AMDGPU/Metadata: Always report a fixed number of hidden arguments
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.
Differential Revision: https://reviews.llvm.org/D45129
llvm-svn: 329341
diff --git a/llvm/test/CodeGen/AMDGPU/hsa-metadata-hidden-args.ll b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hidden-args.ll
new file mode 100644
index 0000000..f0c6e60
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/hsa-metadata-hidden-args.ll
@@ -0,0 +1,70 @@
+; 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}