diff options
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/enqueue-kernel.ll')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/enqueue-kernel.ll | 21 |
1 files changed, 17 insertions, 4 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/enqueue-kernel.ll b/llvm/test/CodeGen/AMDGPU/enqueue-kernel.ll index 67864ed90da..1e4b2ac8093 100644 --- a/llvm/test/CodeGen/AMDGPU/enqueue-kernel.ll +++ b/llvm/test/CodeGen/AMDGPU/enqueue-kernel.ll @@ -1,9 +1,9 @@ ; RUN: opt -data-layout=A5 -amdgpu-lower-enqueued-block -S < %s | FileCheck %s -; CHECK: @__test_block_invoke_kernel.runtime_handle = external addrspace(1) externally_initialized constant i8 addrspace(1)* -; CHECK: @__test_block_invoke_2_kernel.runtime_handle = external addrspace(1) externally_initialized constant i8 addrspace(1)* -; CHECK: @__amdgpu_enqueued_kernel.runtime_handle = external addrspace(1) externally_initialized constant i8 addrspace(1)* -; CHECK: @__amdgpu_enqueued_kernel.1.runtime_handle = external addrspace(1) externally_initialized constant i8 addrspace(1)* +; CHECK: @__test_block_invoke_kernel.runtime_handle = addrspace(1) global i8 addrspace(1)* null +; CHECK: @__test_block_invoke_2_kernel.runtime_handle = addrspace(1) global i8 addrspace(1)* null +; CHECK: @__amdgpu_enqueued_kernel.runtime_handle = addrspace(1) global i8 addrspace(1)* null +; CHECK: @__amdgpu_enqueued_kernel.1.runtime_handle = addrspace(1) global i8 addrspace(1)* null %struct.ndrange_t = type { i32 } %opencl.queue_t = type opaque @@ -80,6 +80,19 @@ entry: ret void } +; __enqueue_kernel* functions may get inlined +; CHECK-LABEL: define amdgpu_kernel void @inlined_caller +; CHECK-SAME: #[[AT_CALLER]] +; CHECK-NOT: @__test_block_invoke_kernel +; CHECK: load i64, i64 addrspace(1)* bitcast (i8 addrspace(1)* addrspace(1)* @__test_block_invoke_kernel.runtime_handle to i64 addrspace(1)*) +define amdgpu_kernel void @inlined_caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr + !kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 { +entry: + %tmp = load i64, i64 addrspace(1)* addrspacecast (i64* bitcast (void (<{ i32, i32, i8 addrspace(1)*, i8 }>)* @__test_block_invoke_kernel to i64*) to i64 addrspace(1)*) + store i64 %tmp, i64 addrspace(1)* %c + ret void +} + ; CHECK-LABEL: define dso_local amdgpu_kernel void @__test_block_invoke_kernel ; CHECK-SAME: #[[AT1:[0-9]+]] define internal amdgpu_kernel void @__test_block_invoke_kernel(<{ i32, i32, i8 addrspace(1)*, i8 }> %arg) #0 |
