AMDGPU: Invert handling of enqueued block detection

[arsenm]

Summary

Invert the sense of the attribute and let the attributor figure this
out like everything else. If needed we can have the not-OpenCL
languages set amdgpu-no-default-queue and amdgpu-no-completion-action
up front so they never have to pay the cost.

There are also so many of these now, the offset use API should
probably consider all of them at once. Maybe they should merge into
one attribute with used fields. Having separate functions for each
field in AMDGPUBaseInfo is also not the greatest API (might as well
fix this when the patch to get the object version from the module
lands).

[arsenm]

Don't use the attribute clang emits since that doesn't actually work, and check the underlying accessed fields like every other implicit arg

[arsenm]

47288cc977fa31c44cc92b4e65044a5b75c2597e

llvm/docs/AMDGPUUsage.rst

"amdgpu-no-heap-ptr"                    Similar to amdgpu-no-implicitarg-ptr, except specific to the implicit
                                              kernel argument that holds the pointer to an initialized memory buffer
                                              that conforms to the requirements of the malloc/free device library V1
                                              version implementation. If this attribute is absent, then the
                                              amdgpu-no-implicitarg-ptr is also removed.
 
      "amdgpu-no-multigrid-sync-arg"          Similar to amdgpu-no-implicitarg-ptr, except specific to the implicit
                                              kernel argument that holds the multigrid synchronization pointer. If this
                                              attribute is absent, then the amdgpu-no-implicitarg-ptr is also removed.
+
+     "amdgpu-no-default-queue"               Similar to amdgpu-no-implicitarg-ptr, except specific to the implicit
+                                             kernel argument that holds the default queue pointer. If this
+                                             attribute is absent, then the amdgpu-no-implicitarg-ptr is also removed.
+
+     "amdgpu-no-completion-action"           Similar to amdgpu-no-implicitarg-ptr, except specific to the implicit
+                                             kernel argument that holds the completion action pointer. If this
+                                             attribute is absent, then the amdgpu-no-implicitarg-ptr is also removed.
+
      ======================================= ==========================================================
 
 .. _amdgpu-elf-code-object:
 
 ELF Code Object
 ===============
 
 The AMDGPU backend generates a standard ELF [ELF]_ relocatable code object that

llvm/lib/Target/AMDGPU/AMDGPUAttributes.def

 AMDGPU_ATTRIBUTE(HEAP_PTR, "amdgpu-no-heap-ptr")
 AMDGPU_ATTRIBUTE(WORKGROUP_ID_X, "amdgpu-no-workgroup-id-x")
 AMDGPU_ATTRIBUTE(WORKGROUP_ID_Y, "amdgpu-no-workgroup-id-y")
 AMDGPU_ATTRIBUTE(WORKGROUP_ID_Z, "amdgpu-no-workgroup-id-z")
 AMDGPU_ATTRIBUTE(WORKITEM_ID_X, "amdgpu-no-workitem-id-x")
 AMDGPU_ATTRIBUTE(WORKITEM_ID_Y, "amdgpu-no-workitem-id-y")
 AMDGPU_ATTRIBUTE(WORKITEM_ID_Z, "amdgpu-no-workitem-id-z")
 AMDGPU_ATTRIBUTE(LDS_KERNEL_ID, "amdgpu-no-lds-kernel-id")
+AMDGPU_ATTRIBUTE(DEFAULT_QUEUE, "amdgpu-no-default-queue")
+AMDGPU_ATTRIBUTE(COMPLETION_ACTION, "amdgpu-no-completion-action")
 
 #undef AMDGPU_ATTRIBUTE

llvm/lib/Target/AMDGPU/AMDGPUAttributor.cpp

bool needsQueuePtr(const Constant *C, Function &Fn) {
     return !HasAperture && (Access & ADDR_SPACE_CAST);
   }
 
 private:
   /// Used to determine if the Constant needs the queue pointer.
   DenseMap<const Constant *, uint8_t> ConstantStatus;
 };
 
-struct AAAMDAttributes : public StateWrapper<
-  BitIntegerState<uint16_t, ALL_ARGUMENT_MASK, 0>, AbstractAttribute> {
-  using Base = StateWrapper<BitIntegerState<uint16_t, ALL_ARGUMENT_MASK, 0>,
+struct AAAMDAttributes
+    : public StateWrapper<BitIntegerState<uint32_t, ALL_ARGUMENT_MASK, 0>,
+                          AbstractAttribute> {
+  using Base = StateWrapper<BitIntegerState<uint32_t, ALL_ARGUMENT_MASK, 0>,
                             AbstractAttribute>;
 
   AAAMDAttributes(const IRPosition &IRP, Attributor &A) : Base(IRP) {}
 
   /// Create an abstract attribute view for the position \p IRP.
   static AAAMDAttributes &createForPosition(const IRPosition &IRP,
                                             Attributor &A);
 
if (isAssumed(QUEUE_PTR) && funcRetrievesQueuePtr(A)) {
       assert(!isAssumed(IMPLICIT_ARG_PTR) && "queue_ptr needs implicitarg_ptr");
       removeAssumedBits(QUEUE_PTR);
     }
 
     if (isAssumed(LDS_KERNEL_ID) && funcRetrievesLDSKernelId(A)) {
       removeAssumedBits(LDS_KERNEL_ID);
     }
 
+    if (isAssumed(DEFAULT_QUEUE) && funcRetrievesDefaultQueue(A))
+      removeAssumedBits(DEFAULT_QUEUE);
+
+    if (isAssumed(COMPLETION_ACTION) && funcRetrievesCompletionAction(A))
+      removeAssumedBits(COMPLETION_ACTION);
+
     return getAssumed() != OrigAssumed ? ChangeStatus::CHANGED
                                        : ChangeStatus::UNCHANGED;
   }
 
   ChangeStatus manifest(Attributor &A) override {
     SmallVector<Attribute, 8> AttrList;
     LLVMContext &Ctx = getAssociatedFunction()->getContext();
 
private:
   }
 
   bool funcRetrievesHostcallPtr(Attributor &A) {
     auto Pos = llvm::AMDGPU::getHostcallImplicitArgPosition();
     AA::RangeTy Range(Pos, 8);
     return funcRetrievesImplicitKernelArg(A, Range);
   }
 
+  bool funcRetrievesDefaultQueue(Attributor &A) {
+    auto Pos = llvm::AMDGPU::getDefaultQueueImplicitArgPosition();
+    AA::RangeTy Range(Pos, 8);
+    return funcRetrievesImplicitKernelArg(A, Range);
+  }
+
+  bool funcRetrievesCompletionAction(Attributor &A) {
+    auto Pos = llvm::AMDGPU::getCompletionActionImplicitArgPosition();
+    AA::RangeTy Range(Pos, 8);
+    return funcRetrievesImplicitKernelArg(A, Range);
+  }
+
   bool funcRetrievesHeapPtr(Attributor &A) {
     if (AMDGPU::getAmdhsaCodeObjectVersion() != 5)
       return false;
     AA::RangeTy Range(AMDGPU::ImplicitArg::HEAP_PTR_OFFSET, 8);
     return funcRetrievesImplicitKernelArg(A, Range);
   }
 
   bool funcRetrievesQueuePtr(Attributor &A) {

llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp

if (HiddenArgNumBytes >= 32) {
     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 >= 48) {
-    if (Func.hasFnAttribute("calls-enqueue-kernel")) {
+  if (HiddenArgNumBytes >= 40) {
+    if (!Func.hasFnAttribute("amdgpu-no-default-queue")) {
       emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenDefaultQueue);
-      emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenCompletionAction);
     } else {
       emitKernelArg(DL, Int8PtrTy, Align(8), ValueKind::HiddenNone);
+    }
+  }
+
+  if (HiddenArgNumBytes >= 48) {
+    if (!Func.hasFnAttribute("amdgpu-no-completion-action")) {
+      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 if (!Func.hasFnAttribute("amdgpu-no-hostcall-ptr"))
       emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_hostcall_buffer", Offset,
                     Args);
     else
       emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_none", Offset, Args);
   }
 
   // Emit "default queue" and "completion action" arguments if enqueue kernel is
   // used, otherwise emit dummy "none" arguments.
-  if (HiddenArgNumBytes >= 48) {
-    if (Func.hasFnAttribute("calls-enqueue-kernel")) {
+  if (HiddenArgNumBytes >= 40) {
+    if (!Func.hasFnAttribute("amdgpu-no-default-queue")) {
       emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_default_queue", Offset,
                     Args);
+    } else {
+      emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_none", Offset, Args);
+    }
+  }
+
+  if (HiddenArgNumBytes >= 48) {
+    if (!Func.hasFnAttribute("amdgpu-no-completion-action")) {
       emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_completion_action", Offset,
                     Args);
     } else {
       emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_none", Offset, Args);
-      emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_none", Offset, Args);
     }
   }
 
   // Emit the pointer argument for multi-grid object.
   if (HiddenArgNumBytes >= 56) {
     if (!Func.hasFnAttribute("amdgpu-no-multigrid-sync-arg")) {
       emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_multigrid_sync_arg", Offset,
                     Args);
if (!Func.hasFnAttribute("amdgpu-no-multigrid-sync-arg")) {
     Offset += 8; // Skipped.
   }
 
   if (!Func.hasFnAttribute("amdgpu-no-heap-ptr"))
     emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_heap_v1", Offset, Args);
   else
     Offset += 8; // Skipped.
 
-  if (Func.hasFnAttribute("calls-enqueue-kernel")) {
+  if (!Func.hasFnAttribute("amdgpu-no-default-queue")) {
     emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_default_queue", Offset,
                   Args);
+  } else {
+    Offset += 8; // Skipped.
+  }
+
+  if (!Func.hasFnAttribute("amdgpu-no-completion-action")) {
     emitKernelArg(DL, Int8PtrTy, Align(8), "hidden_completion_action", Offset,
                   Args);
   } else {
-    Offset += 16; // Skipped.
+    Offset += 8; // Skipped.
   }
 
   Offset += 72; // Reserved.
 
   // hidden_private_base and hidden_shared_base are only when the subtarget has
   // ApertureRegs.
   if (!ST.hasApertureRegs()) {
     emitKernelArg(DL, Int32Ty, Align(4), "hidden_private_base", Offset, Args);

llvm/lib/Target/AMDGPU/AMDGPUOpenCLEnqueuedBlockLowering.cpp

 // literal is actually runtime handle and loads the kernel address from it
 // and put it into AQL packet for dispatching.
 //
 // This cannot be done in FE since FE cannot create a unique global variable
 // with external linkage across LLVM modules. The global variable with internal
 // linkage does not work since optimization passes will try to replace loads
 // of the global variable with its initialization value.
 //
-// It also identifies the kernels directly or indirectly enqueues kernels
-// and adds "calls-enqueue-kernel" function attribute to them, which will
-// be used to determine whether to emit runtime metadata for the kernel
-// enqueue related hidden kernel arguments.
-//
 //===----------------------------------------------------------------------===//
 
 #include "AMDGPU.h"
 #include "llvm/ADT/DenseSet.h"
 #include "llvm/ADT/SmallString.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/Mangler.h"

 
 INITIALIZE_PASS(AMDGPUOpenCLEnqueuedBlockLowering, DEBUG_TYPE,
                 "Lower OpenCL enqueued blocks", false, false)
 
 ModulePass* llvm::createAMDGPUOpenCLEnqueuedBlockLoweringPass() {
   return new AMDGPUOpenCLEnqueuedBlockLowering();
 }
 
-/// Collect direct or indirect callers of \p F and save them
-/// to \p Callers.
-static void collectCallers(Function *F, DenseSet<Function *> &Callers) {
-  for (auto *U : F->users()) {
-    if (auto *CI = dyn_cast<CallInst>(&*U)) {
-      auto *Caller = CI->getParent()->getParent();
-      if (Callers.insert(Caller).second)
-        collectCallers(Caller, Callers);
-    }
-  }
-}
-
-/// If \p U is instruction or constant, collect functions which directly or
-/// indirectly use it.
-static void collectFunctionUsers(User *U, DenseSet<Function *> &Funcs) {
-  if (auto *I = dyn_cast<Instruction>(U)) {
-    auto *F = I->getParent()->getParent();
-    if (Funcs.insert(F).second)
-      collectCallers(F, Funcs);
-    return;
-  }
-  if (!isa<Constant>(U))
-    return;
-  for (auto *UU : U->users())
-    collectFunctionUsers(&*UU, Funcs);
-}
-
 bool AMDGPUOpenCLEnqueuedBlockLowering::runOnModule(Module &M) {
-  DenseSet<Function *> Callers;
   auto &C = M.getContext();
   bool Changed = false;
   for (auto &F : M.functions()) {
     if (F.hasFnAttribute("enqueued-block")) {
       if (!F.hasName()) {
         SmallString<64> Name;
         Mangler::getNameWithPrefix(Name, "__amdgpu_enqueued_kernel",
                                    M.getDataLayout());
         F.setName(Name);
       }
       LLVM_DEBUG(dbgs() << "found enqueued kernel: " << F.getName() << '\n');
       auto RuntimeHandle = (F.getName() + ".runtime_handle").str();
       auto T = ArrayType::get(Type::getInt64Ty(C), 2);
       auto *GV = new GlobalVariable(
           M, T,
           /*isConstant=*/false, GlobalValue::ExternalLinkage,
           /*Initializer=*/Constant::getNullValue(T), RuntimeHandle,
           /*InsertBefore=*/nullptr, GlobalValue::NotThreadLocal,
           AMDGPUAS::GLOBAL_ADDRESS,
           /*isExternallyInitialized=*/false);
       LLVM_DEBUG(dbgs() << "runtime handle created: " << *GV << '\n');
 
-      for (auto *U : F.users()) {
-        auto *UU = &*U;
-
-        if (isa<Constant>(UU))
-          collectFunctionUsers(UU, Callers);
-      }
-
       F.replaceAllUsesWith(ConstantExpr::getAddrSpaceCast(GV, F.getType()));
       F.addFnAttr("runtime-handle", RuntimeHandle);
       F.setLinkage(GlobalValue::ExternalLinkage);
       Changed = true;
     }
   }
 
-  for (auto *F : Callers) {
-    if (F->getCallingConv() != CallingConv::AMDGPU_KERNEL)
-      continue;
-    F->addFnAttr("calls-enqueue-kernel");
-    LLVM_DEBUG(dbgs() << "mark enqueue_kernel caller:" << F->getName() << '\n');
-  }
   return Changed;
 }

llvm/lib/Target/AMDGPU/SIDefines.h

 } // namespace VOP3PEncoding
 
 namespace ImplicitArg {
 // Implicit kernel argument offset for code object version 5.
 enum Offset_COV5 : unsigned {
   HOSTCALL_PTR_OFFSET = 80,
   MULTIGRID_SYNC_ARG_OFFSET = 88,
   HEAP_PTR_OFFSET = 96,
+
+  DEFAULT_QUEUE_OFFSET = 104,
+  COMPLETION_ACTION_OFFSET = 112,
+
   PRIVATE_BASE_OFFSET = 192,
   SHARED_BASE_OFFSET = 196,
   QUEUE_PTR_OFFSET = 200,
 };
 
 } // namespace ImplicitArg
 } // namespace AMDGPU
 

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

 bool isHsaAbiVersion3AndAbove(const MCSubtargetInfo *STI);
 
 /// \returns The offset of the multigrid_sync_arg argument from implicitarg_ptr
 unsigned getMultigridSyncArgImplicitArgPosition();
 
 /// \returns The offset of the hostcall pointer argument from implicitarg_ptr
 unsigned getHostcallImplicitArgPosition();
 
+unsigned getDefaultQueueImplicitArgPosition();
+unsigned getCompletionActionImplicitArgPosition();
+
 /// \returns Code object version.
 unsigned getAmdhsaCodeObjectVersion();
 
 struct GcnBufferFormatInfo {
   unsigned Format;
   unsigned BitsPerComp;
   unsigned NumComponents;
   unsigned NumFormat;

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

unsigned getHostcallImplicitArgPosition() {
   case 5:
     return AMDGPU::ImplicitArg::HOSTCALL_PTR_OFFSET;
   default:
     llvm_unreachable("Unexpected code object version");
     return 0;
   }
 }
 
+unsigned getDefaultQueueImplicitArgPosition() {
+  switch (AmdhsaCodeObjectVersion) {
+  case 2:
+  case 3:
+  case 4:
+    return 32;
+  case 5:
+  default:
+    return AMDGPU::ImplicitArg::DEFAULT_QUEUE_OFFSET;
+  }
+}
+
+unsigned getCompletionActionImplicitArgPosition() {
+  switch (AmdhsaCodeObjectVersion) {
+  case 2:
+  case 3:
+  case 4:
+    return 40;
+  case 5:
+  default:
+    return AMDGPU::ImplicitArg::COMPLETION_ACTION_OFFSET;
+  }
+}
+
 #define GET_MIMGBaseOpcodesTable_IMPL
 #define GET_MIMGDimInfoTable_IMPL
 #define GET_MIMGInfoTable_IMPL
 #define GET_MIMGLZMappingTable_IMPL
 #define GET_MIMGMIPMappingTable_IMPL
 #define GET_MIMGBiasMappingTable_IMPL
 #define GET_MIMGOffsetMappingTable_IMPL
 #define GET_MIMGG16MappingTable_IMPL

llvm/test/CodeGen/AMDGPU/addrspacecast-constantexpr.ll

 
 attributes #0 = { argmemonly nounwind }
 attributes #1 = { nounwind }
 ;.
 ; AKF_HSA: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
 ; AKF_HSA: attributes #[[ATTR1]] = { nounwind }
 ;.
 ; ATTRIBUTOR_HSA: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
-; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
 ;.

llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa-call.ll

 define void @func_call_asm() #3 {
 ; AKF_HSA-LABEL: define {{[^@]+}}@func_call_asm
 ; AKF_HSA-SAME: () #[[ATTR3]] {
 ; AKF_HSA-NEXT:    call void asm sideeffect "", ""() #[[ATTR3]]
 ; AKF_HSA-NEXT:    ret void
 ;
 ; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@func_call_asm
 ; ATTRIBUTOR_HSA-SAME: () #[[ATTR16]] {
-; ATTRIBUTOR_HSA-NEXT:    call void asm sideeffect "", ""() #[[ATTR20:[0-9]+]]
+; ATTRIBUTOR_HSA-NEXT:    call void asm sideeffect "", ""() #[[ATTR24:[0-9]+]]
 ; ATTRIBUTOR_HSA-NEXT:    ret void
 ;
   call void asm sideeffect "", ""() #3
   ret void
 }
 
 define amdgpu_kernel void @kern_call_external() #3 {
 ; AKF_HSA-LABEL: define {{[^@]+}}@kern_call_external

 ; ATTRIBUTOR_HSA-SAME: () #[[ATTR15]] {
 ; ATTRIBUTOR_HSA-NEXT:    call void @extern_func_sanitize_address()
 ; ATTRIBUTOR_HSA-NEXT:    ret void
 ;
   call void @extern_func_sanitize_address()
   ret void
 }
 
+declare void @enqueue_block_decl() #6
+
+define internal void @enqueue_block_def() #6 {
+; AKF_HSA-LABEL: define {{[^@]+}}@enqueue_block_def
+; AKF_HSA-SAME: () #[[ATTR7:[0-9]+]] {
+; AKF_HSA-NEXT:    ret void
+;
+; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@enqueue_block_def
+; ATTRIBUTOR_HSA-SAME: () #[[ATTR21:[0-9]+]] {
+; ATTRIBUTOR_HSA-NEXT:    ret void
+;
+  ret void
+}
+
+define amdgpu_kernel void @kern_call_enqueued_block_decl() {
+; AKF_HSA-LABEL: define {{[^@]+}}@kern_call_enqueued_block_decl
+; AKF_HSA-SAME: () #[[ATTR8:[0-9]+]] {
+; AKF_HSA-NEXT:    call void @enqueue_block_decl()
+; AKF_HSA-NEXT:    ret void
+;
+; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@kern_call_enqueued_block_decl
+; ATTRIBUTOR_HSA-SAME: () #[[ATTR22:[0-9]+]] {
+; ATTRIBUTOR_HSA-NEXT:    call void @enqueue_block_decl()
+; ATTRIBUTOR_HSA-NEXT:    ret void
+;
+  call void @enqueue_block_decl()
+  ret void
+}
+
+define amdgpu_kernel void @kern_call_enqueued_block_def() {
+; AKF_HSA-LABEL: define {{[^@]+}}@kern_call_enqueued_block_def
+; AKF_HSA-SAME: () #[[ATTR8]] {
+; AKF_HSA-NEXT:    call void @enqueue_block_def()
+; AKF_HSA-NEXT:    ret void
+;
+; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@kern_call_enqueued_block_def
+; ATTRIBUTOR_HSA-SAME: () #[[ATTR23:[0-9]+]] {
+; ATTRIBUTOR_HSA-NEXT:    call void @enqueue_block_def()
+; ATTRIBUTOR_HSA-NEXT:    ret void
+;
+  call void @enqueue_block_def()
+  ret void
+}
+
+define void @unused_enqueue_block() {
+; AKF_HSA-LABEL: define {{[^@]+}}@unused_enqueue_block() {
+; AKF_HSA-NEXT:    ret void
+;
+; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@unused_enqueue_block
+; ATTRIBUTOR_HSA-SAME: () #[[ATTR23]] {
+; ATTRIBUTOR_HSA-NEXT:    ret void
+;
+  ret void
+}
+
+define internal void @known_func() {
+; AKF_HSA-LABEL: define {{[^@]+}}@known_func() {
+; AKF_HSA-NEXT:    ret void
+;
+; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@known_func
+; ATTRIBUTOR_HSA-SAME: () #[[ATTR23]] {
+; ATTRIBUTOR_HSA-NEXT:    ret void
+;
+  ret void
+}
+
+; Should never happen
+define amdgpu_kernel void @kern_callsite_enqueue_block() {
+; AKF_HSA-LABEL: define {{[^@]+}}@kern_callsite_enqueue_block
+; AKF_HSA-SAME: () #[[ATTR8]] {
+; AKF_HSA-NEXT:    call void @known_func() #[[ATTR7]]
+; AKF_HSA-NEXT:    ret void
+;
+; ATTRIBUTOR_HSA-LABEL: define {{[^@]+}}@kern_callsite_enqueue_block
+; ATTRIBUTOR_HSA-SAME: () #[[ATTR23]] {
+; ATTRIBUTOR_HSA-NEXT:    call void @known_func() #[[ATTR25:[0-9]+]]
+; ATTRIBUTOR_HSA-NEXT:    ret void
+;
+  call void @known_func() #6
+  ret void
+}
+
 attributes #0 = { nounwind readnone speculatable }
 attributes #1 = { nounwind "target-cpu"="fiji" }
 attributes #2 = { nounwind "target-cpu"="gfx900" }
 attributes #3 = { nounwind }
 attributes #4 = { nounwind sanitize_address }
 attributes #5 = { nounwind sanitize_address "amdgpu-no-implicitarg-ptr" }
+attributes #6 = { "enqueued-block" }
 
 ;.
 ; AKF_HSA: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
 ; AKF_HSA: attributes #[[ATTR1]] = { nounwind "target-cpu"="fiji" }
 ; AKF_HSA: attributes #[[ATTR2]] = { nounwind "target-cpu"="gfx900" }
 ; AKF_HSA: attributes #[[ATTR3]] = { nounwind }
 ; AKF_HSA: attributes #[[ATTR4]] = { nounwind "amdgpu-calls" }
 ; AKF_HSA: attributes #[[ATTR5]] = { nounwind sanitize_address }
 ; AKF_HSA: attributes #[[ATTR6:[0-9]+]] = { nounwind sanitize_address "amdgpu-no-implicitarg-ptr" }
+; AKF_HSA: attributes #[[ATTR7]] = { "enqueued-block" }
+; AKF_HSA: attributes #[[ATTR8]] = { "amdgpu-calls" }
 ;.
 ; ATTRIBUTOR_HSA: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
-; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR3]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR4]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR5]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR6]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR7]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR8]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR9]] = { nounwind "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR10]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR11]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR12]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx900" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR13]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx900" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR14]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR3]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR4]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR5]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR6]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR7]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR8]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR9]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR10]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR11]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR12]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx900" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR13]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="gfx900" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR14]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "target-cpu"="fiji" "uniform-work-group-size"="false" }
 ; ATTRIBUTOR_HSA: attributes #[[ATTR15]] = { nounwind "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR16]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR17]] = { nounwind sanitize_address "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR18]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR16]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR17]] = { nounwind sanitize_address "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR18]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
 ; ATTRIBUTOR_HSA: attributes #[[ATTR19:[0-9]+]] = { nounwind sanitize_address "amdgpu-no-implicitarg-ptr" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR20]] = { nounwind }
+; ATTRIBUTOR_HSA: attributes #[[ATTR20:[0-9]+]] = { "enqueued-block" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR21]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "enqueued-block" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR22]] = { "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR23]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR24]] = { nounwind }
+; ATTRIBUTOR_HSA: attributes #[[ATTR25]] = { "enqueued-block" }
 ;.

llvm/test/CodeGen/AMDGPU/annotate-kernel-features-hsa.ll

 
 declare i32 @llvm.amdgcn.workitem.id.x() #0
 declare i32 @llvm.amdgcn.workitem.id.y() #0
 declare i32 @llvm.amdgcn.workitem.id.z() #0
 
 declare ptr addrspace(4) @llvm.amdgcn.dispatch.ptr() #0
 declare ptr addrspace(4) @llvm.amdgcn.queue.ptr() #0
 declare ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr() #0
+declare ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr() #0
 
 declare i1 @llvm.amdgcn.is.shared(ptr nocapture) #2
 declare i1 @llvm.amdgcn.is.private(ptr nocapture) #2
 
 define amdgpu_kernel void @use_tgid_x(ptr addrspace(1) %ptr) #1 {
 ; HSA-LABEL: define {{[^@]+}}@use_tgid_x
 ; HSA-SAME: (ptr addrspace(1) [[PTR:%.*]]) #[[ATTR1:[0-9]+]] {
 ; HSA-NEXT:    [[VAL:%.*]] = call i32 @llvm.amdgcn.workgroup.id.x()

 attributes #1 = { nounwind }
 
 ;.
 ; AKF_HSA: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
 ; AKF_HSA: attributes #[[ATTR1]] = { nounwind }
 ; AKF_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-stack-objects" }
 ;.
 ; ATTRIBUTOR_HSA: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
-; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR3]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR4]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR5]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR6]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR7]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR8]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR9]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR10]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_HSA: attributes #[[ATTR11]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR1]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR2]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR3]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR4]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR5]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR6]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR7]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR8]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR9]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR10]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_HSA: attributes #[[ATTR11]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
 ;.

llvm/test/CodeGen/AMDGPU/annotate-kernel-features.ll

 ; NOHSA: attributes #[[ATTR7]] = { nounwind "amdgpu-work-group-id-y" "amdgpu-work-item-id-y" "uniform-work-group-size"="false" }
 ; NOHSA: attributes #[[ATTR8]] = { nounwind "amdgpu-work-item-id-y" "amdgpu-work-item-id-z" "uniform-work-group-size"="false" }
 ; NOHSA: attributes #[[ATTR9]] = { nounwind "amdgpu-work-group-id-y" "amdgpu-work-group-id-z" "amdgpu-work-item-id-y" "amdgpu-work-item-id-z" "uniform-work-group-size"="false" }
 ;.
 ; AKF_CHECK: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
 ; AKF_CHECK: attributes #[[ATTR1]] = { nounwind }
 ;.
 ; ATTRIBUTOR_CHECK: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
-; ATTRIBUTOR_CHECK: attributes #[[ATTR1]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_CHECK: attributes #[[ATTR2]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_CHECK: attributes #[[ATTR3]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_CHECK: attributes #[[ATTR4]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_CHECK: attributes #[[ATTR5]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_CHECK: attributes #[[ATTR6]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_CHECK: attributes #[[ATTR7]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_CHECK: attributes #[[ATTR8]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" }
-; ATTRIBUTOR_CHECK: attributes #[[ATTR9]] = { nounwind "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_CHECK: attributes #[[ATTR1]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_CHECK: attributes #[[ATTR2]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_CHECK: attributes #[[ATTR3]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_CHECK: attributes #[[ATTR4]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_CHECK: attributes #[[ATTR5]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_CHECK: attributes #[[ATTR6]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_CHECK: attributes #[[ATTR7]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_CHECK: attributes #[[ATTR8]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_CHECK: attributes #[[ATTR9]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workitem-id-x" "uniform-work-group-size"="false" }
 ;.

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

 ; CHECK-SAME: () #[[ATTR1]] {
 ; CHECK-NEXT:    call void @direct()
 ; CHECK-NEXT:    ret void
 ;
   call void @direct()
   ret void
 }
 ;.
-; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
 ; CHECK: attributes #[[ATTR1]] = { "uniform-work-group-size"="false" }
 ;.

llvm/test/CodeGen/AMDGPU/duplicate-attribute-indirect.ll

;
   ret void
 }
 
 attributes #0 = { "amdgpu-no-dispatch-id" }
 
 ;.
 ; AKF_GCN: attributes #[[ATTR0]] = { "amdgpu-calls" "amdgpu-no-dispatch-id" "amdgpu-stack-objects" }
 ;.
-; ATTRIBUTOR_GCN: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_GCN: attributes #[[ATTR0]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
 ; ATTRIBUTOR_GCN: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "uniform-work-group-size"="false" }
 ;.

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

 ; CHECK-NEXT:    [[BLOCK_CAPTURED10:%.*]] = getelementptr inbounds <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }>, ptr addrspace(5) [[BLOCK2]], i32 0, i32 4
 ; CHECK-NEXT:    store i64 [[D]], ptr addrspace(5) [[BLOCK_CAPTURED10]], align 8
 ; CHECK-NEXT:    [[INST8:%.*]] = addrspacecast ptr addrspace(5) [[BLOCK2]] to ptr
 ; CHECK-NEXT:    [[INST9:%.*]] = call i32 @__enqueue_kernel_basic(ptr addrspace(1) undef, i32 0, ptr addrspace(5) nonnull byval([[STRUCT_NDRANGE_T]]) [[INST3]], ptr addrspacecast (ptr addrspace(1) @__test_block_invoke_2_kernel.runtime_handle to ptr), ptr nonnull [[INST8]])
 ; CHECK-NEXT:    ret void
 ;
 ;
 ; CHECK-LABEL: define {{[^@]+}}@inlined_caller
-; CHECK-SAME: (ptr addrspace(1) [[A:%.*]], i8 [[B:%.*]], ptr addrspace(1) [[C:%.*]], i64 [[D:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-SAME: (ptr addrspace(1) [[A:%.*]], i8 [[B:%.*]], ptr addrspace(1) [[C:%.*]], i64 [[D:%.*]]) {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[INST:%.*]] = load i64, ptr addrspace(1) @__test_block_invoke_kernel.runtime_handle, align 4
 ; CHECK-NEXT:    store i64 [[INST]], ptr addrspace(1) [[C]], align 4
 ; CHECK-NEXT:    ret void
 ;
 ;
 ; CHECK-LABEL: define {{[^@]+}}@__test_block_invoke_kernel
-; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR1:[0-9]+]] {
+; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[DOTFCA_3_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> [[ARG]], 2
 ; CHECK-NEXT:    [[DOTFCA_4_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> [[ARG]], 3
 ; CHECK-NEXT:    store i8 [[DOTFCA_4_EXTRACT]], ptr addrspace(1) [[DOTFCA_3_EXTRACT]], align 1
 ; CHECK-NEXT:    ret void
 ;
 ;
 ; CHECK-LABEL: define {{[^@]+}}@__test_block_invoke_2_kernel
-; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[ARG:%.*]]) #[[ATTR2:[0-9]+]] {
+; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[ARG:%.*]]) #[[ATTR1:[0-9]+]] {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[DOTFCA_3_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[ARG]], 2
 ; CHECK-NEXT:    [[DOTFCA_4_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[ARG]], 3
 ; CHECK-NEXT:    [[DOTFCA_5_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[ARG]], 4
 ; CHECK-NEXT:    [[DOTFCA_6_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), ptr addrspace(1), i64, i8 }> [[ARG]], 5
 ; CHECK-NEXT:    store i8 [[DOTFCA_6_EXTRACT]], ptr addrspace(1) [[DOTFCA_3_EXTRACT]], align 1
 ; CHECK-NEXT:    store i64 [[DOTFCA_5_EXTRACT]], ptr addrspace(1) [[DOTFCA_4_EXTRACT]], align 8
 ; CHECK-NEXT:    ret void
 ;
 ;
 ; CHECK-LABEL: define {{[^@]+}}@block_has_used_kernel_address
-; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR3:[0-9]+]] {
+; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR2:[0-9]+]] {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[DOTFCA_3_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> [[ARG]], 2
 ; CHECK-NEXT:    [[DOTFCA_4_EXTRACT:%.*]] = extractvalue <{ i32, i32, ptr addrspace(1), i8 }> [[ARG]], 3
 ; CHECK-NEXT:    store i8 [[DOTFCA_4_EXTRACT]], ptr addrspace(1) [[DOTFCA_3_EXTRACT]], align 1
 ; CHECK-NEXT:    ret void
 ;
 ;
 ; CHECK-LABEL: define {{[^@]+}}@user_of_kernel_address
 ; CHECK-SAME: (ptr addrspace(1) [[ARG:%.*]]) {
 ; CHECK-NEXT:    store ptr addrspacecast (ptr addrspace(1) @block_has_used_kernel_address.runtime_handle to ptr), ptr addrspace(1) [[ARG]], align 8
 ; CHECK-NEXT:    ret void
 ;
 ;
 ; CHECK-LABEL: define {{[^@]+}}@__amdgpu_enqueued_kernel
-; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR4:[0-9]+]] {
+; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR3:[0-9]+]] {
 ; CHECK-NEXT:    ret void
 ;
 ;
 ; CHECK-LABEL: define {{[^@]+}}@__amdgpu_enqueued_kernel.1
-; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR5:[0-9]+]] {
+; CHECK-SAME: (<{ i32, i32, ptr addrspace(1), i8 }> [[ARG:%.*]]) #[[ATTR4:[0-9]+]] {
 ; CHECK-NEXT:    ret void
 ;
 ;.
-; CHECK: attributes #[[ATTR0]] = { "calls-enqueue-kernel" }
-; CHECK: attributes #[[ATTR1]] = { "enqueued-block" "runtime-handle"="__test_block_invoke_kernel.runtime_handle" }
-; CHECK: attributes #[[ATTR2]] = { "enqueued-block" "runtime-handle"="__test_block_invoke_2_kernel.runtime_handle" }
-; CHECK: attributes #[[ATTR3]] = { "enqueued-block" "runtime-handle"="block_has_used_kernel_address.runtime_handle" }
-; CHECK: attributes #[[ATTR4]] = { "enqueued-block" "runtime-handle"="__amdgpu_enqueued_kernel.runtime_handle" }
-; CHECK: attributes #[[ATTR5]] = { "enqueued-block" "runtime-handle"="__amdgpu_enqueued_kernel.1.runtime_handle" }
+; CHECK: attributes #[[ATTR0]] = { "enqueued-block" "runtime-handle"="__test_block_invoke_kernel.runtime_handle" }
+; CHECK: attributes #[[ATTR1]] = { "enqueued-block" "runtime-handle"="__test_block_invoke_2_kernel.runtime_handle" }
+; CHECK: attributes #[[ATTR2]] = { "enqueued-block" "runtime-handle"="block_has_used_kernel_address.runtime_handle" }
+; CHECK: attributes #[[ATTR3]] = { "enqueued-block" "runtime-handle"="__amdgpu_enqueued_kernel.runtime_handle" }
+; CHECK: attributes #[[ATTR4]] = { "enqueued-block" "runtime-handle"="__amdgpu_enqueued_kernel.1.runtime_handle" }
 ;.

llvm/test/CodeGen/AMDGPU/hsa-metadata-enqueue-kernel-v3.ll

 ; CHECK:          .name:           test_enqueue_kernel_caller
 ; CHECK:          .symbol:         test_enqueue_kernel_caller.kd
 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
 }
 
+; CHECK:        - .args:
+; CHECK-NEXT:       - .name:           a
+; CHECK-NEXT:         .offset:         0
+; CHECK-NEXT:         .size:           1
+; CHECK-NEXT:         .type_name:      char
+; CHECK-NEXT:         .value_kind:     by_value
+; CHECK-NEXT:       - .offset:         8
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_x
+; CHECK-NEXT:       - .offset:         16
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_y
+; CHECK-NEXT:       - .offset:         24
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_z
+; CHECK-NEXT:       - .offset:         32
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_hostcall_buffer
+; CHECK-NEXT:       - .offset:         40
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_default_queue
+; CHECK-NEXT:       - .offset:         48
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_none
+; CHECK:          .language:       OpenCL C
+; CHECK-NEXT:     .language_version:
+; CHECK-NEXT:       - 2
+; CHECK-NEXT:       - 0
+; CHECK:          .name:           test_no_completion_action
+; CHECK:          .symbol:         test_no_completion_action.kd
+define amdgpu_kernel void @test_no_completion_action(i8 %a) #2
+    !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:        - .args:
+; CHECK-NEXT:       - .name:           a
+; CHECK-NEXT:         .offset:         0
+; CHECK-NEXT:         .size:           1
+; CHECK-NEXT:         .type_name:      char
+; CHECK-NEXT:         .value_kind:     by_value
+; CHECK-NEXT:       - .offset:         8
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_x
+; CHECK-NEXT:       - .offset:         16
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_y
+; CHECK-NEXT:       - .offset:         24
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_global_offset_z
+; CHECK-NEXT:       - .offset:         32
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_hostcall_buffer
+; CHECK-NEXT:       - .offset:         40
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_none
+; CHECK-NEXT:       - .offset:         48
+; CHECK-NEXT:         .size:           8
+; CHECK-NEXT:         .value_kind:     hidden_completion_action
+; CHECK:          .language:       OpenCL C
+; CHECK-NEXT:     .language_version:
+; CHECK-NEXT:       - 2
+; CHECK-NEXT:       - 0
+; CHECK:          .name:           test_no_default_queue
+; CHECK:          .symbol:         test_no_default_queue.kd
+define amdgpu_kernel void @test_no_default_queue(i8 %a) #3
+    !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:  amdhsa.version:
 ; CHECK-NEXT: - 1
 ; CHECK-NEXT: - 0
 ; CHECK-NOT:  amdhsa.printf:
 
-attributes #0 = { optnone noinline "amdgpu-implicitarg-num-bytes"="48" }
-attributes #1 = { optnone noinline "calls-enqueue-kernel" "amdgpu-implicitarg-num-bytes"="48" }
+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" }
+attributes #2 = { optnone noinline "amdgpu-no-completion-action" "amdgpu-implicitarg-num-bytes"="48" }
+attributes #3 = { optnone noinline "amdgpu-no-default-queue" "amdgpu-implicitarg-num-bytes"="48" }
 
 !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-enqueue-kernel.ll

 ; 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-implicitarg-num-bytes"="48" }
-attributes #1 = { optnone noinline "calls-enqueue-kernel" "amdgpu-implicitarg-num-bytes"="48" }
+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" }
 
 !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-v3.ll

 
 ; CHECK:  amdhsa.printf:
 ; CHECK-NEXT: - '1:1:4:%d\n'
 ; CHECK-NEXT: - '2:1:8:%g\n'
 ; CHECK:  amdhsa.version:
 ; CHECK-NEXT: - 1
 ; CHECK-NEXT: - 0
 
-attributes #0 = { optnone noinline "amdgpu-implicitarg-num-bytes"="56" }
-attributes #1 = { optnone noinline "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" }
+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" }
 
 !llvm.printf.fmts = !{!100, !101}
 
 !1 = !{i32 0}
 !2 = !{!"none"}
 !3 = !{!"int"}
 !4 = !{!""}
 !5 = !{i32 undef, i32 1}

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

 ; 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-implicitarg-num-bytes"="56" }
-attributes #1 = { optnone noinline "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" }
+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" }
 
 !llvm.printf.fmts = !{!100, !101}
 
 !1 = !{i32 0}
 !2 = !{!"none"}
 !3 = !{!"int"}
 !4 = !{!""}
 !5 = !{i32 undef, i32 1}

llvm/test/CodeGen/AMDGPU/hsa-metadata-hidden-args-v3.ll

 ; CHECK-NEXT:       - .offset:         40
 ; CHECK-NEXT:         .size:           8
 ; CHECK-NEXT:         .value_kind:     hidden_global_offset_z
 ; CHECK-NEXT:       - .offset:         48
 ; CHECK-NEXT:         .size:           8
 ; CHECK-NEXT:         .value_kind:     hidden_hostcall_buffer
 ; CHECK-NEXT:       - .offset:         56
 ; CHECK-NEXT:         .size:           8
-; CHECK-NEXT:         .value_kind:     hidden_none
+; CHECK-NEXT:         .value_kind:     hidden_default_queue
 ; CHECK-NEXT:       - .offset:         64
 ; CHECK-NEXT:         .size:           8
-; CHECK-NEXT:         .value_kind:     hidden_none
+; CHECK-NEXT:         .value_kind:     hidden_completion_action
 ; CHECK:          .name:           test48
 ; CHECK:          .symbol:         test48.kd
 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

 ; CHECK-NEXT:       - .offset:         40
 ; CHECK-NEXT:         .size:           8
 ; CHECK-NEXT:         .value_kind:     hidden_global_offset_z
 ; CHECK-NEXT:       - .offset:         48
 ; CHECK-NEXT:         .size:           8
 ; CHECK-NEXT:         .value_kind:     hidden_hostcall_buffer
 ; CHECK-NEXT:       - .offset:         56
 ; CHECK-NEXT:         .size:           8
-; CHECK-NEXT:         .value_kind:     hidden_none
+; CHECK-NEXT:         .value_kind:     hidden_default_queue
 ; CHECK-NEXT:       - .offset:         64
 ; CHECK-NEXT:         .size:           8
-; CHECK-NEXT:         .value_kind:     hidden_none
+; CHECK-NEXT:         .value_kind:     hidden_completion_action
 ; CHECK-NEXT:       - .offset:         72
 ; CHECK-NEXT:         .size:           8
 ; CHECK-NEXT:         .value_kind:     hidden_multigrid_sync_arg
 ; CHECK:          .name:           test56
 ; CHECK:          .symbol:         test56.kd
 define amdgpu_kernel void @test56(
     ptr addrspace(1) %r,
     ptr addrspace(1) %a,

llvm/test/CodeGen/AMDGPU/hsa-metadata-hidden-args-v5.ll

entry:
   ret void
 }
 
 !llvm.printf.fmts = !{!1, !2}
 
 !1 = !{!"1:1:4:%d\5Cn"}
 !2 = !{!"2:1:8:%g\5Cn"}
 
-attributes #0 = { optnone noinline "calls-enqueue-kernel" }
+attributes #0 = { optnone noinline }
 

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

 ; 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:       HiddenNone
+; CHECK-NEXT:       ValueKind:       HiddenDefaultQueue
 ; CHECK-NEXT:       AddrSpaceQual:   Global
 ; CHECK-NEXT:     - Size:            8
 ; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenNone
+; CHECK-NEXT:       ValueKind:       HiddenCompletionAction
 ; 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

 ; 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:       HiddenNone
+; CHECK-NEXT:       ValueKind:       HiddenDefaultQueue
 ; CHECK-NEXT:       AddrSpaceQual:   Global
 ; CHECK-NEXT:     - Size:            8
 ; CHECK-NEXT:       Align:           8
-; CHECK-NEXT:       ValueKind:       HiddenNone
+; CHECK-NEXT:       ValueKind:       HiddenCompletionAction
 ; 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,

llvm/test/CodeGen/AMDGPU/implicitarg-offset-attributes.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --check-attributes --check-globals
+; RUN: opt -S -mtriple=amdgcn-unknown-unknown -amdgpu-attributor --amdhsa-code-object-version=4 < %s | FileCheck -check-prefixes=CHECK,V4 %s
+; RUN: opt -S -mtriple=amdgcn-unknown-unknown -amdgpu-attributor --amdhsa-code-object-version=5 < %s | FileCheck -check-prefixes=CHECK,V5 %s
+
+declare ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr() #0
+
+declare i32 @llvm.amdgcn.workgroup.id.x() #0
+declare i32 @llvm.amdgcn.workgroup.id.y() #0
+declare i32 @llvm.amdgcn.workgroup.id.z() #0
+
+declare i32 @llvm.amdgcn.workitem.id.x() #0
+declare i32 @llvm.amdgcn.workitem.id.y() #0
+declare i32 @llvm.amdgcn.workitem.id.z() #0
+declare i32 @llvm.amdgcn.lds.kernel.id() #0
+declare i64 @llvm.amdgcn.dispatch.id() #0
+
+
+declare ptr addrspace(4) @llvm.amdgcn.dispatch.ptr() #0
+declare ptr addrspace(4) @llvm.amdgcn.queue.ptr() #0
+declare ptr addrspace(4) @llvm.amdgcn.kernarg.segment.ptr() #0
+
+; Avoid adding all of these to the output attribute sets
+define void @use_everything_else() {
+; CHECK-LABEL: define {{[^@]+}}@use_everything_else
+; CHECK-SAME: () #[[ATTR1:[0-9]+]] {
+; CHECK-NEXT:    [[VAL0:%.*]] = call i32 @llvm.amdgcn.workitem.id.x()
+; CHECK-NEXT:    [[VAL1:%.*]] = call i32 @llvm.amdgcn.workitem.id.y()
+; CHECK-NEXT:    [[VAL2:%.*]] = call i32 @llvm.amdgcn.workitem.id.z()
+; CHECK-NEXT:    [[VAL3:%.*]] = call i32 @llvm.amdgcn.workgroup.id.x()
+; CHECK-NEXT:    [[VAL4:%.*]] = call i32 @llvm.amdgcn.workgroup.id.y()
+; CHECK-NEXT:    [[VAL5:%.*]] = call i32 @llvm.amdgcn.workgroup.id.z()
+; CHECK-NEXT:    store volatile i32 [[VAL0]], ptr addrspace(1) null, align 4
+; CHECK-NEXT:    store volatile i32 [[VAL1]], ptr addrspace(1) null, align 4
+; CHECK-NEXT:    store volatile i32 [[VAL2]], ptr addrspace(1) null, align 4
+; CHECK-NEXT:    store volatile i32 [[VAL3]], ptr addrspace(1) null, align 4
+; CHECK-NEXT:    store volatile i32 [[VAL4]], ptr addrspace(1) null, align 4
+; CHECK-NEXT:    store volatile i32 [[VAL5]], ptr addrspace(1) null, align 4
+; CHECK-NEXT:    [[DISPATCH_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.dispatch.ptr()
+; CHECK-NEXT:    [[QUEUE_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.queue.ptr()
+; CHECK-NEXT:    [[VAL6:%.*]] = load volatile ptr, ptr addrspace(4) [[DISPATCH_PTR]], align 8
+; CHECK-NEXT:    [[VAL7:%.*]] = load volatile ptr, ptr addrspace(4) [[QUEUE_PTR]], align 8
+; CHECK-NEXT:    [[VAL8:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
+; CHECK-NEXT:    store volatile i32 [[VAL8]], ptr addrspace(1) null, align 4
+; CHECK-NEXT:    [[VAL9:%.*]] = call i64 @llvm.amdgcn.dispatch.id()
+; CHECK-NEXT:    store volatile i64 [[VAL9]], ptr addrspace(1) null, align 4
+; CHECK-NEXT:    ret void
+;
+  %val0 = call i32 @llvm.amdgcn.workitem.id.x()
+  %val1 = call i32 @llvm.amdgcn.workitem.id.y()
+  %val2 = call i32 @llvm.amdgcn.workitem.id.z()
+  %val3 = call i32 @llvm.amdgcn.workgroup.id.x()
+  %val4 = call i32 @llvm.amdgcn.workgroup.id.y()
+  %val5 = call i32 @llvm.amdgcn.workgroup.id.z()
+  store volatile i32 %val0, ptr addrspace(1) null
+  store volatile i32 %val1, ptr addrspace(1) null
+  store volatile i32 %val2, ptr addrspace(1) null
+  store volatile i32 %val3, ptr addrspace(1) null
+  store volatile i32 %val4, ptr addrspace(1) null
+  store volatile i32 %val5, ptr addrspace(1) null
+  %dispatch.ptr = call ptr addrspace(4) @llvm.amdgcn.dispatch.ptr()
+  %queue.ptr = call ptr addrspace(4) @llvm.amdgcn.queue.ptr()
+  %val6 = load volatile ptr, ptr addrspace(4) %dispatch.ptr
+  %val7 = load volatile ptr, ptr addrspace(4) %queue.ptr
+  %val8 = call i32 @llvm.amdgcn.lds.kernel.id()
+  store volatile i32 %val8, ptr addrspace(1) null
+  %val9 = call i64 @llvm.amdgcn.dispatch.id()
+  store volatile i64 %val9, ptr addrspace(1) null
+  ret void
+}
+
+define amdgpu_kernel void @test_default_queue_offset_v4_0(ptr addrspace(1) %kernarg) {
+; V4-LABEL: define {{[^@]+}}@test_default_queue_offset_v4_0
+; V4-SAME: (ptr addrspace(1) [[KERNARG:%.*]]) #[[ATTR2:[0-9]+]] {
+; V4-NEXT:    call void @use_everything_else()
+; V4-NEXT:    [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; V4-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 32
+; V4-NEXT:    [[LOAD:%.*]] = load ptr, ptr addrspace(4) [[GEP]], align 8
+; V4-NEXT:    store ptr [[LOAD]], ptr addrspace(1) [[KERNARG]], align 8
+; V4-NEXT:    ret void
+;
+; V5-LABEL: define {{[^@]+}}@test_default_queue_offset_v4_0
+; V5-SAME: (ptr addrspace(1) [[KERNARG:%.*]]) #[[ATTR1]] {
+; V5-NEXT:    call void @use_everything_else()
+; V5-NEXT:    [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; V5-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 32
+; V5-NEXT:    [[LOAD:%.*]] = load ptr, ptr addrspace(4) [[GEP]], align 8
+; V5-NEXT:    store ptr [[LOAD]], ptr addrspace(1) [[KERNARG]], align 8
+; V5-NEXT:    ret void
+;
+  call void @use_everything_else()
+  %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+  %gep = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 32
+  %load = load ptr, ptr addrspace(4) %gep
+  store ptr %load, ptr addrspace(1) %kernarg
+  ret void
+}
+
+define amdgpu_kernel void @test_default_queue_offset_v5_0(ptr addrspace(1) %kernarg) {
+; V4-LABEL: define {{[^@]+}}@test_default_queue_offset_v5_0
+; V4-SAME: (ptr addrspace(1) [[KERNARG:%.*]]) #[[ATTR3:[0-9]+]] {
+; V4-NEXT:    call void @use_everything_else()
+; V4-NEXT:    [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; V4-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 104
+; V4-NEXT:    [[LOAD:%.*]] = load ptr, ptr addrspace(4) [[GEP]], align 8
+; V4-NEXT:    store ptr [[LOAD]], ptr addrspace(1) [[KERNARG]], align 8
+; V4-NEXT:    ret void
+;
+; V5-LABEL: define {{[^@]+}}@test_default_queue_offset_v5_0
+; V5-SAME: (ptr addrspace(1) [[KERNARG:%.*]]) #[[ATTR2:[0-9]+]] {
+; V5-NEXT:    call void @use_everything_else()
+; V5-NEXT:    [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; V5-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 104
+; V5-NEXT:    [[LOAD:%.*]] = load ptr, ptr addrspace(4) [[GEP]], align 8
+; V5-NEXT:    store ptr [[LOAD]], ptr addrspace(1) [[KERNARG]], align 8
+; V5-NEXT:    ret void
+;
+  call void @use_everything_else()
+  %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+  %gep = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 104
+  %load = load ptr, ptr addrspace(4) %gep
+  store ptr %load, ptr addrspace(1) %kernarg
+  ret void
+}
+
+define amdgpu_kernel void @test_completion_action_offset_v4_0(ptr addrspace(1) %kernarg) {
+; V4-LABEL: define {{[^@]+}}@test_completion_action_offset_v4_0
+; V4-SAME: (ptr addrspace(1) [[KERNARG:%.*]]) #[[ATTR4:[0-9]+]] {
+; V4-NEXT:    call void @use_everything_else()
+; V4-NEXT:    [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; V4-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 40
+; V4-NEXT:    [[LOAD:%.*]] = load ptr, ptr addrspace(4) [[GEP]], align 8
+; V4-NEXT:    store ptr [[LOAD]], ptr addrspace(1) [[KERNARG]], align 8
+; V4-NEXT:    ret void
+;
+; V5-LABEL: define {{[^@]+}}@test_completion_action_offset_v4_0
+; V5-SAME: (ptr addrspace(1) [[KERNARG:%.*]]) #[[ATTR1]] {
+; V5-NEXT:    call void @use_everything_else()
+; V5-NEXT:    [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; V5-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 40
+; V5-NEXT:    [[LOAD:%.*]] = load ptr, ptr addrspace(4) [[GEP]], align 8
+; V5-NEXT:    store ptr [[LOAD]], ptr addrspace(1) [[KERNARG]], align 8
+; V5-NEXT:    ret void
+;
+  call void @use_everything_else()
+  %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+  %gep = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 40
+  %load = load ptr, ptr addrspace(4) %gep
+  store ptr %load, ptr addrspace(1) %kernarg
+  ret void
+}
+
+define amdgpu_kernel void @test_completion_action_offset_v5_0(ptr addrspace(1) %kernarg) {
+; CHECK-LABEL: define {{[^@]+}}@test_completion_action_offset_v5_0
+; CHECK-SAME: (ptr addrspace(1) [[KERNARG:%.*]]) #[[ATTR3:[0-9]+]] {
+; CHECK-NEXT:    call void @use_everything_else()
+; CHECK-NEXT:    [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; CHECK-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 112
+; CHECK-NEXT:    [[LOAD:%.*]] = load ptr, ptr addrspace(4) [[GEP]], align 8
+; CHECK-NEXT:    store ptr [[LOAD]], ptr addrspace(1) [[KERNARG]], align 8
+; CHECK-NEXT:    ret void
+;
+  call void @use_everything_else()
+  %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+  %gep = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 112
+  %load = load ptr, ptr addrspace(4) %gep
+  store ptr %load, ptr addrspace(1) %kernarg
+  ret void
+}
+
+define amdgpu_kernel void @test_default_queue_completion_action_offset_v3_0(ptr addrspace(1) %kernarg) {
+; V4-LABEL: define {{[^@]+}}@test_default_queue_completion_action_offset_v3_0
+; V4-SAME: (ptr addrspace(1) [[KERNARG:%.*]]) #[[ATTR5:[0-9]+]] {
+; V4-NEXT:    call void @use_everything_else()
+; V4-NEXT:    [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; V4-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 32
+; V4-NEXT:    [[LOAD:%.*]] = load <2 x ptr>, ptr addrspace(4) [[GEP]], align 16
+; V4-NEXT:    store <2 x ptr> [[LOAD]], ptr addrspace(1) [[KERNARG]], align 16
+; V4-NEXT:    ret void
+;
+; V5-LABEL: define {{[^@]+}}@test_default_queue_completion_action_offset_v3_0
+; V5-SAME: (ptr addrspace(1) [[KERNARG:%.*]]) #[[ATTR1]] {
+; V5-NEXT:    call void @use_everything_else()
+; V5-NEXT:    [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; V5-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 32
+; V5-NEXT:    [[LOAD:%.*]] = load <2 x ptr>, ptr addrspace(4) [[GEP]], align 16
+; V5-NEXT:    store <2 x ptr> [[LOAD]], ptr addrspace(1) [[KERNARG]], align 16
+; V5-NEXT:    ret void
+;
+  call void @use_everything_else()
+  %implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+  %gep = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 32
+  %load = load <2 x ptr>, ptr addrspace(4) %gep
+  store <2 x ptr> %load, ptr addrspace(1) %kernarg
+  ret void
+}
+
+define amdgpu_kernel void @test_default_queue_completion_action_offset_v5_0(ptr addrspace(1) %kernarg) {
+; V4-LABEL: define {{[^@]+}}@test_default_queue_completion_action_offset_v5_0
+; V4-SAME: (ptr addrspace(1) [[KERNARG:%.*]]) #[[ATTR3]] {
+; V4-NEXT:    call void @use_everything_else()
+; V4-NEXT:    [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; V4-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 104
+; V4-NEXT:    [[LOAD:%.*]] = load <2 x ptr>, ptr addrspace(4) [[GEP]], align 16
+; V4-NEXT:    store <2 x ptr> [[LOAD]], ptr addrspace(1) [[KERNARG]], align 16
+; V4-NEXT:    ret void
+;
+; V5-LABEL: define {{[^@]+}}@test_default_queue_completion_action_offset_v5_0
+; V5-SAME: (ptr addrspace(1) [[KERNARG:%.*]]) #[[ATTR4:[0-9]+]] {
+; V5-NEXT:    call void @use_everything_else()
+; V5-NEXT:    [[IMPLICITARG_PTR:%.*]] = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+; V5-NEXT:    [[GEP:%.*]] = getelementptr inbounds i8, ptr addrspace(4) [[IMPLICITARG_PTR]], i64 104
+; V5-NEXT:    [[LOAD:%.*]] = load <2 x ptr>, ptr addrspace(4) [[GEP]], align 16
+; V5-NEXT:    store <2 x ptr> [[LOAD]], ptr addrspace(1) [[KERNARG]], align 16
+; V5-NEXT:    ret void
+;
+
+  call void @use_everything_else()%implicitarg.ptr = call ptr addrspace(4) @llvm.amdgcn.implicitarg.ptr()
+  %gep = getelementptr inbounds i8, ptr addrspace(4) %implicitarg.ptr, i64 104
+  %load = load <2 x ptr>, ptr addrspace(4) %gep
+  store <2 x ptr> %load, ptr addrspace(1) %kernarg
+  ret void
+}
+
+
+attributes #0 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
+
+;.
+; V4: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
+; V4: attributes #[[ATTR1]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-multigrid-sync-arg" "uniform-work-group-size"="false" }
+; V4: attributes #[[ATTR2]] = { "amdgpu-no-completion-action" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-multigrid-sync-arg" "uniform-work-group-size"="false" }
+; V4: attributes #[[ATTR3]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-multigrid-sync-arg" "uniform-work-group-size"="false" }
+; V4: attributes #[[ATTR4]] = { "amdgpu-no-default-queue" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-multigrid-sync-arg" "uniform-work-group-size"="false" }
+; V4: attributes #[[ATTR5]] = { "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-multigrid-sync-arg" "uniform-work-group-size"="false" }
+;.
+; V5: attributes #[[ATTR0:[0-9]+]] = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
+; V5: attributes #[[ATTR1]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-multigrid-sync-arg" "uniform-work-group-size"="false" }
+; V5: attributes #[[ATTR2]] = { "amdgpu-no-completion-action" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-multigrid-sync-arg" "uniform-work-group-size"="false" }
+; V5: attributes #[[ATTR3]] = { "amdgpu-no-default-queue" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-multigrid-sync-arg" "uniform-work-group-size"="false" }
+; V5: attributes #[[ATTR4]] = { "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-multigrid-sync-arg" "uniform-work-group-size"="false" }
+;.

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

 attributes #1 = { "amdgpu-flat-work-group-size"="64,128" }
 attributes #2 = { "amdgpu-flat-work-group-size"="64,64" }
 attributes #3 = { "amdgpu-flat-work-group-size"="128,256" }
 attributes #4 = { "amdgpu-flat-work-group-size"="512,1024" }
 attributes #5 = { "amdgpu-flat-work-group-size"="128,512" }
 attributes #6 = { "amdgpu-flat-work-group-size"="512,512" }
 attributes #7 = { "amdgpu-flat-work-group-size"="64,256" }
 ;.
-; CHECK: attributes #[[ATTR0]] = { "amdgpu-flat-work-group-size"="1,256" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR1]] = { "amdgpu-flat-work-group-size"="64,128" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR2]] = { "amdgpu-flat-work-group-size"="128,512" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR3]] = { "amdgpu-flat-work-group-size"="64,64" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR4]] = { "amdgpu-flat-work-group-size"="128,128" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR5]] = { "amdgpu-flat-work-group-size"="512,512" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR6]] = { "amdgpu-flat-work-group-size"="64,256" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR7]] = { "amdgpu-flat-work-group-size"="128,256" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR8]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR0]] = { "amdgpu-flat-work-group-size"="1,256" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR1]] = { "amdgpu-flat-work-group-size"="64,128" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR2]] = { "amdgpu-flat-work-group-size"="128,512" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR3]] = { "amdgpu-flat-work-group-size"="64,64" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR4]] = { "amdgpu-flat-work-group-size"="128,128" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR5]] = { "amdgpu-flat-work-group-size"="512,512" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR6]] = { "amdgpu-flat-work-group-size"="64,256" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR7]] = { "amdgpu-flat-work-group-size"="128,256" "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR8]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
 ;.

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

; GFX9-NEXT:    s_endpgm
   %fp = load ptr, ptr %fptr.cast
   call void %fp()
   ret void
 }
 
 ;.
 ; AKF_GCN: attributes #[[ATTR0]] = { "amdgpu-calls" "amdgpu-stack-objects" }
 ;.
-; ATTRIBUTOR_GCN: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; ATTRIBUTOR_GCN: attributes #[[ATTR0]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
 ; ATTRIBUTOR_GCN: attributes #[[ATTR1]] = { "uniform-work-group-size"="false" }
 ;.

llvm/test/CodeGen/AMDGPU/uniform-work-group-attribute-missing.ll

 ; CHECK-NEXT:    ret void
 ;
   call void @foo()
   ret void
 }
 
 attributes #0 = { "uniform-work-group-size"="true" }
 ;.
-; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
 ;.

llvm/test/CodeGen/AMDGPU/uniform-work-group-multistep.ll

 ; CHECK-NEXT:    ret void
 ;
   call void @internal2()
   ret void
 }
 
 attributes #0 = { "uniform-work-group-size"="true" }
 ;.
-; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" }
+; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" }
 ;.

llvm/test/CodeGen/AMDGPU/uniform-work-group-nested-function-calls.ll

 ; CHECK-NEXT:    ret void
 ;
   call void @func2()
   ret void
 }
 
 attributes #2 = { "uniform-work-group-size"="true" }
 ;.
-; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" }
+; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" }
 ;.

llvm/test/CodeGen/AMDGPU/uniform-work-group-prevent-attribute-propagation.ll

 ; CHECK-NEXT:    ret void
 ;
   call void @func()
   ret void
 }
 
 attributes #1 = { "uniform-work-group-size"="true" }
 ;.
-; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" }
+; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" }
 ;.

llvm/test/CodeGen/AMDGPU/uniform-work-group-propagate-attribute.ll

 ;
   call void @weak_func()
   ret void
 }
 
 attributes #0 = { nounwind }
 attributes #1 = { "uniform-work-group-size"="false" }
 attributes #2 = { "uniform-work-group-size"="true" }
+;.
+; CHECK: attributes #[[ATTR0]] = { nounwind "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR1]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR2]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" }
+;.

llvm/test/CodeGen/AMDGPU/uniform-work-group-recursion-test.ll

;
   store i32 %r2, ptr addrspace(1) %m
   ret void
 }
 
 ; nounwind and readnone are added to match attributor results.
 attributes #0 = { nounwind readnone }
 attributes #1 = { "uniform-work-group-size"="true" }
 ;.
-; CHECK: attributes #[[ATTR0]] = { nounwind memory(none) "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
-; CHECK: attributes #[[ATTR1]] = { nounwind memory(none) "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" }
-; CHECK: attributes #[[ATTR2]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" }
+; CHECK: attributes #[[ATTR0]] = { nounwind memory(none) "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR1]] = { nounwind memory(none) "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" }
+; CHECK: attributes #[[ATTR2]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="true" }
 ;.

llvm/test/CodeGen/AMDGPU/uniform-work-group-test.ll

 ;
   call void @func2()
   call void @func3()
   ret void
 }
 
 attributes #0 = { "uniform-work-group-size"="false" }
 ;.
-; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
+; CHECK: attributes #[[ATTR0]] = { "amdgpu-no-completion-action" "amdgpu-no-default-queue" "amdgpu-no-dispatch-id" "amdgpu-no-dispatch-ptr" "amdgpu-no-heap-ptr" "amdgpu-no-hostcall-ptr" "amdgpu-no-implicitarg-ptr" "amdgpu-no-lds-kernel-id" "amdgpu-no-multigrid-sync-arg" "amdgpu-no-queue-ptr" "amdgpu-no-workgroup-id-x" "amdgpu-no-workgroup-id-y" "amdgpu-no-workgroup-id-z" "amdgpu-no-workitem-id-x" "amdgpu-no-workitem-id-y" "amdgpu-no-workitem-id-z" "uniform-work-group-size"="false" }
 ;.