AMDGPU/Metadata: Always report a fixed number of hidden arguments

[kzhuravl]

Summary

Currently it is 6. If the "feature" was not used, report dummy hidden argument. Otherwise it does not match the kernarg size reported in the kernel header.

[t-tye]

LGTM

llvm/trunk/lib/Target/AMDGPU/MCTargetDesc/AMDGPUHSAMetadataStreamer.cpp

void MetadataStreamer::emitKernelArgs(const Function &Func) {
   auto Int64Ty = Type::getInt64Ty(Func.getContext());
 
   emitKernelArg(DL, Int64Ty, ValueKind::HiddenGlobalOffsetX);
   emitKernelArg(DL, Int64Ty, ValueKind::HiddenGlobalOffsetY);
   emitKernelArg(DL, Int64Ty, ValueKind::HiddenGlobalOffsetZ);
 
   auto Int8PtrTy = Type::getInt8PtrTy(Func.getContext(),
                                       AMDGPUASI.GLOBAL_ADDRESS);
-  auto CallsPrintf = Func.getParent()->getNamedMetadata("llvm.printf.fmts");
-  if (CallsPrintf)
+
+  // Emit "printf buffer" argument if printf is used, otherwise emit dummy
+  // "none" argument.
+  if (Func.getParent()->getNamedMetadata("llvm.printf.fmts"))
     emitKernelArg(DL, Int8PtrTy, ValueKind::HiddenPrintfBuffer);
-  if (Func.hasFnAttribute("calls-enqueue-kernel")) {
-    if (!CallsPrintf) {
-      // Emit a dummy argument so that the remaining hidden arguments
-      // have a fixed position relative to the first hidden argument.
-      // This is to facilitate library code to access hidden arguments.
-      emitKernelArg(DL, Int8PtrTy, ValueKind::HiddenNone);
-    }
+  else
+
+  // Emit "default queue" and "completion action" arguments if enqueue kernel is
+  // used, otherwise emit dummy "none" arguments.
+  if (Func.hasFnAttribute("calls-enqueue-kernel")) {
     emitKernelArg(DL, Int8PtrTy, ValueKind::HiddenDefaultQueue);
     emitKernelArg(DL, Int8PtrTy, ValueKind::HiddenCompletionAction);
+  } else {
+    emitKernelArg(DL, Int8PtrTy, ValueKind::HiddenNone);
+    emitKernelArg(DL, Int8PtrTy, ValueKind::HiddenNone);
   }
 }
 
 void MetadataStreamer::emitKernelArg(const Argument &Arg) {
   auto Func = Arg.getParent();
   auto ArgNo = Arg.getArgNo();
   const MDNode *Node;
 

llvm/trunk/test/CodeGen/AMDGPU/hsa-metadata-enqueu-kernel.ll

 ; CHECK-NEXT:     - Size:          8
 ; CHECK-NEXT:       Align:         8
 ; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetY
 ; CHECK-NEXT:       ValueType:     I64
 ; CHECK-NEXT:     - Size:          8
 ; CHECK-NEXT:       Align:         8
 ; CHECK-NEXT:       ValueKind:     HiddenGlobalOffsetZ
 ; CHECK-NEXT:       ValueType:     I64
-; CHECK-NOT:        ValueKind:     HiddenNone
 ; CHECK-NOT:        ValueKind:     HiddenDefaultQueue
 ; CHECK-NOT:        ValueKind:     HiddenCompletionAction
 define amdgpu_kernel void @test_non_enqueue_kernel_caller(i8 %a)
     !kernel_arg_addr_space !1 !kernel_arg_access_qual !2 !kernel_arg_type !3
     !kernel_arg_base_type !3 !kernel_arg_type_qual !4 {
   ret void
 }
 

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

+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX700 --check-prefix=NOTES %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX803 --check-prefix=NOTES %s
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -filetype=obj -o - < %s | llvm-readobj -elf-output-style=GNU -notes | FileCheck --check-prefix=CHECK --check-prefix=GFX900 --check-prefix=NOTES %s
+
+; CHECK: ---
+; CHECK:  Version: [ 1, 0 ]
+; CHECK:  Kernels:
+
+; CHECK:      - Name:       test
+; CHECK:        SymbolName: 'test@kd'
+; CHECK:        Args:
+; CHECK-NEXT:     - Name:            r
+; CHECK-NEXT:       Size:            8
+; CHECK-NEXT:       Align:           8
+; CHECK-NEXT:       ValueKind:       GlobalBuffer
+; CHECK-NEXT:       ValueType:       F16
+; CHECK-NEXT:       AddrSpaceQual:   Global
+; CHECK-NEXT:     - Name:            a
+; CHECK-NEXT:       Size:            8
+; CHECK-NEXT:       Align:           8
+; CHECK-NEXT:       ValueKind:       GlobalBuffer
+; CHECK-NEXT:       ValueType:       F16
+; CHECK-NEXT:       AddrSpaceQual:   Global
+; CHECK-NEXT:     - Name:            b
+; CHECK-NEXT:       Size:            8
+; CHECK-NEXT:       Align:           8
+; CHECK-NEXT:       ValueKind:       GlobalBuffer
+; CHECK-NEXT:       ValueType:       F16
+; CHECK-NEXT:       AddrSpaceQual:   Global
+; CHECK-NEXT:     - Size:            8
+; CHECK-NEXT:       Align:           8
+; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetX
+; CHECK-NEXT:       ValueType:       I64
+; CHECK-NEXT:     - Size:            8
+; CHECK-NEXT:       Align:           8
+; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetY
+; CHECK-NEXT:       ValueType:       I64
+; CHECK-NEXT:     - Size:            8
+; CHECK-NEXT:       Align:           8
+; CHECK-NEXT:       ValueKind:       HiddenGlobalOffsetZ
+; CHECK-NEXT:       ValueType:       I64
+; CHECK-NEXT:     - Size:            8
+; CHECK-NEXT:       Align:           8
+; CHECK-NEXT:       ValueKind:       HiddenNone
+; CHECK-NEXT:       ValueType:       I8
+; CHECK-NEXT:       AddrSpaceQual:   Global
+; CHECK-NEXT:     - Size:            8
+; CHECK-NEXT:       Align:           8
+; CHECK-NEXT:       ValueKind:       HiddenNone
+; CHECK-NEXT:       ValueType:       I8
+; CHECK-NEXT:       AddrSpaceQual:   Global
+; CHECK-NEXT:     - Size:            8
+; CHECK-NEXT:       Align:           8
+; CHECK-NEXT:       ValueKind:       HiddenNone
+; CHECK-NEXT:       ValueType:       I8
+; CHECK-NEXT:       AddrSpaceQual:   Global
+define amdgpu_kernel void @test(
+    half addrspace(1)* %r,
+    half addrspace(1)* %a,
+    half addrspace(1)* %b) {
+entry:
+  %a.val = load half, half addrspace(1)* %a
+  %b.val = load half, half addrspace(1)* %b
+  %r.val = fadd half %a.val, %b.val
+  store half %r.val, half addrspace(1)* %r
+  ret void
+}
+
+!opencl.ocl.version = !{!0}
+!0 = !{i32 2, i32 0}