out.addr, align 4
   %arrayidx1 = getelementptr inbounds i32, ptr addrspace(1) %ld1, i32 1
   store i32 2, ptr addrspace(1) %arrayidx1, align 4
 
   ret void
 }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 CODE_OBJECT_VERSION}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/flat-scratch-reg.ll

-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mcpu=kaveri -verify-machineinstrs | FileCheck -check-prefix=CI -check-prefix=GCN %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mcpu=fiji -mattr=-xnack -verify-machineinstrs | FileCheck -check-prefix=VI-NOXNACK -check-prefix=GCN %s
+; RUN: llc < %s -march=amdgcn -mcpu=kaveri -verify-machineinstrs | FileCheck -check-prefix=CI -check-prefix=GCN %s
+; RUN: llc < %s -march=amdgcn -mcpu=fiji -mattr=-xnack -verify-machineinstrs | FileCheck -check-prefix=VI-NOXNACK -check-prefix=GCN %s
 
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mcpu=carrizo -mattr=-xnack -verify-machineinstrs | FileCheck -check-prefixes=VI-NOXNACK,GCN %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mcpu=stoney -mattr=-xnack -verify-machineinstrs | FileCheck -check-prefixes=VI-NOXNACK,GCN %s
+; RUN: llc < %s -march=amdgcn -mcpu=carrizo -mattr=-xnack -verify-machineinstrs | FileCheck -check-prefixes=VI-NOXNACK,GCN %s
+; RUN: llc < %s -march=amdgcn -mcpu=stoney -mattr=-xnack -verify-machineinstrs | FileCheck -check-prefixes=VI-NOXNACK,GCN %s
 
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mcpu=carrizo -mattr=+xnack -verify-machineinstrs | FileCheck -check-prefix=VI-XNACK  -check-prefix=GCN %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mcpu=stoney -mattr=+xnack -verify-machineinstrs | FileCheck -check-prefix=VI-XNACK  -check-prefix=GCN %s
+; RUN: llc < %s -march=amdgcn -mcpu=carrizo -mattr=+xnack -verify-machineinstrs | FileCheck -check-prefix=VI-XNACK  -check-prefix=GCN %s
+; RUN: llc < %s -march=amdgcn -mcpu=stoney -mattr=+xnack -verify-machineinstrs | FileCheck -check-prefix=VI-XNACK  -check-prefix=GCN %s
 
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs | FileCheck -check-prefixes=CI,HSA-CI-V2,GCN %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=carrizo -mattr=+xnack -verify-machineinstrs | FileCheck -check-prefixes=VI-XNACK,HSA-VI-XNACK-V2,GCN %s
-
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs | FileCheck -check-prefixes=GCN %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=carrizo -mattr=-xnack -verify-machineinstrs | FileCheck -check-prefixes=VI-NOXNACK,HSA-VI-NOXNACK,GCN %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=carrizo -mattr=+xnack -verify-machineinstrs | FileCheck -check-prefixes=VI-XNACK,HSA-VI-XNACK,GCN %s
-
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx900 -mattr=+architected-flat-scratch -verify-machineinstrs | FileCheck -check-prefixes=GCN %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx900 -mattr=+architected-flat-scratch,-xnack -verify-machineinstrs | FileCheck -check-prefixes=HSA-VI-NOXNACK,GFX9-ARCH-FLAT,GCN %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx900 -mattr=+architected-flat-scratch,+xnack -verify-machineinstrs | FileCheck -check-prefixes=HSA-VI-XNACK,GFX9-ARCH-FLAT,GCN %s
-
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -mattr=+architected-flat-scratch -verify-machineinstrs | FileCheck -check-prefixes=GCN %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -mattr=+architected-flat-scratch,-xnack -verify-machineinstrs | FileCheck -check-prefixes=HSA-VI-NOXNACK,GFX10-ARCH-FLAT,GCN %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -mattr=+architected-flat-scratch,+xnack -verify-machineinstrs | FileCheck -check-prefixes=HSA-VI-XNACK,GFX10-ARCH-FLAT,GCN %s
+; RUN: llc < %s -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs | FileCheck -check-prefixes=GCN %s
+; RUN: llc < %s -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=carrizo -mattr=-xnack -verify-machineinstrs | FileCheck -check-prefixes=VI-NOXNACK,HSA-VI-NOXNACK,GCN %s
+; RUN: llc < %s -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=carrizo -mattr=+xnack -verify-machineinstrs | FileCheck -check-prefixes=VI-XNACK,HSA-VI-XNACK,GCN %s
+
+; RUN: llc < %s -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx900 -mattr=+architected-flat-scratch -verify-machineinstrs | FileCheck -check-prefixes=GCN %s
+; RUN: llc < %s -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx900 -mattr=+architected-flat-scratch,-xnack -verify-machineinstrs | FileCheck -check-prefixes=HSA-VI-NOXNACK,GFX9-ARCH-FLAT,GCN %s
+; RUN: llc < %s -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx900 -mattr=+architected-flat-scratch,+xnack -verify-machineinstrs | FileCheck -check-prefixes=HSA-VI-XNACK,GFX9-ARCH-FLAT,GCN %s
+
+; RUN: llc < %s -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -mattr=+architected-flat-scratch -verify-machineinstrs | FileCheck -check-prefixes=GCN %s
+; RUN: llc < %s -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -mattr=+architected-flat-scratch,-xnack -verify-machineinstrs | FileCheck -check-prefixes=HSA-VI-NOXNACK,GFX10-ARCH-FLAT,GCN %s
+; RUN: llc < %s -march=amdgcn -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -mattr=+architected-flat-scratch,+xnack -verify-machineinstrs | FileCheck -check-prefixes=HSA-VI-XNACK,GFX10-ARCH-FLAT,GCN %s
 
 ; GCN-LABEL: {{^}}no_vcc_no_flat:
 
-; HSA-CI-V2: is_xnack_enabled = 0
-; HSA-VI-XNACK-V2: is_xnack_enabled = 1
-
 ; NOT-HSA-CI: .amdhsa_reserve_xnack_mask
 ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0
 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1
 
 ; CI: ; NumSgprs: 8
 ; VI-NOXNACK: ; NumSgprs: 8
 ; VI-XNACK: ; NumSgprs: 12
 ; GFX9-ARCH-FLAT: ; NumSgprs: 14
 ; GFX10-ARCH-FLAT: ; NumSgprs: 8
 define amdgpu_kernel void @no_vcc_no_flat() {
 entry:
   call void asm sideeffect "", "~{s7}"()
   ret void
 }
 
 ; GCN-LABEL: {{^}}vcc_no_flat:
 
-; HSA-CI-V2: is_xnack_enabled = 0
-; HSA-VI-XNACK-V2: is_xnack_enabled = 1
-
 ; NOT-HSA-CI: .amdhsa_reserve_xnack_mask
 ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0
 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1
 
 ; CI: ; NumSgprs: 10
 ; VI-NOXNACK: ; NumSgprs: 10
 ; VI-XNACK: ; NumSgprs: 12
 ; GFX9-ARCH-FLAT: ; NumSgprs: 14
 ; GFX10-ARCH-FLAT: ; NumSgprs: 10
 define amdgpu_kernel void @vcc_no_flat() {
 entry:
   call void asm sideeffect "", "~{s7},~{vcc}"()
   ret void
 }
 
 ; GCN-LABEL: {{^}}no_vcc_flat:
 
-; HSA-CI-V2: is_xnack_enabled = 0
-; HSA-VI-XNACK-V2: is_xnack_enabled = 1
-
 ; NOT-HSA-CI: .amdhsa_reserve_xnack_mask
 ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0
 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1
 
 ; CI: ; NumSgprs: 12
 ; VI-NOXNACK: ; NumSgprs: 14
 ; VI-XNACK: ; NumSgprs: 14
 ; GFX9-ARCH-FLAT: ; NumSgprs: 14
 ; GFX10-ARCH-FLAT: ; NumSgprs: 8
 define amdgpu_kernel void @no_vcc_flat() {
 entry:
   call void asm sideeffect "", "~{s7},~{flat_scratch}"()
   ret void
 }
 
 ; GCN-LABEL: {{^}}vcc_flat:
 
-; HSA-CI-V2: is_xnack_enabled = 0
-; HSA-VI-XNACK-V2: is_xnack_enabled = 1
-
 ; NOT-HSA-CI: .amdhsa_reserve_xnack_mask
 ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0
 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1
 
 ; CI: ; NumSgprs: 12
 ; VI-NOXNACK: ; NumSgprs: 14
 ; VI-XNACK: ; NumSgprs: 14
 ; GFX9-ARCH-FLAT: ; NumSgprs: 14
 ; GFX10-ARCH-FLAT: ; NumSgprs: 10
 define amdgpu_kernel void @vcc_flat() {
 entry:
   call void asm sideeffect "", "~{s7},~{vcc},~{flat_scratch}"()
   ret void
 }
 
 ; Make sure used SGPR count for flat_scr is correct when there is no
 ; scratch usage and implicit flat uses.
 
 ; GCN-LABEL: {{^}}use_flat_scr:
 
-; HSA-CI-V2: is_xnack_enabled = 0
-; HSA-VI-XNACK-V2: is_xnack_enabled = 1
-
 ; NOT-HSA-CI: .amdhsa_reserve_xnack_mask
 ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0
 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1
 
 ; CI: NumSgprs: 4
 ; VI-NOXNACK: NumSgprs: 6
 ; VI-XNACK: NumSgprs: 6
 ; GFX9-ARCH-FLAT: ; NumSgprs: 6
 ; GFX10-ARCH-FLAT: ; NumSgprs: 0
 define amdgpu_kernel void @use_flat_scr() #0 {
 entry:
   call void asm sideeffect "; clobber ", "~{flat_scratch}"()
   ret void
 }
 
 ; GCN-LABEL: {{^}}use_flat_scr_lo:
 
-; HSA-CI-V2: is_xnack_enabled = 0
-; HSA-VI-XNACK-V2: is_xnack_enabled = 1
-
 ; NOT-HSA-CI: .amdhsa_reserve_xnack_mask
 ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0
 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1
 
 ; CI: NumSgprs: 4
 ; VI-NOXNACK: NumSgprs: 6
 ; VI-XNACK: NumSgprs: 6
 ; GFX9-ARCH-FLAT: ; NumSgprs: 6
 ; GFX10-ARCH-FLAT: ; NumSgprs: 0
 define amdgpu_kernel void @use_flat_scr_lo() #0 {
 entry:
   call void asm sideeffect "; clobber ", "~{flat_scratch_lo}"()
   ret void
 }
 
 ; GCN-LABEL: {{^}}use_flat_scr_hi:
 
-; HSA-CI-V2: is_xnack_enabled = 0
-; HSA-VI-XNACK-V2: is_xnack_enabled = 1
-
 ; NOT-HSA-CI: .amdhsa_reserve_xnack_mask
 ; HSA-VI-NOXNACK: .amdhsa_reserve_xnack_mask 0
 ; HSA-VI-XNACK: .amdhsa_reserve_xnack_mask 1
 
 ; CI: NumSgprs: 4
 ; VI-NOXNACK: NumSgprs: 6
 ; VI-XNACK: NumSgprs: 6
 ; GFX9-ARCH-FLAT: ; NumSgprs: 6
 ; GFX10-ARCH-FLAT: ; NumSgprs: 0
 define amdgpu_kernel void @use_flat_scr_hi() #0 {
 entry:
   call void asm sideeffect "; clobber ", "~{flat_scratch_hi}"()
   ret void
 }
 
 attributes #0 = { nounwind }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 CODE_OBJECT_VERSION}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/gfx902-without-xnack.ll

 ; RUN: llc -march=amdgcn -mtriple=amdgcn-amd-amdhsa -mcpu=gfx902 -mattr=-xnack < %s | FileCheck %s
 
-; CHECK: .hsa_code_object_isa 9,0,2,"AMD","AMDGPU"
+; CHECK: .amdgcn_target "amdgcn-amd-amdhsa--gfx902:xnack-"
 define amdgpu_kernel void @test_kernel(ptr addrspace(1) %out0, ptr addrspace(1) %out1) nounwind {
   store float 0.0, ptr addrspace(1) %out0
   ret void
 }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
-
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/hsa-default-device.ll

 ; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck %s
 
 ; Make sure that with an HSA triple, we don't default to an
 ; unsupported device.
 
-; CHECK: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
+; CHECK: .amdgcn_target "amdgcn-unknown-amdhsa--gfx700"
 define amdgpu_kernel void @test_kernel(ptr addrspace(1) %out0, ptr addrspace(1) %out1) nounwind {
   store float 0.0, ptr addrspace(1) %out0
   ret void
 }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/hsa-fp-mode.ll

 ; RUN: llc -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 ; GCN-LABEL: {{^}}test_default_ci:
-; GCN: float_mode = 240
-; GCN: enable_dx10_clamp = 1
-; GCN: enable_ieee_mode = 1
+; GCN: .amdhsa_dx10_clamp 1
+; GCN: .amdhsa_ieee_mode 1
+; GCN: FloatMode: 240
 define amdgpu_kernel void @test_default_ci(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #0 {
   store float 0.0, ptr addrspace(1) %out0
   store double 0.0, ptr addrspace(1) %out1
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_default_vi:
-; GCN: float_mode = 240
-; GCN: enable_dx10_clamp = 1
-; GCN: enable_ieee_mode = 1
+; GCN: .amdhsa_dx10_clamp 1
+; GCN: .amdhsa_ieee_mode 1
+; GCN: FloatMode: 240
 define amdgpu_kernel void @test_default_vi(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #1 {
   store float 0.0, ptr addrspace(1) %out0
   store double 0.0, ptr addrspace(1) %out1
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_f64_denormals:
-; GCN: float_mode = 192
-; GCN: enable_dx10_clamp = 1
-; GCN: enable_ieee_mode = 1
+; GCN: .amdhsa_dx10_clamp 1
+; GCN: .amdhsa_ieee_mode 1
+; GCN: FloatMode: 192
 define amdgpu_kernel void @test_f64_denormals(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #2 {
   store float 0.0, ptr addrspace(1) %out0
   store double 0.0, ptr addrspace(1) %out1
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_f32_denormals:
-; GCN: float_mode = 48
-; GCN: enable_dx10_clamp = 1
-; GCN: enable_ieee_mode = 1
+; GCN: .amdhsa_dx10_clamp 1
+; GCN: .amdhsa_ieee_mode 1
+; GCN: FloatMode: 48
 define amdgpu_kernel void @test_f32_denormals(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #3 {
   store float 0.0, ptr addrspace(1) %out0
   store double 0.0, ptr addrspace(1) %out1
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_f32_f64_denormals:
-; GCN: float_mode = 240
-; GCN: enable_dx10_clamp = 1
-; GCN: enable_ieee_mode = 1
+; GCN: .amdhsa_dx10_clamp 1
+; GCN: .amdhsa_ieee_mode 1
+; GCN: FloatMode: 240
 define amdgpu_kernel void @test_f32_f64_denormals(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #4 {
   store float 0.0, ptr addrspace(1) %out0
   store double 0.0, ptr addrspace(1) %out1
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_no_denormals:
-; GCN: float_mode = 0
-; GCN: enable_dx10_clamp = 1
-; GCN: enable_ieee_mode = 1
+; GCN: .amdhsa_dx10_clamp 1
+; GCN: .amdhsa_ieee_mode 1
+; GCN: FloatMode: 0
 define amdgpu_kernel void @test_no_denormals(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #5 {
   store float 0.0, ptr addrspace(1) %out0
   store double 0.0, ptr addrspace(1) %out1
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_no_dx10_clamp_vi:
-; GCN: float_mode = 240
-; GCN: enable_dx10_clamp = 0
-; GCN: enable_ieee_mode = 1
+; GCN: .amdhsa_dx10_clamp 0
+; GCN: .amdhsa_ieee_mode 1
+; GCN: FloatMode: 240
 define amdgpu_kernel void @test_no_dx10_clamp_vi(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #6 {
   store float 0.0, ptr addrspace(1) %out0
   store double 0.0, ptr addrspace(1) %out1
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_no_ieee_mode_vi:
-; GCN: float_mode = 240
-; GCN: enable_dx10_clamp = 1
-; GCN: enable_ieee_mode = 0
+; GCN: .amdhsa_dx10_clamp 1
+; GCN: .amdhsa_ieee_mode 0
+; GCN: FloatMode: 240
 define amdgpu_kernel void @test_no_ieee_mode_vi(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #7 {
   store float 0.0, ptr addrspace(1) %out0
   store double 0.0, ptr addrspace(1) %out1
   ret void
 }
 
 ; GCN-LABEL: {{^}}test_no_ieee_mode_no_dx10_clamp_vi:
-; GCN: float_mode = 240
-; GCN: enable_dx10_clamp = 0
-; GCN: enable_ieee_mode = 0
+; GCN: .amdhsa_dx10_clamp 0
+; GCN: .amdhsa_ieee_mode 0
+; GCN: FloatMode: 240
 define amdgpu_kernel void @test_no_ieee_mode_no_dx10_clamp_vi(ptr addrspace(1) %out0, ptr addrspace(1) %out1) #8 {
   store float 0.0, ptr addrspace(1) %out0
   store double 0.0, ptr addrspace(1) %out1
   ret void
 }
 
 attributes #0 = { nounwind "target-cpu"="kaveri" }
 attributes #1 = { nounwind "target-cpu"="fiji" }
 attributes #2 = { nounwind "denormal-fp-math-f32"="preserve-sign,preserve-sign" }
 attributes #3 = { nounwind "denormal-fp-math-f32"="ieee,ieee" "denormal-fp-math"="preserve-sign,preserve-sign" }
 attributes #4 = { nounwind "denormal-fp-math"="ieee,ieee" }
 attributes #5 = { nounwind "denormal-fp-math"="preserve-sign,preserve-sign" }
 attributes #6 = { nounwind "amdgpu-dx10-clamp"="false" "target-cpu"="fiji" }
 attributes #7 = { nounwind "amdgpu-ieee"="false" "target-cpu"="fiji" }
 attributes #8 = { nounwind "amdgpu-dx10-clamp"="false" "amdgpu-ieee"="false" "target-cpu"="fiji" }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/hsa-func.ll

 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri | FileCheck --check-prefix=HSA %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri | FileCheck --check-prefix=HSA-CI %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=carrizo  | FileCheck --check-prefix=HSA %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=carrizo | FileCheck --check-prefix=HSA-VI %s
 ; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri -filetype=obj | llvm-readobj --symbols -S --sd - | FileCheck --check-prefix=ELF %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri | llvm-mc -filetype=obj -triple amdgcn--amdhsa --amdhsa-code-object-version=2 -mcpu=kaveri | llvm-readobj --symbols -S --sd - | FileCheck %s --check-prefix=ELF
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri | llvm-mc -filetype=obj -triple amdgcn--amdhsa --amdhsa-code-object-version=4 -mcpu=kaveri | llvm-readobj --symbols -S --sd - | FileCheck %s --check-prefix=ELF
 
 ; The SHT_NOTE section contains the output from the .hsa_code_object_*
 ; directives.
 
 ; ELF: Section {
 ; ELF: Name: .text
 ; ELF: Type: SHT_PROGBITS (0x1)
 ; ELF: Flags [ (0x6)
 ; ELF: SHF_ALLOC (0x2)
 ; ELF: SHF_EXECINSTR (0x4)
 ; ELF: AddressAlignment: 4
 ; ELF: }
 
 ; ELF: SHT_NOTE
-; ELF: 0000: 04000000 08000000 01000000 414D4400
-; ELF: 0010: 02000000 01000000 04000000 1B000000
-
-; ELF: 0020: 03000000 414D4400 04000700 07000000
-; ELF: 0030: 00000000 00000000 414D4400 414D4447
-; ELF: 0040: 50550000
+; ELF: 0000: 07000000 4F000000 20000000 414D4447
+; ELF: 0010: 50550000 83AE616D 64687361 2E6B6572
+; ELF: 0020: 6E656C73 90AD616D 64687361 2E746172
+; ELF: 0030: 676574BD 616D6467 636E2D75 6E6B6E6F
+; ELF: 0040: 776E2D61 6D646873 612D2D67 66783730
+; ELF: 0050: 30AE616D 64687361 2E766572 73696F6E
+; ELF: 0060: 92010100
 
 ; ELF: Symbol {
 ; ELF: Name: simple
 ; ELF: Size: 36
 ; ELF: Type: Function (0x2)
 ; ELF: }
 
 ; HSA: .text
-; HSA: .hsa_code_object_version 2,1
-; HSA-CI: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-; HSA-VI: .hsa_code_object_isa 8,0,1,"AMD","AMDGPU"
+; HSA-CI: .amdgcn_target "amdgcn-unknown-amdhsa--gfx700" 
+; HSA-VI: .amdgcn_target "amdgcn-unknown-amdhsa--gfx801" 
 
 ; HSA-NOT: .amdgpu_hsa_kernel simple
 ; HSA: .globl simple
 ; HSA: .p2align 2
 ; HSA: {{^}}simple:
 ; HSA-NOT: amd_kernel_code_t
 ; HSA: flat_load_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v[0:1]
 

 define void @simple_align2(ptr addrspace(4) %ptr.out) align 2 {
 entry:
   %out = load ptr addrspace(1), ptr addrspace(4) %ptr.out
   store i32 0, ptr addrspace(1) %out
   ret void
 }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/hsa-metadata-deduce-ro-arg.ll

-; RUN: llc -mtriple=amdgcn-amd-amdhsa -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s
-
-; CHECK:      - Name:            test_ro_arg
-; CHECK-NEXT:   SymbolName:      'test_ro_arg@kd'
-; CHECK-NEXT:   Args:
-; CHECK-NEXT: - Name:            in
-; CHECK-NEXT:   TypeName:        'float*'
-; CHECK-NEXT:   Size:            8
-; CHECK-NEXT:   Align:           8
-; CHECK-NEXT:   ValueKind:       GlobalBuffer
-; CHECK-NEXT:   AddrSpaceQual:   Global
-; CHECK-NEXT:   AccQual:         ReadOnly
-; CHECK-NEXT:   IsConst:         true
-; CHECK-NEXT:   IsRestrict:      true
-; CHECK-NEXT: - Name:            out
-; CHECK-NEXT:   TypeName:        'float*'
-; CHECK-NEXT:   Size:            8
-; CHECK-NEXT:   Align:           8
-; CHECK-NEXT:   ValueKind:       GlobalBuffer
-; CHECK-NEXT:   AddrSpaceQual:   Global
-; CHECK-NEXT:   AccQual:         Default
-
-define amdgpu_kernel void @test_ro_arg(ptr addrspace(1) noalias readonly %in, ptr addrspace(1) %out)
-    !kernel_arg_addr_space !0 !kernel_arg_access_qual !1 !kernel_arg_type !2
-    !kernel_arg_base_type !2 !kernel_arg_type_qual !3 {
-  ret void
-}
-
-!0 = !{i32 1, i32 1}
-!1 = !{!"none", !"none"}
-!2 = !{!"float*", !"float*"}
-!3 = !{!"const restrict", !""}
-
-!llvm.module.flags = !{!99}
-!99 = !{i32 1, !"amdgpu_code_object_version", i32 200}

llvm/test/CodeGen/AMDGPU/hsa-metadata-enqueue-kernel.ll

-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefix=CHECK %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s
-
-; CHECK: ---
-; CHECK:  Version: [ 1, 0 ]
-; CHECK-NOT:  Printf:
-; CHECK:  Kernels:
-
-; CHECK:      - Name:            test_non_enqueue_kernel_caller
-; CHECK-NEXT:   SymbolName:      'test_non_enqueue_kernel_caller@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      char
-; CHECK-NEXT:       Size:          1
-; CHECK-NEXT:       Align:         1
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenHostcallBuffer
-; CHECK-NOT:        ValueKind:     HiddenDefaultQueue
-; CHECK-NOT:        ValueKind:     HiddenCompletionAction
-define amdgpu_kernel void @test_non_enqueue_kernel_caller(i8 %a) #0
-    !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
-    !kernel_arg_base_type !3 !kernel_arg_type_qual !4 {
-  ret void
-}
-
-; CHECK:      - Name:            test_enqueue_kernel_caller
-; CHECK-NEXT:   SymbolName:      'test_enqueue_kernel_caller@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      char
-; CHECK-NEXT:       Size:          1
-; CHECK-NEXT:       Align:         1
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenHostcallBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenDefaultQueue
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenCompletionAction
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_enqueue_kernel_caller(i8 %a) #1
-    !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
-    !kernel_arg_base_type !3 !kernel_arg_type_qual !4 {
-  ret void
-}
-
-attributes #0 = { optnone noinline "amdgpu-no-default-queue" "amdgpu-no-completion-action" "amdgpu-implicitarg-num-bytes"="48" }
-attributes #1 = { optnone noinline "amdgpu-implicitarg-num-bytes"="48" "calls-enqueue-kernel" }
-
-!llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
-
-!1 = !{i32 0}
-!2 = !{!"none"}
-!3 = !{!"char"}
-!4 = !{!""}
-
-!opencl.ocl.version = !{!90}
-!90 = !{i32 2, i32 0}
-
-; PARSER: AMDGPU HSA Metadata Parser Test: PASS

llvm/test/CodeGen/AMDGPU/hsa-metadata-from-llvm-ir-full.ll

-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefix=CHECK %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx802 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefix=CHECK %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefix=CHECK %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx802 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -amdgpu-dump-hsa-metadata -amdgpu-verify-hsa-metadata -filetype=obj -o - < %s 2>&1 | FileCheck --check-prefix=PARSER %s
-
-%struct.A = type { i8, float }
-%opencl.image1d_t = type opaque
-%opencl.image2d_t = type opaque
-%opencl.image3d_t = type opaque
-%opencl.queue_t = type opaque
-%opencl.pipe_t = type opaque
-%struct.B = type { ptr addrspace(1)}
-%opencl.clk_event_t = type opaque
-
-@__test_block_invoke_kernel_runtime_handle = external addrspace(1) externally_initialized constant ptr addrspace(1)
-
-; CHECK: ---
-; CHECK:  Version: [ 1, 0 ]
-; CHECK:  Printf:
-; CHECK:    - '1:1:4:%d\n'
-; CHECK:    - '2:1:8:%g\n'
-; CHECK:  Kernels:
-
-; CHECK:      - Name:            test_char
-; CHECK-NEXT:   SymbolName:      'test_char@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      char
-; CHECK-NEXT:       Size:          1
-; CHECK-NEXT:       Align:         1
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NOT:        ValueKind:     HiddenHostcallBuffer
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NOT:        ValueKind:     HiddenDefaultQueue
-; CHECK-NOT:        ValueKind:     HiddenCompletionAction
-; CHECK:            ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_char(i8 %a) #0
-    !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:      - Name:            test_char_byref_constant
-; CHECK-NEXT:   SymbolName:      'test_char_byref_constant@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      char
-; CHECK-NEXT:       Size:          1
-; CHECK-NEXT:       Align:         1
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NOT:        ValueKind:     HiddenHostcallBuffer
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NOT:        ValueKind:     HiddenDefaultQueue
-; CHECK-NOT:        ValueKind:     HiddenCompletionAction
-; CHECK:            ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_char_byref_constant(ptr addrspace(4) byref(i8) %a) #0
-    !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:      - Name:            test_char_byref_constant_align512
-; CHECK-NEXT:   SymbolName:      'test_char_byref_constant_align512@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:       TypeName:      char
-; CHECK-NEXT:       Size:          1
-; CHECK-NEXT:       Align:         1
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      char
-; CHECK-NEXT:       Size:          1
-; CHECK-NEXT:       Align:         512
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NOT:        ValueKind:     HiddenHostcallBuffer
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NOT:        ValueKind:     HiddenDefaultQueue
-; CHECK-NOT:        ValueKind:     HiddenCompletionAction
-; CHECK:            ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_char_byref_constant_align512(i8, ptr addrspace(4) byref(i8) align 512 %a) #0
-    !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !111
-    !kernel_arg_base_type !9 !kernel_arg_type_qual !4 {
-  ret void
-}
-
-; CHECK:      - Name:            test_ushort2
-; CHECK-NEXT:   SymbolName:      'test_ushort2@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      ushort2
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_ushort2(<2 x i16> %a) #0
-    !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:      - Name:            test_int3
-; CHECK-NEXT:   SymbolName:      'test_int3@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      int3
-; CHECK-NEXT:       Size:          16
-; CHECK-NEXT:       Align:         16
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_int3(<3 x i32> %a) #0
-    !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:      - Name:            test_ulong4
-; CHECK-NEXT:   SymbolName:      'test_ulong4@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      ulong4
-; CHECK-NEXT:       Size:          32
-; CHECK-NEXT:       Align:         32
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_ulong4(<4 x i64> %a) #0
-    !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:      - Name:            test_half8
-; CHECK-NEXT:   SymbolName:      'test_half8@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      half8
-; CHECK-NEXT:       Size:          16
-; CHECK-NEXT:       Align:         16
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_half8(<8 x half> %a) #0
-    !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:      - Name:            test_float16
-; CHECK-NEXT:   SymbolName:      'test_float16@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      float16
-; CHECK-NEXT:       Size:          64
-; CHECK-NEXT:       Align:         64
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_float16(<16 x float> %a) #0
-    !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:      - Name:            test_double16
-; CHECK-NEXT:   SymbolName:      'test_double16@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      double16
-; CHECK-NEXT:       Size:          128
-; CHECK-NEXT:       Align:         128
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_double16(<16 x double> %a) #0
-    !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:      - Name:            test_pointer
-; CHECK-NEXT:   SymbolName:      'test_pointer@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      'int  addrspace(5)*'
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_pointer(ptr addrspace(1) %a) #0
-    !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:      - Name:            test_image
-; CHECK-NEXT:   SymbolName:      'test_image@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      image2d_t
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     Image
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_image(ptr addrspace(1) %a) #0
-    !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:      - Name:            test_sampler
-; CHECK-NEXT:   SymbolName:      'test_sampler@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      sampler_t
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     Sampler
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_sampler(i32 %a) #0
-    !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:      - Name:            test_queue
-; CHECK-NEXT:   SymbolName:      'test_queue@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      queue_t
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     Queue
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_queue(ptr addrspace(1) %a) #0
-    !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:      - Name:            test_struct
-; CHECK-NEXT:   SymbolName:      'test_struct@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      struct A
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_struct(%struct.A %a) #0
-    !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:      - Name:            test_struct_byref_constant
-; CHECK-NEXT:   SymbolName:      'test_struct_byref_constant@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      struct A
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_struct_byref_constant(ptr addrspace(4) byref(%struct.A) %a) #0
-    !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:      - Name:            test_array
-; CHECK-NEXT:   SymbolName:      'test_array@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      struct A
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         1
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_array([8 x i8] %a) #0
-    !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:      - Name:            test_array_byref_constant
-; CHECK-NEXT:   SymbolName:      'test_array_byref_constant@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      struct A
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         1
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_array_byref_constant(ptr addrspace(4) byref([8 x i8]) %a) #0
-    !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:      - Name:            test_i128
-; CHECK-NEXT:   SymbolName:      'test_i128@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      i128
-; CHECK-NEXT:       Size:          16
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_i128(i128 %a) #0
-    !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:      - Name:            test_multi_arg
-; CHECK-NEXT:   SymbolName:      'test_multi_arg@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      int
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          b
-; CHECK-NEXT:       TypeName:      short2
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          c
-; CHECK-NEXT:       TypeName:      char3
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_multi_arg(i32 %a, <2 x i16> %b, <3 x i8> %c) #0
-    !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:      - Name:            test_addr_space
-; CHECK-NEXT:   SymbolName:      'test_addr_space@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          g
-; CHECK-NEXT:       TypeName:      'int  addrspace(5)*'
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          c
-; CHECK-NEXT:       TypeName:      'int  addrspace(5)*'
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual: Constant
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          l
-; CHECK-NEXT:       TypeName:      'int  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  4
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_addr_space(ptr addrspace(1) %g,
-                                           ptr addrspace(4) %c,
-                                           ptr addrspace(3) align 4 %l) #0
-    !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:      - Name:            test_type_qual
-; CHECK-NEXT:   SymbolName:      'test_type_qual@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      'int  addrspace(5)*'
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:       IsVolatile:    true
-; CHECK-NEXT:     - Name:          b
-; CHECK-NEXT:       TypeName:      'int  addrspace(5)*'
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:       IsConst:       true
-; CHECK-NEXT:       IsRestrict:    true
-; CHECK-NEXT:     - Name:          c
-; CHECK-NEXT:       TypeName:      'int  addrspace(5)*'
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     Pipe
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:       IsPipe:        true
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_type_qual(ptr addrspace(1) %a,
-                                          ptr addrspace(1) %b,
-                                          ptr addrspace(1) %c) #0
-    !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:      - Name:            test_access_qual
-; CHECK-NEXT:   SymbolName:      'test_access_qual@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          ro
-; CHECK-NEXT:       TypeName:      image1d_t
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     Image
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       ReadOnly
-; CHECK-NEXT:     - Name:          wo
-; CHECK-NEXT:       TypeName:      image2d_t
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     Image
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       WriteOnly
-; CHECK-NEXT:     - Name:          rw
-; CHECK-NEXT:       TypeName:      image3d_t
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     Image
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       ReadWrite
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_access_qual(ptr addrspace(1) %ro,
-                                            ptr addrspace(1) %wo,
-                                            ptr addrspace(1) %rw) #0
-    !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:      - Name:            test_vec_type_hint_half
-; CHECK-NEXT:   SymbolName:      'test_vec_type_hint_half@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Attrs:
-; CHECK-NEXT:       VecTypeHint:   half
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      int
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_vec_type_hint_half(i32 %a) #0
-    !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:      - Name:            test_vec_type_hint_float
-; CHECK-NEXT:   SymbolName:      'test_vec_type_hint_float@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Attrs:
-; CHECK-NEXT:       VecTypeHint:   float
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      int
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_vec_type_hint_float(i32 %a) #0
-    !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:      - Name:            test_vec_type_hint_double
-; CHECK-NEXT:   SymbolName:      'test_vec_type_hint_double@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Attrs:
-; CHECK-NEXT:       VecTypeHint:   double
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      int
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_vec_type_hint_double(i32 %a) #0
-    !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:      - Name:            test_vec_type_hint_char
-; CHECK-NEXT:   SymbolName:      'test_vec_type_hint_char@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Attrs:
-; CHECK-NEXT:       VecTypeHint:   char
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      int
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_vec_type_hint_char(i32 %a) #0
-    !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:      - Name:            test_vec_type_hint_short
-; CHECK-NEXT:   SymbolName:      'test_vec_type_hint_short@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Attrs:
-; CHECK-NEXT:       VecTypeHint:   short
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      int
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_vec_type_hint_short(i32 %a) #0
-    !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:      - Name:            test_vec_type_hint_long
-; CHECK-NEXT:   SymbolName:      'test_vec_type_hint_long@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Attrs:
-; CHECK-NEXT:       VecTypeHint:   long
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      int
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_vec_type_hint_long(i32 %a) #0
-    !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:      - Name:            test_vec_type_hint_unknown
-; CHECK-NEXT:   SymbolName:      'test_vec_type_hint_unknown@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Attrs:
-; CHECK-NEXT:       VecTypeHint:   unknown
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      int
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_vec_type_hint_unknown(i32 %a) #0
-    !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:      - Name:            test_reqd_wgs_vec_type_hint
-; CHECK-NEXT:   SymbolName:      'test_reqd_wgs_vec_type_hint@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Attrs:
-; CHECK-NEXT:       ReqdWorkGroupSize: [ 1, 2, 4 ]
-; CHECK-NEXT:       VecTypeHint:       int
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:              a
-; CHECK-NEXT:       TypeName:          int
-; CHECK-NEXT:       Size:              4
-; CHECK-NEXT:       Align:             4
-; CHECK-NEXT:       ValueKind:         ByValue
-; CHECK-NEXT:       AccQual:           Default
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual:     Global
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenNone
-; CHECK-NEXT:       AddrSpaceQual:     Global
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenNone
-; CHECK-NEXT:       AddrSpaceQual:     Global
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual:     Global
-define amdgpu_kernel void @test_reqd_wgs_vec_type_hint(i32 %a) #0
-    !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:      - Name:            test_wgs_hint_vec_type_hint
-; CHECK-NEXT:   SymbolName:      'test_wgs_hint_vec_type_hint@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Attrs:
-; CHECK-NEXT:       WorkGroupSizeHint: [ 8, 16, 32 ]
-; CHECK-NEXT:       VecTypeHint:       uint4
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:              a
-; CHECK-NEXT:       TypeName:          int
-; CHECK-NEXT:       Size:              4
-; CHECK-NEXT:       Align:             4
-; CHECK-NEXT:       ValueKind:         ByValue
-; CHECK-NEXT:       AccQual:           Default
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual:     Global
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenNone
-; CHECK-NEXT:       AddrSpaceQual:     Global
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenNone
-; CHECK-NEXT:       AddrSpaceQual:     Global
-; CHECK-NEXT:     - Size:              8
-; CHECK-NEXT:       Align:             8
-; CHECK-NEXT:       ValueKind:         HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual:     Global
-define amdgpu_kernel void @test_wgs_hint_vec_type_hint(i32 %a) #0
-    !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:      - Name:            test_arg_ptr_to_ptr
-; CHECK-NEXT:   SymbolName:      'test_arg_ptr_to_ptr@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      'int  addrspace(5)* addrspace(5)*'
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_arg_ptr_to_ptr(ptr addrspace(1) %a) #0
-    !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:      - Name:            test_arg_struct_contains_ptr
-; CHECK-NEXT:   SymbolName:      'test_arg_struct_contains_ptr@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      struct B
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_arg_struct_contains_ptr(%struct.B %a) #0
-    !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:      - Name:            test_arg_vector_of_ptr
-; CHECK-NEXT:   SymbolName:      'test_arg_vector_of_ptr@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      'global int addrspace(5)* __attribute__((ext_vector_type(2)))'
-; CHECK-NEXT:       Size:          16
-; CHECK-NEXT:       Align:         16
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_arg_vector_of_ptr(<2 x ptr addrspace(1)> %a) #0
-    !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:      - Name:            test_arg_unknown_builtin_type
-; CHECK-NEXT:   SymbolName:      'test_arg_unknown_builtin_type@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      clk_event_t
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_arg_unknown_builtin_type(
-    ptr addrspace(1) %a) #0
-    !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:      - Name:            test_pointee_align
-; CHECK-NEXT:   SymbolName:      'test_pointee_align@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      'long  addrspace(5)*'
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          b
-; CHECK-NEXT:       TypeName:      'char  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  1
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          c
-; CHECK-NEXT:       TypeName:      'char2  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  2
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          d
-; CHECK-NEXT:       TypeName:      'char3  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  4
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          e
-; CHECK-NEXT:       TypeName:      'char4  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  4
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          f
-; CHECK-NEXT:       TypeName:      'char8  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  8
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          g
-; CHECK-NEXT:       TypeName:      'char16  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  16
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          h
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  1
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_pointee_align(ptr addrspace(1) %a,
-                                              ptr addrspace(3) %b,
-                                              ptr addrspace(3) align 2 %c,
-                                              ptr addrspace(3) align 4 %d,
-                                              ptr addrspace(3) align 4 %e,
-                                              ptr addrspace(3) align 8 %f,
-                                              ptr addrspace(3) align 16 %g,
-                                              ptr addrspace(3) %h) #0
-    !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:      - Name:            test_pointee_align_attribute
-; CHECK-NEXT:   SymbolName:      'test_pointee_align_attribute@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      'long  addrspace(5)*'
-; CHECK-NEXT:       Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          b
-; CHECK-NEXT:       TypeName:      'char  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  8
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          c
-; CHECK-NEXT:       TypeName:      'char2  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  32
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          d
-; CHECK-NEXT:       TypeName:      'char3  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  64
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          e
-; CHECK-NEXT:       TypeName:      'char4  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  256
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          f
-; CHECK-NEXT:       TypeName:      'char8  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  128
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Name:          g
-; CHECK-NEXT:       TypeName:      'char16  addrspace(5)*'
-; CHECK-NEXT:       Size:          4
-; CHECK-NEXT:       Align:         4
-; CHECK-NEXT:       ValueKind:     DynamicSharedPointer
-; CHECK-NEXT:       PointeeAlign:  1024
-; CHECK-NEXT:       AddrSpaceQual: Local
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:      - Name:            h
-; CHECK-NEXT:        Size:            4
-; CHECK-NEXT:        Align:           4
-; CHECK-NEXT:        ValueKind:       DynamicSharedPointer
-; CHECK-NEXT:        PointeeAlign:    16
-; CHECK-NEXT:        AddrSpaceQual:   Local
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_pointee_align_attribute(ptr addrspace(1) align 16 %a,
-                                                        ptr addrspace(3) align 8 %b,
-                                                        ptr addrspace(3) align 32 %c,
-                                                        ptr addrspace(3) align 64 %d,
-                                                        ptr addrspace(3) align 256 %e,
-                                                        ptr addrspace(3) align 128 %f,
-                                                        ptr addrspace(3) align 1024 %g,
-                                                        ptr addrspace(3) align 16 %h) #0
-    !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:      - Name:            __test_block_invoke_kernel
-; CHECK-NEXT:   SymbolName:      '__test_block_invoke_kernel@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Attrs:
-; CHECK-NEXT:       RuntimeHandle: __test_block_invoke_kernel_runtime_handle
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          arg
-; CHECK-NEXT:       TypeName:      __block_literal
-; CHECK-NEXT:       Size:          25
-; CHECK-NEXT:       Align:         1
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenNone
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @__test_block_invoke_kernel(
-    <{ i32, i32, ptr, ptr addrspace(1), i8 }> %arg) #1
-    !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !110
-    !kernel_arg_base_type !110 !kernel_arg_type_qual !4 {
-  ret void
-}
-
-; CHECK:      - Name:            test_enqueue_kernel_caller
-; CHECK-NEXT:   SymbolName:      'test_enqueue_kernel_caller@kd'
-; CHECK-NEXT:   Language:        OpenCL C
-; CHECK-NEXT:   LanguageVersion: [ 2, 0 ]
-; CHECK-NEXT:   Args:
-; CHECK-NEXT:     - Name:          a
-; CHECK-NEXT:       TypeName:      char
-; CHECK-NEXT:       Size:          1
-; CHECK-NEXT:       Align:         1
-; CHECK-NEXT:       ValueKind:     ByValue
-; CHECK-NEXT:       AccQual:       Default
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenPrintfBuffer
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenDefaultQueue
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenCompletionAction
-; CHECK-NEXT:       AddrSpaceQual: Global
-; CHECK-NEXT:     - Size:          8
-; CHECK-NEXT:       Align:         8
-; CHECK-NEXT:       ValueKind:     HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual: Global
-define amdgpu_kernel void @test_enqueue_kernel_caller(i8 %a) #2
-    !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: - Name:            unknown_addrspace_kernarg
-; CHECK: Args:
-; CHECK-NEXT: - Name:            ptr
-; CHECK-NEXT: Size:            8
-; CHECK-NEXT: Align:           8
-; CHECK-NEXT: ValueKind:       GlobalBuffer
-define amdgpu_kernel void @unknown_addrspace_kernarg(ptr addrspace(12345) %ptr) #0 {
-  ret void
-}
-
-attributes #0 = { optnone noinline "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-implicitarg-num-bytes"="56" }
-attributes #1 = { optnone noinline "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-implicitarg-num-bytes"="56" "runtime-handle"="__test_block_invoke_kernel_runtime_handle" }
-attributes #2 = { optnone noinline "amdgpu-implicitarg-num-bytes"="56" "calls-enqueue-kernel" }
-
-!llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
-
-!llvm.printf.fmts = !{!100, !101}
-
-!1 = !{i32 0}
-!2 = !{!"none"}
-!3 = !{!"int"}
-!4 = !{!""}
-!5 = !{i32 undef, i32 1}
-!6 = !{i32 1, i32 2, i32 4}
-!7 = !{<4 x i32> undef, i32 0}
-!8 = !{i32 8, i32 16, i32 32}
-!9 = !{!"char"}
-!10 = !{!"ushort2"}
-!11 = !{!"int3"}
-!12 = !{!"ulong4"}
-!13 = !{!"half8"}
-!14 = !{!"float16"}
-!15 = !{!"double16"}
-!16 = !{!"int  addrspace(5)*"}
-!17 = !{!"image2d_t"}
-!18 = !{!"sampler_t"}
-!19 = !{!"queue_t"}
-!20 = !{!"struct A"}
-!21 = !{!"i128"}
-!22 = !{i32 0, i32 0, i32 0}
-!23 = !{!"none", !"none", !"none"}
-!24 = !{!"int", !"short2", !"char3"}
-!25 = !{!"", !"", !""}
-!26 = !{half undef, i32 1}
-!27 = !{float undef, i32 1}
-!28 = !{double undef, i32 1}
-!29 = !{i8 undef, i32 1}
-!30 = !{i16 undef, i32 1}
-!31 = !{i64 undef, i32 1}
-!32 = !{ptr addrspace(5) undef, i32 1}
-!50 = !{i32 1, i32 2, i32 3}
-!51 = !{!"int  addrspace(5)*", !"int  addrspace(5)*", !"int  addrspace(5)*"}
-!60 = !{i32 1, i32 1, i32 1}
-!61 = !{!"read_only", !"write_only", !"read_write"}
-!62 = !{!"image1d_t", !"image2d_t", !"image3d_t"}
-!70 = !{!"volatile", !"const restrict", !"pipe"}
-!80 = !{!"int  addrspace(5)* addrspace(5)*"}
-!81 = !{i32 1}
-!82 = !{!"struct B"}
-!83 = !{!"global int addrspace(5)* __attribute__((ext_vector_type(2)))"}
-!84 = !{!"clk_event_t"}
-!opencl.ocl.version = !{!90}
-!90 = !{i32 2, i32 0}
-!91 = !{i32 0, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3}
-!92 = !{!"none", !"none", !"none", !"none", !"none", !"none", !"none"}
-!93 = !{!"long  addrspace(5)*", !"char  addrspace(5)*", !"char2  addrspace(5)*", !"char3  addrspace(5)*", !"char4  addrspace(5)*", !"char8  addrspace(5)*", !"char16  addrspace(5)*"}
-!94 = !{!"", !"", !"", !"", !"", !"", !""}
-!100 = !{!"1:1:4:%d\5Cn"}
-!101 = !{!"2:1:8:%g\5Cn"}
-!110 = !{!"__block_literal"}
-!111 = !{!"char", !"char"}
-; PARSER: AMDGPU HSA Metadata Parser Test: PASS

llvm/test/CodeGen/AMDGPU/hsa-metadata-hidden-args.ll

-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefix=CHECK %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefix=CHECK %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefix=CHECK %s
-
-; CHECK: ---
-; CHECK:  Version: [ 1, 0 ]
-; CHECK:  Kernels:
-
-; CHECK:      - Name:       test0
-; CHECK:        SymbolName: 'test0@kd'
-; CHECK:        Args:
-; CHECK-NEXT:     - Name:            r
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            a
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            b
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:   CodeProps:
-define amdgpu_kernel void @test0(
-    ptr addrspace(1) %r,
-    ptr addrspace(1) %a,
-    ptr addrspace(1) %b) {
-entry:
-  %a.val = load half, ptr addrspace(1) %a
-  %b.val = load half, ptr addrspace(1) %b
-  %r.val = fadd half %a.val, %b.val
-  store half %r.val, ptr addrspace(1) %r
-  ret void
-}
-
-; CHECK:      - Name:       test8
-; CHECK:        SymbolName: 'test8@kd'
-; CHECK:        Args:
-; CHECK-NEXT:     - Name:            r
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            a
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            b
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetX
-; CHECK-NEXT:   CodeProps:
-define amdgpu_kernel void @test8(
-    ptr addrspace(1) %r,
-    ptr addrspace(1) %a,
-    ptr addrspace(1) %b) #0 {
-entry:
-  %a.val = load half, ptr addrspace(1) %a
-  %b.val = load half, ptr addrspace(1) %b
-  %r.val = fadd half %a.val, %b.val
-  store half %r.val, ptr addrspace(1) %r
-  ret void
-}
-
-; CHECK:      - Name:       test16
-; CHECK:        SymbolName: 'test16@kd'
-; CHECK:        Args:
-; CHECK-NEXT:     - Name:            r
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            a
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            b
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetY
-; CHECK-NEXT:   CodeProps:
-define amdgpu_kernel void @test16(
-    ptr addrspace(1) %r,
-    ptr addrspace(1) %a,
-    ptr addrspace(1) %b) #1 {
-entry:
-  %a.val = load half, ptr addrspace(1) %a
-  %b.val = load half, ptr addrspace(1) %b
-  %r.val = fadd half %a.val, %b.val
-  store half %r.val, ptr addrspace(1) %r
-  ret void
-}
-
-; CHECK:      - Name:       test24
-; CHECK:        SymbolName: 'test24@kd'
-; CHECK:        Args:
-; CHECK-NEXT:     - Name:            r
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            a
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            b
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetZ
-; CHECK-NEXT:   CodeProps:
-define amdgpu_kernel void @test24(
-    ptr addrspace(1) %r,
-    ptr addrspace(1) %a,
-    ptr addrspace(1) %b) #2 {
-entry:
-  %a.val = load half, ptr addrspace(1) %a
-  %b.val = load half, ptr addrspace(1) %b
-  %r.val = fadd half %a.val, %b.val
-  store half %r.val, ptr addrspace(1) %r
-  ret void
-}
-
-; CHECK:      - Name:       test32
-; CHECK:        SymbolName: 'test32@kd'
-; CHECK:        Args:
-; CHECK-NEXT:     - Name:            r
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            a
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            b
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenHostcallBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:   CodeProps:
-define amdgpu_kernel void @test32(
-    ptr addrspace(1) %r,
-    ptr addrspace(1) %a,
-    ptr addrspace(1) %b) #3 {
-entry:
-  %a.val = load half, ptr addrspace(1) %a
-  %b.val = load half, ptr addrspace(1) %b
-  %r.val = fadd half %a.val, %b.val
-  store half %r.val, ptr addrspace(1) %r
-  ret void
-}
-
-; CHECK:      - Name:       test48
-; CHECK:        SymbolName: 'test48@kd'
-; CHECK:        Args:
-; CHECK-NEXT:     - Name:            r
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            a
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            b
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenHostcallBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenDefaultQueue
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenNone
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:   CodeProps:
-define amdgpu_kernel void @test48(
-    ptr addrspace(1) %r,
-    ptr addrspace(1) %a,
-    ptr addrspace(1) %b) #4 {
-entry:
-  %a.val = load half, ptr addrspace(1) %a
-  %b.val = load half, ptr addrspace(1) %b
-  %r.val = fadd half %a.val, %b.val
-  store half %r.val, ptr addrspace(1) %r
-  ret void
-}
-
-; CHECK:      - Name:       test56
-; CHECK:        SymbolName: 'test56@kd'
-; CHECK:        Args:
-; CHECK-NEXT:     - Name:            r
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            a
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Name:            b
-; CHECK-NEXT:       Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       GlobalBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetX
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetY
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetZ
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenHostcallBuffer
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenDefaultQueue
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenNone
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:     - Size:            8
-; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenMultiGridSyncArg
-; CHECK-NEXT:       AddrSpaceQual:   Global
-; CHECK-NEXT:   CodeProps:
-define amdgpu_kernel void @test56(
-    ptr addrspace(1) %r,
-    ptr addrspace(1) %a,
-    ptr addrspace(1) %b) #5 {
-entry:
-  %a.val = load half, ptr addrspace(1) %a
-  %b.val = load half, ptr addrspace(1) %b
-  %r.val = fadd half %a.val, %b.val
-  store half %r.val, ptr addrspace(1) %r
-  ret void
-}
-
-; We don't have a use of llvm.amdgcn.implicitarg.ptr, so optnone to
-; avoid optimizing out the implicit argument allocation.
-attributes #0 = { optnone noinline "amdgpu-implicitarg-num-bytes"="8" }
-attributes #1 = { optnone noinline "amdgpu-implicitarg-num-bytes"="16" }
-attributes #2 = { optnone noinline "amdgpu-implicitarg-num-bytes"="24" }
-attributes #3 = { optnone noinline "amdgpu-implicitarg-num-bytes"="32" }
-attributes #4 = { optnone noinline "amdgpu-implicitarg-num-bytes"="48" }
-attributes #5 = { optnone noinline "amdgpu-implicitarg-num-bytes"="56" }
-
-!llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}

llvm/test/CodeGen/AMDGPU/hsa-metadata-images.ll

-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefix=CHECK %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx802 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefix=CHECK %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefix=CHECK %s
-
-%opencl.image1d_t = type opaque
-%opencl.image1d_array_t = type opaque
-%opencl.image1d_buffer_t = type opaque
-%opencl.image2d_t = type opaque
-%opencl.image2d_array_t = type opaque
-%opencl.image2d_array_depth_t = type opaque
-%opencl.image2d_array_msaa_t = type opaque
-%opencl.image2d_array_msaa_depth_t = type opaque
-%opencl.image2d_depth_t = type opaque
-%opencl.image2d_msaa_t = type opaque
-%opencl.image2d_msaa_depth_t = type opaque
-%opencl.image3d_t = type opaque
-
-; CHECK: ---
-; CHECK:  Version: [ 1, 0 ]
-
-; CHECK:  Kernels:
-; CHECK:    - Name:       test
-; CHECK:      SymbolName: 'test@kd'
-; CHECK:      Args:
-; CHECK:        - Name:      a
-; CHECK:          TypeName:  image1d_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-; CHECK:        - Name:      b
-; CHECK:          TypeName:  image1d_array_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-; CHECK:        - Name:      c
-; CHECK:          TypeName:  image1d_buffer_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-; CHECK:        - Name:      d
-; CHECK:          TypeName:  image2d_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-; CHECK:        - Name:      e
-; CHECK:          TypeName:  image2d_array_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-; CHECK:        - Name:      f
-; CHECK:          TypeName:  image2d_array_depth_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-; CHECK:        - Name:      g
-; CHECK:          TypeName:  image2d_array_msaa_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-; CHECK:        - Name:      h
-; CHECK:          TypeName:  image2d_array_msaa_depth_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-; CHECK:        - Name:      i
-; CHECK:          TypeName:  image2d_depth_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-; CHECK:        - Name:      j
-; CHECK:          TypeName:  image2d_msaa_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-; CHECK:        - Name:      k
-; CHECK:          TypeName:  image2d_msaa_depth_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-; CHECK:        - Name:      l
-; CHECK:          TypeName:  image3d_t
-; CHECK:          Size:      8
-; CHECK:          ValueKind: Image
-define amdgpu_kernel void @test(ptr addrspace(1) %a,
-                                ptr addrspace(1) %b,
-                                ptr addrspace(1) %c,
-                                ptr addrspace(1) %d,
-                                ptr addrspace(1) %e,
-                                ptr addrspace(1) %f,
-                                ptr addrspace(1) %g,
-                                ptr addrspace(1) %h,
-                                ptr addrspace(1) %i,
-                                ptr addrspace(1) %j,
-                                ptr addrspace(1) %k,
-                                ptr addrspace(1) %l)
-    !kernel_arg_type !1 !kernel_arg_base_type !1 {
-  ret void
-}
-
-!llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
-!1 = !{!"image1d_t", !"image1d_array_t", !"image1d_buffer_t",
-       !"image2d_t", !"image2d_array_t", !"image2d_array_depth_t",
-       !"image2d_array_msaa_t", !"image2d_array_msaa_depth_t",
-       !"image2d_depth_t", !"image2d_msaa_t", !"image2d_msaa_depth_t",
-       !"image3d_t"}

llvm/test/CodeGen/AMDGPU/hsa-metadata-invalid-ocl-version-1.ll

-; RUN: llc -mtriple=amdgcn-amd-amdhsa -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s
-
-; Make sure llc does not crash for invalid opencl version metadata.
-
-; CHECK: ---
-; CHECK: Version: [ 1, 0 ]
-; CHECK: ...
-
-!opencl.ocl.version = !{}
-!llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}

llvm/test/CodeGen/AMDGPU/hsa-metadata-invalid-ocl-version-2-v3.ll

-; RUN: llc -mtriple=amdgcn-amd-amdhsa -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s
-
-; Make sure llc does not crash for invalid opencl version metadata.
-
-; CHECK: ---
-; CHECK: amdhsa.version:
-; CHECK-NEXT: - 1
-; CHECK-NEXT: - 0
-; CHECK: ...
-
-!opencl.ocl.version = !{!0}
-!llvm.module.flags = !{!1}
-!0 = !{}
-!1 = !{i32 1, !"amdgpu_code_object_version", i32 300}

llvm/test/CodeGen/AMDGPU/hsa-metadata-invalid-ocl-version-2.ll

-; RUN: llc -mtriple=amdgcn-amd-amdhsa -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s
-
-; Make sure llc does not crash for invalid opencl version metadata.
-
-; CHECK: ---
-; CHECK: Version: [ 1, 0 ]
-; CHECK: ...
-
-!opencl.ocl.version = !{!0}
-!llvm.module.flags = !{!1}
-!0 = !{}
-!1 = !{i32 1, !"amdgpu_code_object_version", i32 200}

llvm/test/CodeGen/AMDGPU/hsa-metadata-invalid-ocl-version-3.ll

-; RUN: llc -mtriple=amdgcn-amd-amdhsa -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck %s
-
-; Make sure llc does not crash for invalid opencl version metadata.
-
-; CHECK: ---
-; CHECK: Version: [ 1, 0 ]
-; CHECK: ...
-
-!opencl.ocl.version = !{!0}
-!llvm.module.flags = !{!1}
-!0 = !{i32 1}
-!1 = !{i32 1, !"amdgpu_code_object_version", i32 200}

llvm/test/CodeGen/AMDGPU/hsa-metadata-kernel-code-props.ll

-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -enable-misched=0 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefixes=CHECK,GFX700 %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -mattr=-xnack -enable-misched=0 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefixes=CHECK,GFX803 %s
-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-xnack -enable-misched=0 -filetype=obj -o - < %s | llvm-readelf --notes - | FileCheck --check-prefixes=CHECK,GFX900 %s
-
-@var = addrspace(1) global float 0.0
-
-; CHECK: ---
-; CHECK:  Version: [ 1, 0 ]
-; CHECK:  Kernels:
-
-; CHECK-LABEL: - Name:       test
-; CHECK:   SymbolName: 'test@kd'
-; CHECK:   CodeProps:
-; CHECK:     KernargSegmentSize:      24
-; CHECK:     GroupSegmentFixedSize:   0
-; CHECK:     PrivateSegmentFixedSize: 0
-; CHECK:     KernargSegmentAlign:     8
-; CHECK:     WavefrontSize:           64
-; CHECK:     NumSGPRs:                6
-; CHECK:     NumVGPRs:                {{3|6}}
-; CHECK:     MaxFlatWorkGroupSize:    1024
-define amdgpu_kernel void @test(
-    ptr addrspace(1) %r,
-    ptr addrspace(1) %a,
-    ptr addrspace(1) %b) {
-entry:
-  %a.val = load half, ptr addrspace(1) %a
-  %b.val = load half, ptr addrspace(1) %b
-  %r.val = fadd half %a.val, %b.val
-  store half %r.val, ptr addrspace(1) %r
-  ret void
-}
-
-; CHECK-LABEL: - Name:       test_max_flat_workgroup_size
-; CHECK:   SymbolName: 'test_max_flat_workgroup_size@kd'
-; CHECK:   CodeProps:
-; CHECK:     KernargSegmentSize:      24
-; CHECK:     GroupSegmentFixedSize:   0
-; CHECK:     PrivateSegmentFixedSize: 0
-; CHECK:     KernargSegmentAlign:     8
-; CHECK:     WavefrontSize:           64
-; CHECK:     NumSGPRs:                6
-; CHECK:     NumVGPRs:                {{3|6}}
-; CHECK:     MaxFlatWorkGroupSize:    256
-define amdgpu_kernel void @test_max_flat_workgroup_size(
-    ptr addrspace(1) %r,
-    ptr addrspace(1) %a,
-    ptr addrspace(1) %b) #2 {
-entry:
-  %a.val = load half, ptr addrspace(1) %a
-  %b.val = load half, ptr addrspace(1) %b
-  %r.val = fadd half %a.val, %b.val
-  store half %r.val, ptr addrspace(1) %r
-  ret void
-}
-
-; CHECK-LABEL: - Name:       num_spilled_sgprs
-; CHECK:   SymbolName: 'num_spilled_sgprs@kd'
-; CHECK:   CodeProps:
-; GFX700:     NumSpilledSGPRs: 38
-; GFX803:     NumSpilledSGPRs: 22
-; GFX900:     NumSpilledSGPRs: {{22|48}}
-define amdgpu_kernel void @num_spilled_sgprs(
-    ptr addrspace(1) %out0, ptr addrspace(1) %out1, [8 x i32],
-    ptr addrspace(1) %out2, ptr addrspace(1) %out3, [8 x i32],
-    ptr addrspace(1) %out4, ptr addrspace(1) %out5, [8 x i32],
-    ptr addrspace(1) %out6, ptr addrspace(1) %out7, [8 x i32],
-    ptr addrspace(1) %out8, ptr addrspace(1) %out9, [8 x i32],
-    ptr addrspace(1) %outa, ptr addrspace(1) %outb, [8 x i32],
-    ptr addrspace(1) %outc, ptr addrspace(1) %outd, [8 x i32],
-    ptr addrspace(1) %oute, ptr addrspace(1) %outf, [8 x i32],
-    i32 %in0, i32 %in1, i32 %in2, i32 %in3, [8 x i32],
-    i32 %in4, i32 %in5, i32 %in6, i32 %in7, [8 x i32],
-    i32 %in8, i32 %in9, i32 %ina, i32 %inb, [8 x i32],
-    i32 %inc, i32 %ind, i32 %ine, i32 %inf) #0 {
-entry:
-  store i32 %in0, ptr addrspace(1) %out0
-  store i32 %in1, ptr addrspace(1) %out1
-  store i32 %in2, ptr addrspace(1) %out2
-  store i32 %in3, ptr addrspace(1) %out3
-  store i32 %in4, ptr addrspace(1) %out4
-  store i32 %in5, ptr addrspace(1) %out5
-  store i32 %in6, ptr addrspace(1) %out6
-  store i32 %in7, ptr addrspace(1) %out7
-  store i32 %in8, ptr addrspace(1) %out8
-  store i32 %in9, ptr addrspace(1) %out9
-  store i32 %ina, ptr addrspace(1) %outa
-  store i32 %inb, ptr addrspace(1) %outb
-  store i32 %inc, ptr addrspace(1) %outc
-  store i32 %ind, ptr addrspace(1) %outd
-  store i32 %ine, ptr addrspace(1) %oute
-  store i32 %inf, ptr addrspace(1) %outf
-  ret void
-}
-
-; CHECK-LABEL: - Name:       num_spilled_vgprs
-; CHECK:   SymbolName: 'num_spilled_vgprs@kd'
-; CHECK:   CodeProps:
-; CHECK:     NumSpilledVGPRs: {{13|14}}
-define amdgpu_kernel void @num_spilled_vgprs() #1 {
-  %val0 = load volatile float, ptr addrspace(1) @var
-  %val1 = load volatile float, ptr addrspace(1) @var
-  %val2 = load volatile float, ptr addrspace(1) @var
-  %val3 = load volatile float, ptr addrspace(1) @var
-  %val4 = load volatile float, ptr addrspace(1) @var
-  %val5 = load volatile float, ptr addrspace(1) @var
-  %val6 = load volatile float, ptr addrspace(1) @var
-  %val7 = load volatile float, ptr addrspace(1) @var
-  %val8 = load volatile float, ptr addrspace(1) @var
-  %val9 = load volatile float, ptr addrspace(1) @var
-  %val10 = load volatile float, ptr addrspace(1) @var
-  %val11 = load volatile float, ptr addrspace(1) @var
-  %val12 = load volatile float, ptr addrspace(1) @var
-  %val13 = load volatile float, ptr addrspace(1) @var
-  %val14 = load volatile float, ptr addrspace(1) @var
-  %val15 = load volatile float, ptr addrspace(1) @var
-  %val16 = load volatile float, ptr addrspace(1) @var
-  %val17 = load volatile float, ptr addrspace(1) @var
-  %val18 = load volatile float, ptr addrspace(1) @var
-  %val19 = load volatile float, ptr addrspace(1) @var
-  %val20 = load volatile float, ptr addrspace(1) @var
-  %val21 = load volatile float, ptr addrspace(1) @var
-  %val22 = load volatile float, ptr addrspace(1) @var
-  %val23 = load volatile float, ptr addrspace(1) @var
-  %val24 = load volatile float, ptr addrspace(1) @var
-  %val25 = load volatile float, ptr addrspace(1) @var
-  %val26 = load volatile float, ptr addrspace(1) @var
-  %val27 = load volatile float, ptr addrspace(1) @var
-  %val28 = load volatile float, ptr addrspace(1) @var
-  %val29 = load volatile float, ptr addrspace(1) @var
-  %val30 = load volatile float, ptr addrspace(1) @var
-
-  store volatile float %val0, ptr addrspace(1) @var
-  store volatile float %val1, ptr addrspace(1) @var
-  store volatile float %val2, ptr addrspace(1) @var
-  store volatile float %val3, ptr addrspace(1) @var
-  store volatile float %val4, ptr addrspace(1) @var
-  store volatile float %val5, ptr addrspace(1) @var
-  store volatile float %val6, ptr addrspace(1) @var
-  store volatile float %val7, ptr addrspace(1) @var
-  store volatile float %val8, ptr addrspace(1) @var
-  store volatile float %val9, ptr addrspace(1) @var
-  store volatile float %val10, ptr addrspace(1) @var
-  store volatile float %val11, ptr addrspace(1) @var
-  store volatile float %val12, ptr addrspace(1) @var
-  store volatile float %val13, ptr addrspace(1) @var
-  store volatile float %val14, ptr addrspace(1) @var
-  store volatile float %val15, ptr addrspace(1) @var
-  store volatile float %val16, ptr addrspace(1) @var
-  store volatile float %val17, ptr addrspace(1) @var
-  store volatile float %val18, ptr addrspace(1) @var
-  store volatile float %val19, ptr addrspace(1) @var
-  store volatile float %val20, ptr addrspace(1) @var
-  store volatile float %val21, ptr addrspace(1) @var
-  store volatile float %val22, ptr addrspace(1) @var
-  store volatile float %val23, ptr addrspace(1) @var
-  store volatile float %val24, ptr addrspace(1) @var
-  store volatile float %val25, ptr addrspace(1) @var
-  store volatile float %val26, ptr addrspace(1) @var
-  store volatile float %val27, ptr addrspace(1) @var
-  store volatile float %val28, ptr addrspace(1) @var
-  store volatile float %val29, ptr addrspace(1) @var
-  store volatile float %val30, ptr addrspace(1) @var
-
-  ret void
-}
-
-attributes #0 = { "amdgpu-num-sgpr"="14" }
-attributes #1 = { "amdgpu-num-vgpr"="20" }
-attributes #2 = { "amdgpu-flat-work-group-size"="1,256" }
-
-!llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}

llvm/test/CodeGen/AMDGPU/hsa-note-no-func.ll

 ; RUN: llc < %s -mtriple=amdgcn-- -mcpu=gfx600 | FileCheck --check-prefixes=NONHSA-SI600 %s
 ; RUN: llc < %s -mtriple=amdgcn-- -mcpu=gfx601 | FileCheck --check-prefixes=NONHSA-SI601 %s
 ; RUN: llc < %s -mtriple=amdgcn-- -mcpu=gfx602 | FileCheck --check-prefixes=NONHSA-SI602 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx700 | FileCheck --check-prefixes=HSA,HSA-CI700 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri | FileCheck --check-prefixes=HSA,HSA-CI700 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx701 | FileCheck --check-prefixes=HSA,HSA-CI701 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=hawaii | FileCheck --check-prefixes=HSA,HSA-CI701 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx702 | FileCheck --check-prefixes=HSA,HSA-CI702 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx703 | FileCheck --check-prefixes=HSA,HSA-CI703 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kabini | FileCheck --check-prefixes=HSA,HSA-CI703 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=mullins | FileCheck --check-prefixes=HSA,HSA-CI703 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx704 | FileCheck --check-prefixes=HSA,HSA-CI704 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=bonaire | FileCheck --check-prefixes=HSA,HSA-CI704 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx705 | FileCheck --check-prefixes=HSA,HSA-CI705 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx801 | FileCheck --check-prefixes=HSA,HSA-VI801 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=carrizo -mattr=-flat-for-global | FileCheck --check-prefixes=HSA,HSA-VI801 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx802 | FileCheck --check-prefixes=HSA,HSA-VI802 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=iceland -mattr=-flat-for-global | FileCheck --check-prefixes=HSA,HSA-VI802 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=tonga -mattr=-flat-for-global | FileCheck --check-prefixes=HSA,HSA-VI802 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx803 | FileCheck --check-prefixes=HSA,HSA-VI803 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=-flat-for-global | FileCheck --check-prefixes=HSA,HSA-VI803 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=polaris10 | FileCheck --check-prefixes=HSA,HSA-VI803 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=polaris11 | FileCheck --check-prefixes=HSA,HSA-VI803 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx805 | FileCheck --check-prefixes=HSA,HSA-VI805 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=tongapro | FileCheck --check-prefixes=HSA,HSA-VI805 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx810 | FileCheck --check-prefixes=HSA,HSA-VI810 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=stoney | FileCheck --check-prefixes=HSA,HSA-VI810 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx900 -mattr=-xnack | FileCheck --check-prefixes=HSA,HSA-GFX900 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx900 | FileCheck --check-prefixes=HSA,HSA-GFX901 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx902 -mattr=-xnack | FileCheck --check-prefixes=HSA,HSA-GFX902 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx902 | FileCheck --check-prefixes=HSA,HSA-GFX903 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx904 -mattr=-xnack | FileCheck --check-prefixes=HSA,HSA-GFX904 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx904 | FileCheck --check-prefixes=HSA,HSA-GFX905 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx906 -mattr=-xnack | FileCheck --check-prefixes=HSA,HSA-GFX906 %s
-; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx906 | FileCheck --check-prefixes=HSA,HSA-GFX907 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx700 | FileCheck --check-prefix=HSA-CI700 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri | FileCheck --check-prefix=HSA-CI700 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx701 | FileCheck --check-prefix=HSA-CI701 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=hawaii | FileCheck --check-prefix=HSA-CI701 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx702 | FileCheck --check-prefix=HSA-CI702 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx703 | FileCheck --check-prefix=HSA-CI703 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kabini | FileCheck --check-prefix=HSA-CI703 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=mullins | FileCheck --check-prefix=HSA-CI703 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx704 | FileCheck --check-prefix=HSA-CI704 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=bonaire | FileCheck --check-prefix=HSA-CI704 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx705 | FileCheck --check-prefix=HSA-CI705 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx801 | FileCheck --check-prefix=HSA-VI801 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=carrizo -mattr=-flat-for-global | FileCheck --check-prefix=HSA-VI801 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx802 | FileCheck --check-prefix=HSA-VI802 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=iceland -mattr=-flat-for-global | FileCheck --check-prefix=HSA-VI802 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=tonga -mattr=-flat-for-global | FileCheck --check-prefix=HSA-VI802 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx803 | FileCheck --check-prefix=HSA-VI803 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=fiji -mattr=-flat-for-global | FileCheck --check-prefix=HSA-VI803 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=polaris10 | FileCheck --check-prefix=HSA-VI803 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=polaris11 | FileCheck --check-prefix=HSA-VI803 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx805 | FileCheck --check-prefix=HSA-VI805 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=tongapro | FileCheck --check-prefix=HSA-VI805 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx810 | FileCheck --check-prefix=HSA-VI810 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=stoney | FileCheck --check-prefix=HSA-VI810 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx900 -mattr=-xnack | FileCheck --check-prefix=HSA-GFX900 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx900 | FileCheck --check-prefix=HSA-GFX901 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx902 -mattr=-xnack | FileCheck --check-prefix=HSA-GFX902 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx902 | FileCheck --check-prefix=HSA-GFX903 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx904 -mattr=-xnack | FileCheck --check-prefix=HSA-GFX904 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx904 | FileCheck --check-prefix=HSA-GFX905 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx906 -mattr=-xnack | FileCheck --check-prefix=HSA-GFX906 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx906 | FileCheck --check-prefix=HSA-GFX907 %s
 
-; HSA: .hsa_code_object_version 2,1
 ; NONHSA-SI600: .amd_amdgpu_isa "amdgcn-unknown-unknown--gfx600"
 ; NONHSA-SI601: .amd_amdgpu_isa "amdgcn-unknown-unknown--gfx601"
 ; NONHSA-SI602: .amd_amdgpu_isa "amdgcn-unknown-unknown--gfx602"
-; HSA-CI700: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-; HSA-CI701: .hsa_code_object_isa 7,0,1,"AMD","AMDGPU"
-; HSA-CI702: .hsa_code_object_isa 7,0,2,"AMD","AMDGPU"
-; HSA-CI703: .hsa_code_object_isa 7,0,3,"AMD","AMDGPU"
-; HSA-CI704: .hsa_code_object_isa 7,0,4,"AMD","AMDGPU"
-; HSA-CI705: .hsa_code_object_isa 7,0,5,"AMD","AMDGPU"
-; HSA-VI801: .hsa_code_object_isa 8,0,1,"AMD","AMDGPU"
-; HSA-VI802: .hsa_code_object_isa 8,0,2,"AMD","AMDGPU"
-; HSA-VI803: .hsa_code_object_isa 8,0,3,"AMD","AMDGPU"
-; HSA-VI805: .hsa_code_object_isa 8,0,5,"AMD","AMDGPU"
-; HSA-VI810: .hsa_code_object_isa 8,1,0,"AMD","AMDGPU"
-; HSA-GFX900: .hsa_code_object_isa 9,0,0,"AMD","AMDGPU"
-; HSA-GFX901: .hsa_code_object_isa 9,0,1,"AMD","AMDGPU"
-; HSA-GFX902: .hsa_code_object_isa 9,0,2,"AMD","AMDGPU"
-; HSA-GFX903: .hsa_code_object_isa 9,0,3,"AMD","AMDGPU"
-; HSA-GFX904: .hsa_code_object_isa 9,0,4,"AMD","AMDGPU"
-; HSA-GFX905: .hsa_code_object_isa 9,0,5,"AMD","AMDGPU"
-; HSA-GFX906: .hsa_code_object_isa 9,0,6,"AMD","AMDGPU"
-; HSA-GFX907: .hsa_code_object_isa 9,0,7,"AMD","AMDGPU"
+; HSA-CI700: .amdgcn_target "amdgcn-unknown-amdhsa--gfx700"
+; HSA-CI701: .amdgcn_target "amdgcn-unknown-amdhsa--gfx701"
+; HSA-CI702: .amdgcn_target "amdgcn-unknown-amdhsa--gfx702"
+; HSA-CI703: .amdgcn_target "amdgcn-unknown-amdhsa--gfx703"
+; HSA-CI704: .amdgcn_target "amdgcn-unknown-amdhsa--gfx704"
+; HSA-CI705: .amdgcn_target "amdgcn-unknown-amdhsa--gfx705"
+; HSA-VI801: .amdgcn_target "amdgcn-unknown-amdhsa--gfx801"
+; HSA-VI802: .amdgcn_target "amdgcn-unknown-amdhsa--gfx802"
+; HSA-VI803: .amdgcn_target "amdgcn-unknown-amdhsa--gfx803"
+; HSA-VI805: .amdgcn_target "amdgcn-unknown-amdhsa--gfx805"
+; HSA-VI810: .amdgcn_target "amdgcn-unknown-amdhsa--gfx810"
+; HSA-GFX900: .amdgcn_target "amdgcn-unknown-amdhsa--gfx900:xnack-"
+; HSA-GFX901: .amdgcn_target "amdgcn-unknown-amdhsa--gfx900"
+; HSA-GFX902: .amdgcn_target "amdgcn-unknown-amdhsa--gfx902:xnack-"
+; HSA-GFX903: .amdgcn_target "amdgcn-unknown-amdhsa--gfx902"
+; HSA-GFX904: .amdgcn_target "amdgcn-unknown-amdhsa--gfx904:xnack-"
+; HSA-GFX905: .amdgcn_target "amdgcn-unknown-amdhsa--gfx904"
+; HSA-GFX906: .amdgcn_target "amdgcn-unknown-amdhsa--gfx906:xnack-"
+; HSA-GFX907: .amdgcn_target "amdgcn-unknown-amdhsa--gfx906"
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/hsa.ll

 
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=kaveri --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=HSA %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-flat-for-global --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=HSA-CI %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=carrizo --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=HSA %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=carrizo -mattr=-flat-for-global --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=HSA-VI %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -filetype=obj --amdgpu-lower-module-lds-strategy=module | llvm-readobj -S --sd --syms - | FileCheck --check-prefix=ELF %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=kaveri --amdgpu-lower-module-lds-strategy=module | llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=2 | llvm-readobj -S --sd --syms - | FileCheck %s --check-prefix=ELF
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=GFX10 --check-prefix=GFX10-W32 %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=GFX10 --check-prefix=GFX10-W64 %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=gfx1100 -mattr=+wavefrontsize32,-wavefrontsize64 --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=GFX10 --check-prefix=GFX10-W32 %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn--amdhsa -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=GFX10 --check-prefix=GFX10-W64 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=HSA %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri -mattr=-flat-for-global --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=HSA-CI %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=carrizo --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=HSA %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=carrizo -mattr=-flat-for-global --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=HSA-VI %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri -filetype=obj --amdgpu-lower-module-lds-strategy=module | llvm-readobj -S --sd --syms - | FileCheck --check-prefix=ELF %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=kaveri --amdgpu-lower-module-lds-strategy=module | llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=4 | llvm-readobj -S --sd --syms - | FileCheck %s --check-prefix=ELF
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -mattr=+wavefrontsize32,-wavefrontsize64 --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=GFX10 --check-prefix=GFX10-W32 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx1010 -mattr=-wavefrontsize32,+wavefrontsize64 --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=GFX10 --check-prefix=GFX10-W64 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx1100 -mattr=+wavefrontsize32,-wavefrontsize64 --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=GFX10 --check-prefix=GFX10-W32 %s
+; RUN: llc < %s -mtriple=amdgcn--amdhsa -mcpu=gfx1100 -mattr=-wavefrontsize32,+wavefrontsize64 --amdgpu-lower-module-lds-strategy=module | FileCheck --check-prefix=GFX10 --check-prefix=GFX10-W64 %s
 
 ; The SHT_NOTE section contains the output from the .hsa_code_object_*
 ; directives.
 
 ; ELF: Section {
 ; ELF: Name: .text
 ; ELF: Type: SHT_PROGBITS (0x1)
 ; ELF: Flags [ (0x6)
 ; ELF: SHF_ALLOC (0x2)
 ; ELF: SHF_EXECINSTR (0x4)
 ; ELF: }
 
 ; ELF: SHT_NOTE
 ; ELF: Flags [ (0x2)
 ; ELF: SHF_ALLOC (0x2)
 ; ELF: ]
 ; ELF: SectionData (
-; ELF: 0000: 04000000 08000000 01000000 414D4400
-; ELF: 0010: 02000000 01000000 04000000 1B000000
-; ELF: 0020: 03000000 414D4400 04000700 07000000
-; ELF: 0030: 00000000 00000000 414D4400 414D4447
-; ELF: 0040: 50550000
+; ELF:   0000: 07000000 A8020000 20000000 414D4447
+; ELF:   0010: 50550000 83AE616D 64687361 2E6B6572
+; ELF:   0020: 6E656C73 928DA52E 61726773 9185AE2E
+; ELF:   0030: 61646472 6573735F 73706163 65A6676C
+; ELF:   0040: 6F62616C A52E6E61 6D65A36F 7574A72E
+; ELF:   0050: 6F666673 657400A5 2E73697A 6508AB2E
+; ELF:   0060: 76616C75 655F6B69 6E64AD67 6C6F6261
+; ELF:   0070: 6C5F6275 66666572 B92E6772 6F75705F
+; ELF:   0080: 7365676D 656E745F 66697865 645F7369
+; ELF:   0090: 7A6500B6 2E6B6572 6E617267 5F736567
+; ELF:   00A0: 6D656E74 5F616C69 676E08B5 2E6B6572
+; ELF:   00B0: 6E617267 5F736567 6D656E74 5F73697A
+; ELF:   00C0: 6508B82E 6D61785F 666C6174 5F776F72
+; ELF:   00D0: 6B67726F 75705F73 697A65CD 0400A52E
+; ELF:   00E0: 6E616D65 A673696D 706C65BB 2E707269
+; ELF:   00F0: 76617465 5F736567 6D656E74 5F666978
+; ELF:   0100: 65645F73 697A6500 AB2E7367 70725F63
+; ELF:   0110: 6F756E74 06B12E73 6770725F 7370696C
+; ELF:   0120: 6C5F636F 756E7400 A72E7379 6D626F6C
+; ELF:   0130: A973696D 706C652E 6B64AB2E 76677072
+; ELF:   0140: 5F636F75 6E7403B1 2E766770 725F7370
+; ELF:   0150: 696C6C5F 636F756E 7400AF2E 77617665
+; ELF:   0160: 66726F6E 745F7369 7A65408D A52E6172
+; ELF:   0170: 677390B9 2E67726F 75705F73 65676D65
+; ELF:   0180: 6E745F66 69786564 5F73697A 6500B62E
+; ELF:   0190: 6B65726E 6172675F 7365676D 656E745F
+; ELF:   01A0: 616C6967 6E04B52E 6B65726E 6172675F
+; ELF:   01B0: 7365676D 656E745F 73697A65 00B82E6D
+; ELF:   01C0: 61785F66 6C61745F 776F726B 67726F75
+; ELF:   01D0: 705F7369 7A65CD04 00A52E6E 616D65B2
+; ELF:   01E0: 73696D70 6C655F6E 6F5F6B65 726E6172
+; ELF:   01F0: 6773BB2E 70726976 6174655F 7365676D
+; ELF:   0200: 656E745F 66697865 645F7369 7A6500AB
+; ELF:   0210: 2E736770 725F636F 756E7400 B12E7367
+; ELF:   0220: 70725F73 70696C6C 5F636F75 6E7400A7
+; ELF:   0230: 2E73796D 626F6CB5 73696D70 6C655F6E
+; ELF:   0240: 6F5F6B65 726E6172 67732E6B 64AB2E76
+; ELF:   0250: 6770725F 636F756E 7402B12E 76677072
+; ELF:   0260: 5F737069 6C6C5F63 6F756E74 00AF2E77
+; ELF:   0270: 61766566 726F6E74 5F73697A 6540AD61
+; ELF:   0280: 6D646873 612E7461 72676574 BD616D64
+; ELF:   0290: 67636E2D 756E6B6E 6F776E2D 616D6468
+; ELF:   02A0: 73612D2D 67667837 3030AE61 6D646873
+; ELF:   02B0: 612E7665 7273696F 6E920101
 ; ELF: )
 
 ; ELF: Symbol {
 ; ELF: Name: simple
-; ELF: Size: 288
-; ELF: Type: AMDGPU_HSA_KERNEL (0xA)
+; ELF: Size: 32
 ; ELF: }
 
 ; HSA-NOT: .AMDGPU.config
 ; HSA: .text
-; HSA: .hsa_code_object_version 2,1
-; HSA-CI: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-; HSA-VI: .hsa_code_object_isa 8,0,1,"AMD","AMDGPU"
-
-; HSA-LABEL: .amdgpu_hsa_kernel simple
-; HSA: {{^}}simple:
-; HSA: .amd_kernel_code_t
-; HSA: enable_sgpr_private_segment_buffer = 1
-; HSA: enable_sgpr_kernarg_segment_ptr = 1
+; HSA-CI: .amdgcn_target "amdgcn-unknown-amdhsa--gfx700"
+; HSA-VI: .amdgcn_target "amdgcn-unknown-amdhsa--gfx801"
 
-; PRE-GFX10: enable_wavefront_size32 = 0
-; GFX10-W32: .amdhsa_wavefront_size32 1
-; GFX10-W64: .amdhsa_wavefront_size32 0
+; HSA-LABEL: {{^}}simple:
 
 ; PRE-GFX10: wavefront_size = 6
 
-; HSA: call_convention = -1
-; HSA: .end_amd_kernel_code_t
 ; HSA: s_load_{{dwordx2|b64}} s[{{[0-9]+:[0-9]+}}], s[4:5], 0x0
 
 ; Make sure we are setting the ATC bit:
 ; HSA-CI: s_mov_b32 s[[HI:[0-9]]], 0x100f000
 ; On VI+ we also need to set MTYPE = 2
 ; HSA-VI: s_mov_b32 s[[HI:[0-9]]], 0x1100f000
 ; Make sure we generate flat store for HSA
 ; PRE-GFX10: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}
 ; GFX10: global_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, off
 
+; HSA: .amdhsa_user_sgpr_private_segment_buffer 1
+; HSA: .amdhsa_user_sgpr_kernarg_segment_ptr 1
+
+; PRE-GFX10-NOT: .amdhsa_wavefront_size32
+; GFX10-W32: .amdhsa_wavefront_size32 1
+; GFX10-W64: .amdhsa_wavefront_size32 0
+
 ; HSA: .Lfunc_end0:
 ; HSA: .size   simple, .Lfunc_end0-simple
 
 define amdgpu_kernel void @simple(ptr addrspace(1) %out) {
 entry:
   store i32 0, ptr addrspace(1) %out
   ret void
 }
 
-; HSA-LABEL: .amdgpu_hsa_kernel simple_no_kernargs
-; HSA: enable_sgpr_kernarg_segment_ptr = 0
+; HSA-LABEL: {{^}}simple_no_kernargs:
+; HSA: .amdhsa_user_sgpr_kernarg_segment_ptr 0
 define amdgpu_kernel void @simple_no_kernargs() {
 entry:
   store volatile i32 0, ptr addrspace(1) undef
   ret void
 }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 CODE_OBJECT_VERSION}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/indirect-call.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 ; RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs -global-isel < %s | FileCheck -check-prefix=GISEL %s
 
 @gv.fptr0 = external hidden unnamed_addr addrspace(4) constant ptr, align 4
 @gv.fptr1 = external hidden unnamed_addr addrspace(4) constant ptr, align 4
 
 define amdgpu_kernel void @test_indirect_call_sgpr_ptr(i8) {
 ; GCN-LABEL: test_indirect_call_sgpr_ptr:
-; GCN:         .amd_kernel_code_t
-; GCN-NEXT:     amd_code_version_major = 1
-; GCN-NEXT:     amd_code_version_minor = 2
-; GCN-NEXT:     amd_machine_kind = 1
-; GCN-NEXT:     amd_machine_version_major = 7
-; GCN-NEXT:     amd_machine_version_minor = 0
-; GCN-NEXT:     amd_machine_version_stepping = 0
-; GCN-NEXT:     kernel_code_entry_byte_offset = 256
-; GCN-NEXT:     kernel_code_prefetch_byte_size = 0
-; GCN-NEXT:     granulated_workitem_vgpr_count = 10
-; GCN-NEXT:     granulated_wavefront_sgpr_count = 8
-; GCN-NEXT:     priority = 0
-; GCN-NEXT:     float_mode = 240
-; GCN-NEXT:     priv = 0
-; GCN-NEXT:     enable_dx10_clamp = 1
-; GCN-NEXT:     debug_mode = 0
-; GCN-NEXT:     enable_ieee_mode = 1
-; GCN-NEXT:     enable_wgp_mode = 0
-; GCN-NEXT:     enable_mem_ordered = 0
-; GCN-NEXT:     enable_fwd_progress = 0
-; GCN-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 1
-; GCN-NEXT:     user_sgpr_count = 14
-; GCN-NEXT:     enable_trap_handler = 0
-; GCN-NEXT:     enable_sgpr_workgroup_id_x = 1
-; GCN-NEXT:     enable_sgpr_workgroup_id_y = 1
-; GCN-NEXT:     enable_sgpr_workgroup_id_z = 1
-; GCN-NEXT:     enable_sgpr_workgroup_info = 0
-; GCN-NEXT:     enable_vgpr_workitem_id = 2
-; GCN-NEXT:     enable_exception_msb = 0
-; GCN-NEXT:     granulated_lds_size = 0
-; GCN-NEXT:     enable_exception = 0
-; GCN-NEXT:     enable_sgpr_private_segment_buffer = 1
-; GCN-NEXT:     enable_sgpr_dispatch_ptr = 1
-; GCN-NEXT:     enable_sgpr_queue_ptr = 1
-; GCN-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; GCN-NEXT:     enable_sgpr_dispatch_id = 1
-; GCN-NEXT:     enable_sgpr_flat_scratch_init = 1
-; GCN-NEXT:     enable_sgpr_private_segment_size = 0
-; GCN-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; GCN-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; GCN-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; GCN-NEXT:     enable_wavefront_size32 = 0
-; GCN-NEXT:     enable_ordered_append_gds = 0
-; GCN-NEXT:     private_element_size = 1
-; GCN-NEXT:     is_ptr64 = 1
-; GCN-NEXT:     is_dynamic_callstack = 1
-; GCN-NEXT:     is_debug_enabled = 0
-; GCN-NEXT:     is_xnack_enabled = 0
-; GCN-NEXT:     workitem_private_segment_byte_size = 16384
-; GCN-NEXT:     workgroup_group_segment_byte_size = 0
-; GCN-NEXT:     gds_segment_byte_size = 0
-; GCN-NEXT:     kernarg_segment_byte_size = 64
-; GCN-NEXT:     workgroup_fbarrier_count = 0
-; GCN-NEXT:     wavefront_sgpr_count = 68
-; GCN-NEXT:     workitem_vgpr_count = 42
-; GCN-NEXT:     reserved_vgpr_first = 0
-; GCN-NEXT:     reserved_vgpr_count = 0
-; GCN-NEXT:     reserved_sgpr_first = 0
-; GCN-NEXT:     reserved_sgpr_count = 0
-; GCN-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; GCN-NEXT:     debug_private_segment_buffer_sgpr = 0
-; GCN-NEXT:     kernarg_segment_alignment = 4
-; GCN-NEXT:     group_segment_alignment = 4
-; GCN-NEXT:     private_segment_alignment = 4
-; GCN-NEXT:     wavefront_size = 6
-; GCN-NEXT:     call_convention = -1
-; GCN-NEXT:     runtime_loader_kernel_symbol = 0
-; GCN-NEXT:    .end_amd_kernel_code_t
-; GCN-NEXT:  ; %bb.0:
+; GCN:       ; %bb.0:
 ; GCN-NEXT:    s_mov_b32 s32, 0
 ; GCN-NEXT:    s_mov_b32 flat_scratch_lo, s13
 ; GCN-NEXT:    s_add_i32 s12, s12, s17
 ; GCN-NEXT:    s_lshr_b32 flat_scratch_hi, s12, 8
 ; GCN-NEXT:    s_add_u32 s0, s0, s17
 ; GCN-NEXT:    s_addc_u32 s1, s1, 0
 ; GCN-NEXT:    s_mov_b32 s13, s15
 ; GCN-NEXT:    s_mov_b32 s12, s14
 ; GCN-NEXT:    s_getpc_b64 s[14:15]
 ; GCN-NEXT:    s_add_u32 s14, s14, gv.fptr0@rel32@lo+4
 ; GCN-NEXT:    s_addc_u32 s15, s15, gv.fptr0@rel32@hi+12
 ; GCN-NEXT:    v_lshlrev_b32_e32 v2, 20, v2
 ; GCN-NEXT:    s_load_dwordx2 s[18:19], s[14:15], 0x0
 ; GCN-NEXT:    s_add_u32 s8, s8, 8
 ; GCN-NEXT:    s_addc_u32 s9, s9, 0
 ; GCN-NEXT:    v_lshlrev_b32_e32 v1, 10, v1
 ; GCN-NEXT:    v_or_b32_e32 v0, v0, v1
 ; GCN-NEXT:    v_or_b32_e32 v31, v0, v2
 ; GCN-NEXT:    s_mov_b32 s14, s16
 ; GCN-NEXT:    s_waitcnt lgkmcnt(0)
 ; GCN-NEXT:    s_swappc_b64 s[30:31], s[18:19]
 ; GCN-NEXT:    s_endpgm
 ;
 ; GISEL-LABEL: test_indirect_call_sgpr_ptr:
-; GISEL:         .amd_kernel_code_t
-; GISEL-NEXT:     amd_code_version_major = 1
-; GISEL-NEXT:     amd_code_version_minor = 2
-; GISEL-NEXT:     amd_machine_kind = 1
-; GISEL-NEXT:     amd_machine_version_major = 7
-; GISEL-NEXT:     amd_machine_version_minor = 0
-; GISEL-NEXT:     amd_machine_version_stepping = 0
-; GISEL-NEXT:     kernel_code_entry_byte_offset = 256
-; GISEL-NEXT:     kernel_code_prefetch_byte_size = 0
-; GISEL-NEXT:     granulated_workitem_vgpr_count = 10
-; GISEL-NEXT:     granulated_wavefront_sgpr_count = 8
-; GISEL-NEXT:     priority = 0
-; GISEL-NEXT:     float_mode = 240
-; GISEL-NEXT:     priv = 0
-; GISEL-NEXT:     enable_dx10_clamp = 1
-; GISEL-NEXT:     debug_mode = 0
-; GISEL-NEXT:     enable_ieee_mode = 1
-; GISEL-NEXT:     enable_wgp_mode = 0
-; GISEL-NEXT:     enable_mem_ordered = 0
-; GISEL-NEXT:     enable_fwd_progress = 0
-; GISEL-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 1
-; GISEL-NEXT:     user_sgpr_count = 14
-; GISEL-NEXT:     enable_trap_handler = 0
-; GISEL-NEXT:     enable_sgpr_workgroup_id_x = 1
-; GISEL-NEXT:     enable_sgpr_workgroup_id_y = 1
-; GISEL-NEXT:     enable_sgpr_workgroup_id_z = 1
-; GISEL-NEXT:     enable_sgpr_workgroup_info = 0
-; GISEL-NEXT:     enable_vgpr_workitem_id = 2
-; GISEL-NEXT:     enable_exception_msb = 0
-; GISEL-NEXT:     granulated_lds_size = 0
-; GISEL-NEXT:     enable_exception = 0
-; GISEL-NEXT:     enable_sgpr_private_segment_buffer = 1
-; GISEL-NEXT:     enable_sgpr_dispatch_ptr = 1
-; GISEL-NEXT:     enable_sgpr_queue_ptr = 1
-; GISEL-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; GISEL-NEXT:     enable_sgpr_dispatch_id = 1
-; GISEL-NEXT:     enable_sgpr_flat_scratch_init = 1
-; GISEL-NEXT:     enable_sgpr_private_segment_size = 0
-; GISEL-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; GISEL-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; GISEL-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; GISEL-NEXT:     enable_wavefront_size32 = 0
-; GISEL-NEXT:     enable_ordered_append_gds = 0
-; GISEL-NEXT:     private_element_size = 1
-; GISEL-NEXT:     is_ptr64 = 1
-; GISEL-NEXT:     is_dynamic_callstack = 1
-; GISEL-NEXT:     is_debug_enabled = 0
-; GISEL-NEXT:     is_xnack_enabled = 0
-; GISEL-NEXT:     workitem_private_segment_byte_size = 16384
-; GISEL-NEXT:     workgroup_group_segment_byte_size = 0
-; GISEL-NEXT:     gds_segment_byte_size = 0
-; GISEL-NEXT:     kernarg_segment_byte_size = 64
-; GISEL-NEXT:     workgroup_fbarrier_count = 0
-; GISEL-NEXT:     wavefront_sgpr_count = 68
-; GISEL-NEXT:     workitem_vgpr_count = 42
-; GISEL-NEXT:     reserved_vgpr_first = 0
-; GISEL-NEXT:     reserved_vgpr_count = 0
-; GISEL-NEXT:     reserved_sgpr_first = 0
-; GISEL-NEXT:     reserved_sgpr_count = 0
-; GISEL-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; GISEL-NEXT:     debug_private_segment_buffer_sgpr = 0
-; GISEL-NEXT:     kernarg_segment_alignment = 4
-; GISEL-NEXT:     group_segment_alignment = 4
-; GISEL-NEXT:     private_segment_alignment = 4
-; GISEL-NEXT:     wavefront_size = 6
-; GISEL-NEXT:     call_convention = -1
-; GISEL-NEXT:     runtime_loader_kernel_symbol = 0
-; GISEL-NEXT:    .end_amd_kernel_code_t
-; GISEL-NEXT:  ; %bb.0:
+; GISEL:       ; %bb.0:
 ; GISEL-NEXT:    s_mov_b32 s32, 0
 ; GISEL-NEXT:    s_mov_b32 flat_scratch_lo, s13
 ; GISEL-NEXT:    s_add_i32 s12, s12, s17
 ; GISEL-NEXT:    s_lshr_b32 flat_scratch_hi, s12, 8
 ; GISEL-NEXT:    s_add_u32 s0, s0, s17
 ; GISEL-NEXT:    s_addc_u32 s1, s1, 0
 ; GISEL-NEXT:    s_mov_b32 s13, s15
 ; GISEL-NEXT:    s_mov_b32 s12, s14

 ; GISEL-NEXT:    s_endpgm
   %fptr = load ptr, ptr addrspace(4) @gv.fptr0
   call void %fptr()
   ret void
 }
 
 define amdgpu_kernel void @test_indirect_call_sgpr_ptr_arg(i8) {
 ; GCN-LABEL: test_indirect_call_sgpr_ptr_arg:
-; GCN:         .amd_kernel_code_t
-; GCN-NEXT:     amd_code_version_major = 1
-; GCN-NEXT:     amd_code_version_minor = 2
-; GCN-NEXT:     amd_machine_kind = 1
-; GCN-NEXT:     amd_machine_version_major = 7
-; GCN-NEXT:     amd_machine_version_minor = 0
-; GCN-NEXT:     amd_machine_version_stepping = 0
-; GCN-NEXT:     kernel_code_entry_byte_offset = 256
-; GCN-NEXT:     kernel_code_prefetch_byte_size = 0
-; GCN-NEXT:     granulated_workitem_vgpr_count = 10
-; GCN-NEXT:     granulated_wavefront_sgpr_count = 8
-; GCN-NEXT:     priority = 0
-; GCN-NEXT:     float_mode = 240
-; GCN-NEXT:     priv = 0
-; GCN-NEXT:     enable_dx10_clamp = 1
-; GCN-NEXT:     debug_mode = 0
-; GCN-NEXT:     enable_ieee_mode = 1
-; GCN-NEXT:     enable_wgp_mode = 0
-; GCN-NEXT:     enable_mem_ordered = 0
-; GCN-NEXT:     enable_fwd_progress = 0
-; GCN-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 1
-; GCN-NEXT:     user_sgpr_count = 14
-; GCN-NEXT:     enable_trap_handler = 0
-; GCN-NEXT:     enable_sgpr_workgroup_id_x = 1
-; GCN-NEXT:     enable_sgpr_workgroup_id_y = 1
-; GCN-NEXT:     enable_sgpr_workgroup_id_z = 1
-; GCN-NEXT:     enable_sgpr_workgroup_info = 0
-; GCN-NEXT:     enable_vgpr_workitem_id = 2
-; GCN-NEXT:     enable_exception_msb = 0
-; GCN-NEXT:     granulated_lds_size = 0
-; GCN-NEXT:     enable_exception = 0
-; GCN-NEXT:     enable_sgpr_private_segment_buffer = 1
-; GCN-NEXT:     enable_sgpr_dispatch_ptr = 1
-; GCN-NEXT:     enable_sgpr_queue_ptr = 1
-; GCN-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; GCN-NEXT:     enable_sgpr_dispatch_id = 1
-; GCN-NEXT:     enable_sgpr_flat_scratch_init = 1
-; GCN-NEXT:     enable_sgpr_private_segment_size = 0
-; GCN-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; GCN-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; GCN-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; GCN-NEXT:     enable_wavefront_size32 = 0
-; GCN-NEXT:     enable_ordered_append_gds = 0
-; GCN-NEXT:     private_element_size = 1
-; GCN-NEXT:     is_ptr64 = 1
-; GCN-NEXT:     is_dynamic_callstack = 1
-; GCN-NEXT:     is_debug_enabled = 0
-; GCN-NEXT:     is_xnack_enabled = 0
-; GCN-NEXT:     workitem_private_segment_byte_size = 16384
-; GCN-NEXT:     workgroup_group_segment_byte_size = 0
-; GCN-NEXT:     gds_segment_byte_size = 0
-; GCN-NEXT:     kernarg_segment_byte_size = 64
-; GCN-NEXT:     workgroup_fbarrier_count = 0
-; GCN-NEXT:     wavefront_sgpr_count = 68
-; GCN-NEXT:     workitem_vgpr_count = 42
-; GCN-NEXT:     reserved_vgpr_first = 0
-; GCN-NEXT:     reserved_vgpr_count = 0
-; GCN-NEXT:     reserved_sgpr_first = 0
-; GCN-NEXT:     reserved_sgpr_count = 0
-; GCN-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; GCN-NEXT:     debug_private_segment_buffer_sgpr = 0
-; GCN-NEXT:     kernarg_segment_alignment = 4
-; GCN-NEXT:     group_segment_alignment = 4
-; GCN-NEXT:     private_segment_alignment = 4
-; GCN-NEXT:     wavefront_size = 6
-; GCN-NEXT:     call_convention = -1
-; GCN-NEXT:     runtime_loader_kernel_symbol = 0
-; GCN-NEXT:    .end_amd_kernel_code_t
-; GCN-NEXT:  ; %bb.0:
+; GCN:       ; %bb.0:
 ; GCN-NEXT:    s_mov_b32 s32, 0
 ; GCN-NEXT:    s_mov_b32 flat_scratch_lo, s13
 ; GCN-NEXT:    s_add_i32 s12, s12, s17
 ; GCN-NEXT:    s_lshr_b32 flat_scratch_hi, s12, 8
 ; GCN-NEXT:    s_add_u32 s0, s0, s17
 ; GCN-NEXT:    s_addc_u32 s1, s1, 0
 ; GCN-NEXT:    s_mov_b32 s13, s15
 ; GCN-NEXT:    s_mov_b32 s12, s14

 ; GCN-NEXT:    v_or_b32_e32 v31, v0, v2
 ; GCN-NEXT:    v_mov_b32_e32 v0, 0x7b
 ; GCN-NEXT:    s_mov_b32 s14, s16
 ; GCN-NEXT:    s_waitcnt lgkmcnt(0)
 ; GCN-NEXT:    s_swappc_b64 s[30:31], s[18:19]
 ; GCN-NEXT:    s_endpgm
 ;
 ; GISEL-LABEL: test_indirect_call_sgpr_ptr_arg:
-; GISEL:         .amd_kernel_code_t
-; GISEL-NEXT:     amd_code_version_major = 1
-; GISEL-NEXT:     amd_code_version_minor = 2
-; GISEL-NEXT:     amd_machine_kind = 1
-; GISEL-NEXT:     amd_machine_version_major = 7
-; GISEL-NEXT:     amd_machine_version_minor = 0
-; GISEL-NEXT:     amd_machine_version_stepping = 0
-; GISEL-NEXT:     kernel_code_entry_byte_offset = 256
-; GISEL-NEXT:     kernel_code_prefetch_byte_size = 0
-; GISEL-NEXT:     granulated_workitem_vgpr_count = 10
-; GISEL-NEXT:     granulated_wavefront_sgpr_count = 8
-; GISEL-NEXT:     priority = 0
-; GISEL-NEXT:     float_mode = 240
-; GISEL-NEXT:     priv = 0
-; GISEL-NEXT:     enable_dx10_clamp = 1
-; GISEL-NEXT:     debug_mode = 0
-; GISEL-NEXT:     enable_ieee_mode = 1
-; GISEL-NEXT:     enable_wgp_mode = 0
-; GISEL-NEXT:     enable_mem_ordered = 0
-; GISEL-NEXT:     enable_fwd_progress = 0
-; GISEL-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 1
-; GISEL-NEXT:     user_sgpr_count = 14
-; GISEL-NEXT:     enable_trap_handler = 0
-; GISEL-NEXT:     enable_sgpr_workgroup_id_x = 1
-; GISEL-NEXT:     enable_sgpr_workgroup_id_y = 1
-; GISEL-NEXT:     enable_sgpr_workgroup_id_z = 1
-; GISEL-NEXT:     enable_sgpr_workgroup_info = 0
-; GISEL-NEXT:     enable_vgpr_workitem_id = 2
-; GISEL-NEXT:     enable_exception_msb = 0
-; GISEL-NEXT:     granulated_lds_size = 0
-; GISEL-NEXT:     enable_exception = 0
-; GISEL-NEXT:     enable_sgpr_private_segment_buffer = 1
-; GISEL-NEXT:     enable_sgpr_dispatch_ptr = 1
-; GISEL-NEXT:     enable_sgpr_queue_ptr = 1
-; GISEL-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; GISEL-NEXT:     enable_sgpr_dispatch_id = 1
-; GISEL-NEXT:     enable_sgpr_flat_scratch_init = 1
-; GISEL-NEXT:     enable_sgpr_private_segment_size = 0
-; GISEL-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; GISEL-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; GISEL-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; GISEL-NEXT:     enable_wavefront_size32 = 0
-; GISEL-NEXT:     enable_ordered_append_gds = 0
-; GISEL-NEXT:     private_element_size = 1
-; GISEL-NEXT:     is_ptr64 = 1
-; GISEL-NEXT:     is_dynamic_callstack = 1
-; GISEL-NEXT:     is_debug_enabled = 0
-; GISEL-NEXT:     is_xnack_enabled = 0
-; GISEL-NEXT:     workitem_private_segment_byte_size = 16384
-; GISEL-NEXT:     workgroup_group_segment_byte_size = 0
-; GISEL-NEXT:     gds_segment_byte_size = 0
-; GISEL-NEXT:     kernarg_segment_byte_size = 64
-; GISEL-NEXT:     workgroup_fbarrier_count = 0
-; GISEL-NEXT:     wavefront_sgpr_count = 68
-; GISEL-NEXT:     workitem_vgpr_count = 42
-; GISEL-NEXT:     reserved_vgpr_first = 0
-; GISEL-NEXT:     reserved_vgpr_count = 0
-; GISEL-NEXT:     reserved_sgpr_first = 0
-; GISEL-NEXT:     reserved_sgpr_count = 0
-; GISEL-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; GISEL-NEXT:     debug_private_segment_buffer_sgpr = 0
-; GISEL-NEXT:     kernarg_segment_alignment = 4
-; GISEL-NEXT:     group_segment_alignment = 4
-; GISEL-NEXT:     private_segment_alignment = 4
-; GISEL-NEXT:     wavefront_size = 6
-; GISEL-NEXT:     call_convention = -1
-; GISEL-NEXT:     runtime_loader_kernel_symbol = 0
-; GISEL-NEXT:    .end_amd_kernel_code_t
-; GISEL-NEXT:  ; %bb.0:
+; GISEL:       ; %bb.0:
 ; GISEL-NEXT:    s_mov_b32 s32, 0
 ; GISEL-NEXT:    s_mov_b32 flat_scratch_lo, s13
 ; GISEL-NEXT:    s_add_i32 s12, s12, s17
 ; GISEL-NEXT:    s_lshr_b32 flat_scratch_hi, s12, 8
 ; GISEL-NEXT:    s_add_u32 s0, s0, s17
 ; GISEL-NEXT:    s_addc_u32 s1, s1, 0
 ; GISEL-NEXT:    s_mov_b32 s13, s15
 ; GISEL-NEXT:    s_mov_b32 s12, s14

 ; GISEL-NEXT:    s_mov_b32 s33, s10
 ; GISEL-NEXT:    s_waitcnt vmcnt(0)
 ; GISEL-NEXT:    s_setpc_b64 s[30:31]
   tail call amdgpu_gfx void %fptr()
   ret void
 }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/kernel-argument-dag-lowering.ll

 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx900 -amdgpu-ir-lower-kernel-arguments=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,HSA-VI,FUNC %s
 
 ; Repeat of some problematic tests in kernel-args.ll, with the IR
 ; argument lowering pass disabled. Struct padding needs to be
 ; accounted for, as well as legalization of types changing offsets.
 
 ; FUNC-LABEL: {{^}}i1_arg:
-; HSA-VI: kernarg_segment_byte_size = 12
-; HSA-VI: kernarg_segment_alignment = 4
 
 ; GCN: s_load_dword s
 ; GCN: s_and_b32
+
+; HSA-VI: .amdhsa_kernarg_size 12
 define amdgpu_kernel void @i1_arg(ptr addrspace(1) %out, i1 %x) nounwind {
   store i1 %x, ptr addrspace(1) %out, align 1
   ret void
 }
 
 ; FUNC-LABEL: {{^}}v3i8_arg:
-; HSA-VI: kernarg_segment_byte_size = 12
-; HSA-VI: kernarg_segment_alignment = 4
+
 ; HSA-VI: s_load_dword s{{[0-9]+}}, s[4:5], 0x8
 ; HSA-VI: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s[4:5], 0x0
+
+; HSA-VI: .amdhsa_kernarg_size 12
 define amdgpu_kernel void @v3i8_arg(ptr addrspace(1) nocapture %out, <3 x i8> %in) nounwind {
 entry:
   store <3 x i8> %in, ptr addrspace(1) %out, align 4
   ret void
 }
 
 ; FUNC-LABEL: {{^}}i65_arg:
-; HSA-VI: kernarg_segment_byte_size = 24
-; HSA-VI: kernarg_segment_alignment = 4
 ; HSA-VI: s_load_dwordx4 s{{\[[0-9]+:[0-9]+\]}}, s[4:5], 0x0
+
+; HSA-VI: .amdhsa_kernarg_size 24
 define amdgpu_kernel void @i65_arg(ptr addrspace(1) nocapture %out, i65 %in) nounwind {
 entry:
   store i65 %in, ptr addrspace(1) %out, align 4
   ret void
 }
 
 ; FUNC-LABEL: {{^}}empty_struct_arg:
-; HSA-VI: kernarg_segment_byte_size = 0
+; HSA-VI: .amdhsa_kernarg_size 0
 define amdgpu_kernel void @empty_struct_arg({} %in) nounwind {
   ret void
 }
 
 ; The correct load offsets for these:
 ; load 4 from 0,
 ; load 8 from 8
 ; load 4 from 24
 ; load 8 from 32
 
 ; With the SelectionDAG argument lowering, the alignments for the
 ; struct members is not properly considered, making these wrong.
 
 ; FIXME: Total argument size is computed wrong
 ; FUNC-LABEL: {{^}}struct_argument_alignment:
-; HSA-VI: kernarg_segment_byte_size = 40
 ; HSA-VI: s_load_dword s{{[0-9]+}}, s[4:5], 0x0
 ; HSA-VI: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s[4:5], 0x8
 ; HSA-VI: s_load_dword s{{[0-9]+}}, s[4:5], 0x18
 ; HSA-VI: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s[4:5], 0x20
+
+; HSA-VI: .amdhsa_kernarg_size 40
 define amdgpu_kernel void @struct_argument_alignment({i32, i64} %arg0, i8, {i32, i64} %arg1) {
   %val0 = extractvalue {i32, i64} %arg0, 0
   %val1 = extractvalue {i32, i64} %arg0, 1
   %val2 = extractvalue {i32, i64} %arg1, 0
   %val3 = extractvalue {i32, i64} %arg1, 1
   store volatile i32 %val0, ptr addrspace(1) null
   store volatile i64 %val1, ptr addrspace(1) null
   store volatile i32 %val2, ptr addrspace(1) null
   store volatile i64 %val3, ptr addrspace(1) null
   ret void
 }
 
 ; No padding between i8 and next struct, but round up at end to 4 byte
 ; multiple.
 ; FUNC-LABEL: {{^}}packed_struct_argument_alignment:
-; HSA-VI: kernarg_segment_byte_size = 28
 ; HSA-VI-DAG: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
 ; HSA-VI: global_load_dword v{{[0-9]+}}, [[ZERO]], s{{\[[0-9]+:[0-9]+\]}} offset:13
 ; HSA-VI: global_load_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]], s{{\[[0-9]+:[0-9]+\]}} offset:17
 ; HSA-VI: s_load_dword s{{[0-9]+}}, s[4:5], 0x0
 ; HSA-VI: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s[4:5], 0x4
+
+; HSA-VI: .amdhsa_kernarg_size 28
 define amdgpu_kernel void @packed_struct_argument_alignment(<{i32, i64}> %arg0, i8, <{i32, i64}> %arg1) {
   %val0 = extractvalue <{i32, i64}> %arg0, 0
   %val1 = extractvalue <{i32, i64}> %arg0, 1
   %val2 = extractvalue <{i32, i64}> %arg1, 0
   %val3 = extractvalue <{i32, i64}> %arg1, 1
   store volatile i32 %val0, ptr addrspace(1) null
   store volatile i64 %val1, ptr addrspace(1) null
   store volatile i32 %val2, ptr addrspace(1) null
   store volatile i64 %val3, ptr addrspace(1) null
   ret void
 }
 
 ; GCN-LABEL: {{^}}struct_argument_alignment_after:
-; HSA-VI: kernarg_segment_byte_size = 64
 ; HSA-VI: s_load_dword s{{[0-9]+}}, s[4:5], 0x0
 ; HSA-VI: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s[4:5], 0x8
 ; HSA-VI: s_load_dword s{{[0-9]+}}, s[4:5], 0x18
 ; HSA-VI: s_load_dwordx2 s{{\[[0-9]+:[0-9]+\]}}, s[4:5], 0x20
 ; HSA-VI: s_load_dwordx4 s{{\[[0-9]+:[0-9]+\]}}, s[4:5], 0x30
+
+; HSA-VI: .amdhsa_kernarg_size 64
 define amdgpu_kernel void @struct_argument_alignment_after({i32, i64} %arg0, i8, {i32, i64} %arg2, i8, <4 x i32> %arg4) {
   %val0 = extractvalue {i32, i64} %arg0, 0
   %val1 = extractvalue {i32, i64} %arg0, 1
   %val2 = extractvalue {i32, i64} %arg2, 0
   %val3 = extractvalue {i32, i64} %arg2, 1
   store volatile i32 %val0, ptr addrspace(1) null
   store volatile i64 %val1, ptr addrspace(1) null
   store volatile i32 %val2, ptr addrspace(1) null

 define amdgpu_kernel void @v3i15_arg(ptr addrspace(1) nocapture %out, <3 x i15> %in) {
 entry:
   store <3 x i15> %in, ptr addrspace(1) %out, align 4
   ret void
 }
 
 ; Byref pointers should only be treated as offsets from kernarg
 ; GCN-LABEL: {{^}}byref_constant_i8_arg:
-; GCN: kernarg_segment_byte_size = 12
 ; GCN: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
 ; GCN: global_load_ubyte v{{[0-9]+}}, [[ZERO]], s[4:5] offset:8
+; GCN: .amdhsa_kernarg_size 12
 define amdgpu_kernel void @byref_constant_i8_arg(ptr addrspace(1) nocapture %out, ptr addrspace(4) byref(i8) %in.byref) {
   %in = load i8, ptr addrspace(4) %in.byref
   %ext = zext i8 %in to i32
   store i32 %ext, ptr addrspace(1) %out, align 4
   ret void
 }
 
 ; GCN-LABEL: {{^}}byref_constant_i16_arg:
-; GCN: kernarg_segment_byte_size = 12
 ; GCN: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
 ; GCN: global_load_ushort v{{[0-9]+}}, [[ZERO]], s[4:5] offset:8
+; GCN: .amdhsa_kernarg_size 12
 define amdgpu_kernel void @byref_constant_i16_arg(ptr addrspace(1) nocapture %out, ptr addrspace(4) byref(i16) %in.byref) {
   %in = load i16, ptr addrspace(4) %in.byref
   %ext = zext i16 %in to i32
   store i32 %ext, ptr addrspace(1) %out, align 4
   ret void
 }
 
 ; GCN-LABEL: {{^}}byref_constant_i32_arg:
-; GCN: kernarg_segment_byte_size = 16
 ; GCN: s_load_dwordx4 [[LOAD:s\[[0-9]+:[0-9]+\]]], s[4:5], 0x0{{$}}
+; GCN: .amdhsa_kernarg_size 16
 define amdgpu_kernel void @byref_constant_i32_arg(ptr addrspace(1) nocapture %out, ptr addrspace(4) byref(i32) %in.byref, i32 %after.offset) {
   %in = load i32, ptr addrspace(4) %in.byref
   store volatile i32 %in, ptr addrspace(1) %out, align 4
   store volatile i32 %after.offset, ptr addrspace(1) %out, align 4
   ret void
 }
 
 ; GCN-LABEL: {{^}}byref_constant_v4i32_arg:
-; GCN: kernarg_segment_byte_size = 36
 ; GCN: s_load_dwordx4 s{{\[[0-9]+:[0-9]+\]}}, s[4:5], 0x10{{$}}
 ; GCN: s_load_dword s{{[0-9]+}}, s[4:5], 0x20{{$}}
+; GCN: .amdhsa_kernarg_size 36
 define amdgpu_kernel void @byref_constant_v4i32_arg(ptr addrspace(1) nocapture %out, ptr addrspace(4) byref(<4 x i32>) %in.byref, i32 %after.offset) {
   %in = load <4 x i32>, ptr addrspace(4) %in.byref
   store volatile <4 x i32> %in, ptr addrspace(1) %out, align 4
   store volatile i32 %after.offset, ptr addrspace(1) %out, align 4
   ret void
 }
 
 ; GCN-LABEL: {{^}}byref_align_constant_i32_arg:
-; GCN: kernarg_segment_byte_size = 264
 ; GCN-DAG: s_load_dwordx2 s[[[IN:[0-9]+]]:[[AFTER_OFFSET:[0-9]+]]], s[4:5], 0x100{{$}}
 ; GCN-DAG: v_mov_b32_e32 [[V_IN:v[0-9]+]], s[[IN]]
 ; GCN-DAG: v_mov_b32_e32 [[V_AFTER_OFFSET:v[0-9]+]], s[[AFTER_OFFSET]]
 ; GCN: global_store_dword v{{[0-9]+}}, [[V_IN]], s
 ; GCN: global_store_dword v{{[0-9]+}}, [[V_AFTER_OFFSET]], s
+; GCN: .amdhsa_kernarg_size 264
 define amdgpu_kernel void @byref_align_constant_i32_arg(ptr addrspace(1) nocapture %out, ptr addrspace(4) byref(i32) align(256) %in.byref, i32 %after.offset) {
   %in = load i32, ptr addrspace(4) %in.byref
   store volatile i32 %in, ptr addrspace(1) %out, align 4
   store volatile i32 %after.offset, ptr addrspace(1) %out, align 4
   ret void
 }
 
 ; GCN-LABEL: {{^}}byref_natural_align_constant_v16i32_arg:
-; GCN: kernarg_segment_byte_size = 132
 ; GCN-DAG: s_load_dword s{{[0-9]+}}, s[4:5], 0x80
 ; GCN-DAG: s_load_dwordx16 s{{\[[0-9]+:[0-9]+\]}}, s[4:5], 0x40{{$}}
+; GCN: .amdhsa_kernarg_size 132
 define amdgpu_kernel void @byref_natural_align_constant_v16i32_arg(ptr addrspace(1) nocapture %out, i8, ptr addrspace(4) byref(<16 x i32>) align(64) %in.byref, i32 %after.offset) {
   %in = load <16 x i32>, ptr addrspace(4) %in.byref
   store volatile <16 x i32> %in, ptr addrspace(1) %out, align 4
   store volatile i32 %after.offset, ptr addrspace(1) %out, align 4
   ret void
 }
 
 ; Also accept byref kernel arguments with other global address spaces.
 ; GCN-LABEL: {{^}}byref_global_i32_arg:
-; GCN: kernarg_segment_byte_size = 12
 ; GCN: s_load_dword [[IN:s[0-9]+]], s[4:5], 0x8{{$}}
+; GCN: .amdhsa_kernarg_size 12
 define amdgpu_kernel void @byref_global_i32_arg(ptr addrspace(1) nocapture %out, ptr addrspace(1) byref(i32) %in.byref) {
   %in = load i32, ptr addrspace(1) %in.byref
   store i32 %in, ptr addrspace(1) %out, align 4
   ret void
 }
 
 ; GCN-LABEL: {{^}}byref_flat_i32_arg:
 ; GCN: flat_load_dword [[IN:v[0-9]+]], v{{\[[0-9]+:[0-9]+\]}} offset:8{{$}}

 
 ; define amdgpu_kernel void @byref_unknown_as_i32_arg(ptr addrspace(1) nocapture %out, ptr addrspace(999) byref %in.byref) {
 ;   %in = load i32, ptr addrspace(999) %in.byref
 ;   store i32 %in, ptr addrspace(1) %out, align 4
 ;   ret void
 ; }
 
 ; GCN-LABEL: {{^}}multi_byref_constant_i32_arg:
-; GCN: kernarg_segment_byte_size = 20
 ; GCN: s_load_dwordx4 {{s\[[0-9]+:[0-9]+\]}}, s[4:5], 0x0
+; GCN: .amdhsa_kernarg_size 20
 define amdgpu_kernel void @multi_byref_constant_i32_arg(ptr addrspace(1) nocapture %out, ptr addrspace(4) byref(i32) %in0.byref, ptr addrspace(4) byref(i32) %in1.byref, i32 %after.offset) {
   %in0 = load i32, ptr addrspace(4) %in0.byref
   %in1 = load i32, ptr addrspace(4) %in1.byref
   store volatile i32 %in0, ptr addrspace(1) %out, align 4
   store volatile i32 %in1, ptr addrspace(1) %out, align 4
   store volatile i32 %after.offset, ptr addrspace(1) %out, align 4
   ret void
 }
 
 ; GCN-LABEL: {{^}}byref_constant_i32_arg_offset0:
-; GCN: kernarg_segment_byte_size = 4
 ; GCN-NOT: s4
 ; GCN-NOT: s5
 ; GCN: s_load_dword {{s[0-9]+}}, s[4:5], 0x0{{$}}
+; GCN: .amdhsa_kernarg_size 4
 define amdgpu_kernel void @byref_constant_i32_arg_offset0(ptr addrspace(4) byref(i32) %in.byref) {
   %in = load i32, ptr addrspace(4) %in.byref
   store i32 %in, ptr addrspace(1) undef, align 4
   ret void
 }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/lds-alignment.ll

 ; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefix=HSA %s
 
 @lds.align16.0 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 16
 @lds.align16.1 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 16
 
 @lds.align8.0 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 8
 @lds.align32.0 = internal unnamed_addr addrspace(3) global [38 x i8] undef, align 32
 
 @lds.missing.align.0 = internal unnamed_addr addrspace(3) global [39 x i32] undef
 @lds.missing.align.1 = internal unnamed_addr addrspace(3) global [7 x i64] undef
 
 declare void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) nocapture, ptr addrspace(1) nocapture readonly, i32, i1) #0
 declare void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) nocapture, ptr addrspace(3) nocapture readonly, i32, i1) #0
 
 
 ; HSA-LABEL: {{^}}test_no_round_size_1:
-; HSA: workgroup_group_segment_byte_size = 38
+; HSA: .amdhsa_group_segment_fixed_size 38
 define amdgpu_kernel void @test_no_round_size_1(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 4 @lds.align16.0, ptr addrspace(1) align 4 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 4 %out, ptr addrspace(3) align 4 @lds.align16.0, i32 38, i1 false)
   ret void
 }
 
 ; There are two objects, so one requires padding to be correctly
 ; aligned after the other.
 
 ; (38 -> 48) + 38 = 92
 
 ; I don't think it is necessary to add padding after since if there
 ; were to be a dynamically sized LDS kernel arg, the runtime should
 ; add the alignment padding if necessary alignment padding if needed.
 
 ; HSA-LABEL: {{^}}test_round_size_2:
-; HSA: workgroup_group_segment_byte_size = 86
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 86
 define amdgpu_kernel void @test_round_size_2(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 4 @lds.align16.0, ptr addrspace(1) align 4 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 4 %out, ptr addrspace(3) align 4 @lds.align16.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 4 @lds.align16.1, ptr addrspace(1) align 4 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 4 %out, ptr addrspace(3) align 4 @lds.align16.1, i32 38, i1 false)
 
   ret void
 }
 
 ; 38 + (10 pad) + 38  (= 86)
 ; HSA-LABEL: {{^}}test_round_size_2_align_8:
-; HSA: workgroup_group_segment_byte_size = 86
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 86
 define amdgpu_kernel void @test_round_size_2_align_8(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align16.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align16.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align8.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align8.0, i32 38, i1 false)
 
   ret void
 }
 
 ; HSA-LABEL: {{^}}test_round_local_lds_and_arg:
-; HSA: workgroup_group_segment_byte_size = 38
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 38
 define amdgpu_kernel void @test_round_local_lds_and_arg(ptr addrspace(1) %out, ptr addrspace(1) %in, ptr addrspace(3) %lds.arg) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 4 @lds.align16.0, ptr addrspace(1) align 4 %in, i32 38, i1 false)
 
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 4 %out, ptr addrspace(3) align 4 @lds.align16.0, i32 38, i1 false)
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 4 %lds.arg, ptr addrspace(1) align 4 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 4 %out, ptr addrspace(3) align 4 %lds.arg, i32 38, i1 false)
   ret void
 }
 
 ; HSA-LABEL: {{^}}test_round_lds_arg:
-; HSA: workgroup_group_segment_byte_size = 0
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 0
 define amdgpu_kernel void @test_round_lds_arg(ptr addrspace(1) %out, ptr addrspace(1) %in, ptr addrspace(3) %lds.arg) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 4 %lds.arg, ptr addrspace(1) align 4 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 4 %out, ptr addrspace(3) align 4 %lds.arg, i32 38, i1 false)
   ret void
 }
 
 ; FIXME: Parameter alignment not considered
 ; HSA-LABEL: {{^}}test_high_align_lds_arg:
-; HSA: workgroup_group_segment_byte_size = 0
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 0
 define amdgpu_kernel void @test_high_align_lds_arg(ptr addrspace(1) %out, ptr addrspace(1) %in, ptr addrspace(3) align 64 %lds.arg) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 64 %lds.arg, ptr addrspace(1) align 64 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 64 %out, ptr addrspace(3) align 64 %lds.arg, i32 38, i1 false)
   ret void
 }
 
 ; (39 * 4) + (4 pad) + (7 * 8) = 216
 ; HSA-LABEL: {{^}}test_missing_alignment_size_2_order0:
-; HSA: workgroup_group_segment_byte_size = 216
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 216
 define amdgpu_kernel void @test_missing_alignment_size_2_order0(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 4 @lds.missing.align.0, ptr addrspace(1) align 4 %in, i32 160, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 4 %out, ptr addrspace(3) align 4 @lds.missing.align.0, i32 160, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.missing.align.1, ptr addrspace(1) align 8 %in, i32 56, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.missing.align.1, i32 56, i1 false)
 
   ret void
 }
 
 ; (39 * 4) + (4 pad) + (7 * 8) = 216
 ; HSA-LABEL: {{^}}test_missing_alignment_size_2_order1:
-; HSA: workgroup_group_segment_byte_size = 216
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 216
 define amdgpu_kernel void @test_missing_alignment_size_2_order1(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.missing.align.1, ptr addrspace(1) align 8 %in, i32 56, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.missing.align.1, i32 56, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 4 @lds.missing.align.0, ptr addrspace(1) align 4 %in, i32 160, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 4 %out, ptr addrspace(3) align 4 @lds.missing.align.0, i32 160, i1 false)
 
   ret void
 }
 
 ; align 32, 16, 16
 ; 38 + (10 pad) + 38 + (10 pad) + 38  ( = 134)
 ; HSA-LABEL: {{^}}test_round_size_3_order0:
-; HSA: workgroup_group_segment_byte_size = 134
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 134
 define amdgpu_kernel void @test_round_size_3_order0(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align32.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align32.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align16.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align16.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align8.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align8.0, i32 38, i1 false)
 
   ret void
 }
 
 ; align 32, 16, 16
 ; 38 (+ 10 pad) + 38 + (10 pad) + 38 ( = 134)
 ; HSA-LABEL: {{^}}test_round_size_3_order1:
-; HSA: workgroup_group_segment_byte_size = 134
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 134
 define amdgpu_kernel void @test_round_size_3_order1(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align32.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align32.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align8.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align8.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align16.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align16.0, i32 38, i1 false)
 
   ret void
 }
 
 ; align 32, 16, 16
 ; 38 + (10 pad) + 38 + (10 pad) + 38  ( = 126)
 ; HSA-LABEL: {{^}}test_round_size_3_order2:
-; HSA: workgroup_group_segment_byte_size = 134
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 134
 define amdgpu_kernel void @test_round_size_3_order2(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align16.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align16.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align32.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align32.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align8.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align8.0, i32 38, i1 false)
 
   ret void
 }
 
 ; align 32, 16, 16
 ; 38 + (10 pad) + 38 + (10 pad) + 38 ( = 134)
 ; HSA-LABEL: {{^}}test_round_size_3_order3:
-; HSA: workgroup_group_segment_byte_size = 134
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 134
 define amdgpu_kernel void @test_round_size_3_order3(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align16.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align16.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align8.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align8.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align32.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align32.0, i32 38, i1 false)
 
   ret void
 }
 
 ; align 32, 16, 16
 ; 38 + (10 pad) + 38 + (10 pad) + 38  (= 134)
 ; HSA-LABEL: {{^}}test_round_size_3_order4:
-; HSA: workgroup_group_segment_byte_size = 134
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 134
 define amdgpu_kernel void @test_round_size_3_order4(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align8.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align8.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align32.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align32.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align16.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align16.0, i32 38, i1 false)
 
   ret void
 }
 
 ; align 32, 16, 16
 ; 38 + (10 pad) + 38 + (10 pad) + 38  (= 134)
 ; HSA-LABEL: {{^}}test_round_size_3_order5:
-; HSA: workgroup_group_segment_byte_size = 134
-; HSA: group_segment_alignment = 4
+; HSA: .amdhsa_group_segment_fixed_size 134
 define amdgpu_kernel void @test_round_size_3_order5(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align8.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align8.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align16.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align16.0, i32 38, i1 false)
 
   call void @llvm.memcpy.p3.p1.i32(ptr addrspace(3) align 8 @lds.align32.0, ptr addrspace(1) align 8 %in, i32 38, i1 false)
   call void @llvm.memcpy.p1.p3.i32(ptr addrspace(1) align 8 %out, ptr addrspace(3) align 8 @lds.align32.0, i32 38, i1 false)
 
   ret void
 }
 
 attributes #0 = { argmemonly nounwind }
 attributes #1 = { nounwind }
 attributes #2 = { convergent nounwind }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/lds-size.ll

 ; RUN: llc -global-isel=0 -mtriple=amdgcn-amd-amdhsa < %s | FileCheck -check-prefix=ALL -check-prefix=HSA %s
 ; RUN: llc -global-isel=1 -mtriple=amdgcn-amd-amdhsa < %s | FileCheck -check-prefix=ALL -check-prefix=HSA %s
 ; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=ALL -check-prefix=EG %s
 
 ; This test makes sure we do not double count global values when they are
 ; used in different basic blocks.
 
 ; GCN: .long 47180
 ; GCN-NEXT: .long 32900
 
 ; EG: .long 166120
 ; EG-NEXT: .long 1
 ; ALL: {{^}}test:
 
-; HSA: granulated_lds_size = 0
-; HSA: workgroup_group_segment_byte_size = 4
+; HSA-NOT: COMPUTE_PGM_RSRC2.LDS_SIZE
+; HSA: .amdhsa_group_segment_fixed_size 4
 
 ; GCN: ; LDSByteSize: 4 bytes/workgroup (compile time only)
 @lds = internal unnamed_addr addrspace(3) global i32 undef, align 4
 
 define amdgpu_kernel void @test(ptr addrspace(1) %out, i32 %cond) {
 entry:
   %0 = icmp eq i32 %cond, 0
   br i1 %0, label %if, label %else
 
 if:
   store i32 1, ptr addrspace(3) @lds
   br label %endif
 
 else:
   store i32 2, ptr addrspace(3) @lds
   br label %endif
 
 endif:
   ret void
 }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.dispatch.id.ll

 ; RUN: llc -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 
 declare i64 @llvm.amdgcn.dispatch.id() #1
 
 ; GCN-LABEL: {{^}}dispatch_id:
-; GCN: .amd_kernel_code_t
-; GCN: enable_sgpr_dispatch_id = 1
 
 ; GCN-DAG: v_mov_b32_e32 v[[LO:[0-9]+]], s6
 ; GCN-DAG: v_mov_b32_e32 v[[HI:[0-9]+]], s7
 ; GCN: flat_store_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v[[[LO]]:[[HI]]]
+; GCN: .amdhsa_user_sgpr_dispatch_id 1
 define amdgpu_kernel void @dispatch_id(ptr addrspace(1) %out) #0 {
   %tmp0 = call i64 @llvm.amdgcn.dispatch.id()
   store i64 %tmp0, ptr addrspace(1) %out
   ret void
 }
 
 attributes #0 = { nounwind }
 attributes #1 = { nounwind readnone }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.dispatch.ptr.ll

 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 ; RUN: not llc -mtriple=amdgcn-unknown-unknown -mcpu=kaveri -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=ERROR %s
 
 ; ERROR: in function test{{.*}}: unsupported hsa intrinsic without hsa target
 
 ; GCN-LABEL: {{^}}test:
-; GCN: enable_sgpr_dispatch_ptr = 1
 ; GCN: s_load_dword s{{[0-9]+}}, s[4:5], 0x0
+; GCN: .amdhsa_user_sgpr_dispatch_ptr 1
 define amdgpu_kernel void @test(ptr addrspace(1) %out) {
   %dispatch_ptr = call noalias ptr addrspace(4) @llvm.amdgcn.dispatch.ptr() #0
   %value = load i32, ptr addrspace(4) %dispatch_ptr
   store i32 %value, ptr addrspace(1) %out
   ret void
 }
 
 ; GCN-LABEL: {{^}}test2
-; GCN: enable_sgpr_dispatch_ptr = 1
 ; GCN: s_load_dword s[[REG:[0-9]+]], s[4:5], 0x1
 ; GCN: s_lshr_b32 s{{[0-9]+}}, s[[REG]], 16
 ; GCN-NOT: load_ushort
 ; GCN: s_endpgm
+; GCN: .amdhsa_user_sgpr_dispatch_ptr 1
 define amdgpu_kernel void @test2(ptr addrspace(1) %out) {
   %dispatch_ptr = call noalias ptr addrspace(4) @llvm.amdgcn.dispatch.ptr() #0
   %d1 = getelementptr inbounds i8, ptr addrspace(4) %dispatch_ptr, i64 6
   %v1 = load i16, ptr addrspace(4) %d1
   %e1 = zext i16 %v1 to i32
   store i32 %e1, ptr addrspace(1) %out
   ret void
 }
 
 declare noalias ptr addrspace(4) @llvm.amdgcn.dispatch.ptr() #0
 
 attributes #0 = { readnone }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.implicitarg.ptr.ll

-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=kaveri -verify-machineinstrs | FileCheck -check-prefixes=GCN,HSA %s
-; RUN: sed 's/CODE_OBJECT_VERSION/500/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=kaveri -verify-machineinstrs | FileCheck -check-prefixes=GCN,COV5 %s
+; RUN: sed 's/CODE_OBJECT_VERSION/500/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=kaveri -verify-machineinstrs | FileCheck -check-prefixes=GCN,HSA,COV5 %s
+; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=kaveri -verify-machineinstrs | FileCheck -check-prefixes=GCN,HSA,COV4 %s
 ; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -verify-machineinstrs | FileCheck -check-prefixes=GCN,MESA %s
 
 ; GCN-LABEL: {{^}}kernel_implicitarg_ptr_empty:
-; HSA: enable_sgpr_kernarg_segment_ptr = 1
-; HSA: kernarg_segment_byte_size = 56
-; HSA: kernarg_segment_alignment = 4
 
 ; MESA: enable_sgpr_kernarg_segment_ptr = 1
 ; MESA: kernarg_segment_byte_size = 16
 ; MESA: kernarg_segment_alignment = 4
 
 ; HSA: s_load_dword s0, s[4:5], 0x0
 
+; COV4: .amdhsa_kernarg_size 56
 ; COV5: .amdhsa_kernarg_size 256
 define amdgpu_kernel void @kernel_implicitarg_ptr_empty() #0 {
   %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %load = load volatile i32, ptr addrspace(4) %implicitarg.ptr
   ret void
 }
 
 ; GCN-LABEL: {{^}}kernel_implicitarg_ptr_empty_0implicit:
-; HSA: enable_sgpr_kernarg_segment_ptr = 0
-; HSA: kernarg_segment_byte_size = 0
-; HSA: kernarg_segment_alignment = 4
-
 ; MESA: enable_sgpr_kernarg_segment_ptr = 1
 ; MESA: kernarg_segment_byte_size = 16
 ; MESA: kernarg_segment_alignment = 4
 
 ; HSA: s_mov_b64 [[NULL:s\[[0-9]+:[0-9]+\]]], 0{{$}}
 ; HSA: s_load_dword s0, [[NULL]], 0x0
 
 ; MESA: s_load_dword s0, s[4:5], 0x0
 
+; COV4: .amdhsa_kernarg_size 0
 ; COV5: .amdhsa_kernarg_size 0
 define amdgpu_kernel void @kernel_implicitarg_ptr_empty_0implicit() #3 {
   %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %load = load volatile i32, ptr addrspace(4) %implicitarg.ptr
   ret void
 }
 
 ; GCN-LABEL: {{^}}opencl_kernel_implicitarg_ptr_empty:
 
-; HSA: enable_sgpr_kernarg_segment_ptr = 1
-; HSA: kernarg_segment_byte_size = 48
-; HSA: kernarg_segment_alignment = 4
-
 ; MESA: enable_sgpr_kernarg_segment_ptr = 1
 ; MESA: kernarg_segment_byte_size = 16
 ; MESA: kernarg_segment_alignment = 4
 
 ; HSA: s_load_dword s0, s[4:5], 0x0
 
-; COV5: .amdhsa_kernarg_size 48
+; HSA: .amdhsa_kernarg_size 48
 define amdgpu_kernel void @opencl_kernel_implicitarg_ptr_empty() #1 {
   %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %load = load volatile i32, ptr addrspace(4) %implicitarg.ptr
   ret void
 }
 
 ; GCN-LABEL: {{^}}kernel_implicitarg_ptr:
 
-; HSA: enable_sgpr_kernarg_segment_ptr = 1
-; HSA: kernarg_segment_byte_size = 168
-; HSA: kernarg_segment_alignment = 4
-
 ; MESA: enable_sgpr_kernarg_segment_ptr = 1
 ; MESA: kernarg_segment_byte_size = 128
 ; MESA: kernarg_segment_alignment = 4
 
 ; HSA: s_load_dword s0, s[4:5], 0x1c
 
+; COV4: .amdhsa_kernarg_size 168
 ; COV5: .amdhsa_kernarg_size 368
 define amdgpu_kernel void @kernel_implicitarg_ptr([112 x i8]) #0 {
   %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %load = load volatile i32, ptr addrspace(4) %implicitarg.ptr
   ret void
 }
 
 ; GCN-LABEL: {{^}}opencl_kernel_implicitarg_ptr:
 
-; HSA: enable_sgpr_kernarg_segment_ptr = 1
-; HSA: kernarg_segment_byte_size = 160
-; HSA: kernarg_segment_alignment = 4
-
 ; MESA: enable_sgpr_kernarg_segment_ptr = 1
 ; MESA: kernarg_segment_byte_size = 128
 ; MESA: kernarg_segment_alignment = 4
 
 ; HSA: s_load_dword s0, s[4:5], 0x1c
 
-; COV5: .amdhsa_kernarg_size 160
+; HSA: .amdhsa_kernarg_size 160
 define amdgpu_kernel void @opencl_kernel_implicitarg_ptr([112 x i8]) #1 {
   %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %load = load volatile i32, ptr addrspace(4) %implicitarg.ptr
   ret void
 }
 
 ; GCN-LABEL: {{^}}func_implicitarg_ptr:
 ; GCN: s_waitcnt

 ; GCN-NEXT: s_setpc_b64
 define void @opencl_func_implicitarg_ptr() #0 {
   %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %load = load volatile i32, ptr addrspace(4) %implicitarg.ptr
   ret void
 }
 
 ; GCN-LABEL: {{^}}kernel_call_implicitarg_ptr_func_empty:
-; HSA: enable_sgpr_kernarg_segment_ptr = 1
-; HSA: kernarg_segment_byte_size = 56
-; HSA: kernarg_segment_alignment = 4
 
 ; MESA: enable_sgpr_kernarg_segment_ptr = 1
 ; MESA: kernarg_segment_byte_size = 16
 ; MESA: kernarg_segment_alignment = 4
 
 ; GCN: s_mov_b64 s[8:9], s[4:5]
 ; GCN: s_swappc_b64
 
+; COV4: .amdhsa_kernarg_size 56
 ; COV5: .amdhsa_kernarg_size 256
 define amdgpu_kernel void @kernel_call_implicitarg_ptr_func_empty() #0 {
   call void @func_implicitarg_ptr()
   ret void
 }
 
 ; GCN-LABEL: {{^}}kernel_call_implicitarg_ptr_func_empty_implicit0:
-; HSA: enable_sgpr_kernarg_segment_ptr = 0
-; HSA: kernarg_segment_byte_size = 0
-; HSA: kernarg_segment_alignment = 4
-
 ; MESA: enable_sgpr_kernarg_segment_ptr = 1
 ; MESA: kernarg_segment_byte_size = 16
 ; MESA: kernarg_segment_alignment = 4
 
 ; HSA: s_mov_b64 s[8:9], 0{{$}}
 ; MESA: s_mov_b64 s[8:9], s[4:5]{{$}}
 ; GCN: s_swappc_b64
 
-; COV5: .amdhsa_kernarg_size 0
+; HSA: .amdhsa_kernarg_size 0
 define amdgpu_kernel void @kernel_call_implicitarg_ptr_func_empty_implicit0() #3 {
   call void @func_implicitarg_ptr()
   ret void
 }
 
 ; GCN-LABEL: {{^}}opencl_kernel_call_implicitarg_ptr_func_empty:
-; HSA: enable_sgpr_kernarg_segment_ptr = 1
-; HSA: kernarg_segment_byte_size = 48
-; HSA: kernarg_segment_alignment = 4
 ; MESA: enable_sgpr_kernarg_segment_ptr = 1
 ; MESA: kernarg_segment_byte_size = 16
 ; GCN: s_mov_b64 s[8:9], s[4:5]
 ; GCN-NOT: s4
 ; GCN-NOT: s5
 ; GCN: s_swappc_b64
 
-; COV5: .amdhsa_kernarg_size 48
+; HSA: .amdhsa_kernarg_size 48
 define amdgpu_kernel void @opencl_kernel_call_implicitarg_ptr_func_empty() #1 {
   call void @func_implicitarg_ptr()
   ret void
 }
 
 ; GCN-LABEL: {{^}}kernel_call_implicitarg_ptr_func:
-; HSA: enable_sgpr_kernarg_segment_ptr = 1
-; HSA: kernarg_segment_byte_size = 168
-; HSA: kernarg_segment_alignment = 4
-
 ; MESA: enable_sgpr_kernarg_segment_ptr = 1
 ; MESA: kernarg_segment_byte_size = 128
 ; MESA: kernarg_segment_alignment = 4
 
 ; HSA: s_add_u32 s8, s4, 0x70
 ; MESA: s_add_u32 s8, s4, 0x70
 
 ; GCN: s_addc_u32 s9, s5, 0{{$}}
 ; GCN: s_swappc_b64
 
+; COV4: .amdhsa_kernarg_size 168
 ; COV5: .amdhsa_kernarg_size 368
 define amdgpu_kernel void @kernel_call_implicitarg_ptr_func([112 x i8]) #0 {
   call void @func_implicitarg_ptr()
   ret void
 }
 
 ; GCN-LABEL: {{^}}opencl_kernel_call_implicitarg_ptr_func:
-; HSA: enable_sgpr_kernarg_segment_ptr = 1
-; HSA: kernarg_segment_byte_size = 160
-; HSA: kernarg_segment_alignment = 4
 ; MESA: enable_sgpr_kernarg_segment_ptr = 1
 ; MESA: kernarg_segment_byte_size = 128
 ; MESA: kernarg_segment_alignment = 4
 
 ; GCN: s_add_u32 s8, s4, 0x70
 ; GCN: s_addc_u32 s9, s5, 0{{$}}
 ; GCN: s_swappc_b64
 
-; COV5: .amdhsa_kernarg_size 160
+; HSA: .amdhsa_kernarg_size 160
 define amdgpu_kernel void @opencl_kernel_call_implicitarg_ptr_func([112 x i8]) #1 {
   call void @func_implicitarg_ptr()
   ret void
 }
 
 ; GCN-LABEL: {{^}}func_call_implicitarg_ptr_func:
 ; GCN-NOT: s8
 ; GCN-NOT: s9

 ; GCN: s_addc_u32 s9, s5, 0
 ; GCN: s_swappc_b64
 define amdgpu_kernel void @kernel_call_kernarg_implicitarg_ptr_func([112 x i8]) #0 {
   call void @func_kernarg_implicitarg_ptr()
   ret void
 }
 
 ; GCN-LABEL: {{^}}kernel_implicitarg_no_struct_align_padding:
-; HSA: kernarg_segment_byte_size = 120
-; HSA: kernarg_segment_alignment = 6
 ; MESA: kernarg_segment_byte_size = 84
 ; MESA: kernarg_segment_alignment = 6
 
-; COV5: .amdhsa_kernarg_size 120
+; HSA: .amdhsa_kernarg_size 120
 define amdgpu_kernel void @kernel_implicitarg_no_struct_align_padding(<16 x i32>, i32) #1 {
   %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %load = load volatile i32, ptr addrspace(4) %implicitarg.ptr
   ret void
 }
 
-; HSA-LABEL: Kernels:
-; HSA-LABEL: - Name:            kernel_implicitarg_ptr_empty
-; HSA: CodeProps:
-; HSA: KernargSegmentSize: 56
-; HSA: KernargSegmentAlign: 8
-
-; HSA-LABEL: - Name:            kernel_implicitarg_ptr_empty_0implicit
-; HSA: KernargSegmentSize: 0
-; HSA: KernargSegmentAlign: 4
-
-; HSA-LABEL: - Name:            opencl_kernel_implicitarg_ptr_empty
-; HSA: KernargSegmentSize: 48
-; HSA: KernargSegmentAlign: 8
-
-; HSA-LABEL: - Name:            kernel_implicitarg_ptr
-; HSA: KernargSegmentSize: 168
-; HSA: KernargSegmentAlign: 8
-
-; HSA-LABEL: - Name:            opencl_kernel_implicitarg_ptr
-; HSA: KernargSegmentSize: 160
-; HSA: KernargSegmentAlign: 8
-
-; HSA-LABEL: - Name:            kernel_call_implicitarg_ptr_func_empty
-; HSA: KernargSegmentSize: 56
-; HSA: KernargSegmentAlign: 8
-
-; HSA-LABEL: - Name:            kernel_call_implicitarg_ptr_func_empty_implicit0
-; HSA: KernargSegmentSize: 0
-; HSA: KernargSegmentAlign: 4
-
-; HSA-LABEL:  - Name:            opencl_kernel_call_implicitarg_ptr_func_empty
-; HSA: KernargSegmentSize: 48
-; HSA: KernargSegmentAlign: 8
-
-; HSA-LABEL:  - Name:            kernel_call_implicitarg_ptr_func
-; HSA: KernargSegmentSize: 168
-; HSA: KernargSegmentAlign: 8
-
-; HSA-LABEL:  - Name:            opencl_kernel_call_implicitarg_ptr_func
-; HSA: KernargSegmentSize: 160
-; HSA: KernargSegmentAlign: 8
-
-; HSA-LABEL: - Name:            kernel_call_kernarg_implicitarg_ptr_func
-; HSA: KernargSegmentSize: 168
-; HSA: KernargSegmentAlign: 8
-
-; HSA-LABEL: - Name:            kernel_implicitarg_no_struct_align_padding
-; HSA: KernargSegmentSize: 120
-; HSA: KernargSegmentAlign: 64
-
-; COV5-LABEL:   amdhsa.kernels:
-; COV5:         .kernarg_segment_align: 8
+; HSA-LABEL:   amdhsa.kernels:
+; HSA:         .kernarg_segment_align: 8
 ; COV5-NEXT:    .kernarg_segment_size: 256
-; COV5-LABEL:   .name:           kernel_implicitarg_ptr_empty
+; COV4-NEXT:    .kernarg_segment_size: 56
+; HSA-LABEL:   .name:           kernel_implicitarg_ptr_empty
 
-; COV5:         .kernarg_segment_align: 4
-; COV5-NEXT:    .kernarg_segment_size: 0
-; COV5-LABEL:   .name:           kernel_implicitarg_ptr_empty_0implicit
+; HSA:         .kernarg_segment_align: 4
+; HSA-NEXT:    .kernarg_segment_size: 0
+; HSA-LABEL:   .name:           kernel_implicitarg_ptr_empty_0implicit
+
+; HSA:         .kernarg_segment_align: 8
+; HSA-NEXT:    .kernarg_segment_size: 48
+; HSA-LABEL:   .name:           opencl_kernel_implicitarg_ptr_empty
 
-; COV5:         .kernarg_segment_align: 8
-; COV5-NEXT:    .kernarg_segment_size: 48
-; COV5-LABEL:   .name:           opencl_kernel_implicitarg_ptr_empty
-
-; COV5:         .kernarg_segment_align: 8
+; HSA:         .kernarg_segment_align: 8
 ; COV5-NEXT:    .kernarg_segment_size: 368
-; COV5-LABEL:   .name:           kernel_implicitarg_ptr
+; COV4-NEXT:    .kernarg_segment_size: 168
+; HSA-LABEL:   .name:           kernel_implicitarg_ptr
 
-; COV5:         .kernarg_segment_align: 8
-; COV5-NEXT:    .kernarg_segment_size: 160
-; COV5-LABEL:   .name:           opencl_kernel_implicitarg_ptr
+; HSA:         .kernarg_segment_align: 8
+; HSA-NEXT:    .kernarg_segment_size: 160
+; HSA-LABEL:   .name:           opencl_kernel_implicitarg_ptr
 
-; COV5:         .kernarg_segment_align: 8
+; HSA:         .kernarg_segment_align: 8
 ; COV5-NEXT:    .kernarg_segment_size: 256
-; COV5-LABEL:   .name:           kernel_call_implicitarg_ptr_func_empty
-
-; COV5:         .kernarg_segment_align: 4
-; COV5-NEXT:    .kernarg_segment_size: 0
-; COV5-LABEL:   .name:           kernel_call_implicitarg_ptr_func_empty_implicit0
+; COV4-NEXT:    .kernarg_segment_size: 56
+; HSA-LABEL:   .name:           kernel_call_implicitarg_ptr_func_empty
 
-; COV5:         .kernarg_segment_align: 8
-; COV5-NEXT:    .kernarg_segment_size: 48
-; COV5-LABEL:   .name:           opencl_kernel_call_implicitarg_ptr_func_empty
+; HSA:         .kernarg_segment_align: 4
+; HSA-NEXT:    .kernarg_segment_size: 0
+; HSA-LABEL:   .name:           kernel_call_implicitarg_ptr_func_empty_implicit0
+
+; HSA:         .kernarg_segment_align: 8
+; HSA-NEXT:    .kernarg_segment_size: 48
+; HSA-LABEL:   .name:           opencl_kernel_call_implicitarg_ptr_func_empty
 
-; COV5:         .kernarg_segment_align: 8
+; HSA:         .kernarg_segment_align: 8
 ; COV5-NEXT:    .kernarg_segment_size: 368
-; COV5-LABEL:   .name:           kernel_call_implicitarg_ptr_func
+; COV4-NEXT:    .kernarg_segment_size: 168
+; HSA-LABEL:   .name:           kernel_call_implicitarg_ptr_func
 
-; COV5:         .kernarg_segment_align: 8
-; COV5-NEXT:    .kernarg_segment_size: 160
-; COV5-LABEL:   .name:           opencl_kernel_call_implicitarg_ptr_func
+; HSA:         .kernarg_segment_align: 8
+; HSA-NEXT:    .kernarg_segment_size: 160
+; HSA-LABEL:   .name:           opencl_kernel_call_implicitarg_ptr_func
 
-; COV5:         .kernarg_segment_align: 8
+; HSA:         .kernarg_segment_align: 8
 ; COV5-NEXT:    .kernarg_segment_size: 368
-; COV5-LABEL:   .name:           kernel_call_kernarg_implicitarg_ptr_func
+; COV4-NEXT:    .kernarg_segment_size: 168
+; HSA-LABEL:   .name:           kernel_call_kernarg_implicitarg_ptr_func
 
-; COV5:         .kernarg_segment_align: 64
-; COV5-NEXT:    .kernarg_segment_size: 120
-; COV5-LABEL:   .name:           kernel_implicitarg_no_struct_align_padding
+; HSA:         .kernarg_segment_align: 64
+; HSA-NEXT:    .kernarg_segment_size: 120
+; HSA-LABEL:   .name:           kernel_implicitarg_no_struct_align_padding
 
 declare ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr() #2
 declare ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr() #2
 
 attributes #0 = { nounwind noinline }
 attributes #1 = { nounwind noinline "amdgpu-implicitarg-num-bytes"="48" }
 attributes #2 = { nounwind readnone speculatable }
 attributes #3 = { nounwind noinline "amdgpu-implicitarg-num-bytes"="0" }
 
 !llvm.module.flags = !{!0}
 !0 = !{i32 1, !"amdgpu_code_object_version", i32 CODE_OBJECT_VERSION}

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.kernarg.segment.ptr.ll

-; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V2,HSA,ALL %s
-; RUN: llc -mtriple=amdgcn-mesa-mesa3d -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V2,OS-MESA3D,MESA,ALL %s
-; RUN: llc -mtriple=amdgcn-mesa-unknown -verify-machineinstrs < %s | FileCheck -check-prefixes=OS-UNKNOWN,MESA,ALL %s
+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V4,HSA,ALL %s
+; RUN: llc -mtriple=amdgcn-mesa-mesa3d -verify-machineinstrs < %s | FileCheck -check-prefixes=CO-V4,OS-MESA3D,ALL %s
+; RUN: llc -mtriple=amdgcn-mesa-unknown -verify-machineinstrs < %s | FileCheck -check-prefixes=OS-UNKNOWN,ALL %s
 
 ; ALL-LABEL: {{^}}test:
-; CO-V2: enable_sgpr_kernarg_segment_ptr = 1
-; HSA: kernarg_segment_byte_size = 8
-; HSA: kernarg_segment_alignment = 4
-
-; CO-V2: s_load_dword s{{[0-9]+}}, s[4:5], 0xa
+; OS-MESA3D: enable_sgpr_kernarg_segment_ptr = 1
+; CO-V4: s_load_dword s{{[0-9]+}}, s[4:5], 0xa
 
 ; OS-UNKNOWN: s_load_dword s{{[0-9]+}}, s[0:1], 0xa
+
+; HSA: .amdhsa_kernarg_size 8
+; HSA: .amdhsa_user_sgpr_kernarg_segment_ptr 1
 define amdgpu_kernel void @test(ptr addrspace(1) %out) #1 {
   %kernarg.segment.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
   %gep = getelementptr i32, ptr addrspace(4) %kernarg.segment.ptr, i64 10
   %value = load i32, ptr addrspace(4) %gep
   store i32 %value, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_implicit:
-; HSA: kernarg_segment_byte_size = 64
 ; OS-MESA3D: kernarg_segment_byte_size = 24
-; CO-V2: kernarg_segment_alignment = 4
+; OS-MESA3D: kernarg_segment_alignment = 4
 
 ; 10 + 9 (36 prepended implicit bytes) + 2(out pointer) = 21 = 0x15
 ; OS-UNKNOWN: s_load_dword s{{[0-9]+}}, s[0:1], 0x15
+; HSA:        .amdhsa_kernarg_size 8
 define amdgpu_kernel void @test_implicit(ptr addrspace(1) %out) #1 {
   %implicitarg.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %gep = getelementptr i32, ptr addrspace(4) %implicitarg.ptr, i64 10
   %value = load i32, ptr addrspace(4) %gep
   store i32 %value, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_implicit_alignment:
-; HSA: kernarg_segment_byte_size = 72
 ; OS-MESA3D: kernarg_segment_byte_size = 28
-; CO-V2: kernarg_segment_alignment = 4
-
+; OS-MESA3D: kernarg_segment_alignment = 4
 
 ; OS-UNKNOWN: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0xc
 ; HSA: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x4
 ; OS-MESA3D: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x3
 ; ALL: v_mov_b32_e32 [[V_VAL:v[0-9]+]], [[VAL]]
 ; MESA: buffer_store_dword [[V_VAL]]
 ; HSA: flat_store_dword v[{{[0-9]+:[0-9]+}}], [[V_VAL]]
+
+; HSA:        .amdhsa_kernarg_size 12
 define amdgpu_kernel void @test_implicit_alignment(ptr addrspace(1) %out, <2 x i8> %in) #1 {
   %implicitarg.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %val = load i32, ptr addrspace(4) %implicitarg.ptr
   store i32 %val, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}opencl_test_implicit_alignment
-; HSA: kernarg_segment_byte_size = 64
 ; OS-MESA3D: kernarg_segment_byte_size = 28
-; CO-V2: kernarg_segment_alignment = 4
-
+; OS-MESA3D: kernarg_segment_alignment = 4
 
 ; OS-UNKNOWN: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0xc
 ; HSA: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x4
 ; OS-MESA3D: s_load_dword [[VAL:s[0-9]+]], s[{{[0-9]+:[0-9]+}}], 0x3
 ; ALL: v_mov_b32_e32 [[V_VAL:v[0-9]+]], [[VAL]]
 ; MESA: buffer_store_dword [[V_VAL]]
 ; HSA: flat_store_dword v[{{[0-9]+:[0-9]+}}], [[V_VAL]]
+; HSA:        .amdhsa_kernarg_size 64
 define amdgpu_kernel void @opencl_test_implicit_alignment(ptr addrspace(1) %out, <2 x i8> %in) #2 {
   %implicitarg.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %val = load i32, ptr addrspace(4) %implicitarg.ptr
   store i32 %val, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_no_kernargs:
-; CO-V2: enable_sgpr_kernarg_segment_ptr = 0
-; CO-V2: kernarg_segment_byte_size = 0
+; OS-MESA3D: enable_sgpr_kernarg_segment_ptr = 0
+; OS-MESA3D: kernarg_segment_byte_size = 0
+; OS-MESA3D: kernarg_segment_alignment = 4
 
-; CO-V2: kernarg_segment_alignment = 4
 
-; HSA: s_mov_b64 [[NULL:s\[[0-9]+:[0-9]+\]]], 0{{$}}
-; HSA: s_load_dword s{{[0-9]+}}, [[NULL]], 0xa{{$}}
+; HSA: .amdhsa_kernarg_size 0
+; HSA: .amdhsa_user_sgpr_kernarg_segment_ptr 0
 define amdgpu_kernel void @test_no_kernargs() #1 {
   %kernarg.segment.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
   %gep = getelementptr i32, ptr addrspace(4) %kernarg.segment.ptr, i64 10
   %value = load i32, ptr addrspace(4) %gep
   store volatile i32 %value, ptr addrspace(1) undef
   ret void
 }
 
 ; ALL-LABEL: {{^}}opencl_test_implicit_alignment_no_explicit_kernargs:
-; HSA: kernarg_segment_byte_size = 48
-; OS-MESA3d: kernarg_segment_byte_size = 16
-; CO-V2: kernarg_segment_alignment = 4
+; OS-MESA3D: kernarg_segment_byte_size = 16
+; OS-MESA3D: kernarg_segment_alignment = 4
+; HSA:        .amdhsa_kernarg_size 48
 define amdgpu_kernel void @opencl_test_implicit_alignment_no_explicit_kernargs() #2 {
   %implicitarg.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %val = load volatile i32, ptr addrspace(4) %implicitarg.ptr
   store volatile i32 %val, ptr addrspace(1) null
   ret void
 }
 
 ; ALL-LABEL: {{^}}opencl_test_implicit_alignment_no_explicit_kernargs_round_up:
-; HSA: kernarg_segment_byte_size = 40
 ; OS-MESA3D: kernarg_segment_byte_size = 16
-; CO-V2: kernarg_segment_alignment = 4
+; OS-MESA3D: kernarg_segment_alignment = 4
+; HSA:        .amdhsa_kernarg_size 40
 define amdgpu_kernel void @opencl_test_implicit_alignment_no_explicit_kernargs_round_up() #3 {
   %implicitarg.ptr = call noalias ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
   %val = load volatile i32, ptr addrspace(4) %implicitarg.ptr
   store volatile i32 %val, ptr addrspace(1) null
   ret void
 }
 
+; ALL-LABEL: {{^}}func_kernarg_segment_ptr:
+; ALL: v_mov_b32_e32 v0, 0{{$}}
+; ALL: v_mov_b32_e32 v1, 0{{$}}
+define ptr addrspace(4) @func_kernarg_segment_ptr() {
+  %ptr = call ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr()
+  ret ptr addrspace(4) %ptr
+}
+
 declare ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr() #0
 declare ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr() #0
 
 attributes #0 = { nounwind readnone }
-attributes #1 = { nounwind }
+attributes #1 = { nounwind "amdgpu-implicitarg-num-bytes"="0" }
 attributes #2 = { nounwind "amdgpu-implicitarg-num-bytes"="48" }
 attributes #3 = { nounwind "amdgpu-implicitarg-num-bytes"="38" }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.queue.ptr.ll

 ; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
 ; RUN: not llc -mtriple=amdgcn-unknown-unknown -mcpu=kaveri -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=ERROR %s
 
 ; ERROR: in function test{{.*}}: unsupported hsa intrinsic without hsa target
 
 ; GCN-LABEL: {{^}}test:
-; GCN: enable_sgpr_queue_ptr = 1
 ; GCN: s_load_dword s{{[0-9]+}}, s[4:5], 0x0
+; GCN: .amdhsa_user_sgpr_queue_ptr 1
 define amdgpu_kernel void @test(ptr addrspace(1) %out) {
   %queue_ptr = call noalias ptr addrspace(4) @llvm.amdgcn.queue.ptr() #0
   %value = load i32, ptr addrspace(4) %queue_ptr
   store i32 %value, ptr addrspace(1) %out
   ret void
 }
 
 declare noalias ptr addrspace(4) @llvm.amdgcn.queue.ptr() #0
 
 attributes #0 = { nounwind readnone }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.workgroup.id.ll

-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=kaveri -verify-machineinstrs | FileCheck --check-prefixes=ALL,CO-V2  %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=carrizo -verify-machineinstrs | FileCheck --check-prefixes=ALL,CO-V2  %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs | FileCheck --check-prefixes=ALL,UNKNOWN-OS %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck --check-prefixes=ALL,UNKNOWN-OS %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tahiti -verify-machineinstrs | FileCheck -check-prefixes=ALL,CO-V2 %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefixes=ALL,CO-V2 %s
+; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,UNKNOWN-OS %s
+; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,UNKNOWN-OS %s
+; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,MESA3D %s
+; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,MESA3D %s
 
 declare i32 @llvm.amdgcn.workgroup.id.x() #0
 declare i32 @llvm.amdgcn.workgroup.id.y() #0
 declare i32 @llvm.amdgcn.workgroup.id.z() #0
 
 ; ALL-LABEL: {{^}}test_workgroup_id_x:
 
-; CO-V2: .amd_kernel_code_t
-; CO-V2: user_sgpr_count = 6
-; CO-V2: enable_sgpr_workgroup_id_x = 1
-; CO-V2: enable_sgpr_workgroup_id_y = 0
-; CO-V2: enable_sgpr_workgroup_id_z = 0
-; CO-V2: enable_sgpr_workgroup_info = 0
-; CO-V2: enable_vgpr_workitem_id = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_x = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_y = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_z = 0
-; CO-V2: .end_amd_kernel_code_t
+; MESA3D: .amd_kernel_code_t
+; MESA3D: user_sgpr_count = 6
+; MESA3D: enable_sgpr_workgroup_id_x = 1
+; MESA3D: enable_sgpr_workgroup_id_y = 0
+; MESA3D: enable_sgpr_workgroup_id_z = 0
+; MESA3D: enable_sgpr_workgroup_info = 0
+; MESA3D: enable_vgpr_workitem_id = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_x = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_y = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_z = 0
+; MESA3D: .end_amd_kernel_code_t
 
 ; UNKNOWN-OS: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s2{{$}}
-; CO-V2: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s6{{$}}
+; MESA3D: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s6{{$}}
 
 ; ALL: {{buffer|flat}}_store_dword {{.*}}[[VCOPY]]
 
-; CO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 6
-; ALL-NOCO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 2
+; MESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 6
+; ALL-NOMESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 2
 ; ALL: COMPUTE_PGM_RSRC2:TGID_X_EN: 1
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Y_EN: 0
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Z_EN: 0
 ; ALL: COMPUTE_PGM_RSRC2:TIDIG_COMP_CNT: 0
 define amdgpu_kernel void @test_workgroup_id_x(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workgroup.id.x()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_workgroup_id_y:
-; CO-V2: user_sgpr_count = 6
-; CO-V2: enable_sgpr_workgroup_id_x = 1
-; CO-V2: enable_sgpr_workgroup_id_y = 1
-; CO-V2: enable_sgpr_workgroup_id_z = 0
-; CO-V2: enable_sgpr_workgroup_info = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_x = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_y = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_z = 0
+; MESA3D: user_sgpr_count = 6
+; MESA3D: enable_sgpr_workgroup_id_x = 1
+; MESA3D: enable_sgpr_workgroup_id_y = 1
+; MESA3D: enable_sgpr_workgroup_id_z = 0
+; MESA3D: enable_sgpr_workgroup_info = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_x = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_y = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_z = 0
 
 ; UNKNOWN-OS: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s3{{$}}
 ; HSA: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s7{{$}}
 
 ; ALL: {{buffer|flat}}_store_dword {{.*}}[[VCOPY]]
 
-; CO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 6
-; ALL-NOCO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 2
+; MESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 6
+; ALL-NOMESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 2
 ; ALL: COMPUTE_PGM_RSRC2:TGID_X_EN: 1
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Y_EN: 1
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Z_EN: 0
 ; ALL: COMPUTE_PGM_RSRC2:TIDIG_COMP_CNT: 0
 define amdgpu_kernel void @test_workgroup_id_y(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workgroup.id.y()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_workgroup_id_z:
-; CO-V2: user_sgpr_count = 6
-; CO-V2: enable_sgpr_workgroup_id_x = 1
-; CO-V2: enable_sgpr_workgroup_id_y = 0
-; CO-V2: enable_sgpr_workgroup_id_z = 1
-; CO-V2: enable_sgpr_workgroup_info = 0
-; CO-V2: enable_vgpr_workitem_id = 0
-; CO-V2: enable_sgpr_private_segment_buffer = 1
-; CO-V2: enable_sgpr_dispatch_ptr = 0
-; CO-V2: enable_sgpr_queue_ptr = 0
-; CO-V2: enable_sgpr_kernarg_segment_ptr = 1
-; CO-V2: enable_sgpr_dispatch_id = 0
-; CO-V2: enable_sgpr_flat_scratch_init = 0
-; CO-V2: enable_sgpr_private_segment_size = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_x = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_y = 0
-; CO-V2: enable_sgpr_grid_workgroup_count_z = 0
+; MESA3D: user_sgpr_count = 6
+; MESA3D: enable_sgpr_workgroup_id_x = 1
+; MESA3D: enable_sgpr_workgroup_id_y = 0
+; MESA3D: enable_sgpr_workgroup_id_z = 1
+; MESA3D: enable_sgpr_workgroup_info = 0
+; MESA3D: enable_vgpr_workitem_id = 0
+; MESA3D: enable_sgpr_private_segment_buffer = 1
+; MESA3D: enable_sgpr_dispatch_ptr = 0
+; MESA3D: enable_sgpr_queue_ptr = 0
+; MESA3D: enable_sgpr_kernarg_segment_ptr = 1
+; MESA3D: enable_sgpr_dispatch_id = 0
+; MESA3D: enable_sgpr_flat_scratch_init = 0
+; MESA3D: enable_sgpr_private_segment_size = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_x = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_y = 0
+; MESA3D: enable_sgpr_grid_workgroup_count_z = 0
 
 ; UNKNOWN-OS: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s3{{$}}
 ; HSA: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s7{{$}}
 
 ; ALL: {{buffer|flat}}_store_dword {{.*}}[[VCOPY]]
 
-; CO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 6
-; ALL-NOCO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 2
+; MESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 6
+; ALL-NOMESA3D: COMPUTE_PGM_RSRC2:USER_SGPR: 2
 ; ALL: COMPUTE_PGM_RSRC2:TGID_X_EN: 1
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Y_EN: 0
 ; ALL: COMPUTE_PGM_RSRC2:TGID_Z_EN: 1
 ; ALL: COMPUTE_PGM_RSRC2:TIDIG_COMP_CNT: 0
 define amdgpu_kernel void @test_workgroup_id_z(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workgroup.id.z()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 attributes #0 = { nounwind readnone }
 attributes #1 = { nounwind }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 CODE_OBJECT_VERSION}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.workitem.id.ll

-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=kaveri -verify-machineinstrs | FileCheck --check-prefixes=ALL,CO-V2,UNPACKED  %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=carrizo -mattr=-flat-for-global -verify-machineinstrs | FileCheck --check-prefixes=ALL,CO-V2,UNPACKED  %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mcpu=hawaii -verify-machineinstrs | FileCheck --check-prefixes=ALL,MESA,UNPACKED %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs | FileCheck --check-prefixes=ALL,MESA,UNPACKED %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-unknown-mesa3d -mcpu=hawaii -verify-machineinstrs | FileCheck -check-prefixes=ALL,CO-V2,UNPACKED %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs | FileCheck -check-prefixes=ALL,CO-V2,UNPACKED %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a -verify-machineinstrs | FileCheck -check-prefixes=ALL,PACKED-TID %s
-; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1100 -verify-machineinstrs -amdgpu-enable-vopd=0 | FileCheck -check-prefixes=ALL,PACKED-TID %s
+; RUN: llc -march=amdgcn -mcpu=hawaii -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,MESA,UNPACKED %s
+; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck --check-prefixes=ALL,MESA,UNPACKED %s
+; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=hawaii -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,MESA3D,UNPACKED %s
+; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,MESA3D,UNPACKED %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx90a -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,PACKED-TID %s
+; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=gfx1100 -verify-machineinstrs -amdgpu-enable-vopd=0 < %s | FileCheck -check-prefixes=ALL,PACKED-TID %s
 
 declare i32 @llvm.amdgcn.workitem.id.x() #0
 declare i32 @llvm.amdgcn.workitem.id.y() #0
 declare i32 @llvm.amdgcn.workitem.id.z() #0
 
 ; MESA: .section .AMDGPU.config
 ; MESA: .long 47180
 ; MESA-NEXT: .long 132{{$}}
 
 ; ALL-LABEL: {{^}}test_workitem_id_x:
-; CO-V2: enable_vgpr_workitem_id = 0
+; MESA3D: enable_vgpr_workitem_id = 0
 
 ; ALL-NOT: v0
 ; ALL: {{buffer|flat|global}}_store_{{dword|b32}} {{.*}}v0
 
 ; PACKED-TID: .amdhsa_system_vgpr_workitem_id 0
 define amdgpu_kernel void @test_workitem_id_x(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workitem.id.x()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 ; MESA: .section .AMDGPU.config
 ; MESA: .long 47180
 ; MESA-NEXT: .long 2180{{$}}
 
 ; ALL-LABEL: {{^}}test_workitem_id_y:
-; CO-V2: enable_vgpr_workitem_id = 1
-; CO-V2-NOT: v1
-; CO-V2: {{buffer|flat}}_store_dword {{.*}}v1
+; MESA3D: enable_vgpr_workitem_id = 1
+; MESA3D-NOT: v1
+; MESA3D: {{buffer|flat}}_store_dword {{.*}}v1
 
 ; PACKED-TID: v_bfe_u32 [[ID:v[0-9]+]], v0, 10, 10
 ; PACKED-TID: {{buffer|flat|global}}_store_{{dword|b32}} {{.*}}[[ID]]
 ; PACKED-TID: .amdhsa_system_vgpr_workitem_id 1
 define amdgpu_kernel void @test_workitem_id_y(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workitem.id.y()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 ; MESA: .section .AMDGPU.config
 ; MESA: .long 47180
 ; MESA-NEXT: .long 4228{{$}}
 
 ; ALL-LABEL: {{^}}test_workitem_id_z:
-; CO-V2: enable_vgpr_workitem_id = 2
-; CO-V2-NOT: v2
-; CO-V2: {{buffer|flat}}_store_dword {{.*}}v2
+; MESA3D: enable_vgpr_workitem_id = 2
+; MESA3D-NOT: v2
+; MESA3D: {{buffer|flat}}_store_dword {{.*}}v2
 
 ; PACKED-TID: v_bfe_u32 [[ID:v[0-9]+]], v0, 20, 10
 ; PACKED-TID: {{buffer|flat|global}}_store_{{dword|b32}} {{.*}}[[ID]]
 ; PACKED-TID: .amdhsa_system_vgpr_workitem_id 2
 define amdgpu_kernel void @test_workitem_id_z(ptr addrspace(1) %out) #1 {
   %id = call i32 @llvm.amdgcn.workitem.id.z()
   store i32 %id, ptr addrspace(1) %out
   ret void
 }
 
 ; FIXME: Packed tid should avoid the and
 ; ALL-LABEL: {{^}}test_reqd_workgroup_size_x_only:
-; CO-V2: enable_vgpr_workitem_id = 0
+; MESA3D: enable_vgpr_workitem_id = 0
 
 ; ALL-DAG: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
 ; UNPACKED-DAG: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v0
 
 ; PACKED: v_and_b32_e32 [[MASKED:v[0-9]+]], 0x3ff, v0
 ; PACKED: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[MASKED]]
 
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 define amdgpu_kernel void @test_reqd_workgroup_size_x_only(ptr %out) !reqd_work_group_size !0 {
   %id.x = call i32 @llvm.amdgcn.workitem.id.x()
   %id.y = call i32 @llvm.amdgcn.workitem.id.y()
   %id.z = call i32 @llvm.amdgcn.workitem.id.z()
   store volatile i32 %id.x, ptr %out
   store volatile i32 %id.y, ptr %out
   store volatile i32 %id.z, ptr %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_reqd_workgroup_size_y_only:
-; CO-V2: enable_vgpr_workitem_id = 1
+; MESA3D: enable_vgpr_workitem_id = 1
 
 ; ALL: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 
 ; UNPACKED: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v1
 
 ; PACKED: v_bfe_u32 [[MASKED:v[0-9]+]], v0, 10, 10
 ; PACKED: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, [[MASKED]]
 
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 define amdgpu_kernel void @test_reqd_workgroup_size_y_only(ptr %out) !reqd_work_group_size !1 {
   %id.x = call i32 @llvm.amdgcn.workitem.id.x()
   %id.y = call i32 @llvm.amdgcn.workitem.id.y()
   %id.z = call i32 @llvm.amdgcn.workitem.id.z()
   store volatile i32 %id.x, ptr %out
   store volatile i32 %id.y, ptr %out
   store volatile i32 %id.z, ptr %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}test_reqd_workgroup_size_z_only:
-; CO-V2: enable_vgpr_workitem_id = 2
+; MESA3D: enable_vgpr_workitem_id = 2
 
 ; ALL: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 ; ALL: flat_store_{{dword|b32}} v{{\[[0-9]+:[0-9]+\]}}, [[ZERO]]
 
 ; UNPACKED: flat_store_dword v{{\[[0-9]+:[0-9]+\]}}, v2
 
 ; PACKED: v_bfe_u32 [[MASKED:v[0-9]+]], v0, 10, 20

 attributes #0 = { nounwind readnone }
 attributes #1 = { nounwind }
 
 !llvm.module.flags = !{!3}
 
 !0 = !{i32 64, i32 1, i32 1}
 !1 = !{i32 1, i32 64, i32 1}
 !2 = !{i32 1, i32 1, i32 64}
-!3 = !{i32 1, !"amdgpu_code_object_version", i32 CODE_OBJECT_VERSION}
+!3 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/no-hsa-graphics-shaders.ll

 }
 
 ; CHECK: in function geometry_s{{.*}}: unsupported non-compute shaders with HSA
 define amdgpu_gs void @geometry_shader() #0 {
   ret void
 }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/nop-data.ll

 ; CHECK-NEXT: s_nop 0
 
 ; CHECK-NEXT: s_nop 0
 ; CHECK-NEXT: s_nop 0
 ; CHECK-NEXT: s_nop 0
 ; CHECK-NEXT: s_nop 0
 ; CHECK-NEXT: s_nop 0
 ; CHECK-NEXT: s_nop 0
-; CHECK-NEXT: s_nop 0  // 0000000001FC: BF800000
+; CHECK-NEXT: s_nop 0  // 0000000000FC: BF800000
 
 ; CHECK-EMPTY:
 ; CHECK-NEXT: <kernel1>:
 ; CHECK: s_endpgm
 define amdgpu_kernel void @kernel1(ptr addrspace(4) %ptr.out) align 256 {
 entry:
   ret void
 }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/private-element-size.ll

-; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=-promote-alloca,+max-private-element-size-16 -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap --check-prefixes=HSA-ELT16,ALL %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=-promote-alloca,+max-private-element-size-8 -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap --check-prefixes=HSA-ELT8,ALL,HSA-ELTGE8 %s
-; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=-promote-alloca,+max-private-element-size-4 -verify-machineinstrs < %s | FileCheck -allow-deprecated-dag-overlap --check-prefixes=HSA-ELT4,ALL %s
-
-
-; ALL-LABEL: {{^}}private_elt_size_v4i32:
-
-; HSA-ELT16: private_element_size = 3
-; HSA-ELT8: private_element_size = 2
-; HSA-ELT4: private_element_size = 1
-
-
-; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:16
-; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
-; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
-
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:24{{$}}
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:16
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:40
-
-; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
-; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
-
-
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:16{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:20{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:24{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:28{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:32{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:36{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:40{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:44{{$}}
-
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:4{{$}}
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:8{{$}}
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:12{{$}}
-define amdgpu_kernel void @private_elt_size_v4i32(ptr addrspace(1) %out, ptr addrspace(1) %index.array) #0 {
-entry:
-  %tid = call i32 @llvm.amdgcn.workitem.id.x()
-  %idxprom = sext i32 %tid to i64
-  %gep.index = getelementptr inbounds i32, ptr addrspace(1) %index.array, i64 %idxprom
-  %index.load = load i32, ptr addrspace(1) %gep.index
-  %index = and i32 %index.load, 2
-  %alloca = alloca [2 x <4 x i32>], align 16, addrspace(5)
-  %gep1 = getelementptr inbounds [2 x <4 x i32>], ptr addrspace(5) %alloca, i32 0, i32 1
-  store <4 x i32> zeroinitializer, ptr addrspace(5) %alloca
-  store <4 x i32> <i32 1, i32 2, i32 3, i32 4>, ptr addrspace(5) %gep1
-  %gep2 = getelementptr inbounds [2 x <4 x i32>], ptr addrspace(5) %alloca, i32 0, i32 %index
-  %load = load <4 x i32>, ptr addrspace(5) %gep2
-  store <4 x i32> %load, ptr addrspace(1) %out
-  ret void
-}
-
-; ALL-LABEL: {{^}}private_elt_size_v8i32:
-; HSA-ELT16: private_element_size = 3
-; HSA-ELT8: private_element_size = 2
-; HSA-ELT4: private_element_size = 1
-
-; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
-; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:48
-; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:64
-; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:80
-
-; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
-; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
-
-
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:40
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:48
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:56
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:88
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:80
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:72
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:64
-
-; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
-; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
-
-
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:32{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:36{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:40{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:44{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:48{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:52{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:56{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:60{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:64{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:68{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:72{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:76{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:80{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:84{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:88{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:92{{$}}
-
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:4{{$}}
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:8{{$}}
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:12{{$}}
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:16{{$}}
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:20{{$}}
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:24{{$}}
-; HSA-ELT4-DAG: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:28{{$}}
-define amdgpu_kernel void @private_elt_size_v8i32(ptr addrspace(1) %out, ptr addrspace(1) %index.array) #0 {
-entry:
-  %tid = call i32 @llvm.amdgcn.workitem.id.x()
-  %idxprom = sext i32 %tid to i64
-  %gep.index = getelementptr inbounds i32, ptr addrspace(1) %index.array, i64 %idxprom
-  %index.load = load i32, ptr addrspace(1) %gep.index
-  %index = and i32 %index.load, 2
-  %alloca = alloca [2 x <8 x i32>], align 32, addrspace(5)
-  %gep1 = getelementptr inbounds [2 x <8 x i32>], ptr addrspace(5) %alloca, i32 0, i32 1
-  store <8 x i32> zeroinitializer, ptr addrspace(5) %alloca
-  store <8 x i32> <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>, ptr addrspace(5) %gep1
-  %gep2 = getelementptr inbounds [2 x <8 x i32>], ptr addrspace(5) %alloca, i32 0, i32 %index
-  %load = load <8 x i32>, ptr addrspace(5) %gep2
-  store <8 x i32> %load, ptr addrspace(1) %out
-  ret void
-}
-
-
-; ALL-LABEL: {{^}}private_elt_size_i64:
-; HSA-ELT16: private_element_size = 3
-; HSA-ELT8: private_element_size = 2
-; HSA-ELT4: private_element_size = 1
-
-; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, {{off|v[0-9]}}, s[0:3], 0 offset:1
-; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, {{off|v[0-9]}}, s[0:3], 0 offset:2
-; HSA-ELTGE8-DAG: buffer_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]], v{{[0-9]+}}, s[0:3], 0 offen
-; HSA-ELTGE8: flat_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, [[VAL]]
-
-
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:16{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:20{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:24{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:28{{$}}
-
-; HSA-ELT4-DAG: buffer_load_dword v[[HI:[0-9]+]], v{{[0-9]+}}, s[0:3], 0 offen offset:4{{$}}
-; HSA-ELT4-DAG: buffer_load_dword v[[LO:[0-9]+]], v{{[0-9]+}}, s[0:3], 0 offen{{$}}
-; HSA-ELT4: flat_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v[[[LO]]:[[HI]]]
-define amdgpu_kernel void @private_elt_size_i64(ptr addrspace(1) %out, ptr addrspace(1) %index.array) #0 {
-entry:
-  %tid = call i32 @llvm.amdgcn.workitem.id.x()
-  %idxprom = sext i32 %tid to i64
-  %gep.index = getelementptr inbounds i32, ptr addrspace(1) %index.array, i64 %idxprom
-  %index.load = load i32, ptr addrspace(1) %gep.index
-  %index = and i32 %index.load, 2
-  %alloca = alloca [2 x i64], align 16, addrspace(5)
-  %gep1 = getelementptr inbounds [2 x i64], ptr addrspace(5) %alloca, i32 0, i32 1
-  store i64 0, ptr addrspace(5) %alloca
-  store i64 34359738602, ptr addrspace(5) %gep1
-  %gep2 = getelementptr inbounds [2 x i64], ptr addrspace(5) %alloca, i32 0, i32 %index
-  %load = load i64, ptr addrspace(5) %gep2
-  store i64 %load, ptr addrspace(1) %out
-  ret void
-}
-
-; ALL-LABEL: {{^}}private_elt_size_f64:
-; HSA-ELT16: private_element_size = 3
-; HSA-ELT8: private_element_size = 2
-; HSA-ELT4: private_element_size = 1
-
-; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:16
-; HSA-ELTGE8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:24
-; HSA-ELTGE8-DAG: buffer_load_dwordx2 [[VAL:v\[[0-9]+:[0-9]+\]]], v{{[0-9]+}}, s[0:3], 0 offen
-; HSA-ELTGE8: flat_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, [[VAL]]
-
-
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:16{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:20{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:24{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:28{{$}}
-
-; HSA-ELT4-DAG: buffer_load_dword v[[HI:[0-9]+]], v{{[0-9]+}}, s[0:3], 0 offen offset:4{{$}}
-; HSA-ELT4-DAG: buffer_load_dword v[[LO:[0-9]+]], v{{[0-9]+}}, s[0:3], 0 offen{{$}}
-; HSA-ELT4: flat_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v[[[LO]]:[[HI]]]
-define amdgpu_kernel void @private_elt_size_f64(ptr addrspace(1) %out, ptr addrspace(1) %index.array) #0 {
-entry:
-  %tid = call i32 @llvm.amdgcn.workitem.id.x()
-  %idxprom = sext i32 %tid to i64
-  %gep.index = getelementptr inbounds i32, ptr addrspace(1) %index.array, i64 %idxprom
-  %index.load = load i32, ptr addrspace(1) %gep.index
-  %index = and i32 %index.load, 2
-  %alloca = alloca [2 x double], align 16, addrspace(5)
-  %gep1 = getelementptr inbounds [2 x double], ptr addrspace(5) %alloca, i32 0, i32 1
-  store double 0.0, ptr addrspace(5) %alloca
-  store double 4.0, ptr addrspace(5) %gep1
-  %gep2 = getelementptr inbounds [2 x double], ptr addrspace(5) %alloca, i32 0, i32 %index
-  %load = load double, ptr addrspace(5) %gep2
-  store double %load, ptr addrspace(1) %out
-  ret void
-}
-
-; ALL-LABEL: {{^}}private_elt_size_v2i64:
-; HSA-ELT16: private_element_size = 3
-; HSA-ELT8: private_element_size = 2
-; HSA-ELT4: private_element_size = 1
-
-; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:16
-; HSA-ELT16-DAG: buffer_store_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
-; HSA-ELT16-DAG: buffer_load_dwordx4 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
-
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:16{{$}}
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:24
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:40
-; HSA-ELT8-DAG: buffer_store_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 0 offset:32
-
-; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
-; HSA-ELT8: buffer_load_dwordx2 {{v\[[0-9]+:[0-9]+\]}}, v{{[0-9]+}}, s[0:3], 0 offen
-
-
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:16{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:20{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:24{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:28{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:32{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:36{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:40{{$}}
-; HSA-ELT4-DAG: buffer_store_dword {{v[0-9]+}}, off, s[0:3], 0 offset:44{{$}}
-
-; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:12{{$}}
-; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:8{{$}}
-; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen offset:4{{$}}
-; HSA-ELT4: buffer_load_dword {{v[0-9]+}}, v{{[0-9]+}}, s[0:3], 0 offen{{$}}
-define amdgpu_kernel void @private_elt_size_v2i64(ptr addrspace(1) %out, ptr addrspace(1) %index.array) #0 {
-entry:
-  %tid = call i32 @llvm.amdgcn.workitem.id.x()
-  %idxprom = sext i32 %tid to i64
-  %gep.index = getelementptr inbounds i32, ptr addrspace(1) %index.array, i64 %idxprom
-  %index.load = load i32, ptr addrspace(1) %gep.index
-  %index = and i32 %index.load, 2
-  %alloca = alloca [2 x <2 x i64>], align 16, addrspace(5)
-  %gep1 = getelementptr inbounds [2 x <2 x i64>], ptr addrspace(5) %alloca, i32 0, i32 1
-  store <2 x i64> zeroinitializer, ptr addrspace(5) %alloca
-  store <2 x i64> <i64 1, i64 2>, ptr addrspace(5) %gep1
-  %gep2 = getelementptr inbounds [2 x <2 x i64>], ptr addrspace(5) %alloca, i32 0, i32 %index
-  %load = load <2 x i64>, ptr addrspace(5) %gep2
-  store <2 x i64> %load, ptr addrspace(1) %out
-  ret void
-}
-
-declare i32 @llvm.amdgcn.workitem.id.x() #1
-
-attributes #0 = { nounwind }
-attributes #1 = { nounwind readnone }
-
-!llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}

llvm/test/CodeGen/AMDGPU/promote-alloca-no-opts.ll

 ; RUN: llc -O0 -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=kaveri -mattr=+promote-alloca < %s | FileCheck -check-prefix=NOOPTS -check-prefix=ALL %s
 ; RUN: llc -O1 -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mcpu=kaveri -mattr=+promote-alloca < %s | FileCheck -check-prefix=OPTS -check-prefix=ALL %s
 
 ; ALL-LABEL: {{^}}promote_alloca_i32_array_array:
-; NOOPTS: workgroup_group_segment_byte_size = 0{{$}}
+; NOOPTS: .amdhsa_group_segment_fixed_size 0
 ; NOOPTS-NOT: ds_write
 ; OPTS: ds_write
 define amdgpu_kernel void @promote_alloca_i32_array_array(ptr addrspace(1) %out, i32 %index) #0 {
 entry:
   %alloca = alloca [2 x [2 x i32]], addrspace(5)
   %gep1 = getelementptr inbounds [2 x [2 x i32]], ptr addrspace(5) %alloca, i32 0, i32 0, i32 1
   store i32 0, ptr addrspace(5) %alloca
   store i32 1, ptr addrspace(5) %gep1
   %gep2 = getelementptr inbounds [2 x [2 x i32]], ptr addrspace(5) %alloca, i32 0, i32 0, i32 %index
   %load = load i32, ptr addrspace(5) %gep2
   store i32 %load, ptr addrspace(1) %out
   ret void
 }
 
 ; ALL-LABEL: {{^}}optnone_promote_alloca_i32_array_array:
-; ALL: workgroup_group_segment_byte_size = 0{{$}}
+; ALL: .amdhsa_group_segment_fixed_size 0
 ; ALL-NOT: ds_write
 define amdgpu_kernel void @optnone_promote_alloca_i32_array_array(ptr addrspace(1) %out, i32 %index) #1 {
 entry:
   %alloca = alloca [2 x [2 x i32]], addrspace(5)
   %gep1 = getelementptr inbounds [2 x [2 x i32]], ptr addrspace(5) %alloca, i32 0, i32 0, i32 1
   store i32 0, ptr addrspace(5) %alloca
   store i32 1, ptr addrspace(5) %gep1
   %gep2 = getelementptr inbounds [2 x [2 x i32]], ptr addrspace(5) %alloca, i32 0, i32 0, i32 %index
   %load = load i32, ptr addrspace(5) %gep2
   store i32 %load, ptr addrspace(1) %out
   ret void
 }
 
 attributes #0 = { nounwind "amdgpu-flat-work-group-size"="64,64" }
 attributes #1 = { nounwind optnone noinline "amdgpu-flat-work-group-size"="64,64" }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/promote-alloca-padding-size-estimate.ll

 
 
 @lds0 = internal unnamed_addr addrspace(3) global [32 x <4 x i32>] undef, align 16
 @lds2 = internal unnamed_addr addrspace(3) global [32 x i64] undef, align 8
 @lds1 = internal unnamed_addr addrspace(3) global [73 x i32] undef, align 4
 
 
 ; GCN-LABEL: {{^}}promote_alloca_size_order_0:
-; GCN: workgroup_group_segment_byte_size = 1060
+; GCN: .amdhsa_group_segment_fixed_size 1060
 define amdgpu_kernel void @promote_alloca_size_order_0(ptr addrspace(1) nocapture %out, ptr addrspace(1) nocapture %in, i32 %idx) #0 {
 entry:
   %stack = alloca [5 x i32], align 4, addrspace(5)
   %tmp0 = load i32, ptr addrspace(1) %in, align 4
   %arrayidx1 = getelementptr inbounds [5 x i32], ptr addrspace(5) %stack, i32 0, i32 %tmp0
   store i32 4, ptr addrspace(5) %arrayidx1, align 4
   %arrayidx2 = getelementptr inbounds i32, ptr addrspace(1) %in, i32 1
   %tmp1 = load i32, ptr addrspace(1) %arrayidx2, align 4
entry:
 
   %gep.lds0 = getelementptr inbounds [32 x <4 x i32>], ptr addrspace(3) @lds0, i32 0, i32 %idx
   store volatile <4 x i32> zeroinitializer, ptr addrspace(3) %gep.lds0, align 16
 
   ret void
 }
 
 ; GCN-LABEL: {{^}}promote_alloca_size_order_1:
-; GCN: workgroup_group_segment_byte_size = 1072
+; GCN: .amdhsa_group_segment_fixed_size 1072
 define amdgpu_kernel void @promote_alloca_size_order_1(ptr addrspace(1) nocapture %out, ptr addrspace(1) nocapture %in, i32 %idx) #0 {
 entry:
   %stack = alloca [5 x i32], align 4, addrspace(5)
   %tmp0 = load i32, ptr addrspace(1) %in, align 4
   %arrayidx1 = getelementptr inbounds [5 x i32], ptr addrspace(5) %stack, i32 0, i32 %tmp0
   store i32 4, ptr addrspace(5) %arrayidx1, align 4
   %arrayidx2 = getelementptr inbounds i32, ptr addrspace(1) %in, i32 1
   %tmp1 = load i32, ptr addrspace(1) %arrayidx2, align 4

 
 @lds3 = internal unnamed_addr addrspace(3) global [13 x i32] undef, align 4
 @lds4 = internal unnamed_addr addrspace(3) global [63 x <4 x i32>] undef, align 16
 
 ; The guess from the alignment padding pushes this over the determined
 ; size limit, so it isn't promoted
 
 ; GCN-LABEL: {{^}}promote_alloca_align_pad_guess_over_limit:
-; GCN: workgroup_group_segment_byte_size = 1060
+; GCN: .amdhsa_group_segment_fixed_size 1060
 define amdgpu_kernel void @promote_alloca_align_pad_guess_over_limit(ptr addrspace(1) nocapture %out, ptr addrspace(1) nocapture %in, i32 %idx) #0 {
 entry:
   %stack = alloca [5 x i32], align 4, addrspace(5)
   %tmp0 = load i32, ptr addrspace(1) %in, align 4
   %arrayidx1 = getelementptr inbounds [5 x i32], ptr addrspace(5) %stack, i32 0, i32 %tmp0
   store i32 4, ptr addrspace(5) %arrayidx1, align 4
   %arrayidx2 = getelementptr inbounds i32, ptr addrspace(1) %in, i32 1
   %tmp1 = load i32, ptr addrspace(1) %arrayidx2, align 4
entry:
   store volatile <4 x i32> zeroinitializer, ptr addrspace(3) %gep.lds4, align 16
 
   ret void
 }
 
 attributes #0 = { nounwind "amdgpu-flat-work-group-size"="64,64" "amdgpu-waves-per-eu"="1,7" }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/CodeGen/AMDGPU/tid-code-object-v2-backwards-compatibility.ll

-; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90c -mattr=-xnack < %s 2>&1 | FileCheck --check-prefix=GFX90C-VALID %s
-; RUN: not --crash llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90c < %s 2>&1 | FileCheck --check-prefix=GFX90C-ERROR %s
-; RUN: not --crash llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx940 < %s 2>&1 | FileCheck --check-prefix=GFX940-ERROR %s
-
-; GFX90C-VALID: .hsa_code_object_isa 9,0,12,"AMD","AMDGPU"
-; GFX90C-VALID: .amd_amdgpu_isa "amdgcn-amd-amdhsa--gfx90c"
-; GFX90C-ERROR: LLVM ERROR: AMD GPU code object V2 does not support processor gfx90c with XNACK being ON or ANY
-
-; GFX940-ERROR: LLVM ERROR: AMD GPU code object V2 does not support processor gfx940
-
-!llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}

llvm/test/CodeGen/AMDGPU/trap-abis.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck --check-prefix=NOHSA-TRAP-GFX900-V2 %s
 ; RUN: sed 's/CODE_OBJECT_VERSION/300/g' %s | llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck --check-prefix=NOHSA-TRAP-GFX900-V3 %s
 ; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck --check-prefix=NOHSA-TRAP-GFX900-V4 %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -verify-machineinstrs | FileCheck --check-prefix=HSA-TRAP-GFX803-V2 %s
 ; RUN: sed 's/CODE_OBJECT_VERSION/300/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -verify-machineinstrs | FileCheck --check-prefix=HSA-TRAP-GFX803-V3 %s
 ; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -verify-machineinstrs | FileCheck --check-prefix=HSA-TRAP-GFX803-V4 %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs | FileCheck --check-prefix=HSA-TRAP-GFX900-V2 %s
 ; RUN: sed 's/CODE_OBJECT_VERSION/300/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs | FileCheck --check-prefix=HSA-TRAP-GFX900-V3 %s
 ; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs | FileCheck --check-prefix=HSA-TRAP-GFX900-V4 %s
-; RUN: sed 's/CODE_OBJECT_VERSION/200/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-trap-handler -verify-machineinstrs | FileCheck --check-prefix=HSA-NOTRAP-GFX900-V2 %s
 ; RUN: sed 's/CODE_OBJECT_VERSION/300/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-trap-handler -verify-machineinstrs | FileCheck --check-prefix=HSA-NOTRAP-GFX900-V3 %s
 ; RUN: sed 's/CODE_OBJECT_VERSION/400/g' %s | llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-trap-handler -verify-machineinstrs | FileCheck --check-prefix=HSA-NOTRAP-GFX900-V4 %s
 
 declare void @llvm.trap() #0
 declare void @llvm.debugtrap() #1
 
 define amdgpu_kernel void @trap(ptr addrspace(1) nocapture readonly %arg0) {
-; NOHSA-TRAP-GFX900-V2-LABEL: trap:
-; NOHSA-TRAP-GFX900-V2:       ; %bb.0:
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[0:1], s[2:3], 0x24
-; NOHSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
-; NOHSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 1
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; NOHSA-TRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[0:1]
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_endpgm
-;
 ; NOHSA-TRAP-GFX900-V3-LABEL: trap:
 ; NOHSA-TRAP-GFX900-V3:       ; %bb.0:
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[0:1], s[2:3], 0x24
 ; NOHSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; NOHSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v1, 1
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; NOHSA-TRAP-GFX900-V3-NEXT:    global_store_dword v0, v1, s[0:1]
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_endpgm
 ;
 ; NOHSA-TRAP-GFX900-V4-LABEL: trap:
 ; NOHSA-TRAP-GFX900-V4:       ; %bb.0:
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x24
 ; NOHSA-TRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v0, 0
 ; NOHSA-TRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v1, 1
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_waitcnt lgkmcnt(0)
 ; NOHSA-TRAP-GFX900-V4-NEXT:    global_store_dword v0, v1, s[0:1]
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_endpgm
 ;
-; HSA-TRAP-GFX803-V2-LABEL: trap:
-; HSA-TRAP-GFX803-V2:         .amd_kernel_code_t
-; HSA-TRAP-GFX803-V2-NEXT:     amd_code_version_major = 1
-; HSA-TRAP-GFX803-V2-NEXT:     amd_code_version_minor = 2
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_kind = 1
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_version_major = 8
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_version_minor = 0
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_version_stepping = 3
-; HSA-TRAP-GFX803-V2-NEXT:     kernel_code_entry_byte_offset = 256
-; HSA-TRAP-GFX803-V2-NEXT:     kernel_code_prefetch_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     granulated_workitem_vgpr_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     granulated_wavefront_sgpr_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     priority = 0
-; HSA-TRAP-GFX803-V2-NEXT:     float_mode = 240
-; HSA-TRAP-GFX803-V2-NEXT:     priv = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_dx10_clamp = 1
-; HSA-TRAP-GFX803-V2-NEXT:     debug_mode = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_ieee_mode = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_wgp_mode = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_mem_ordered = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_fwd_progress = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 0
-; HSA-TRAP-GFX803-V2-NEXT:     user_sgpr_count = 8
-; HSA-TRAP-GFX803-V2-NEXT:     enable_trap_handler = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_id_x = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_id_y = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_id_z = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_info = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_vgpr_workitem_id = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_exception_msb = 0
-; HSA-TRAP-GFX803-V2-NEXT:     granulated_lds_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_exception = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_private_segment_buffer = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_dispatch_ptr = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_queue_ptr = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_dispatch_id = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_flat_scratch_init = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_private_segment_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_wavefront_size32 = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_ordered_append_gds = 0
-; HSA-TRAP-GFX803-V2-NEXT:     private_element_size = 1
-; HSA-TRAP-GFX803-V2-NEXT:     is_ptr64 = 1
-; HSA-TRAP-GFX803-V2-NEXT:     is_dynamic_callstack = 0
-; HSA-TRAP-GFX803-V2-NEXT:     is_debug_enabled = 0
-; HSA-TRAP-GFX803-V2-NEXT:     is_xnack_enabled = 0
-; HSA-TRAP-GFX803-V2-NEXT:     workitem_private_segment_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     workgroup_group_segment_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     gds_segment_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     kernarg_segment_byte_size = 8
-; HSA-TRAP-GFX803-V2-NEXT:     workgroup_fbarrier_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     wavefront_sgpr_count = 8
-; HSA-TRAP-GFX803-V2-NEXT:     workitem_vgpr_count = 3
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_vgpr_first = 0
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_vgpr_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_sgpr_first = 0
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_sgpr_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; HSA-TRAP-GFX803-V2-NEXT:     debug_private_segment_buffer_sgpr = 0
-; HSA-TRAP-GFX803-V2-NEXT:     kernarg_segment_alignment = 4
-; HSA-TRAP-GFX803-V2-NEXT:     group_segment_alignment = 4
-; HSA-TRAP-GFX803-V2-NEXT:     private_segment_alignment = 4
-; HSA-TRAP-GFX803-V2-NEXT:     wavefront_size = 6
-; HSA-TRAP-GFX803-V2-NEXT:     call_convention = -1
-; HSA-TRAP-GFX803-V2-NEXT:     runtime_loader_kernel_symbol = 0
-; HSA-TRAP-GFX803-V2-NEXT:    .end_amd_kernel_code_t
-; HSA-TRAP-GFX803-V2-NEXT:  ; %bb.0:
-; HSA-TRAP-GFX803-V2-NEXT:    s_load_dwordx2 s[2:3], s[6:7], 0x0
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v2, 1
-; HSA-TRAP-GFX803-V2-NEXT:    s_mov_b64 s[0:1], s[4:5]
-; HSA-TRAP-GFX803-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v0, s2
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v1, s3
-; HSA-TRAP-GFX803-V2-NEXT:    flat_store_dword v[0:1], v2
-; HSA-TRAP-GFX803-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-TRAP-GFX803-V2-NEXT:    s_trap 2
-;
 ; HSA-TRAP-GFX803-V3-LABEL: trap:
 ; HSA-TRAP-GFX803-V3:       ; %bb.0:
 ; HSA-TRAP-GFX803-V3-NEXT:    s_load_dwordx2 s[2:3], s[6:7], 0x0
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v2, 1
 ; HSA-TRAP-GFX803-V3-NEXT:    s_mov_b64 s[0:1], s[4:5]
 ; HSA-TRAP-GFX803-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v0, s2
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v1, s3
 ; HSA-TRAP-GFX803-V3-NEXT:    flat_store_dword v[0:1], v2
 ; HSA-TRAP-GFX803-V3-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX803-V3-NEXT:    s_trap 2
 ;
 ; HSA-TRAP-GFX803-V4-LABEL: trap:
 ; HSA-TRAP-GFX803-V4:       ; %bb.0:
 ; HSA-TRAP-GFX803-V4-NEXT:    s_load_dwordx2 s[2:3], s[6:7], 0x0
 ; HSA-TRAP-GFX803-V4-NEXT:    v_mov_b32_e32 v2, 1
 ; HSA-TRAP-GFX803-V4-NEXT:    s_mov_b64 s[0:1], s[4:5]
 ; HSA-TRAP-GFX803-V4-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX803-V4-NEXT:    v_mov_b32_e32 v0, s2
 ; HSA-TRAP-GFX803-V4-NEXT:    v_mov_b32_e32 v1, s3
 ; HSA-TRAP-GFX803-V4-NEXT:    flat_store_dword v[0:1], v2
 ; HSA-TRAP-GFX803-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX803-V4-NEXT:    s_trap 2
 ;
-; HSA-TRAP-GFX900-V2-LABEL: trap:
-; HSA-TRAP-GFX900-V2:         .amd_kernel_code_t
-; HSA-TRAP-GFX900-V2-NEXT:     amd_code_version_major = 1
-; HSA-TRAP-GFX900-V2-NEXT:     amd_code_version_minor = 2
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_kind = 1
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_version_major = 9
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_version_minor = 0
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_version_stepping = 0
-; HSA-TRAP-GFX900-V2-NEXT:     kernel_code_entry_byte_offset = 256
-; HSA-TRAP-GFX900-V2-NEXT:     kernel_code_prefetch_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     granulated_workitem_vgpr_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     granulated_wavefront_sgpr_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     priority = 0
-; HSA-TRAP-GFX900-V2-NEXT:     float_mode = 240
-; HSA-TRAP-GFX900-V2-NEXT:     priv = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_dx10_clamp = 1
-; HSA-TRAP-GFX900-V2-NEXT:     debug_mode = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_ieee_mode = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_wgp_mode = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_mem_ordered = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_fwd_progress = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 0
-; HSA-TRAP-GFX900-V2-NEXT:     user_sgpr_count = 8
-; HSA-TRAP-GFX900-V2-NEXT:     enable_trap_handler = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_x = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_y = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_z = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_info = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_vgpr_workitem_id = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_exception_msb = 0
-; HSA-TRAP-GFX900-V2-NEXT:     granulated_lds_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_exception = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_buffer = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_ptr = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_queue_ptr = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_id = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_flat_scratch_init = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_wavefront_size32 = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_ordered_append_gds = 0
-; HSA-TRAP-GFX900-V2-NEXT:     private_element_size = 1
-; HSA-TRAP-GFX900-V2-NEXT:     is_ptr64 = 1
-; HSA-TRAP-GFX900-V2-NEXT:     is_dynamic_callstack = 0
-; HSA-TRAP-GFX900-V2-NEXT:     is_debug_enabled = 0
-; HSA-TRAP-GFX900-V2-NEXT:     is_xnack_enabled = 1
-; HSA-TRAP-GFX900-V2-NEXT:     workitem_private_segment_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     workgroup_group_segment_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     gds_segment_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     kernarg_segment_byte_size = 8
-; HSA-TRAP-GFX900-V2-NEXT:     workgroup_fbarrier_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     wavefront_sgpr_count = 8
-; HSA-TRAP-GFX900-V2-NEXT:     workitem_vgpr_count = 2
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_vgpr_first = 0
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_vgpr_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_sgpr_first = 0
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_sgpr_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; HSA-TRAP-GFX900-V2-NEXT:     debug_private_segment_buffer_sgpr = 0
-; HSA-TRAP-GFX900-V2-NEXT:     kernarg_segment_alignment = 4
-; HSA-TRAP-GFX900-V2-NEXT:     group_segment_alignment = 4
-; HSA-TRAP-GFX900-V2-NEXT:     private_segment_alignment = 4
-; HSA-TRAP-GFX900-V2-NEXT:     wavefront_size = 6
-; HSA-TRAP-GFX900-V2-NEXT:     call_convention = -1
-; HSA-TRAP-GFX900-V2-NEXT:     runtime_loader_kernel_symbol = 0
-; HSA-TRAP-GFX900-V2-NEXT:    .end_amd_kernel_code_t
-; HSA-TRAP-GFX900-V2-NEXT:  ; %bb.0:
-; HSA-TRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[2:3], s[6:7], 0x0
-; HSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
-; HSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 1
-; HSA-TRAP-GFX900-V2-NEXT:    s_mov_b64 s[0:1], s[4:5]
-; HSA-TRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; HSA-TRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[2:3]
-; HSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-TRAP-GFX900-V2-NEXT:    s_trap 2
-;
 ; HSA-TRAP-GFX900-V3-LABEL: trap:
 ; HSA-TRAP-GFX900-V3:       ; %bb.0:
 ; HSA-TRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[2:3], s[6:7], 0x0
 ; HSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v1, 1
 ; HSA-TRAP-GFX900-V3-NEXT:    s_mov_b64 s[0:1], s[4:5]
 ; HSA-TRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX900-V3-NEXT:    global_store_dword v0, v1, s[2:3]
 ; HSA-TRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V3-NEXT:    s_trap 2
 ;
 ; HSA-TRAP-GFX900-V4-LABEL: trap:
 ; HSA-TRAP-GFX900-V4:       ; %bb.0:
 ; HSA-TRAP-GFX900-V4-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; HSA-TRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-TRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v1, 1
 ; HSA-TRAP-GFX900-V4-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX900-V4-NEXT:    global_store_dword v0, v1, s[0:1]
 ; HSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V4-NEXT:    s_trap 2
 ;
-; HSA-NOTRAP-GFX900-V2-LABEL: trap:
-; HSA-NOTRAP-GFX900-V2:         .amd_kernel_code_t
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_code_version_major = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_code_version_minor = 2
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_kind = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_version_major = 9
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_version_minor = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_version_stepping = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernel_code_entry_byte_offset = 256
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernel_code_prefetch_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     granulated_workitem_vgpr_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     granulated_wavefront_sgpr_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     priority = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     float_mode = 240
-; HSA-NOTRAP-GFX900-V2-NEXT:     priv = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_dx10_clamp = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     debug_mode = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_ieee_mode = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_wgp_mode = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_mem_ordered = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_fwd_progress = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     user_sgpr_count = 8
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_trap_handler = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_x = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_y = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_z = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_info = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_vgpr_workitem_id = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_exception_msb = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     granulated_lds_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_exception = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_buffer = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_ptr = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_queue_ptr = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_id = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_flat_scratch_init = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_wavefront_size32 = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_ordered_append_gds = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     private_element_size = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_ptr64 = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_dynamic_callstack = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_debug_enabled = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_xnack_enabled = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     workitem_private_segment_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     workgroup_group_segment_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     gds_segment_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernarg_segment_byte_size = 8
-; HSA-NOTRAP-GFX900-V2-NEXT:     workgroup_fbarrier_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     wavefront_sgpr_count = 8
-; HSA-NOTRAP-GFX900-V2-NEXT:     workitem_vgpr_count = 2
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_vgpr_first = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_vgpr_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_sgpr_first = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_sgpr_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     debug_private_segment_buffer_sgpr = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernarg_segment_alignment = 4
-; HSA-NOTRAP-GFX900-V2-NEXT:     group_segment_alignment = 4
-; HSA-NOTRAP-GFX900-V2-NEXT:     private_segment_alignment = 4
-; HSA-NOTRAP-GFX900-V2-NEXT:     wavefront_size = 6
-; HSA-NOTRAP-GFX900-V2-NEXT:     call_convention = -1
-; HSA-NOTRAP-GFX900-V2-NEXT:     runtime_loader_kernel_symbol = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:    .end_amd_kernel_code_t
-; HSA-NOTRAP-GFX900-V2-NEXT:  ; %bb.0:
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
-; HSA-NOTRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
-; HSA-NOTRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 1
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; HSA-NOTRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[0:1]
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_endpgm
-;
 ; HSA-NOTRAP-GFX900-V3-LABEL: trap:
 ; HSA-NOTRAP-GFX900-V3:       ; %bb.0:
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-NOTRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-NOTRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v1, 1
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-NOTRAP-GFX900-V3-NEXT:    global_store_dword v0, v1, s[0:1]
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
; HSA-NOTRAP-GFX900-V4-NEXT:    s_endpgm
   store volatile i32 1, ptr addrspace(1) %arg0
   call void @llvm.trap()
   unreachable
   store volatile i32 2, ptr addrspace(1) %arg0
   ret void
 }
 
 define amdgpu_kernel void @non_entry_trap(ptr addrspace(1) nocapture readonly %arg0) local_unnamed_addr {
-; NOHSA-TRAP-GFX900-V2-LABEL: non_entry_trap:
-; NOHSA-TRAP-GFX900-V2:       ; %bb.0: ; %entry
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[0:1], s[2:3], 0x24
-; NOHSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; NOHSA-TRAP-GFX900-V2-NEXT:    global_load_dword v1, v0, s[0:1] glc
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; NOHSA-TRAP-GFX900-V2-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_cbranch_vccz .LBB1_2
-; NOHSA-TRAP-GFX900-V2-NEXT:  ; %bb.1: ; %ret
-; NOHSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 3
-; NOHSA-TRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[0:1]
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_endpgm
-; NOHSA-TRAP-GFX900-V2-NEXT:  .LBB1_2: ; %trap
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_endpgm
-;
 ; NOHSA-TRAP-GFX900-V3-LABEL: non_entry_trap:
 ; NOHSA-TRAP-GFX900-V3:       ; %bb.0: ; %entry
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[0:1], s[2:3], 0x24
 ; NOHSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; NOHSA-TRAP-GFX900-V3-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V3-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1

 ; NOHSA-TRAP-GFX900-V4-NEXT:  ; %bb.1: ; %ret
 ; NOHSA-TRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v1, 3
 ; NOHSA-TRAP-GFX900-V4-NEXT:    global_store_dword v0, v1, s[0:1]
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_endpgm
 ; NOHSA-TRAP-GFX900-V4-NEXT:  .LBB1_2: ; %trap
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_endpgm
 ;
-; HSA-TRAP-GFX803-V2-LABEL: non_entry_trap:
-; HSA-TRAP-GFX803-V2:         .amd_kernel_code_t
-; HSA-TRAP-GFX803-V2-NEXT:     amd_code_version_major = 1
-; HSA-TRAP-GFX803-V2-NEXT:     amd_code_version_minor = 2
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_kind = 1
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_version_major = 8
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_version_minor = 0
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_version_stepping = 3
-; HSA-TRAP-GFX803-V2-NEXT:     kernel_code_entry_byte_offset = 256
-; HSA-TRAP-GFX803-V2-NEXT:     kernel_code_prefetch_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     granulated_workitem_vgpr_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     granulated_wavefront_sgpr_count = 1
-; HSA-TRAP-GFX803-V2-NEXT:     priority = 0
-; HSA-TRAP-GFX803-V2-NEXT:     float_mode = 240
-; HSA-TRAP-GFX803-V2-NEXT:     priv = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_dx10_clamp = 1
-; HSA-TRAP-GFX803-V2-NEXT:     debug_mode = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_ieee_mode = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_wgp_mode = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_mem_ordered = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_fwd_progress = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 0
-; HSA-TRAP-GFX803-V2-NEXT:     user_sgpr_count = 8
-; HSA-TRAP-GFX803-V2-NEXT:     enable_trap_handler = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_id_x = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_id_y = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_id_z = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_info = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_vgpr_workitem_id = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_exception_msb = 0
-; HSA-TRAP-GFX803-V2-NEXT:     granulated_lds_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_exception = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_private_segment_buffer = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_dispatch_ptr = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_queue_ptr = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_dispatch_id = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_flat_scratch_init = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_private_segment_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_wavefront_size32 = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_ordered_append_gds = 0
-; HSA-TRAP-GFX803-V2-NEXT:     private_element_size = 1
-; HSA-TRAP-GFX803-V2-NEXT:     is_ptr64 = 1
-; HSA-TRAP-GFX803-V2-NEXT:     is_dynamic_callstack = 0
-; HSA-TRAP-GFX803-V2-NEXT:     is_debug_enabled = 0
-; HSA-TRAP-GFX803-V2-NEXT:     is_xnack_enabled = 0
-; HSA-TRAP-GFX803-V2-NEXT:     workitem_private_segment_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     workgroup_group_segment_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     gds_segment_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     kernarg_segment_byte_size = 8
-; HSA-TRAP-GFX803-V2-NEXT:     workgroup_fbarrier_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     wavefront_sgpr_count = 10
-; HSA-TRAP-GFX803-V2-NEXT:     workitem_vgpr_count = 3
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_vgpr_first = 0
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_vgpr_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_sgpr_first = 0
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_sgpr_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; HSA-TRAP-GFX803-V2-NEXT:     debug_private_segment_buffer_sgpr = 0
-; HSA-TRAP-GFX803-V2-NEXT:     kernarg_segment_alignment = 4
-; HSA-TRAP-GFX803-V2-NEXT:     group_segment_alignment = 4
-; HSA-TRAP-GFX803-V2-NEXT:     private_segment_alignment = 4
-; HSA-TRAP-GFX803-V2-NEXT:     wavefront_size = 6
-; HSA-TRAP-GFX803-V2-NEXT:     call_convention = -1
-; HSA-TRAP-GFX803-V2-NEXT:     runtime_loader_kernel_symbol = 0
-; HSA-TRAP-GFX803-V2-NEXT:    .end_amd_kernel_code_t
-; HSA-TRAP-GFX803-V2-NEXT:  ; %bb.0: ; %entry
-; HSA-TRAP-GFX803-V2-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
-; HSA-TRAP-GFX803-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v0, s0
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v1, s1
-; HSA-TRAP-GFX803-V2-NEXT:    flat_load_dword v0, v[0:1] glc
-; HSA-TRAP-GFX803-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-TRAP-GFX803-V2-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v0
-; HSA-TRAP-GFX803-V2-NEXT:    s_cbranch_vccz .LBB1_2
-; HSA-TRAP-GFX803-V2-NEXT:  ; %bb.1: ; %ret
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v0, s0
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v2, 3
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v1, s1
-; HSA-TRAP-GFX803-V2-NEXT:    flat_store_dword v[0:1], v2
-; HSA-TRAP-GFX803-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-TRAP-GFX803-V2-NEXT:    s_endpgm
-; HSA-TRAP-GFX803-V2-NEXT:  .LBB1_2: ; %trap
-; HSA-TRAP-GFX803-V2-NEXT:    s_mov_b64 s[0:1], s[4:5]
-; HSA-TRAP-GFX803-V2-NEXT:    s_trap 2
-;
 ; HSA-TRAP-GFX803-V3-LABEL: non_entry_trap:
 ; HSA-TRAP-GFX803-V3:       ; %bb.0: ; %entry
 ; HSA-TRAP-GFX803-V3-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-TRAP-GFX803-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v0, s0
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v1, s1
 ; HSA-TRAP-GFX803-V3-NEXT:    flat_load_dword v0, v[0:1] glc
 ; HSA-TRAP-GFX803-V3-NEXT:    s_waitcnt vmcnt(0)

 ; HSA-TRAP-GFX803-V4-NEXT:    v_mov_b32_e32 v1, s1
 ; HSA-TRAP-GFX803-V4-NEXT:    flat_store_dword v[0:1], v2
 ; HSA-TRAP-GFX803-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX803-V4-NEXT:    s_endpgm
 ; HSA-TRAP-GFX803-V4-NEXT:  .LBB1_2: ; %trap
 ; HSA-TRAP-GFX803-V4-NEXT:    s_mov_b64 s[0:1], s[4:5]
 ; HSA-TRAP-GFX803-V4-NEXT:    s_trap 2
 ;
-; HSA-TRAP-GFX900-V2-LABEL: non_entry_trap:
-; HSA-TRAP-GFX900-V2:         .amd_kernel_code_t
-; HSA-TRAP-GFX900-V2-NEXT:     amd_code_version_major = 1
-; HSA-TRAP-GFX900-V2-NEXT:     amd_code_version_minor = 2
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_kind = 1
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_version_major = 9
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_version_minor = 0
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_version_stepping = 0
-; HSA-TRAP-GFX900-V2-NEXT:     kernel_code_entry_byte_offset = 256
-; HSA-TRAP-GFX900-V2-NEXT:     kernel_code_prefetch_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     granulated_workitem_vgpr_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     granulated_wavefront_sgpr_count = 1
-; HSA-TRAP-GFX900-V2-NEXT:     priority = 0
-; HSA-TRAP-GFX900-V2-NEXT:     float_mode = 240
-; HSA-TRAP-GFX900-V2-NEXT:     priv = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_dx10_clamp = 1
-; HSA-TRAP-GFX900-V2-NEXT:     debug_mode = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_ieee_mode = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_wgp_mode = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_mem_ordered = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_fwd_progress = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 0
-; HSA-TRAP-GFX900-V2-NEXT:     user_sgpr_count = 8
-; HSA-TRAP-GFX900-V2-NEXT:     enable_trap_handler = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_x = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_y = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_z = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_info = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_vgpr_workitem_id = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_exception_msb = 0
-; HSA-TRAP-GFX900-V2-NEXT:     granulated_lds_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_exception = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_buffer = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_ptr = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_queue_ptr = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_id = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_flat_scratch_init = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_wavefront_size32 = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_ordered_append_gds = 0
-; HSA-TRAP-GFX900-V2-NEXT:     private_element_size = 1
-; HSA-TRAP-GFX900-V2-NEXT:     is_ptr64 = 1
-; HSA-TRAP-GFX900-V2-NEXT:     is_dynamic_callstack = 0
-; HSA-TRAP-GFX900-V2-NEXT:     is_debug_enabled = 0
-; HSA-TRAP-GFX900-V2-NEXT:     is_xnack_enabled = 1
-; HSA-TRAP-GFX900-V2-NEXT:     workitem_private_segment_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     workgroup_group_segment_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     gds_segment_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     kernarg_segment_byte_size = 8
-; HSA-TRAP-GFX900-V2-NEXT:     workgroup_fbarrier_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     wavefront_sgpr_count = 10
-; HSA-TRAP-GFX900-V2-NEXT:     workitem_vgpr_count = 2
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_vgpr_first = 0
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_vgpr_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_sgpr_first = 0
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_sgpr_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; HSA-TRAP-GFX900-V2-NEXT:     debug_private_segment_buffer_sgpr = 0
-; HSA-TRAP-GFX900-V2-NEXT:     kernarg_segment_alignment = 4
-; HSA-TRAP-GFX900-V2-NEXT:     group_segment_alignment = 4
-; HSA-TRAP-GFX900-V2-NEXT:     private_segment_alignment = 4
-; HSA-TRAP-GFX900-V2-NEXT:     wavefront_size = 6
-; HSA-TRAP-GFX900-V2-NEXT:     call_convention = -1
-; HSA-TRAP-GFX900-V2-NEXT:     runtime_loader_kernel_symbol = 0
-; HSA-TRAP-GFX900-V2-NEXT:    .end_amd_kernel_code_t
-; HSA-TRAP-GFX900-V2-NEXT:  ; %bb.0: ; %entry
-; HSA-TRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
-; HSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
-; HSA-TRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; HSA-TRAP-GFX900-V2-NEXT:    global_load_dword v1, v0, s[0:1] glc
-; HSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-TRAP-GFX900-V2-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; HSA-TRAP-GFX900-V2-NEXT:    s_cbranch_vccz .LBB1_2
-; HSA-TRAP-GFX900-V2-NEXT:  ; %bb.1: ; %ret
-; HSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 3
-; HSA-TRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[0:1]
-; HSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-TRAP-GFX900-V2-NEXT:    s_endpgm
-; HSA-TRAP-GFX900-V2-NEXT:  .LBB1_2: ; %trap
-; HSA-TRAP-GFX900-V2-NEXT:    s_mov_b64 s[0:1], s[4:5]
-; HSA-TRAP-GFX900-V2-NEXT:    s_trap 2
-;
 ; HSA-TRAP-GFX900-V3-LABEL: non_entry_trap:
 ; HSA-TRAP-GFX900-V3:       ; %bb.0: ; %entry
 ; HSA-TRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-TRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX900-V3-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; HSA-TRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V3-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1

 ; HSA-TRAP-GFX900-V4-NEXT:  ; %bb.1: ; %ret
 ; HSA-TRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v1, 3
 ; HSA-TRAP-GFX900-V4-NEXT:    global_store_dword v0, v1, s[0:1]
 ; HSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V4-NEXT:    s_endpgm
 ; HSA-TRAP-GFX900-V4-NEXT:  .LBB1_2: ; %trap
 ; HSA-TRAP-GFX900-V4-NEXT:    s_trap 2
 ;
-; HSA-NOTRAP-GFX900-V2-LABEL: non_entry_trap:
-; HSA-NOTRAP-GFX900-V2:         .amd_kernel_code_t
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_code_version_major = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_code_version_minor = 2
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_kind = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_version_major = 9
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_version_minor = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_version_stepping = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernel_code_entry_byte_offset = 256
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernel_code_prefetch_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     granulated_workitem_vgpr_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     granulated_wavefront_sgpr_count = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     priority = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     float_mode = 240
-; HSA-NOTRAP-GFX900-V2-NEXT:     priv = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_dx10_clamp = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     debug_mode = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_ieee_mode = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_wgp_mode = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_mem_ordered = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_fwd_progress = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     user_sgpr_count = 8
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_trap_handler = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_x = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_y = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_z = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_info = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_vgpr_workitem_id = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_exception_msb = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     granulated_lds_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_exception = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_buffer = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_ptr = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_queue_ptr = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_id = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_flat_scratch_init = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_wavefront_size32 = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_ordered_append_gds = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     private_element_size = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_ptr64 = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_dynamic_callstack = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_debug_enabled = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_xnack_enabled = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     workitem_private_segment_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     workgroup_group_segment_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     gds_segment_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernarg_segment_byte_size = 8
-; HSA-NOTRAP-GFX900-V2-NEXT:     workgroup_fbarrier_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     wavefront_sgpr_count = 10
-; HSA-NOTRAP-GFX900-V2-NEXT:     workitem_vgpr_count = 2
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_vgpr_first = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_vgpr_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_sgpr_first = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_sgpr_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     debug_private_segment_buffer_sgpr = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernarg_segment_alignment = 4
-; HSA-NOTRAP-GFX900-V2-NEXT:     group_segment_alignment = 4
-; HSA-NOTRAP-GFX900-V2-NEXT:     private_segment_alignment = 4
-; HSA-NOTRAP-GFX900-V2-NEXT:     wavefront_size = 6
-; HSA-NOTRAP-GFX900-V2-NEXT:     call_convention = -1
-; HSA-NOTRAP-GFX900-V2-NEXT:     runtime_loader_kernel_symbol = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:    .end_amd_kernel_code_t
-; HSA-NOTRAP-GFX900-V2-NEXT:  ; %bb.0: ; %entry
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
-; HSA-NOTRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; HSA-NOTRAP-GFX900-V2-NEXT:    global_load_dword v1, v0, s[0:1] glc
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-NOTRAP-GFX900-V2-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_cbranch_vccz .LBB1_2
-; HSA-NOTRAP-GFX900-V2-NEXT:  ; %bb.1: ; %ret
-; HSA-NOTRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 3
-; HSA-NOTRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[0:1]
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_endpgm
-; HSA-NOTRAP-GFX900-V2-NEXT:  .LBB1_2: ; %trap
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_endpgm
-;
 ; HSA-NOTRAP-GFX900-V3-LABEL: non_entry_trap:
 ; HSA-NOTRAP-GFX900-V3:       ; %bb.0: ; %entry
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[0:1], s[6:7], 0x0
 ; HSA-NOTRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-NOTRAP-GFX900-V3-NEXT:    global_load_dword v1, v0, s[0:1] glc
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-NOTRAP-GFX900-V3-NEXT:    v_cmp_eq_u32_e32 vcc, -1, v1
trap:
   unreachable
 
 ret:
   store volatile i32 3, ptr addrspace(1) %arg0
   ret void
 }
 
 define amdgpu_kernel void @debugtrap(ptr addrspace(1) nocapture readonly %arg0) {
-; NOHSA-TRAP-GFX900-V2-LABEL: debugtrap:
-; NOHSA-TRAP-GFX900-V2:       ; %bb.0:
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x24
-; NOHSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
-; NOHSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 1
-; NOHSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v2, 2
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; NOHSA-TRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[0:1]
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; NOHSA-TRAP-GFX900-V2-NEXT:    global_store_dword v0, v2, s[0:1]
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; NOHSA-TRAP-GFX900-V2-NEXT:    s_endpgm
-;
 ; NOHSA-TRAP-GFX900-V3-LABEL: debugtrap:
 ; NOHSA-TRAP-GFX900-V3:       ; %bb.0:
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[0:1], s[0:1], 0x24
 ; NOHSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; NOHSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v1, 1
 ; NOHSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v2, 2
 ; NOHSA-TRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; NOHSA-TRAP-GFX900-V3-NEXT:    global_store_dword v0, v1, s[0:1]

 ; NOHSA-TRAP-GFX900-V4-NEXT:    v_mov_b32_e32 v2, 2
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_waitcnt lgkmcnt(0)
 ; NOHSA-TRAP-GFX900-V4-NEXT:    global_store_dword v0, v1, s[0:1]
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V4-NEXT:    global_store_dword v0, v2, s[0:1]
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; NOHSA-TRAP-GFX900-V4-NEXT:    s_endpgm
 ;
-; HSA-TRAP-GFX803-V2-LABEL: debugtrap:
-; HSA-TRAP-GFX803-V2:         .amd_kernel_code_t
-; HSA-TRAP-GFX803-V2-NEXT:     amd_code_version_major = 1
-; HSA-TRAP-GFX803-V2-NEXT:     amd_code_version_minor = 2
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_kind = 1
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_version_major = 8
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_version_minor = 0
-; HSA-TRAP-GFX803-V2-NEXT:     amd_machine_version_stepping = 3
-; HSA-TRAP-GFX803-V2-NEXT:     kernel_code_entry_byte_offset = 256
-; HSA-TRAP-GFX803-V2-NEXT:     kernel_code_prefetch_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     granulated_workitem_vgpr_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     granulated_wavefront_sgpr_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     priority = 0
-; HSA-TRAP-GFX803-V2-NEXT:     float_mode = 240
-; HSA-TRAP-GFX803-V2-NEXT:     priv = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_dx10_clamp = 1
-; HSA-TRAP-GFX803-V2-NEXT:     debug_mode = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_ieee_mode = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_wgp_mode = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_mem_ordered = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_fwd_progress = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 0
-; HSA-TRAP-GFX803-V2-NEXT:     user_sgpr_count = 6
-; HSA-TRAP-GFX803-V2-NEXT:     enable_trap_handler = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_id_x = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_id_y = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_id_z = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_workgroup_info = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_vgpr_workitem_id = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_exception_msb = 0
-; HSA-TRAP-GFX803-V2-NEXT:     granulated_lds_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_exception = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_private_segment_buffer = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_dispatch_ptr = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_queue_ptr = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_dispatch_id = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_flat_scratch_init = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_private_segment_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_wavefront_size32 = 0
-; HSA-TRAP-GFX803-V2-NEXT:     enable_ordered_append_gds = 0
-; HSA-TRAP-GFX803-V2-NEXT:     private_element_size = 1
-; HSA-TRAP-GFX803-V2-NEXT:     is_ptr64 = 1
-; HSA-TRAP-GFX803-V2-NEXT:     is_dynamic_callstack = 0
-; HSA-TRAP-GFX803-V2-NEXT:     is_debug_enabled = 0
-; HSA-TRAP-GFX803-V2-NEXT:     is_xnack_enabled = 0
-; HSA-TRAP-GFX803-V2-NEXT:     workitem_private_segment_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     workgroup_group_segment_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     gds_segment_byte_size = 0
-; HSA-TRAP-GFX803-V2-NEXT:     kernarg_segment_byte_size = 8
-; HSA-TRAP-GFX803-V2-NEXT:     workgroup_fbarrier_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     wavefront_sgpr_count = 6
-; HSA-TRAP-GFX803-V2-NEXT:     workitem_vgpr_count = 4
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_vgpr_first = 0
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_vgpr_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_sgpr_first = 0
-; HSA-TRAP-GFX803-V2-NEXT:     reserved_sgpr_count = 0
-; HSA-TRAP-GFX803-V2-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; HSA-TRAP-GFX803-V2-NEXT:     debug_private_segment_buffer_sgpr = 0
-; HSA-TRAP-GFX803-V2-NEXT:     kernarg_segment_alignment = 4
-; HSA-TRAP-GFX803-V2-NEXT:     group_segment_alignment = 4
-; HSA-TRAP-GFX803-V2-NEXT:     private_segment_alignment = 4
-; HSA-TRAP-GFX803-V2-NEXT:     wavefront_size = 6
-; HSA-TRAP-GFX803-V2-NEXT:     call_convention = -1
-; HSA-TRAP-GFX803-V2-NEXT:     runtime_loader_kernel_symbol = 0
-; HSA-TRAP-GFX803-V2-NEXT:    .end_amd_kernel_code_t
-; HSA-TRAP-GFX803-V2-NEXT:  ; %bb.0:
-; HSA-TRAP-GFX803-V2-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v2, 1
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v3, 2
-; HSA-TRAP-GFX803-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v0, s0
-; HSA-TRAP-GFX803-V2-NEXT:    v_mov_b32_e32 v1, s1
-; HSA-TRAP-GFX803-V2-NEXT:    flat_store_dword v[0:1], v2
-; HSA-TRAP-GFX803-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-TRAP-GFX803-V2-NEXT:    s_trap 3
-; HSA-TRAP-GFX803-V2-NEXT:    flat_store_dword v[0:1], v3
-; HSA-TRAP-GFX803-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-TRAP-GFX803-V2-NEXT:    s_endpgm
-;
 ; HSA-TRAP-GFX803-V3-LABEL: debugtrap:
 ; HSA-TRAP-GFX803-V3:       ; %bb.0:
 ; HSA-TRAP-GFX803-V3-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v2, 1
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v3, 2
 ; HSA-TRAP-GFX803-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v0, s0
 ; HSA-TRAP-GFX803-V3-NEXT:    v_mov_b32_e32 v1, s1

 ; HSA-TRAP-GFX803-V4-NEXT:    v_mov_b32_e32 v1, s1
 ; HSA-TRAP-GFX803-V4-NEXT:    flat_store_dword v[0:1], v2
 ; HSA-TRAP-GFX803-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX803-V4-NEXT:    s_trap 3
 ; HSA-TRAP-GFX803-V4-NEXT:    flat_store_dword v[0:1], v3
 ; HSA-TRAP-GFX803-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX803-V4-NEXT:    s_endpgm
 ;
-; HSA-TRAP-GFX900-V2-LABEL: debugtrap:
-; HSA-TRAP-GFX900-V2:         .amd_kernel_code_t
-; HSA-TRAP-GFX900-V2-NEXT:     amd_code_version_major = 1
-; HSA-TRAP-GFX900-V2-NEXT:     amd_code_version_minor = 2
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_kind = 1
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_version_major = 9
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_version_minor = 0
-; HSA-TRAP-GFX900-V2-NEXT:     amd_machine_version_stepping = 0
-; HSA-TRAP-GFX900-V2-NEXT:     kernel_code_entry_byte_offset = 256
-; HSA-TRAP-GFX900-V2-NEXT:     kernel_code_prefetch_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     granulated_workitem_vgpr_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     granulated_wavefront_sgpr_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     priority = 0
-; HSA-TRAP-GFX900-V2-NEXT:     float_mode = 240
-; HSA-TRAP-GFX900-V2-NEXT:     priv = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_dx10_clamp = 1
-; HSA-TRAP-GFX900-V2-NEXT:     debug_mode = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_ieee_mode = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_wgp_mode = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_mem_ordered = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_fwd_progress = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 0
-; HSA-TRAP-GFX900-V2-NEXT:     user_sgpr_count = 6
-; HSA-TRAP-GFX900-V2-NEXT:     enable_trap_handler = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_x = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_y = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_z = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_info = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_vgpr_workitem_id = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_exception_msb = 0
-; HSA-TRAP-GFX900-V2-NEXT:     granulated_lds_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_exception = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_buffer = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_ptr = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_queue_ptr = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_id = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_flat_scratch_init = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_wavefront_size32 = 0
-; HSA-TRAP-GFX900-V2-NEXT:     enable_ordered_append_gds = 0
-; HSA-TRAP-GFX900-V2-NEXT:     private_element_size = 1
-; HSA-TRAP-GFX900-V2-NEXT:     is_ptr64 = 1
-; HSA-TRAP-GFX900-V2-NEXT:     is_dynamic_callstack = 0
-; HSA-TRAP-GFX900-V2-NEXT:     is_debug_enabled = 0
-; HSA-TRAP-GFX900-V2-NEXT:     is_xnack_enabled = 1
-; HSA-TRAP-GFX900-V2-NEXT:     workitem_private_segment_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     workgroup_group_segment_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     gds_segment_byte_size = 0
-; HSA-TRAP-GFX900-V2-NEXT:     kernarg_segment_byte_size = 8
-; HSA-TRAP-GFX900-V2-NEXT:     workgroup_fbarrier_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     wavefront_sgpr_count = 6
-; HSA-TRAP-GFX900-V2-NEXT:     workitem_vgpr_count = 3
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_vgpr_first = 0
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_vgpr_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_sgpr_first = 0
-; HSA-TRAP-GFX900-V2-NEXT:     reserved_sgpr_count = 0
-; HSA-TRAP-GFX900-V2-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; HSA-TRAP-GFX900-V2-NEXT:     debug_private_segment_buffer_sgpr = 0
-; HSA-TRAP-GFX900-V2-NEXT:     kernarg_segment_alignment = 4
-; HSA-TRAP-GFX900-V2-NEXT:     group_segment_alignment = 4
-; HSA-TRAP-GFX900-V2-NEXT:     private_segment_alignment = 4
-; HSA-TRAP-GFX900-V2-NEXT:     wavefront_size = 6
-; HSA-TRAP-GFX900-V2-NEXT:     call_convention = -1
-; HSA-TRAP-GFX900-V2-NEXT:     runtime_loader_kernel_symbol = 0
-; HSA-TRAP-GFX900-V2-NEXT:    .end_amd_kernel_code_t
-; HSA-TRAP-GFX900-V2-NEXT:  ; %bb.0:
-; HSA-TRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
-; HSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
-; HSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 1
-; HSA-TRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v2, 2
-; HSA-TRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; HSA-TRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[0:1]
-; HSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-TRAP-GFX900-V2-NEXT:    s_trap 3
-; HSA-TRAP-GFX900-V2-NEXT:    global_store_dword v0, v2, s[0:1]
-; HSA-TRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-TRAP-GFX900-V2-NEXT:    s_endpgm
-;
 ; HSA-TRAP-GFX900-V3-LABEL: debugtrap:
 ; HSA-TRAP-GFX900-V3:       ; %bb.0:
 ; HSA-TRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; HSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v1, 1
 ; HSA-TRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v2, 2
 ; HSA-TRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX900-V3-NEXT:    global_store_dword v0, v1, s[0:1]

 ; HSA-TRAP-GFX900-V4-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-TRAP-GFX900-V4-NEXT:    global_store_dword v0, v1, s[0:1]
 ; HSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V4-NEXT:    s_trap 3
 ; HSA-TRAP-GFX900-V4-NEXT:    global_store_dword v0, v2, s[0:1]
 ; HSA-TRAP-GFX900-V4-NEXT:    s_waitcnt vmcnt(0)
 ; HSA-TRAP-GFX900-V4-NEXT:    s_endpgm
 ;
-; HSA-NOTRAP-GFX900-V2-LABEL: debugtrap:
-; HSA-NOTRAP-GFX900-V2:         .amd_kernel_code_t
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_code_version_major = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_code_version_minor = 2
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_kind = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_version_major = 9
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_version_minor = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     amd_machine_version_stepping = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernel_code_entry_byte_offset = 256
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernel_code_prefetch_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     granulated_workitem_vgpr_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     granulated_wavefront_sgpr_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     priority = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     float_mode = 240
-; HSA-NOTRAP-GFX900-V2-NEXT:     priv = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_dx10_clamp = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     debug_mode = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_ieee_mode = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_wgp_mode = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_mem_ordered = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_fwd_progress = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_wave_byte_offset = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     user_sgpr_count = 6
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_trap_handler = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_x = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_y = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_id_z = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_workgroup_info = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_vgpr_workitem_id = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_exception_msb = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     granulated_lds_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_exception = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_buffer = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_ptr = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_queue_ptr = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_kernarg_segment_ptr = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_dispatch_id = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_flat_scratch_init = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_private_segment_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_x = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_y = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_sgpr_grid_workgroup_count_z = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_wavefront_size32 = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     enable_ordered_append_gds = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     private_element_size = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_ptr64 = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_dynamic_callstack = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_debug_enabled = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     is_xnack_enabled = 1
-; HSA-NOTRAP-GFX900-V2-NEXT:     workitem_private_segment_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     workgroup_group_segment_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     gds_segment_byte_size = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernarg_segment_byte_size = 8
-; HSA-NOTRAP-GFX900-V2-NEXT:     workgroup_fbarrier_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     wavefront_sgpr_count = 6
-; HSA-NOTRAP-GFX900-V2-NEXT:     workitem_vgpr_count = 3
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_vgpr_first = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_vgpr_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_sgpr_first = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     reserved_sgpr_count = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     debug_wavefront_private_segment_offset_sgpr = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     debug_private_segment_buffer_sgpr = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:     kernarg_segment_alignment = 4
-; HSA-NOTRAP-GFX900-V2-NEXT:     group_segment_alignment = 4
-; HSA-NOTRAP-GFX900-V2-NEXT:     private_segment_alignment = 4
-; HSA-NOTRAP-GFX900-V2-NEXT:     wavefront_size = 6
-; HSA-NOTRAP-GFX900-V2-NEXT:     call_convention = -1
-; HSA-NOTRAP-GFX900-V2-NEXT:     runtime_loader_kernel_symbol = 0
-; HSA-NOTRAP-GFX900-V2-NEXT:    .end_amd_kernel_code_t
-; HSA-NOTRAP-GFX900-V2-NEXT:  ; %bb.0:
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
-; HSA-NOTRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v0, 0
-; HSA-NOTRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v1, 1
-; HSA-NOTRAP-GFX900-V2-NEXT:    v_mov_b32_e32 v2, 2
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_waitcnt lgkmcnt(0)
-; HSA-NOTRAP-GFX900-V2-NEXT:    global_store_dword v0, v1, s[0:1]
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-NOTRAP-GFX900-V2-NEXT:    global_store_dword v0, v2, s[0:1]
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_waitcnt vmcnt(0)
-; HSA-NOTRAP-GFX900-V2-NEXT:    s_endpgm
-;
 ; HSA-NOTRAP-GFX900-V3-LABEL: debugtrap:
 ; HSA-NOTRAP-GFX900-V3:       ; %bb.0:
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_load_dwordx2 s[0:1], s[4:5], 0x0
 ; HSA-NOTRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v0, 0
 ; HSA-NOTRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v1, 1
 ; HSA-NOTRAP-GFX900-V3-NEXT:    v_mov_b32_e32 v2, 2
 ; HSA-NOTRAP-GFX900-V3-NEXT:    s_waitcnt lgkmcnt(0)
 ; HSA-NOTRAP-GFX900-V3-NEXT:    global_store_dword v0, v1, s[0:1]

llvm/test/CodeGen/AMDGPU/trap.ll

 ; MESA-TRAP:  .long   47180
 ; MESA-TRAP-NEXT: .long   208
 
 ; NOMESA-TRAP: .section .AMDGPU.config
 ; NOMESA-TRAP:  .long   47180
 ; NOMESA-TRAP-NEXT: .long   144
 
 ; GCN-LABEL: {{^}}hsa_trap:
-; HSA-TRAP: enable_trap_handler = 0
 ; HSA-TRAP: s_mov_b64 s[0:1], s[4:5]
 ; HSA-TRAP: s_trap 2
+; HSA-TRAP: COMPUTE_PGM_RSRC2:TRAP_HANDLER: 0
 
 ; for llvm.trap in hsa path without ABI, direct generate s_endpgm instruction without any warning information
-; NO-HSA-TRAP: enable_trap_handler = 0
 ; NO-HSA-TRAP: s_endpgm
 ; NO-HSA-TRAP: COMPUTE_PGM_RSRC2:TRAP_HANDLER: 0
 
 ; TRAP-BIT: enable_trap_handler = 1
 ; NO-TRAP-BIT: enable_trap_handler = 0
 ; NO-MESA-TRAP: s_endpgm
 define amdgpu_kernel void @hsa_trap(ptr addrspace(1) nocapture readonly %arg0) {
   store volatile i32 1, ptr addrspace(1) %arg0
   call void @llvm.trap()
   unreachable
   store volatile i32 2, ptr addrspace(1) %arg0
   ret void
 }
 
 ; MESA-TRAP: .section .AMDGPU.config
 ; MESA-TRAP:  .long   47180
 ; MESA-TRAP-NEXT: .long   204
 
 ; NOMESA-TRAP: .section .AMDGPU.config
 ; NOMESA-TRAP:  .long   47180
 ; NOMESA-TRAP-NEXT: .long   140
 
 ; GCN-LABEL: {{^}}hsa_debugtrap:
-; HSA-TRAP: enable_trap_handler = 0
 ; HSA-TRAP: s_trap 3
 ; HSA-TRAP: flat_store_dword v[0:1], v3
+; HSA-TRAP: COMPUTE_PGM_RSRC2:TRAP_HANDLER: 0
 
 ; for llvm.debugtrap in non-hsa path without ABI, generate a warning and a s_endpgm instruction
-; NO-HSA-TRAP: enable_trap_handler = 0
 ; NO-HSA-TRAP: s_endpgm
 
 ; TRAP-BIT: enable_trap_handler = 1
 ; NO-TRAP-BIT: enable_trap_handler = 0
 ; NO-MESA-TRAP: s_endpgm
 define amdgpu_kernel void @hsa_debugtrap(ptr addrspace(1) nocapture readonly %arg0) {
   store volatile i32 1, ptr addrspace(1) %arg0
   call void @llvm.debugtrap()
ret:
   store volatile i32 3, ptr addrspace(1) %arg0
   ret void
 }
 
 attributes #0 = { nounwind noreturn }
 attributes #1 = { nounwind }
 
 !llvm.module.flags = !{!0}
-!0 = !{i32 1, !"amdgpu_code_object_version", i32 200}
+!0 = !{i32 1, !"amdgpu_code_object_version", i32 400}

llvm/test/MC/AMDGPU/hsa-exp.s

-// RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=2 -show-encoding %s | FileCheck %s --check-prefix=ASM
-// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=2 -show-encoding %s | llvm-readobj --symbols -S --sd - | FileCheck %s --check-prefix=ELF
+// RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=4 -show-encoding %s | FileCheck %s --check-prefix=ASM
+// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=4 -show-encoding %s | llvm-readobj --symbols -S --sd - | FileCheck %s --check-prefix=ELF
 
 // ELF: Section {
 // ELF: Name: .text
 // ELF: Type: SHT_PROGBITS (0x1)
 // ELF: Flags [ (0x6)
 // ELF: SHF_ALLOC (0x2)
 // ELF: SHF_EXECINSTR (0x4)
 
-// ELF: SHT_NOTE
-// ELF: 0000: 04000000 08000000 01000000 414D4400
-// ELF: 0010: 02000000 00000000 04000000 1B000000
-// ELF: 0020: 03000000 414D4400 04000700 07000000
-// ELF: 0030: 00000000 00000000 414D4400 414D4447
-// ELF: 0040: 50550000
-
 // ELF: Symbol {
-// ELF: Name: amd_kernel_code_t_minimal
-// ELF: Type: AMDGPU_HSA_KERNEL (0xA)
+// ELF: Name: minimal
 // ELF: Section: .text
 // ELF: }
 
 .text
 // ASM: .text
 
-.hsa_code_object_version 2,0
-// ASM: .hsa_code_object_version 2,0
-
-.hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-// ASM: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-
-.amdgpu_hsa_kernel amd_kernel_code_t_minimal
+.amdgcn_target "amdgcn-unknown-amdhsa--gfx700"
+// ASM: .amdgcn_target "amdgcn-unknown-amdhsa--gfx700"
 
 .set my_is_ptr64, 1
 
 .if my_is_ptr64 == 0
-.set my_kernarg_segment_byte_size, 32
+.set my_next_free_vgpr, 4
 .else
-.set my_kernarg_segment_byte_size, 16
+.set my_next_free_vgpr, 8
 .endif
 
-.set my_sgpr, 8
+.set my_sgpr, 6
 
-
-amd_kernel_code_t_minimal:
-.amd_kernel_code_t
-        amd_code_version_major = .option.machine_version_major
-  enable_sgpr_kernarg_segment_ptr = 1
-  is_ptr64 = my_is_ptr64
-  granulated_workitem_vgpr_count = 1
-  granulated_wavefront_sgpr_count = 1+(my_sgpr-1)/8
-  user_sgpr_count = 2
-  kernarg_segment_byte_size = my_kernarg_segment_byte_size
-  wavefront_sgpr_count = my_sgpr
-//      wavefront_sgpr_count = 7
-; wavefront_sgpr_count = 7
+minimal:
+.amdhsa_kernel minimal
+  .amdhsa_next_free_vgpr 1+(my_next_free_vgpr-1)
   // Make sure a blank line won't break anything:
 
-// Make sure a line with whitespace won't break anything:
-
-  workitem_vgpr_count = 16
-.end_amd_kernel_code_t
+  .amdhsa_next_free_sgpr my_sgpr/2+3
+.end_amdhsa_kernel
 
-// ASM-LABEL: {{^}}amd_kernel_code_t_minimal:
-// ASM: .amd_kernel_code_t
-// ASM: amd_code_version_major = 7
-// ASM: amd_code_version_minor = 2
-// ASM: amd_machine_kind = 1
-// ASM: amd_machine_version_major = 7
-// ASM: amd_machine_version_minor = 0
-// ASM: amd_machine_version_stepping = 0
-// ASM: kernel_code_entry_byte_offset = 256
-// ASM: kernel_code_prefetch_byte_size = 0
-// ASM: granulated_workitem_vgpr_count = 1
-// ASM: granulated_wavefront_sgpr_count = 1
-// ASM: priority = 0
-// ASM: float_mode = 0
-// ASM: priv = 0
-// ASM: enable_dx10_clamp = 0
-// ASM: debug_mode = 0
-// ASM: enable_ieee_mode = 0
-// ASM: enable_sgpr_private_segment_wave_byte_offset = 0
-// ASM: user_sgpr_count = 2
-// ASM: enable_sgpr_workgroup_id_x = 0
-// ASM: enable_sgpr_workgroup_id_y = 0
-// ASM: enable_sgpr_workgroup_id_z = 0
-// ASM: enable_sgpr_workgroup_info = 0
-// ASM: enable_vgpr_workitem_id = 0
-// ASM: enable_exception_msb = 0
-// ASM: granulated_lds_size = 0
-// ASM: enable_exception = 0
-// ASM: enable_sgpr_private_segment_buffer = 0
-// ASM: enable_sgpr_dispatch_ptr = 0
-// ASM: enable_sgpr_queue_ptr = 0
-// ASM: enable_sgpr_kernarg_segment_ptr = 1
-// ASM: enable_sgpr_dispatch_id = 0
-// ASM: enable_sgpr_flat_scratch_init = 0
-// ASM: enable_sgpr_private_segment_size = 0
-// ASM: enable_sgpr_grid_workgroup_count_x = 0
-// ASM: enable_sgpr_grid_workgroup_count_y = 0
-// ASM: enable_sgpr_grid_workgroup_count_z = 0
-// ASM: enable_ordered_append_gds = 0
-// ASM: private_element_size = 0
-// ASM: is_ptr64 = 1
-// ASM: is_dynamic_callstack = 0
-// ASM: is_debug_enabled = 0
-// ASM: is_xnack_enabled = 0
-// ASM: workitem_private_segment_byte_size = 0
-// ASM: workgroup_group_segment_byte_size = 0
-// ASM: gds_segment_byte_size = 0
-// ASM: kernarg_segment_byte_size = 16
-// ASM: workgroup_fbarrier_count = 0
-// ASM: wavefront_sgpr_count = 8
-// ASM: workitem_vgpr_count = 16
-// ASM: reserved_vgpr_first = 0
-// ASM: reserved_vgpr_count = 0
-// ASM: reserved_sgpr_first = 0
-// ASM: reserved_sgpr_count = 0
-// ASM: debug_wavefront_private_segment_offset_sgpr = 0
-// ASM: debug_private_segment_buffer_sgpr = 0
-// ASM: kernarg_segment_alignment = 4
-// ASM: group_segment_alignment = 4
-// ASM: private_segment_alignment = 4
-// ASM: wavefront_size = 6
-// ASM: call_convention = -1
-// ASM: runtime_loader_kernel_symbol = 0
-// ASM: .end_amd_kernel_code_t
+; ASM-LABEL: minimal:
+; ASM: .amdhsa_kernel minimal
+; ASM:         .amdhsa_group_segment_fixed_size 0
+; ASM:         .amdhsa_private_segment_fixed_size 0
+; ASM:         .amdhsa_kernarg_size 0
+; ASM:         .amdhsa_user_sgpr_count 0
+; ASM:         .amdhsa_user_sgpr_private_segment_buffer 0
+; ASM:         .amdhsa_user_sgpr_dispatch_ptr 0
+; ASM:         .amdhsa_user_sgpr_queue_ptr 0
+; ASM:         .amdhsa_user_sgpr_kernarg_segment_ptr 0
+; ASM:         .amdhsa_user_sgpr_dispatch_id 0
+; ASM:         .amdhsa_user_sgpr_flat_scratch_init 0
+; ASM:         .amdhsa_user_sgpr_private_segment_size 0
+; ASM:         .amdhsa_system_sgpr_private_segment_wavefront_offset 0
+; ASM:         .amdhsa_system_sgpr_workgroup_id_x 1
+; ASM:         .amdhsa_system_sgpr_workgroup_id_y 0
+; ASM:         .amdhsa_system_sgpr_workgroup_id_z 0
+; ASM:         .amdhsa_system_sgpr_workgroup_info 0
+; ASM:         .amdhsa_system_vgpr_workitem_id 0
+; ASM:         .amdhsa_next_free_vgpr 8
+; ASM:         .amdhsa_next_free_sgpr 6
+; ASM:         .amdhsa_float_round_mode_32 0
+; ASM:         .amdhsa_float_round_mode_16_64 0
+; ASM:         .amdhsa_float_denorm_mode_32 0
+; ASM:         .amdhsa_float_denorm_mode_16_64 3
+; ASM:         .amdhsa_dx10_clamp 1
+; ASM:         .amdhsa_ieee_mode 1
+; ASM:         .amdhsa_exception_fp_ieee_invalid_op 0
+; ASM:         .amdhsa_exception_fp_denorm_src 0
+; ASM:         .amdhsa_exception_fp_ieee_div_zero 0
+; ASM:         .amdhsa_exception_fp_ieee_overflow 0
+; ASM:         .amdhsa_exception_fp_ieee_underflow 0
+; ASM:         .amdhsa_exception_fp_ieee_inexact 0
+; ASM:         .amdhsa_exception_int_div_zero 0
+; ASM: .end_amdhsa_kernel

llvm/test/MC/AMDGPU/hsa-gfx10.s

-// RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=gfx1010 --amdhsa-code-object-version=2 -mattr=-wavefrontsize32,+wavefrontsize64 -show-encoding %s | FileCheck %s --check-prefix=ASM
-// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=gfx1010 --amdhsa-code-object-version=2 -mattr=-wavefrontsize32,+wavefrontsize64 -show-encoding %s | llvm-readobj -S --sd --syms - | FileCheck %s --check-prefix=ELF
-
-// ELF: Section {
-// ELF: Name: .text
-// ELF: Type: SHT_PROGBITS (0x1)
-// ELF: Flags [ (0x6)
-// ELF: SHF_ALLOC (0x2)
-// ELF: SHF_EXECINSTR (0x4)
-
-// ELF: SHT_NOTE
-// ELF: 0000: 04000000 08000000 01000000 414D4400
-// ELF: 0010: 02000000 00000000 04000000 1B000000
-// ELF: 0020: 03000000 414D4400 04000700 07000000
-// ELF: 0030: 00000000 00000000 414D4400 414D4447
-// ELF: 0040: 50550000
-// We can't check binary representation of metadata note: it is different on
-// Windows and Linux because of carriage return on Windows
-
-// ELF: Symbol {
-// ELF: Name: amd_kernel_code_t_test_all
-// ELF: Type: AMDGPU_HSA_KERNEL (0xA)
-// ELF: Section: .text
-// ELF: }
-// ELF: Symbol {
-// ELF: Name: amd_kernel_code_t_minimal
-// ELF: Type: AMDGPU_HSA_KERNEL (0xA)
-// ELF: Section: .text
-// ELF: }
-
-.text
-// ASM: .text
-
-.hsa_code_object_version 2,0
-// ASM: .hsa_code_object_version 2,0
-
-.hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-// ASM: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-
-.amd_amdgpu_hsa_metadata
-  Version: [ 3, 0 ]
-  Kernels:
-    - Name:       amd_kernel_code_t_test_all
-      SymbolName: amd_kernel_code_t_test_all@kd
-    - Name:       amd_kernel_code_t_minimal
-      SymbolName: amd_kernel_code_t_minimal@kd
-.end_amd_amdgpu_hsa_metadata
-
-// ASM: .amd_amdgpu_hsa_metadata
-// ASM:    Version: [ 3, 0 ]
-// ASM:    Kernels:
-// ASM:      - Name:       amd_kernel_code_t_test_all
-// ASM:        SymbolName: 'amd_kernel_code_t_test_all@kd'
-// ASM:      - Name:       amd_kernel_code_t_minimal
-// ASM:        SymbolName: 'amd_kernel_code_t_minimal@kd'
-// ASM: .end_amd_amdgpu_hsa_metadata
-
-.amdgpu_hsa_kernel amd_kernel_code_t_test_all
-.amdgpu_hsa_kernel amd_kernel_code_t_minimal
-
-amd_kernel_code_t_test_all:
-; Test all amd_kernel_code_t members with non-default values.
-.amd_kernel_code_t
-    kernel_code_version_major = 100
-    kernel_code_version_minor = 100
-    machine_kind = 0
-    machine_version_major = 5
-    machine_version_minor = 5
-    machine_version_stepping = 5
-    kernel_code_entry_byte_offset = 512
-    kernel_code_prefetch_byte_size = 1
-    max_scratch_backing_memory_byte_size = 1
-    compute_pgm_rsrc1_vgprs = 1
-    compute_pgm_rsrc1_sgprs = 1
-    compute_pgm_rsrc1_priority = 1
-    compute_pgm_rsrc1_float_mode = 1
-    compute_pgm_rsrc1_priv = 1
-    compute_pgm_rsrc1_dx10_clamp = 1
-    compute_pgm_rsrc1_debug_mode = 1
-    compute_pgm_rsrc1_ieee_mode = 1
-    compute_pgm_rsrc1_wgp_mode = 0
-    compute_pgm_rsrc1_mem_ordered = 0
-    compute_pgm_rsrc1_fwd_progress = 1
-    compute_pgm_rsrc2_scratch_en = 1
-    compute_pgm_rsrc2_user_sgpr = 1
-    compute_pgm_rsrc2_tgid_x_en = 1
-    compute_pgm_rsrc2_tgid_y_en = 1
-    compute_pgm_rsrc2_tgid_z_en = 1
-    compute_pgm_rsrc2_tg_size_en = 1
-    compute_pgm_rsrc2_tidig_comp_cnt = 1
-    compute_pgm_rsrc2_excp_en_msb = 1
-    compute_pgm_rsrc2_lds_size = 1
-    compute_pgm_rsrc2_excp_en = 1
-    enable_sgpr_private_segment_buffer = 1
-    enable_sgpr_dispatch_ptr = 1
-    enable_sgpr_queue_ptr = 1
-    enable_sgpr_kernarg_segment_ptr = 1
-    enable_sgpr_dispatch_id = 1
-    enable_sgpr_flat_scratch_init = 1
-    enable_sgpr_private_segment_size = 1
-    enable_sgpr_grid_workgroup_count_x = 1
-    enable_sgpr_grid_workgroup_count_y = 1
-    enable_sgpr_grid_workgroup_count_z = 1
-    enable_ordered_append_gds = 1
-    private_element_size = 1
-    is_ptr64 = 1
-    is_dynamic_callstack = 1
-    is_debug_enabled = 1
-    is_xnack_enabled = 1
-    workitem_private_segment_byte_size = 1
-    workgroup_group_segment_byte_size = 1
-    gds_segment_byte_size = 1
-    kernarg_segment_byte_size = 1
-    workgroup_fbarrier_count = 1
-    wavefront_sgpr_count = 1
-    workitem_vgpr_count = 1
-    reserved_vgpr_first = 1
-    reserved_vgpr_count = 1
-    reserved_sgpr_first = 1
-    reserved_sgpr_count = 1
-    debug_wavefront_private_segment_offset_sgpr = 1
-    debug_private_segment_buffer_sgpr = 1
-    kernarg_segment_alignment = 5
-    group_segment_alignment = 5
-    private_segment_alignment = 5
-    wavefront_size = 6
-    call_convention = 1
-    runtime_loader_kernel_symbol = 1
-.end_amd_kernel_code_t
-
-// ASM-LABEL: {{^}}amd_kernel_code_t_test_all:
-// ASM: .amd_kernel_code_t
-// ASM: amd_code_version_major = 100
-// ASM: amd_code_version_minor = 100
-// ASM: amd_machine_kind = 0
-// ASM: amd_machine_version_major = 5
-// ASM: amd_machine_version_minor = 5
-// ASM: amd_machine_version_stepping = 5
-// ASM: kernel_code_entry_byte_offset = 512
-// ASM: kernel_code_prefetch_byte_size = 1
-// ASM: granulated_workitem_vgpr_count = 1
-// ASM: granulated_wavefront_sgpr_count = 1
-// ASM: priority = 1
-// ASM: float_mode = 1
-// ASM: priv = 1
-// ASM: enable_dx10_clamp = 1
-// ASM: debug_mode = 1
-// ASM: enable_ieee_mode = 1
-// ASM: enable_wgp_mode = 0
-// ASM: enable_mem_ordered = 0
-// ASM: enable_fwd_progress = 1
-// ASM: enable_sgpr_private_segment_wave_byte_offset = 1
-// ASM: user_sgpr_count = 1
-// ASM: enable_sgpr_workgroup_id_x = 1
-// ASM: enable_sgpr_workgroup_id_y = 1
-// ASM: enable_sgpr_workgroup_id_z = 1
-// ASM: enable_sgpr_workgroup_info = 1
-// ASM: enable_vgpr_workitem_id = 1
-// ASM: enable_exception_msb = 1
-// ASM: granulated_lds_size = 1
-// ASM: enable_exception = 1
-// ASM: enable_sgpr_private_segment_buffer = 1
-// ASM: enable_sgpr_dispatch_ptr = 1
-// ASM: enable_sgpr_queue_ptr = 1
-// ASM: enable_sgpr_kernarg_segment_ptr = 1
-// ASM: enable_sgpr_dispatch_id = 1
-// ASM: enable_sgpr_flat_scratch_init = 1
-// ASM: enable_sgpr_private_segment_size = 1
-// ASM: enable_sgpr_grid_workgroup_count_x = 1
-// ASM: enable_sgpr_grid_workgroup_count_y = 1
-// ASM: enable_sgpr_grid_workgroup_count_z = 1
-// ASM: enable_ordered_append_gds = 1
-// ASM: private_element_size = 1
-// ASM: is_ptr64 = 1
-// ASM: is_dynamic_callstack = 1
-// ASM: is_debug_enabled = 1
-// ASM: is_xnack_enabled = 1
-// ASM: workitem_private_segment_byte_size = 1
-// ASM: workgroup_group_segment_byte_size = 1
-// ASM: gds_segment_byte_size = 1
-// ASM: kernarg_segment_byte_size = 1
-// ASM: workgroup_fbarrier_count = 1
-// ASM: wavefront_sgpr_count = 1
-// ASM: workitem_vgpr_count = 1
-// ASM: reserved_vgpr_first = 1
-// ASM: reserved_vgpr_count = 1
-// ASM: reserved_sgpr_first = 1
-// ASM: reserved_sgpr_count = 1
-// ASM: debug_wavefront_private_segment_offset_sgpr = 1
-// ASM: debug_private_segment_buffer_sgpr = 1
-// ASM: kernarg_segment_alignment = 5
-// ASM: group_segment_alignment = 5
-// ASM: private_segment_alignment = 5
-// ASM: wavefront_size = 6
-// ASM: call_convention = 1
-// ASM: runtime_loader_kernel_symbol = 1
-// ASM: .end_amd_kernel_code_t
-
-amd_kernel_code_t_minimal:
-.amd_kernel_code_t
-  enable_sgpr_kernarg_segment_ptr = 1
-  is_ptr64 = 1
-  granulated_workitem_vgpr_count = 1
-  granulated_wavefront_sgpr_count = 1
-  user_sgpr_count = 2
-  kernarg_segment_byte_size = 16
-  wavefront_sgpr_count = 8
-//      wavefront_sgpr_count = 7
-; wavefront_sgpr_count = 7
-// Make sure a blank line won't break anything:
-
-// Make sure a line with whitespace won't break anything:
-
-  workitem_vgpr_count = 16
-.end_amd_kernel_code_t
-
-// ASM-LABEL: {{^}}amd_kernel_code_t_minimal:
-// ASM: .amd_kernel_code_t
-// ASM: amd_code_version_major = 1
-// ASM: amd_code_version_minor = 2
-// ASM: amd_machine_kind = 1
-// ASM: amd_machine_version_major = 10
-// ASM: amd_machine_version_minor = 1
-// ASM: amd_machine_version_stepping = 0
-// ASM: kernel_code_entry_byte_offset = 256
-// ASM: kernel_code_prefetch_byte_size = 0
-// ASM: granulated_workitem_vgpr_count = 1
-// ASM: granulated_wavefront_sgpr_count = 1
-// ASM: priority = 0
-// ASM: float_mode = 0
-// ASM: priv = 0
-// ASM: enable_dx10_clamp = 0
-// ASM: debug_mode = 0
-// ASM: enable_ieee_mode = 0
-// ASM: enable_wgp_mode = 1
-// ASM: enable_mem_ordered = 1
-// ASM: enable_fwd_progress = 0
-// ASM: enable_sgpr_private_segment_wave_byte_offset = 0
-// ASM: user_sgpr_count = 2
-// ASM: enable_sgpr_workgroup_id_x = 0
-// ASM: enable_sgpr_workgroup_id_y = 0
-// ASM: enable_sgpr_workgroup_id_z = 0
-// ASM: enable_sgpr_workgroup_info = 0
-// ASM: enable_vgpr_workitem_id = 0
-// ASM: enable_exception_msb = 0
-// ASM: granulated_lds_size = 0
-// ASM: enable_exception = 0
-// ASM: enable_sgpr_private_segment_buffer = 0
-// ASM: enable_sgpr_dispatch_ptr = 0
-// ASM: enable_sgpr_queue_ptr = 0
-// ASM: enable_sgpr_kernarg_segment_ptr = 1
-// ASM: enable_sgpr_dispatch_id = 0
-// ASM: enable_sgpr_flat_scratch_init = 0
-// ASM: enable_sgpr_private_segment_size = 0
-// ASM: enable_sgpr_grid_workgroup_count_x = 0
-// ASM: enable_sgpr_grid_workgroup_count_y = 0
-// ASM: enable_sgpr_grid_workgroup_count_z = 0
-// ASM: enable_wavefront_size32 = 0
-// ASM: enable_ordered_append_gds = 0
-// ASM: private_element_size = 0
-// ASM: is_ptr64 = 1
-// ASM: is_dynamic_callstack = 0
-// ASM: is_debug_enabled = 0
-// ASM: is_xnack_enabled = 0
-// ASM: workitem_private_segment_byte_size = 0
-// ASM: workgroup_group_segment_byte_size = 0
-// ASM: gds_segment_byte_size = 0
-// ASM: kernarg_segment_byte_size = 16
-// ASM: workgroup_fbarrier_count = 0
-// ASM: wavefront_sgpr_count = 8
-// ASM: workitem_vgpr_count = 16
-// ASM: reserved_vgpr_first = 0
-// ASM: reserved_vgpr_count = 0
-// ASM: reserved_sgpr_first = 0
-// ASM: reserved_sgpr_count = 0
-// ASM: debug_wavefront_private_segment_offset_sgpr = 0
-// ASM: debug_private_segment_buffer_sgpr = 0
-// ASM: kernarg_segment_alignment = 4
-// ASM: group_segment_alignment = 4
-// ASM: private_segment_alignment = 4
-// ASM: wavefront_size = 6
-// ASM: call_convention = -1
-// ASM: runtime_loader_kernel_symbol = 0
-// ASM: .end_amd_kernel_code_t

llvm/test/MC/AMDGPU/hsa-metadata-kernel-args.s

-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-
-// The legacy ValueType field should be parsed without error, but not
-// re-emitted.
-
-// CHECK:  .amd_amdgpu_hsa_metadata
-// CHECK:    Version: [ 1, 0 ]
-// CHECK:    Printf:
-// CHECK:      - '1:1:4:%d\n'
-// CHECK:      - '2:1:8:%g\n'
-// CHECK:    Kernels:
-// CHECK:      - Name:            test_kernel
-// CHECK:        SymbolName:      'test_kernel@kd'
-// CHECK:        Language:        OpenCL C
-// CHECK:        LanguageVersion: [ 2, 0 ]
-// CHECK:        Args:
-// CHECK:          - TypeName:      char
-// CHECK:            Size:          1
-// CHECK:            Align:         1
-// CHECK:            ValueKind:     ByValue
-// CHECK:            AccQual:       Default
-// CHECK:          - Size:          8
-// CHECK:            Align:         8
-// CHECK:            ValueKind:     HiddenGlobalOffsetX
-// CHECK:          - Size:          8
-// CHECK:            Align:         8
-// CHECK:            ValueKind:     HiddenGlobalOffsetY
-// CHECK:          - Size:          8
-// CHECK:            Align:         8
-// CHECK:            ValueKind:     HiddenGlobalOffsetZ
-// CHECK:          - Size:          8
-// CHECK:            Align:         8
-// CHECK:            ValueKind:     HiddenPrintfBuffer
-// CHECK:            AddrSpaceQual: Global
-// CHECK:  .end_amd_amdgpu_hsa_metadata
-.amd_amdgpu_hsa_metadata
-  Version: [ 1, 0 ]
-  Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
-  Kernels:
-    - Name:            test_kernel
-      SymbolName:      test_kernel@kd
-      Language:        OpenCL C
-      LanguageVersion: [ 2, 0 ]
-      Args:
-        - TypeName:      char
-          Size:          1
-          Align:         1
-          ValueKind:     ByValue
-          ValueType:     I8
-          AccQual:       Default
-        - Size:          8
-          Align:         8
-          ValueKind:     HiddenGlobalOffsetX
-          ValueType:     I64
-        - Size:          8
-          Align:         8
-          ValueKind:     HiddenGlobalOffsetY
-          ValueType:     I64
-        - Size:          8
-          Align:         8
-          ValueKind:     HiddenGlobalOffsetZ
-          ValueType:     I64
-        - Size:          8
-          Align:         8
-          ValueKind:     HiddenPrintfBuffer
-          ValueType:     I8
-          AddrSpaceQual: Global
-.end_amd_amdgpu_hsa_metadata

llvm/test/MC/AMDGPU/hsa-metadata-kernel-attrs.s

-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-
-// CHECK:  .amd_amdgpu_hsa_metadata
-// CHECK:    Version: [ 1, 0 ]
-// CHECK:    Printf:
-// CHECK:      - '1:1:4:%d\n'
-// CHECK:      - '2:1:8:%g\n'
-// CHECK:    Kernels:
-// CHECK:      - Name:            test_kernel
-// CHECK:        SymbolName:      'test_kernel@kd'
-// 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_amd_amdgpu_hsa_metadata
-.amd_amdgpu_hsa_metadata
-  Version: [ 1, 0 ]
-  Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
-  Kernels:
-    - Name:            test_kernel
-      SymbolName:      test_kernel@kd
-      Language:        OpenCL C
-      LanguageVersion: [ 2, 0 ]
-      Attrs:
-        ReqdWorkGroupSize: [ 1, 2, 4 ]
-        WorkGroupSizeHint: [ 8, 16, 32 ]
-        VecTypeHint:       int
-.end_amd_amdgpu_hsa_metadata

llvm/test/MC/AMDGPU/hsa-metadata-kernel-code-props.s

-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-
-// CHECK:  .amd_amdgpu_hsa_metadata
-// CHECK:    Version: [ 1, 0 ]
-// CHECK:    Kernels:
-// CHECK:      - Name:       test_kernel
-// CHECK:        SymbolName: 'test_kernel@kd'
-// CHECK:        CodeProps:
-// CHECK:          KernargSegmentSize:      24
-// CHECK:          GroupSegmentFixedSize:   24
-// CHECK:          PrivateSegmentFixedSize: 16
-// CHECK:          KernargSegmentAlign:     16
-// CHECK:          WavefrontSize:           64
-// CHECK:          MaxFlatWorkGroupSize:    256
-// CHECK:          NumSpilledSGPRs: 1
-// CHECK:          NumSpilledVGPRs: 1
-.amd_amdgpu_hsa_metadata
-  Version: [ 1, 0 ]
-  Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
-  Kernels:
-    - Name:            test_kernel
-      SymbolName:      test_kernel@kd
-      CodeProps:
-        KernargSegmentSize:      24
-        GroupSegmentFixedSize:   24
-        PrivateSegmentFixedSize: 16
-        KernargSegmentAlign:     16
-        WavefrontSize:           64
-        MaxFlatWorkGroupSize:    256
-        NumSpilledSGPRs:         1
-        NumSpilledVGPRs:         1
-.end_amd_amdgpu_hsa_metadata

llvm/test/MC/AMDGPU/hsa-metadata-kernel-debug-props.s

-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-// RUN: llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck --check-prefix=CHECK %s
-
-// CHECK:  .amd_amdgpu_hsa_metadata
-// CHECK:    Version: [ 1, 0 ]
-// CHECK:    Kernels:
-// CHECK:      - Name:       test_kernel
-// CHECK:        SymbolName: 'test_kernel@kd'
-// CHECK:        DebugProps:
-// CHECK:          DebuggerABIVersion:                [ 1, 0 ]
-// CHECK:          ReservedNumVGPRs:                  4
-// CHECK:          ReservedFirstVGPR:                 11
-// CHECK:          PrivateSegmentBufferSGPR:          0
-// CHECK:          WavefrontPrivateSegmentOffsetSGPR: 11
-.amd_amdgpu_hsa_metadata
-  Version: [ 1, 0 ]
-  Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
-  Kernels:
-    - Name:            test_kernel
-      SymbolName:      test_kernel@kd
-      DebugProps:
-        DebuggerABIVersion:                [ 1, 0 ]
-        ReservedNumVGPRs:                  4
-        ReservedFirstVGPR:                 11
-        PrivateSegmentBufferSGPR:          0
-        WavefrontPrivateSegmentOffsetSGPR: 11
-.end_amd_amdgpu_hsa_metadata

llvm/test/MC/AMDGPU/hsa-metadata-unknown-key.s

-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 --amdhsa-code-object-version=2 %s 2>&1 | FileCheck %s
-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 --amdhsa-code-object-version=2 %s 2>&1 | FileCheck %s
-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=2 %s 2>&1 | FileCheck %s
-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 --amdhsa-code-object-version=2 -filetype=obj %s 2>&1 | FileCheck %s
-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx800 --amdhsa-code-object-version=2 -filetype=obj %s 2>&1 | FileCheck %s
-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=2 -filetype=obj %s 2>&1 | FileCheck %s
-
-// CHECK: error: unknown key 'UnknownKey'
-.amd_amdgpu_hsa_metadata
-  UnknownKey: [ 2, 0 ]
-  Version: [ 1, 0 ]
-  Printf: [ '1:1:4:%d\n', '2:1:8:%g\n' ]
-  Kernels:
-    - Name:            test_kernel
-      SymbolName:      test_kernel@kd
-      Language:        OpenCL C
-      LanguageVersion: [ 2, 0 ]
-      Args:
-        - Size:          1
-          Align:         1
-          ValueKind:     ByValue
-          ValueType:     I8
-          AccQual:       Default
-          TypeName:      char
-        - Size:          8
-          Align:         8
-          ValueKind:     HiddenGlobalOffsetX
-          ValueType:     I64
-        - Size:          8
-          Align:         8
-          ValueKind:     HiddenGlobalOffsetY
-          ValueType:     I64
-        - Size:          8
-          Align:         8
-          ValueKind:     HiddenGlobalOffsetZ
-          ValueType:     I64
-        - Size:          8
-          Align:         8
-          ValueKind:     HiddenPrintfBuffer
-          ValueType:     I8
-          AddrSpaceQual: Global
-.end_amd_amdgpu_hsa_metadata

llvm/test/MC/AMDGPU/hsa-text.s

-// RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=2 -show-encoding %s | FileCheck %s --check-prefix=ASM
-// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=2 -show-encoding %s | llvm-readobj -S --sd - | FileCheck %s --check-prefix=ELF
-
-// For compatibility reasons we treat convert .text sections to .hsatext
-
-// ELF: Section {
-
-// ELF: Name: .text
-// ELF: Type: SHT_PROGBITS (0x1)
-// ELF: Flags [ (0x6)
-// ELF: SHF_ALLOC (0x2)
-// ELF: SHF_EXECINSTR (0x4)
-// ELF: Size: 260
-// ELF: }
-
-.text
-// ASM: .text
-
-.hsa_code_object_version 1,0
-// ASM: .hsa_code_object_version 1,0
-
-.hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-// ASM: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-
-.amd_kernel_code_t
-.end_amd_kernel_code_t
-
-s_endpgm

llvm/test/MC/AMDGPU/hsa-wave-size.s

-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 --amdhsa-code-object-version=2 %s | FileCheck --check-prefixes=GCN,GFX7 %s
-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx1010 --amdhsa-code-object-version=2 -mattr=+wavefrontsize32,-wavefrontsize64 %s | FileCheck --check-prefixes=GCN,GFX10-W32 %s
-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx1010 --amdhsa-code-object-version=2 -mattr=-wavefrontsize32,+wavefrontsize64 %s | FileCheck --check-prefixes=GCN,GFX10-W64 %s
-
-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx700 --amdhsa-code-object-version=2 %s 2>&1 | FileCheck --check-prefix=GFX7-ERR %s
-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx1010 --amdhsa-code-object-version=2 -mattr=+wavefrontsize32,-wavefrontsize64 %s 2>&1 | FileCheck --check-prefix=GFX10-W32-ERR %s
-// RUN: not llvm-mc -triple=amdgcn-amd-amdhsa -mcpu=gfx1010 --amdhsa-code-object-version=2 -mattr=-wavefrontsize32,+wavefrontsize64 %s 2>&1 | FileCheck --check-prefix=GFX10-W64-ERR %s
-
-// GCN: test0:
-// GFX7: enable_wavefront_size32 = 0
-// GFX7: wavefront_size = 6
-// GFX10-W32: enable_wavefront_size32 = 1
-// GFX10-W32: wavefront_size = 5
-// GFX10-W64: enable_wavefront_size32 = 0
-// GFX10-W64: wavefront_size = 6
-.amdgpu_hsa_kernel test0
-test0:
-.amd_kernel_code_t
-.end_amd_kernel_code_t
-
-// GCN: test1:
-// GFX7: enable_wavefront_size32 = 0
-// GFX7: wavefront_size = 6
-// GFX10-W32-ERR: error: enable_wavefront_size32=0 requires +WavefrontSize64
-// GFX10-W64: enable_wavefront_size32 = 0
-// GFX10-W64: wavefront_size = 6
-.amdgpu_hsa_kernel test1
-test1:
-.amd_kernel_code_t
-  enable_wavefront_size32 = 0
-.end_amd_kernel_code_t
-
-// GCN: test2:
-// GFX7: enable_wavefront_size32 = 0
-// GFX7: wavefront_size = 6
-// GFX10-W32-ERR: error: wavefront_size=6 requires +WavefrontSize64
-// GFX10-W64: enable_wavefront_size32 = 0
-// GFX10-W64: wavefront_size = 6
-.amdgpu_hsa_kernel test2
-test2:
-.amd_kernel_code_t
-  wavefront_size = 6
-.end_amd_kernel_code_t
-
-// GCN: test3:
-// GFX7-ERR: error: enable_wavefront_size32=1 is only allowed on GFX10+
-// GFX10-W32: enable_wavefront_size32 = 1
-// GFX10-W32: wavefront_size = 5
-// GFX10-W64-ERR: error: enable_wavefront_size32=1 requires +WavefrontSize32
-.amdgpu_hsa_kernel test3
-test3:
-.amd_kernel_code_t
-  enable_wavefront_size32 = 1
-.end_amd_kernel_code_t
-
-// GCN: test4:
-// GFX7-ERR: error: wavefront_size=5 is only allowed on GFX10+
-// GFX10-W32: enable_wavefront_size32 = 1
-// GFX10-W32: wavefront_size = 5
-// GFX10-W64-ERR: error: wavefront_size=5 requires +WavefrontSize32
-.amdgpu_hsa_kernel test4
-test4:
-.amd_kernel_code_t
-  wavefront_size = 5
-.end_amd_kernel_code_t

llvm/test/MC/AMDGPU/hsa.s

-// RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=2 -show-encoding %s | FileCheck %s --check-prefix=ASM
-// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=2 -show-encoding %s | llvm-readobj --symbols -S --sd - | FileCheck %s --check-prefix=ELF
-
-// ELF: Section {
-// ELF: Name: .text
-// ELF: Type: SHT_PROGBITS (0x1)
-// ELF: Flags [ (0x6)
-// ELF: SHF_ALLOC (0x2)
-// ELF: SHF_EXECINSTR (0x4)
-
-// ELF: SHT_NOTE
-// ELF: 0000: 04000000 08000000 01000000 414D4400
-// ELF: 0010: 02000000 00000000 04000000 1B000000
-// ELF: 0020: 03000000 414D4400 04000700 07000000
-// ELF: 0030: 00000000 00000000 414D4400 414D4447
-// ELF: 0040: 50550000
-// We can't check binary representation of metadata note: it is different on
-// Windows and Linux because of carriage return on Windows
-
-// ELF: Symbol {
-// ELF: Name: amd_kernel_code_t_test_all
-// ELF: Type: AMDGPU_HSA_KERNEL (0xA)
-// ELF: Section: .text
-// ELF: }
-// ELF: Symbol {
-// ELF: Name: amd_kernel_code_t_minimal
-// ELF: Type: AMDGPU_HSA_KERNEL (0xA)
-// ELF: Section: .text
-// ELF: }
-
-.text
-// ASM: .text
-
-.hsa_code_object_version 2,0
-// ASM: .hsa_code_object_version 2,0
-
-.hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-// ASM: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-
-.amd_amdgpu_hsa_metadata
-  Version: [ 3, 0 ]
-  Kernels:
-    - Name:       amd_kernel_code_t_test_all
-      SymbolName: amd_kernel_code_t_test_all@kd
-    - Name:       amd_kernel_code_t_minimal
-      SymbolName: amd_kernel_code_t_minimal@kd
-.end_amd_amdgpu_hsa_metadata
-
-// ASM: .amd_amdgpu_hsa_metadata
-// ASM:    Version: [ 3, 0 ]
-// ASM:    Kernels:
-// ASM:      - Name:       amd_kernel_code_t_test_all
-// ASM:        SymbolName: 'amd_kernel_code_t_test_all@kd'
-// ASM:      - Name:       amd_kernel_code_t_minimal
-// ASM:        SymbolName: 'amd_kernel_code_t_minimal@kd'
-// ASM: .end_amd_amdgpu_hsa_metadata
-
-.amdgpu_hsa_kernel amd_kernel_code_t_test_all
-.amdgpu_hsa_kernel amd_kernel_code_t_minimal
-
-amd_kernel_code_t_test_all:
-; Test all amd_kernel_code_t members with non-default values.
-.amd_kernel_code_t
-    kernel_code_version_major = 100
-    kernel_code_version_minor = 100
-    machine_kind = 0
-    machine_version_major = 5
-    machine_version_minor = 5
-    machine_version_stepping = 5
-    kernel_code_entry_byte_offset = 512
-    kernel_code_prefetch_byte_size = 1
-    max_scratch_backing_memory_byte_size = 1
-    compute_pgm_rsrc1_vgprs = 1
-    compute_pgm_rsrc1_sgprs = 1
-    compute_pgm_rsrc1_priority = 1
-    compute_pgm_rsrc1_float_mode = 1
-    compute_pgm_rsrc1_priv = 1
-    compute_pgm_rsrc1_dx10_clamp = 1
-    compute_pgm_rsrc1_debug_mode = 1
-    compute_pgm_rsrc1_ieee_mode = 1
-    compute_pgm_rsrc2_scratch_en = 1
-    compute_pgm_rsrc2_user_sgpr = 1
-    compute_pgm_rsrc2_tgid_x_en = 1
-    compute_pgm_rsrc2_tgid_y_en = 1
-    compute_pgm_rsrc2_tgid_z_en = 1
-    compute_pgm_rsrc2_tg_size_en = 1
-    compute_pgm_rsrc2_tidig_comp_cnt = 1
-    compute_pgm_rsrc2_excp_en_msb = 1
-    compute_pgm_rsrc2_lds_size = 1
-    compute_pgm_rsrc2_excp_en = 1
-    enable_sgpr_private_segment_buffer = 1
-    enable_sgpr_dispatch_ptr = 1
-    enable_sgpr_queue_ptr = 1
-    enable_sgpr_kernarg_segment_ptr = 1
-    enable_sgpr_dispatch_id = 1
-    enable_sgpr_flat_scratch_init = 1
-    enable_sgpr_private_segment_size = 1
-    enable_sgpr_grid_workgroup_count_x = 1
-    enable_sgpr_grid_workgroup_count_y = 1
-    enable_sgpr_grid_workgroup_count_z = 1
-    enable_ordered_append_gds = 1
-    private_element_size = 1
-    is_ptr64 = 1
-    is_dynamic_callstack = 1
-    is_debug_enabled = 1
-    is_xnack_enabled = 1
-    workitem_private_segment_byte_size = 1
-    workgroup_group_segment_byte_size = 1
-    gds_segment_byte_size = 1
-    kernarg_segment_byte_size = 1
-    workgroup_fbarrier_count = 1
-    wavefront_sgpr_count = 1
-    workitem_vgpr_count = 1
-    reserved_vgpr_first = 1
-    reserved_vgpr_count = 1
-    reserved_sgpr_first = 1
-    reserved_sgpr_count = 1
-    debug_wavefront_private_segment_offset_sgpr = 1
-    debug_private_segment_buffer_sgpr = 1
-    kernarg_segment_alignment = 5
-    group_segment_alignment = 5
-    private_segment_alignment = 5
-    wavefront_size = 6
-    call_convention = 1
-    runtime_loader_kernel_symbol = 1
-.end_amd_kernel_code_t
-
-// ASM-LABEL: {{^}}amd_kernel_code_t_test_all:
-// ASM: .amd_kernel_code_t
-// ASM: amd_code_version_major = 100
-// ASM: amd_code_version_minor = 100
-// ASM: amd_machine_kind = 0
-// ASM: amd_machine_version_major = 5
-// ASM: amd_machine_version_minor = 5
-// ASM: amd_machine_version_stepping = 5
-// ASM: kernel_code_entry_byte_offset = 512
-// ASM: kernel_code_prefetch_byte_size = 1
-// ASM: granulated_workitem_vgpr_count = 1
-// ASM: granulated_wavefront_sgpr_count = 1
-// ASM: priority = 1
-// ASM: float_mode = 1
-// ASM: priv = 1
-// ASM: enable_dx10_clamp = 1
-// ASM: debug_mode = 1
-// ASM: enable_ieee_mode = 1
-// ASM: enable_sgpr_private_segment_wave_byte_offset = 1
-// ASM: user_sgpr_count = 1
-// ASM: enable_sgpr_workgroup_id_x = 1
-// ASM: enable_sgpr_workgroup_id_y = 1
-// ASM: enable_sgpr_workgroup_id_z = 1
-// ASM: enable_sgpr_workgroup_info = 1
-// ASM: enable_vgpr_workitem_id = 1
-// ASM: enable_exception_msb = 1
-// ASM: granulated_lds_size = 1
-// ASM: enable_exception = 1
-// ASM: enable_sgpr_private_segment_buffer = 1
-// ASM: enable_sgpr_dispatch_ptr = 1
-// ASM: enable_sgpr_queue_ptr = 1
-// ASM: enable_sgpr_kernarg_segment_ptr = 1
-// ASM: enable_sgpr_dispatch_id = 1
-// ASM: enable_sgpr_flat_scratch_init = 1
-// ASM: enable_sgpr_private_segment_size = 1
-// ASM: enable_sgpr_grid_workgroup_count_x = 1
-// ASM: enable_sgpr_grid_workgroup_count_y = 1
-// ASM: enable_sgpr_grid_workgroup_count_z = 1
-// ASM: enable_ordered_append_gds = 1
-// ASM: private_element_size = 1
-// ASM: is_ptr64 = 1
-// ASM: is_dynamic_callstack = 1
-// ASM: is_debug_enabled = 1
-// ASM: is_xnack_enabled = 1
-// ASM: workitem_private_segment_byte_size = 1
-// ASM: workgroup_group_segment_byte_size = 1
-// ASM: gds_segment_byte_size = 1
-// ASM: kernarg_segment_byte_size = 1
-// ASM: workgroup_fbarrier_count = 1
-// ASM: wavefront_sgpr_count = 1
-// ASM: workitem_vgpr_count = 1
-// ASM: reserved_vgpr_first = 1
-// ASM: reserved_vgpr_count = 1
-// ASM: reserved_sgpr_first = 1
-// ASM: reserved_sgpr_count = 1
-// ASM: debug_wavefront_private_segment_offset_sgpr = 1
-// ASM: debug_private_segment_buffer_sgpr = 1
-// ASM: kernarg_segment_alignment = 5
-// ASM: group_segment_alignment = 5
-// ASM: private_segment_alignment = 5
-// ASM: wavefront_size = 6
-// ASM: call_convention = 1
-// ASM: runtime_loader_kernel_symbol = 1
-// ASM: .end_amd_kernel_code_t
-
-amd_kernel_code_t_minimal:
-.amd_kernel_code_t
-  enable_sgpr_kernarg_segment_ptr = 1
-  is_ptr64 = 1
-  granulated_workitem_vgpr_count = 1
-  granulated_wavefront_sgpr_count = 1
-  user_sgpr_count = 2
-  kernarg_segment_byte_size = 16
-  wavefront_sgpr_count = 8
-//      wavefront_sgpr_count = 7
-; wavefront_sgpr_count = 7
-// Make sure a blank line won't break anything:
-
-// Make sure a line with whitespace won't break anything:
-
-  workitem_vgpr_count = 16
-.end_amd_kernel_code_t
-
-// ASM-LABEL: {{^}}amd_kernel_code_t_minimal:
-// ASM: .amd_kernel_code_t
-// ASM: amd_code_version_major = 1
-// ASM: amd_code_version_minor = 2
-// ASM: amd_machine_kind = 1
-// ASM: amd_machine_version_major = 7
-// ASM: amd_machine_version_minor = 0
-// ASM: amd_machine_version_stepping = 0
-// ASM: kernel_code_entry_byte_offset = 256
-// ASM: kernel_code_prefetch_byte_size = 0
-// ASM: granulated_workitem_vgpr_count = 1
-// ASM: granulated_wavefront_sgpr_count = 1
-// ASM: priority = 0
-// ASM: float_mode = 0
-// ASM: priv = 0
-// ASM: enable_dx10_clamp = 0
-// ASM: debug_mode = 0
-// ASM: enable_ieee_mode = 0
-// ASM: enable_sgpr_private_segment_wave_byte_offset = 0
-// ASM: user_sgpr_count = 2
-// ASM: enable_sgpr_workgroup_id_x = 0
-// ASM: enable_sgpr_workgroup_id_y = 0
-// ASM: enable_sgpr_workgroup_id_z = 0
-// ASM: enable_sgpr_workgroup_info = 0
-// ASM: enable_vgpr_workitem_id = 0
-// ASM: enable_exception_msb = 0
-// ASM: granulated_lds_size = 0
-// ASM: enable_exception = 0
-// ASM: enable_sgpr_private_segment_buffer = 0
-// ASM: enable_sgpr_dispatch_ptr = 0
-// ASM: enable_sgpr_queue_ptr = 0
-// ASM: enable_sgpr_kernarg_segment_ptr = 1
-// ASM: enable_sgpr_dispatch_id = 0
-// ASM: enable_sgpr_flat_scratch_init = 0
-// ASM: enable_sgpr_private_segment_size = 0
-// ASM: enable_sgpr_grid_workgroup_count_x = 0
-// ASM: enable_sgpr_grid_workgroup_count_y = 0
-// ASM: enable_sgpr_grid_workgroup_count_z = 0
-// ASM: enable_ordered_append_gds = 0
-// ASM: private_element_size = 0
-// ASM: is_ptr64 = 1
-// ASM: is_dynamic_callstack = 0
-// ASM: is_debug_enabled = 0
-// ASM: is_xnack_enabled = 0
-// ASM: workitem_private_segment_byte_size = 0
-// ASM: workgroup_group_segment_byte_size = 0
-// ASM: gds_segment_byte_size = 0
-// ASM: kernarg_segment_byte_size = 16
-// ASM: workgroup_fbarrier_count = 0
-// ASM: wavefront_sgpr_count = 8
-// ASM: workitem_vgpr_count = 16
-// ASM: reserved_vgpr_first = 0
-// ASM: reserved_vgpr_count = 0
-// ASM: reserved_sgpr_first = 0
-// ASM: reserved_sgpr_count = 0
-// ASM: debug_wavefront_private_segment_offset_sgpr = 0
-// ASM: debug_private_segment_buffer_sgpr = 0
-// ASM: kernarg_segment_alignment = 4
-// ASM: group_segment_alignment = 4
-// ASM: private_segment_alignment = 4
-// ASM: wavefront_size = 6
-// ASM: call_convention = -1
-// ASM: runtime_loader_kernel_symbol = 0
-// ASM: .end_amd_kernel_code_t

llvm/test/MC/AMDGPU/hsa_code_object_isa_args.s

-// RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=2 -show-encoding %s | FileCheck %s --check-prefix=ASM --check-prefix=ASM_700
-// RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=gfx803 --amdhsa-code-object-version=2 -show-encoding %s | FileCheck %s --check-prefix=ASM --check-prefix=ASM_803
-// RUN: llvm-mc -triple amdgcn--amdhsa -mcpu=stoney --amdhsa-code-object-version=2 -show-encoding %s | FileCheck %s --check-prefix=ASM --check-prefix=ASM_810
-// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=kaveri --amdhsa-code-object-version=2 -show-encoding %s | llvm-readobj -S --sd - | FileCheck %s --check-prefix=ELF --check-prefix=ELF_700
-// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=gfx803 --amdhsa-code-object-version=2 -show-encoding %s | llvm-readobj -S --sd - | FileCheck %s --check-prefix=ELF --check-prefix=ELF_803
-// RUN: llvm-mc -filetype=obj -triple amdgcn--amdhsa -mcpu=stoney --amdhsa-code-object-version=2 -show-encoding %s | llvm-readobj -S --sd - | FileCheck %s --check-prefix=ELF --check-prefix=ELF_810
-
-// ELF: SHT_NOTE
-// ELF: 0000: 04000000 08000000 01000000 414D4400
-// ELF: 0010: 01000000 00000000 04000000 1B000000
-// ELF_700: 0020: 03000000 414D4400 04000700 07000000
-// ELF_700: 0030: 00000000 00000000 414D4400 414D4447
-// ELF_803: 0020: 03000000 414D4400 04000700 08000000
-// ELF_803: 0030: 00000000 03000000 414D4400 414D4447
-// ELF_810: 0020: 03000000 414D4400 04000700 08000000
-// ELF_810: 0030: 01000000 00000000 414D4400 414D4447
-// ELF: 0040: 50550000
-
-.hsa_code_object_version 1,0
-// ASM: .hsa_code_object_version 1,0
-
-// Test defaults
-.hsa_code_object_isa
-// ASM_700: .hsa_code_object_isa 7,0,0,"AMD","AMDGPU"
-// ASM_803: .hsa_code_object_isa 8,0,3,"AMD","AMDGPU"
-// ASM_810: .hsa_code_object_isa 8,1,0,"AMD","AMDGPU"
-
-// Test expressions and symbols
-.set A,2
-.hsa_code_object_isa A+1,A*2,A/A+4,"AMD","AMDGPU"
-// ASM: .hsa_code_object_isa 3,4,5,"AMD","AMDGPU"

llvm/test/MC/AMDGPU/isa-version-hsa.s

 // RUN: not llvm-mc -triple amdgcn-amd-unknown -mcpu=gfx802 %s 2>&1 | FileCheck --check-prefix=OSABI-UNK-ERR %s
 // RUN: not llvm-mc -triple amdgcn-amd-unknown -mcpu=iceland %s 2>&1 | FileCheck --check-prefix=OSABI-UNK-ERR %s
-// RUN: llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=gfx802 %s | FileCheck --check-prefix=OSABI-HSA %s
-// RUN: llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=iceland %s | FileCheck --check-prefix=OSABI-HSA %s
-// RUN: not llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=gfx803 %s 2>&1 | FileCheck --check-prefix=OSABI-HSA-ERR %s
+// RUN: llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=4 -mcpu=gfx802 %s | FileCheck --check-prefix=OSABI-HSA %s
+// RUN: llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=4 -mcpu=iceland %s | FileCheck --check-prefix=OSABI-HSA %s
+// RUN: not llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=4 -mcpu=gfx803 %s 2>&1 | FileCheck --check-prefix=OSABI-HSA-ERR %s
 // RUN: not llvm-mc -triple amdgcn-amd-amdpal -mcpu=gfx802 %s 2>&1 | FileCheck --check-prefix=OSABI-PAL-ERR %s
 // RUN: not llvm-mc -triple amdgcn-amd-amdpal -mcpu=iceland %s 2>&1 | FileCheck --check-prefix=OSABI-PAL-ERR %s
 
-// OSABI-HSA: .amd_amdgpu_isa "amdgcn-amd-amdhsa--gfx802"
-// OSABI-UNK-ERR: error: target id must match options
-// OSABI-HSA-ERR: error: target id must match options
-// OSABI-PAL-ERR: error: target id must match options
-.amd_amdgpu_isa "amdgcn-amd-amdhsa--gfx802"
+// OSABI-HSA: .amdgcn_target "amdgcn-amd-amdhsa--gfx802"
+// OSABI-UNK-ERR: error: .amdgcn_target directive's target id amdgcn-amd-amdhsa--gfx802 does not match the specified target id amdgcn-amd-unknown--gfx802
+// OSABI-HSA-ERR: error: .amdgcn_target directive's target id amdgcn-amd-amdhsa--gfx802 does not match the specified target id amdgcn-amd-amdhsa--gfx803
+// OSABI-PAL-ERR: error: .amdgcn_target directive's target id amdgcn-amd-amdhsa--gfx802 does not match the specified target id amdgcn-amd-amdpal--gfx802
+.amdgcn_target "amdgcn-amd-amdhsa--gfx802"

llvm/test/MC/AMDGPU/isa-version-pal.s

 // RUN: not llvm-mc -triple amdgcn-amd-unknown -mcpu=gfx802 %s 2>&1 | FileCheck --check-prefix=OSABI-UNK-ERR %s
 // RUN: not llvm-mc -triple amdgcn-amd-unknown -mcpu=iceland %s 2>&1 | FileCheck --check-prefix=OSABI-UNK-ERR %s
-// RUN: not llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=gfx802 %s 2>&1 | FileCheck --check-prefix=OSABI-HSA-ERR %s
-// RUN: not llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=iceland %s 2>&1 | FileCheck --check-prefix=OSABI-HSA-ERR %s
+// RUN: not llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=4 -mcpu=gfx802 %s 2>&1 | FileCheck --check-prefix=OSABI-HSA-ERR %s
+// RUN: not llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=4 -mcpu=iceland %s 2>&1 | FileCheck --check-prefix=OSABI-HSA-ERR %s
 // RUN: llvm-mc -triple amdgcn-amd-amdpal -mcpu=gfx802 %s | FileCheck --check-prefix=OSABI-PAL %s
 // RUN: llvm-mc -triple amdgcn-amd-amdpal -mcpu=iceland %s | FileCheck --check-prefix=OSABI-PAL %s
 // RUN: not llvm-mc -triple amdgcn-amd-unknown -mcpu=gfx802 %s 2>&1 | FileCheck --check-prefix=OSABI-UNK-ERR %s
 
 // OSABI-PAL: .amd_amdgpu_isa "amdgcn-amd-amdpal--gfx802"
 // OSABI-UNK-ERR: error: target id must match options
-// OSABI-HSA-ERR: error: target id must match options
+// OSABI-HSA-ERR: error: .amdgcn_target directive's target id amdgcn-amd-amdpal--gfx802 does not match the specified target id amdgcn-amd-amdhsa--gfx802
 // OSABI-PAL-ERR: error: target id must match options
 .amd_amdgpu_isa "amdgcn-amd-amdpal--gfx802"
+.amdgcn_target "amdgcn-amd-amdpal--gfx802"

llvm/test/MC/AMDGPU/isa-version-unk.s

 // RUN: llvm-mc -triple amdgcn-amd-unknown -mcpu=gfx802 %s | FileCheck --check-prefix=OSABI-UNK %s
 // RUN: llvm-mc -triple amdgcn-amd-unknown -mcpu=iceland %s | FileCheck --check-prefix=OSABI-UNK %s
 // RUN: not llvm-mc -triple amdgcn-amd-unknown -mcpu=gfx803 %s 2>&1 | FileCheck --check-prefix=OSABI-UNK-ERR %s
-// RUN: not llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=gfx802 %s 2>&1 | FileCheck --check-prefix=OSABI-HSA-ERR %s
-// RUN: not llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=2 -mcpu=iceland %s 2>&1 | FileCheck --check-prefix=OSABI-HSA-ERR %s
+// RUN: not llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=4 -mcpu=gfx802 %s 2>&1 | FileCheck --check-prefix=OSABI-HSA-ERR %s
+// RUN: not llvm-mc -triple amdgcn-amd-amdhsa --amdhsa-code-object-version=4 -mcpu=iceland %s 2>&1 | FileCheck --check-prefix=OSABI-HSA-ERR %s
 // RUN: not llvm-mc -triple amdgcn-amd-amdpal -mcpu=gfx802 %s 2>&1 | FileCheck --check-prefix=OSABI-PAL-ERR %s
 // RUN: not llvm-mc -triple amdgcn-amd-amdpal -mcpu=iceland %s 2>&1 | FileCheck --check-prefix=OSABI-PAL-ERR %s
 
 // OSABI-UNK: .amd_amdgpu_isa "amdgcn-amd-unknown--gfx802"
 // OSABI-UNK-ERR: error: target id must match options
-// OSABI-HSA-ERR: error: target id must match options
+// OSABI-HSA-ERR: error: .amdgcn_target directive's target id amdgcn-amd-unknown--gfx802 does not match the specified target id amdgcn-amd-amdhsa--gfx802
 // OSABI-PAL-ERR: error: target id must match options
 .amd_amdgpu_isa "amdgcn-amd-unknown--gfx802"
+.amdgcn_target "amdgcn-amd-unknown--gfx802"

llvm/tools/llvm-readobj/ELFDumper.cpp

default:
     return {"", ""};
   case ELF::NT_AMDGPU_METADATA: {
     StringRef MsgPackString =
         StringRef(reinterpret_cast<const char *>(Desc.data()), Desc.size());
     msgpack::Document MsgPackDoc;
     if (!MsgPackDoc.readFromBlob(MsgPackString, /*Multi=*/false))
       return {"", ""};
 
-    AMDGPU::HSAMD::V3::MetadataVerifier Verifier(true);
+    // Use a newline in any case so the "---" is at the start
+    // of the line in the YAML dump.
     std::string MetadataString;
+
+    // FIXME: Metadata Verifier doesn't work with AMDPAL MD.
+    //  This is a ugly workaround to avoid the verifier.
+    if (MsgPackString.find("amdpal.") == StringRef::npos) {
+      AMDGPU::HSAMD::V3::MetadataVerifier Verifier(true);
       if (!Verifier.verify(MsgPackDoc.getRoot()))
         MetadataString = "Invalid AMDGPU Metadata\n";
+    }
 
     raw_string_ostream StrOS(MetadataString);
     if (MsgPackDoc.getRoot().isScalar()) {
       // TODO: passing a scalar root to toYAML() asserts:
       // (PolymorphicTraits<T>::getKind(Val) != NodeKind::Scalar &&
       //    "plain scalar documents are not supported")
       // To avoid this crash we print the raw data instead.
       return {"", ""};