AMDGPU: Add hidden kernel arguments to runtime metadata

[yaxunl]

Summary

OpenCL kernels have hidden kernel arguments for global offset and printf buffer. For consistency, these hidden argument should be included in the runtime metadata. Also updated kernel argument kind metadata.

[yaxunl]

Make changes about argument kind and address space qualifier.

[arsenm]

lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp

884 ↗

(On Diff #68383)

Should Pass MCStreamer & instead of unique_ptr &

938–939 ↗

(On Diff #68383)

Space before (. Should also move switch into function with return instead of assign and break

940 ↗

(On Diff #68383)

Should use enum

1005 ↗

(On Diff #68383)

Enum. Remove ! and swap order

[yaxunl]

Revised as Matt suggested.

[yaxunl]

Rebase patch.

[yaxunl]

Fix base type name and type name metadata.

[yaxunl]

Ping!

runtime is ready for this change and waiting.

[• tstellarAMD]

LGTM.

llvm/trunk/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp

if (MD->getNumOperands() != 0) {
                          ->getZExtValue();
         uint16_t Minor = mdconst::extract<ConstantInt>(Node->getOperand(1))
                          ->getZExtValue();
         emitRuntimeMDIntValue(*OutStreamer, RuntimeMD::KeyLanguageVersion,
                               Major * 100 + Minor * 10, 2);
       }
     }
   }
+
+  if (auto MD = M.getNamedMetadata("llvm.printf.fmts")) {
+    for (unsigned I = 0; I < MD->getNumOperands(); ++I) {
+      auto Node = MD->getOperand(I);
+      if (Node->getNumOperands() > 0)
+        emitRuntimeMDStringValue(*OutStreamer, RuntimeMD::KeyPrintfInfo,
+            cast<MDString>(Node->getOperand(0))->getString());
+    }
+  }
 }
 
 static std::string getOCLTypeName(Type *Ty, bool Signed) {
   switch (Ty->getTypeID()) {
   case Type::HalfTyID:
     return "half";
   case Type::FloatTyID:
     return "float";
case Type::VectorTyID:
     return getRuntimeMDValueType(Ty->getVectorElementType(), TypeName);
   case Type::PointerTyID:
     return getRuntimeMDValueType(Ty->getPointerElementType(), TypeName);
   default:
     return RuntimeMD::KernelArg::Struct;
   }
 }
 
-void AMDGPUAsmPrinter::emitRuntimeMetadata(const Function &F) {
-  if (!F.getMetadata("kernel_arg_type"))
-    return;
-
-  MCContext &Context = getObjFileLowering().getContext();
-  OutStreamer->SwitchSection(
-      Context.getELFSection(RuntimeMD::SectionName, ELF::SHT_PROGBITS, 0));
-  OutStreamer->EmitIntValue(RuntimeMD::KeyKernelBegin, 1);
-  emitRuntimeMDStringValue(*OutStreamer, RuntimeMD::KeyKernelName, F.getName());
+static RuntimeMD::KernelArg::AddressSpaceQualifer getRuntimeAddrSpace(
+    AMDGPUAS::AddressSpaces A) {
+  switch (A) {
+  case AMDGPUAS::GLOBAL_ADDRESS:
+    return RuntimeMD::KernelArg::Global;
+  case AMDGPUAS::CONSTANT_ADDRESS:
+    return RuntimeMD::KernelArg::Constant;
+  case AMDGPUAS::LOCAL_ADDRESS:
+    return RuntimeMD::KernelArg::Local;
+  case AMDGPUAS::FLAT_ADDRESS:
+    return RuntimeMD::KernelArg::Generic;
+  case AMDGPUAS::REGION_ADDRESS:
+    return RuntimeMD::KernelArg::Region;
+  default:
+    return RuntimeMD::KernelArg::Private;
+  }
+}
 
-  for (auto &Arg : F.args()) {
-    // Emit KeyArgBegin.
-    unsigned I = Arg.getArgNo();
-    OutStreamer->EmitIntValue(RuntimeMD::KeyArgBegin, 1);
+static void emitRuntimeMetadataForKernelArg(const DataLayout &DL,
+    MCStreamer &OutStreamer, Type *T,
+    RuntimeMD::KernelArg::Kind Kind,
+    StringRef BaseTypeName = "", StringRef TypeName = "",
+    StringRef ArgName = "", StringRef TypeQual = "", StringRef AccQual = "") {
+  OutStreamer.EmitIntValue(RuntimeMD::KeyArgBegin, 1);
 
-    // Emit KeyArgSize, KeyArgAlign and KeyArgPointeeAlign.
-    Type *T = Arg.getType();
-    const DataLayout &DL = F.getParent()->getDataLayout();
-    emitRuntimeMDIntValue(*OutStreamer, RuntimeMD::KeyArgSize,
-                          DL.getTypeAllocSize(T), 4);
-    emitRuntimeMDIntValue(*OutStreamer, RuntimeMD::KeyArgAlign,
-                          DL.getABITypeAlignment(T), 4);
-    if (auto PT = dyn_cast<PointerType>(T)) {
-      auto ET = PT->getElementType();
-      if (ET->isSized())
-        emitRuntimeMDIntValue(*OutStreamer, RuntimeMD::KeyArgPointeeAlign,
-                          DL.getABITypeAlignment(ET), 4);
-    }
+  // Emit KeyArgSize and KeyArgAlign.
+  emitRuntimeMDIntValue(OutStreamer, RuntimeMD::KeyArgSize,
+  emitRuntimeMDIntValue(OutStreamer, RuntimeMD::KeyArgAlign,
+    if (PT->getAddressSpace() == AMDGPUAS::LOCAL_ADDRESS && ET->isSized())
+      emitRuntimeMDIntValue(OutStreamer, RuntimeMD::KeyArgPointeeAlign,
 
-    // Emit KeyArgTypeName.
-    auto TypeName = dyn_cast<MDString>(F.getMetadata(
-      "kernel_arg_type")->getOperand(I))->getString();
-    emitRuntimeMDStringValue(*OutStreamer, RuntimeMD::KeyArgTypeName, TypeName);
+  if (!TypeName.empty())
+    emitRuntimeMDStringValue(OutStreamer, RuntimeMD::KeyArgTypeName, TypeName);
 
-    // Emit KeyArgName.
-    if (auto ArgNameMD = F.getMetadata("kernel_arg_name")) {
-      auto ArgName = cast<MDString>(ArgNameMD->getOperand(I))->getString();
-      emitRuntimeMDStringValue(*OutStreamer, RuntimeMD::KeyArgName, ArgName);
-    }
+  if (!ArgName.empty())
+    emitRuntimeMDStringValue(OutStreamer, RuntimeMD::KeyArgName, ArgName);
 
-    // Emit KeyArgIsVolatile, KeyArgIsRestrict, KeyArgIsConst and KeyArgIsPipe.
-    auto TypeQual = cast<MDString>(F.getMetadata(
-      "kernel_arg_type_qual")->getOperand(I))->getString();
-    SmallVector<StringRef, 1> SplitQ;
-    TypeQual.split(SplitQ, " ", -1, false /* Drop empty entry */);
 
-    for (StringRef KeyName : SplitQ) {
-      auto Key = StringSwitch<RuntimeMD::Key>(KeyName)
-        .Case("volatile", RuntimeMD::KeyArgIsVolatile)
-        .Case("restrict", RuntimeMD::KeyArgIsRestrict)
-        .Case("const",    RuntimeMD::KeyArgIsConst)
-        .Case("pipe",     RuntimeMD::KeyArgIsPipe)
-        .Default(RuntimeMD::KeyNull);
-      OutStreamer->EmitIntValue(Key, 1);
-    }
+    OutStreamer.EmitIntValue(Key, 1);
 
-    // Emit KeyArgTypeKind.
-    auto BaseTypeName = cast<MDString>(
-      F.getMetadata("kernel_arg_base_type")->getOperand(I))->getString();
-    auto TypeKind = StringSwitch<RuntimeMD::KernelArg::TypeKind>(BaseTypeName)
-      .Case("sampler_t", RuntimeMD::KernelArg::Sampler)
-      .Case("queue_t",   RuntimeMD::KernelArg::Queue)
-      .Cases("image1d_t", "image1d_array_t", "image1d_buffer_t",
-             "image2d_t" , "image2d_array_t",  RuntimeMD::KernelArg::Image)
-      .Cases("image2d_depth_t", "image2d_array_depth_t",
-             "image2d_msaa_t", "image2d_array_msaa_t",
-             "image2d_msaa_depth_t",  RuntimeMD::KernelArg::Image)
-      .Cases("image2d_array_msaa_depth_t", "image3d_t",
-             RuntimeMD::KernelArg::Image)
-      .Default(isa<PointerType>(T) ? RuntimeMD::KernelArg::Pointer :
-               RuntimeMD::KernelArg::Value);
-    emitRuntimeMDIntValue(*OutStreamer, RuntimeMD::KeyArgTypeKind, TypeKind, 1);
+  // Emit KeyArgKind.
+  emitRuntimeMDIntValue(OutStreamer, RuntimeMD::KeyArgKind, Kind, 1);
 
-    // Emit KeyArgValueType.
-    emitRuntimeMDIntValue(*OutStreamer, RuntimeMD::KeyArgValueType,
-                          getRuntimeMDValueType(T, BaseTypeName), 2);
+  emitRuntimeMDIntValue(OutStreamer, RuntimeMD::KeyArgValueType,
 
-    // Emit KeyArgAccQual.
-    auto AccQual = cast<MDString>(F.getMetadata(
-      "kernel_arg_access_qual")->getOperand(I))->getString();
+  if (!AccQual.empty()) {
     auto AQ = StringSwitch<RuntimeMD::KernelArg::AccessQualifer>(AccQual)
       .Case("read_only",  RuntimeMD::KernelArg::ReadOnly)
       .Case("write_only", RuntimeMD::KernelArg::WriteOnly)
       .Case("read_write", RuntimeMD::KernelArg::ReadWrite)
       .Default(RuntimeMD::KernelArg::None);
-    emitRuntimeMDIntValue(*OutStreamer, RuntimeMD::KeyArgAccQual, AQ, 1);
+    emitRuntimeMDIntValue(OutStreamer, RuntimeMD::KeyArgAccQual, AQ, 1);
+  }
 
-    // Emit KeyArgAddrQual.
-    if (auto *PT = dyn_cast<PointerType>(T)) {
-      emitRuntimeMDIntValue(*OutStreamer, RuntimeMD::KeyArgAddrQual,
-                            PT->getAddressSpace(), 1);
-    }
+  if (auto *PT = dyn_cast<PointerType>(T))
+    emitRuntimeMDIntValue(OutStreamer, RuntimeMD::KeyArgAddrQual,
+        getRuntimeAddrSpace(static_cast<AMDGPUAS::AddressSpaces>(
+            PT->getAddressSpace())), 1);
 
-    // Emit KeyArgEnd
-    OutStreamer->EmitIntValue(RuntimeMD::KeyArgEnd, 1);
+  OutStreamer.EmitIntValue(RuntimeMD::KeyArgEnd, 1);
+}
+
+void AMDGPUAsmPrinter::emitRuntimeMetadata(const Function &F) {
+  if (!F.getMetadata("kernel_arg_type"))
+    return;
+
+  MCContext &Context = getObjFileLowering().getContext();
+  OutStreamer->SwitchSection(
+      Context.getELFSection(RuntimeMD::SectionName, ELF::SHT_PROGBITS, 0));
+  OutStreamer->EmitIntValue(RuntimeMD::KeyKernelBegin, 1);
+  emitRuntimeMDStringValue(*OutStreamer, RuntimeMD::KeyKernelName, F.getName());
+
+  const DataLayout &DL = F.getParent()->getDataLayout();
+  for (auto &Arg : F.args()) {
+    unsigned I = Arg.getArgNo();
+    Type *T = Arg.getType();
+    auto TypeName = dyn_cast<MDString>(F.getMetadata(
+        "kernel_arg_type")->getOperand(I))->getString();
+    auto BaseTypeName = cast<MDString>(F.getMetadata(
+        "kernel_arg_base_type")->getOperand(I))->getString();
+    StringRef ArgName;
+    if (auto ArgNameMD = F.getMetadata("kernel_arg_name"))
+      ArgName = cast<MDString>(ArgNameMD->getOperand(I))->getString();
+    auto TypeQual = cast<MDString>(F.getMetadata(
+        "kernel_arg_type_qual")->getOperand(I))->getString();
+    auto AccQual = cast<MDString>(F.getMetadata(
+        "kernel_arg_access_qual")->getOperand(I))->getString();
+    RuntimeMD::KernelArg::Kind Kind;
+    if (TypeQual.find("pipe") != StringRef::npos)
+      Kind = RuntimeMD::KernelArg::Pipe;
+    else Kind = StringSwitch<RuntimeMD::KernelArg::Kind>(BaseTypeName)
+      .Case("sampler_t", RuntimeMD::KernelArg::Sampler)
+      .Case("queue_t",   RuntimeMD::KernelArg::Queue)
+      .Cases("image1d_t", "image1d_array_t", "image1d_buffer_t",
+             "image2d_t" , "image2d_array_t",  RuntimeMD::KernelArg::Image)
+      .Cases("image2d_depth_t", "image2d_array_depth_t",
+             "image2d_msaa_t", "image2d_array_msaa_t",
+             "image2d_msaa_depth_t",  RuntimeMD::KernelArg::Image)
+      .Cases("image2d_array_msaa_depth_t", "image3d_t",
+             RuntimeMD::KernelArg::Image)
+      .Default(isa<PointerType>(T) ?
+                   (T->getPointerAddressSpace() == AMDGPUAS::LOCAL_ADDRESS ?
+                   RuntimeMD::KernelArg::DynamicSharedPointer :
+                   RuntimeMD::KernelArg::GlobalBuffer) :
+                   RuntimeMD::KernelArg::ByValue);
+    emitRuntimeMetadataForKernelArg(DL, *OutStreamer, T,
+        Kind, BaseTypeName, TypeName, ArgName, TypeQual, AccQual);
+  }
+
+  // Emit hidden kernel arguments for OpenCL kernels.
+  if (F.getParent()->getNamedMetadata("opencl.ocl.version")) {
+    auto Int64T = Type::getInt64Ty(F.getContext());
+    emitRuntimeMetadataForKernelArg(DL, *OutStreamer, Int64T,
+                                    RuntimeMD::KernelArg::HiddenGlobalOffsetX);
+    emitRuntimeMetadataForKernelArg(DL, *OutStreamer, Int64T,
+                                    RuntimeMD::KernelArg::HiddenGlobalOffsetY);
+    emitRuntimeMetadataForKernelArg(DL, *OutStreamer, Int64T,
+                                    RuntimeMD::KernelArg::HiddenGlobalOffsetZ);
+    if (auto MD = F.getParent()->getNamedMetadata("llvm.printf.fmts")) {
+      auto Int8PtrT = Type::getInt8PtrTy(F.getContext(),
+          RuntimeMD::KernelArg::Global);
+      emitRuntimeMetadataForKernelArg(DL, *OutStreamer, Int8PtrT,
+                                      RuntimeMD::KernelArg::HiddenPrintfBuffer);
+    }
   }
 
   // Emit KeyReqdWorkGroupSize, KeyWorkGroupSizeHint, and KeyVecTypeHint.
   if (auto RWGS = F.getMetadata("reqd_work_group_size")) {
     emitRuntimeMDThreeIntValues(*OutStreamer, RuntimeMD::KeyReqdWorkGroupSize,
                                 RWGS, 4);
   }
 

llvm/trunk/lib/Target/AMDGPU/AMDGPURuntimeMetadata.h

enum Key {
     KeyKernelEnd                = 5, // End of kernel-level stream
     KeyKernelName               = 6, // Kernel name
     KeyArgBegin                 = 7, // Beginning of kernel-arg-level stream
     KeyArgEnd                   = 8, // End of kernel-arg-level stream
     KeyArgSize                  = 9, // Kernel arg size
     KeyArgAlign                 = 10, // Kernel arg alignment
     KeyArgTypeName              = 11, // Kernel type name
     KeyArgName                  = 12, // Kernel name
-    KeyArgTypeKind              = 13, // Kernel argument type kind
+    KeyArgKind                  = 13, // Kernel argument kind
     KeyArgValueType             = 14, // Kernel argument value type
     KeyArgAddrQual              = 15, // Kernel argument address qualifier
     KeyArgAccQual               = 16, // Kernel argument access qualifier
     KeyArgIsConst               = 17, // Kernel argument is const qualified
     KeyArgIsRestrict            = 18, // Kernel argument is restrict qualified
     KeyArgIsVolatile            = 19, // Kernel argument is volatile qualified
     KeyArgIsPipe                = 20, // Kernel argument is pipe qualified
     KeyReqdWorkGroupSize        = 21, // Required work group size
     KeyWorkGroupSizeHint        = 22, // Work group size hint
     KeyVecTypeHint              = 23, // Vector type hint
     KeyKernelIndex              = 24, // Kernel index for device enqueue
-    KeySGPRs                    = 25, // Number of SGPRs
-    KeyVGPRs                    = 26, // Number of VGPRs
-    KeyMinWavesPerSIMD          = 27, // Minimum number of waves per SIMD
-    KeyMaxWavesPerSIMD          = 28, // Maximum number of waves per SIMD
-    KeyFlatWorkGroupSizeLimits  = 29, // Flat work group size limits
-    KeyMaxWorkGroupSize         = 30, // Maximum work group size
-    KeyNoPartialWorkGroups      = 31, // No partial work groups
+    KeyMinWavesPerSIMD          = 25, // Minimum number of waves per SIMD
+    KeyMaxWavesPerSIMD          = 26, // Maximum number of waves per SIMD
+    KeyFlatWorkGroupSizeLimits  = 27, // Flat work group size limits
+    KeyMaxWorkGroupSize         = 28, // Maximum work group size
+    KeyNoPartialWorkGroups      = 29, // No partial work groups
+    KeyPrintfInfo               = 30, // Prinf function call information
+    KeyArgActualAcc             = 31, // The actual kernel argument access qualifier
     KeyArgPointeeAlign          = 32, // Alignment of pointee type
   };
 
   enum Language : uint8_t {
     OpenCL_C      = 0,
     HCC           = 1,
     OpenMP        = 2,
     OpenCL_CPP    = 3,
 };
 
   enum LanguageVersion : uint16_t {
     V100          = 100,
     V110          = 110,
     V120          = 120,
     V200          = 200,
     V210          = 210,
   };
 
   namespace KernelArg {
-    enum TypeKind : uint8_t {
-      Value     = 0,
-      Pointer   = 1,
-      Image     = 2,
-      Sampler   = 3,
-      Queue     = 4,
+    enum Kind : uint8_t {
+      ByValue                 = 0,
+      GlobalBuffer            = 1,
+      DynamicSharedPointer    = 2,
+      Sampler                 = 3,
+      Image                   = 4,
+      Pipe                    = 5,
+      Queue                   = 6,
+      HiddenGlobalOffsetX     = 7,
+      HiddenGlobalOffsetY     = 8,
+      HiddenGlobalOffsetZ     = 9,
+      HiddenNone              = 10,
+      HiddenPrintfBuffer      = 11,
+      HiddenDefaultQueue      = 12,
+      HiddenCompletionAction  = 13,
     };
 
     enum ValueType : uint16_t {
       Struct  = 0,
       I8      = 1,
       U8      = 2,
       I16     = 3,
       U16     = 4,
enum AccessQualifer : uint8_t {
       ReadWrite  = 3,
     };
 
     enum AddressSpaceQualifer : uint8_t {
       Private    = 0,
       Global     = 1,
       Constant   = 2,
       Local      = 3,
+      Generic    = 4,
+      Region     = 5,
     };
   } // namespace KernelArg
 } // namespace RuntimeMD
 } // namespace AMDGPU
 
 #endif // LLVM_LIB_TARGET_AMDGPU_AMDGPURUNTIMEMETADATA_H

llvm/trunk/test/CodeGen/AMDGPU/runtime-metadata.ll

 
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .short  256
 ; CHECK-NEXT: .byte 2
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 3
 ; CHECK-NEXT: .short  200
+; CHECK-NEXT: .byte 30
+; CHECK-NEXT: .long 10
+; CHECK-NEXT: .ascii  "1:1:4:%d\\n"
+; CHECK-NEXT: .byte 30
+; CHECK-NEXT: .long 10
+; CHECK-NEXT: .ascii  "2:1:8:%g\\n"
 
 ; CHECK-LABEL:{{^}}test_char:
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 9
 ; CHECK-NEXT: .ascii  "test_char"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 1
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 1
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .ascii  "char"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  1
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_char(i8 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !9 !kernel_arg_base_type !9 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_ushort2:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .ascii  "ushort2"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  4
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_ushort2(<2 x i16> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !10 !kernel_arg_base_type !10 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_int3:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .ascii  "int3"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_int3(<3 x i32> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !11 !kernel_arg_base_type !11 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_ulong4:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .ascii  "ulong4"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  10
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_ulong4(<4 x i64> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !12 !kernel_arg_base_type !12 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_half8:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .ascii  "half8"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  5
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_half8(<8 x half> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !13 !kernel_arg_base_type !13 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_float16:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .ascii  "float16"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  8
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_float16(<16 x float> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !14 !kernel_arg_base_type !14 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_double16:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .ascii  "double16"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  11
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_double16(<16 x double> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !15 !kernel_arg_base_type !15 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_pointer:
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 12
 ; CHECK-NEXT: .ascii  "test_pointer"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
-; CHECK-NEXT: .byte 32
-; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_pointer(i32 addrspace(1)* %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !16 !kernel_arg_base_type !16 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_image:
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 10
 ; CHECK-NEXT: .ascii  "test_image"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 9
 ; CHECK-NEXT: .ascii  "image2d_t"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 2
+; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_image(%opencl.image2d_t addrspace(1)* %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !17 !kernel_arg_base_type !17 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_sampler:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .ascii  "sampler_t"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 3
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_sampler(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !18 !kernel_arg_base_type !18 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_queue:
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 10
 ; CHECK-NEXT: .ascii  "test_queue"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 7
 ; CHECK-NEXT: .ascii  "queue_t"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 4
+; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_queue(%opencl.queue_t addrspace(1)* %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !19 !kernel_arg_base_type !19 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_struct:
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 11
 ; CHECK-NEXT: .ascii  "test_struct"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
-; CHECK-NEXT: .byte 32
-; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .ascii  "struct A"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_struct(%struct.A* byval %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !20 !kernel_arg_base_type !20 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_i128:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .ascii  "i128"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_i128(i128 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !21 !kernel_arg_base_type !21 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_multi_arg:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .ascii  "char3"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  1
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_multi_arg(i32 %a, <2 x i16> %b, <3 x i8> %c) !kernel_arg_addr_space !22 !kernel_arg_access_qual !23 !kernel_arg_type !24 !kernel_arg_base_type !24 !kernel_arg_type_qual !25 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_addr_space:
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 15
 ; CHECK-NEXT: .ascii  "test_addr_space"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
-; CHECK-NEXT: .byte 32
-; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
-; CHECK-NEXT: .byte 32
-; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 2
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 32
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 2
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 3
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_addr_space(i32 addrspace(1)* %g, i32 addrspace(2)* %c, i32 addrspace(3)* %l) !kernel_arg_addr_space !50 !kernel_arg_access_qual !23 !kernel_arg_type !51 !kernel_arg_base_type !51 !kernel_arg_type_qual !25 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_type_qual:
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 14
 ; CHECK-NEXT: .ascii  "test_type_qual"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
-; CHECK-NEXT: .byte 32
-; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 19
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
-; CHECK-NEXT: .byte 32
-; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 17
 ; CHECK-NEXT: .byte 18
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "int *"
 ; CHECK-NEXT: .byte 20
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 5
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_type_qual(i32 addrspace(1)* %a, i32 addrspace(1)* %b, %opencl.pipe_t addrspace(1)* %c) !kernel_arg_addr_space !22 !kernel_arg_access_qual !23 !kernel_arg_type !51 !kernel_arg_base_type !51 !kernel_arg_type_qual !70 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_access_qual:
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 16
 ; CHECK-NEXT: .ascii  "test_access_qual"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 9
 ; CHECK-NEXT: .ascii  "image1d_t"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 2
+; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 9
 ; CHECK-NEXT: .ascii  "image2d_t"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 2
+; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 2
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 9
 ; CHECK-NEXT: .ascii  "image3d_t"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 2
+; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 3
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_access_qual(%opencl.image1d_t addrspace(1)* %ro, %opencl.image2d_t addrspace(1)* %wo, %opencl.image3d_t addrspace(1)* %rw) !kernel_arg_addr_space !60 !kernel_arg_access_qual !61 !kernel_arg_type !62 !kernel_arg_base_type !62 !kernel_arg_type_qual !25 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_vec_type_hint_half:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .ascii  "int"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 23
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .ascii  "half"
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_vec_type_hint_half(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !26 {
   ret void
 }

 ; CHECK-NEXT: .ascii  "int"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 23
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "float"
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_vec_type_hint_float(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !27 {
   ret void
 }

 ; CHECK-NEXT: .ascii  "int"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 23
 ; CHECK-NEXT: .long 6
 ; CHECK-NEXT: .ascii  "double"
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_vec_type_hint_double(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !28 {
   ret void
 }

 ; CHECK-NEXT: .ascii  "int"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 23
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .ascii  "char"
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_vec_type_hint_char(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !29 {
   ret void
 }

 ; CHECK-NEXT: .ascii  "int"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 23
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "short"
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_vec_type_hint_short(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !30 {
   ret void
 }

 ; CHECK-NEXT: .ascii  "int"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 23
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .ascii  "long"
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_vec_type_hint_long(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !31 {
   ret void
 }

 ; CHECK-NEXT: .ascii  "int"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 23
 ; CHECK-NEXT: .long 7
 ; CHECK-NEXT: .ascii  "unknown"
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_vec_type_hint_unknown(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !32 {
   ret void
 }

 ; CHECK-NEXT: .ascii  "int"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 21
 ; CHECK-NEXT: .long 1
 ; CHECK-NEXT: .long 2
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 23
 ; CHECK-NEXT: .long 3
 ; CHECK-NEXT: .ascii  "int"
 ; CHECK-NEXT: .byte 5

 ; CHECK-NEXT: .ascii  "int"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 22
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .long 16
 ; CHECK-NEXT: .long 32
 ; CHECK-NEXT: .byte 23
 ; CHECK-NEXT: .long 5
 ; CHECK-NEXT: .ascii  "uint4"
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_wgs_hint_vec_type_hint(i32 %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3 !kernel_arg_base_type !3 !kernel_arg_type_qual !4 !vec_type_hint !7 !work_group_size_hint !8 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_arg_ptr_to_ptr:
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 19
 ; CHECK-NEXT: .ascii  "test_arg_ptr_to_ptr"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
-; CHECK-NEXT: .byte 32
-; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 6
 ; CHECK-NEXT: .ascii  "int **"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_arg_ptr_to_ptr(i32 * addrspace(1)* %a) !kernel_arg_addr_space !81 !kernel_arg_access_qual !2 !kernel_arg_type !80 !kernel_arg_base_type !80 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_arg_struct_contains_ptr:
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 28
 ; CHECK-NEXT: .ascii  "test_arg_struct_contains_ptr"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
-; CHECK-NEXT: .byte 32
-; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .ascii  "struct B"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_arg_struct_contains_ptr(%struct.B * byval %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !82 !kernel_arg_base_type !82 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_arg_vector_of_ptr:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .ascii  "global int* __attribute__((ext_vector_type(2)))"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  6
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_arg_vector_of_ptr(<2 x i32 addrspace(1)*> %a) !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !83 !kernel_arg_base_type !83 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_arg_unknown_builtin_type:
 ; CHECK: .section        .AMDGPU.runtime_metadata

 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  0
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
+
 define amdgpu_kernel void @test_arg_unknown_builtin_type(%opencl.clk_event_t addrspace(1)* %a) !kernel_arg_addr_space !81 !kernel_arg_access_qual !2 !kernel_arg_type !84 !kernel_arg_base_type !84 !kernel_arg_type_qual !4 {
   ret void
 }
 
 ; CHECK-LABEL:{{^}}test_pointee_align:
 ; CHECK: .section        .AMDGPU.runtime_metadata
 ; CHECK-NEXT: .byte 4
 ; CHECK-NEXT: .byte 6
 ; CHECK-NEXT: .long 18
 ; CHECK-NEXT: .ascii  "test_pointee_align"
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 8
-; CHECK-NEXT: .byte 32
-; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 6
 ; CHECK-NEXT: .ascii  "long *"
 ; CHECK-NEXT: .byte 13
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  9
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 1
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 32
 ; CHECK-NEXT: .long 1
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 6
 ; CHECK-NEXT: .ascii  "char *"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 2
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  1
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 3
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 32
 ; CHECK-NEXT: .long 2
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 7
 ; CHECK-NEXT: .ascii  "char2 *"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 2
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  1
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 3
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 32
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 7
 ; CHECK-NEXT: .ascii  "char3 *"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 2
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  1
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 3
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 32
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 7
 ; CHECK-NEXT: .ascii  "char4 *"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 2
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  1
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 3
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 32
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 7
 ; CHECK-NEXT: .ascii  "char8 *"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 2
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  1
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 3
 ; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 7
 ; CHECK-NEXT: .byte 9
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 10
 ; CHECK-NEXT: .long 4
 ; CHECK-NEXT: .byte 32
 ; CHECK-NEXT: .long 16
 ; CHECK-NEXT: .byte 11
 ; CHECK-NEXT: .long 8
 ; CHECK-NEXT: .ascii  "char16 *"
 ; CHECK-NEXT: .byte 13
-; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 2
 ; CHECK-NEXT: .byte 14
 ; CHECK-NEXT: .short  1
 ; CHECK-NEXT: .byte 16
 ; CHECK-NEXT: .byte 0
 ; CHECK-NEXT: .byte 15
 ; CHECK-NEXT: .byte 3
 ; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  9
+; CHECK-NEXT: .byte 8
+; CHECK-NEXT: .byte 7
+; CHECK-NEXT: .byte 9
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 10
+; CHECK-NEXT: .long 8
+; CHECK-NEXT: .byte 13
+; CHECK-NEXT: .byte 11
+; CHECK-NEXT: .byte 14
+; CHECK-NEXT: .short  1
+; CHECK-NEXT: .byte 15
+; CHECK-NEXT: .byte 1
+; CHECK-NEXT: .byte 8
 ; CHECK-NEXT: .byte 5
 
 define amdgpu_kernel void @test_pointee_align(i64 addrspace(1)* %a, i8 addrspace(3)* %b, <2 x i8> addrspace(3)* %c, <3 x i8> addrspace(3)* %d, <4 x i8> addrspace(3)* %e, <8 x i8> addrspace(3)* %f, <16 x i8> addrspace(3)* %g) !kernel_arg_addr_space !91 !kernel_arg_access_qual !92 !kernel_arg_type !93 !kernel_arg_base_type !93 !kernel_arg_type_qual !94 {
   ret void
 }
 
+!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}

 !83 = !{!"global int* __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 *", !"char *", !"char2 *", !"char3 *", !"char4 *", !"char8 *", !"char16 *"}
 !94 = !{!"", !"", !"", !"", !"", !"", !""}
+!100 = !{!"1:1:4:%d\5Cn"}
+!101 = !{!"2:1:8:%g\5Cn"}