[clang] [Clang][OpenCL][AMDGPU] Allow a kernel to call another kernel (PR #115821)

[Matt Arsenault via cfe-commits]

================
@@ -299,11 +196,243 @@ Mat64X64 __attribute__((noinline)) foo_large(Mat32X32 in) {
 // X86-NEXT:    call void @llvm.memcpy.p1.p0.i32(ptr addrspace(1) align 4 [[ARRAYIDX]], ptr align 4 [[TMP]], i32 16384, i1 false)
 // X86-NEXT:    ret void
 //
+//
+// X86-LABEL: define void @FuncOneMember(
+// X86-SAME: ptr noundef byval([[STRUCT_STRUCTONEMEMBER:%.*]]) align 4 [[TMP0:%.*]]) #[[ATTR0]] {
+// X86-NEXT:  [[ENTRY:.*:]]
+// X86-NEXT:    [[U:%.*]] = alloca [[STRUCT_STRUCTONEMEMBER]], align 8
+// X86-NEXT:    [[DOTCOMPOUNDLITERAL:%.*]] = alloca <2 x i32>, align 8
+// X86-NEXT:    call void @llvm.memcpy.p0.p0.i32(ptr align 8 [[U]], ptr align 4 [[TMP0]], i32 8, i1 false)
+// X86-NEXT:    store <2 x i32> zeroinitializer, ptr [[DOTCOMPOUNDLITERAL]], align 8
+// X86-NEXT:    [[TMP1:%.*]] = load <2 x i32>, ptr [[DOTCOMPOUNDLITERAL]], align 8
+// X86-NEXT:    [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_STRUCTONEMEMBER]], ptr [[U]], i32 0, i32 0
+// X86-NEXT:    store <2 x i32> [[TMP1]], ptr [[X]], align 8
+// X86-NEXT:    ret void
+//
+//
+// X86-LABEL: define void @FuncOneLargeMember(
+// X86-SAME: ptr noundef byval([[STRUCT_LARGESTRUCTONEMEMBER:%.*]]) align 4 [[TMP0:%.*]]) #[[ATTR0]] {
+// X86-NEXT:  [[ENTRY:.*:]]
+// X86-NEXT:    [[U:%.*]] = alloca [[STRUCT_LARGESTRUCTONEMEMBER]], align 8
+// X86-NEXT:    [[DOTCOMPOUNDLITERAL:%.*]] = alloca <2 x i32>, align 8
+// X86-NEXT:    call void @llvm.memcpy.p0.p0.i32(ptr align 8 [[U]], ptr align 4 [[TMP0]], i32 800, i1 false)
+// X86-NEXT:    store <2 x i32> zeroinitializer, ptr [[DOTCOMPOUNDLITERAL]], align 8
+// X86-NEXT:    [[TMP1:%.*]] = load <2 x i32>, ptr [[DOTCOMPOUNDLITERAL]], align 8
+// X86-NEXT:    [[X:%.*]] = getelementptr inbounds nuw [[STRUCT_LARGESTRUCTONEMEMBER]], ptr [[U]], i32 0, i32 0
+// X86-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [100 x <2 x i32>], ptr [[X]], i32 0, i32 0
+// X86-NEXT:    store <2 x i32> [[TMP1]], ptr [[ARRAYIDX]], align 8
+// X86-NEXT:    ret void
+//
+//
+// X86-LABEL: define spir_kernel void @test_indirect_arg_local(
+// X86-SAME: ) #[[ATTR1]] !kernel_arg_addr_space [[META9:![0-9]+]] !kernel_arg_access_qual [[META9]] !kernel_arg_type [[META9]] !kernel_arg_base_type [[META9]] !kernel_arg_type_qual [[META9]] {
+// X86-NEXT:  [[ENTRY:.*:]]
+// X86-NEXT:    call void @__clang_ocl_kern_imp_test_indirect_arg_local() #[[ATTR3]]
+// X86-NEXT:    ret void
+//
+//
+// X86-LABEL: define void @__clang_ocl_kern_imp_test_indirect_arg_local(
+// X86-SAME: ) #[[ATTR0]] !kernel_arg_addr_space [[META9]] !kernel_arg_access_qual [[META9]] !kernel_arg_type [[META9]] !kernel_arg_base_type [[META9]] !kernel_arg_type_qual [[META9]] {
+// X86-NEXT:  [[ENTRY:.*:]]
+// X86-NEXT:    [[BYVAL_TEMP:%.*]] = alloca [[STRUCT_LARGESTRUCTONEMEMBER:%.*]], align 4
+// X86-NEXT:    call void @llvm.memcpy.p0.p3.i32(ptr align 4 [[BYVAL_TEMP]], ptr addrspace(3) align 8 @test_indirect_arg_local.l_s, i32 800, i1 false)
+// X86-NEXT:    call void @FuncOneLargeMember(ptr noundef byval([[STRUCT_LARGESTRUCTONEMEMBER]]) align 4 [[BYVAL_TEMP]]) #[[ATTR3]]
+// X86-NEXT:    ret void
+//
+//
+// X86-LABEL: define void @test_indirect_arg_private(
+// X86-SAME: ) #[[ATTR0]] {
+// X86-NEXT:  [[ENTRY:.*:]]
+// X86-NEXT:    [[P_S:%.*]] = alloca [[STRUCT_LARGESTRUCTONEMEMBER:%.*]], align 8
+// X86-NEXT:    call void @FuncOneLargeMember(ptr noundef byval([[STRUCT_LARGESTRUCTONEMEMBER]]) align 4 [[P_S]]) #[[ATTR3]]
+// X86-NEXT:    ret void
+//
+//
+// X86-LABEL: define spir_kernel void @KernelOneMember(
+// X86-SAME: ptr noundef byval([[STRUCT_STRUCTONEMEMBER:%.*]]) align 8 [[U:%.*]]) #[[ATTR1]] !kernel_arg_addr_space [[META10:![0-9]+]] !kernel_arg_access_qual [[META11:![0-9]+]] !kernel_arg_type [[META12:![0-9]+]] !kernel_arg_base_type [[META12]] !kernel_arg_type_qual [[META13:![0-9]+]] {
+// X86-NEXT:  [[ENTRY:.*:]]
+// X86-NEXT:    call void @__clang_ocl_kern_imp_KernelOneMember(ptr noundef byval([[STRUCT_STRUCTONEMEMBER]]) align 4 [[U]]) #[[ATTR3]]
+// X86-NEXT:    ret void
+//
+//
+// X86-LABEL: define void @__clang_ocl_kern_imp_KernelOneMember(
+// X86-SAME: ptr noundef byval([[STRUCT_STRUCTONEMEMBER:%.*]]) align 4 [[TMP0:%.*]]) #[[ATTR0]] !kernel_arg_addr_space [[META10]] !kernel_arg_access_qual [[META11]] !kernel_arg_type [[META12]] !kernel_arg_base_type [[META12]] !kernel_arg_type_qual [[META13]] {
+// X86-NEXT:  [[ENTRY:.*:]]
+// X86-NEXT:    [[U:%.*]] = alloca [[STRUCT_STRUCTONEMEMBER]], align 8
+// X86-NEXT:    call void @llvm.memcpy.p0.p0.i32(ptr align 8 [[U]], ptr align 4 [[TMP0]], i32 8, i1 false)
+// X86-NEXT:    call void @FuncOneMember(ptr noundef byval([[STRUCT_STRUCTONEMEMBER]]) align 4 [[U]]) #[[ATTR3]]
+// X86-NEXT:    ret void
+//
+//
+// X86-LABEL: define spir_kernel void @KernelOneMemberSpir(
+// X86-SAME: ptr addrspace(1) noundef align 8 [[U:%.*]]) #[[ATTR1]] !kernel_arg_addr_space [[META14:![0-9]+]] !kernel_arg_access_qual [[META11]] !kernel_arg_type [[META15:![0-9]+]] !kernel_arg_base_type [[META15]] !kernel_arg_type_qual [[META13]] {
+// X86-NEXT:  [[ENTRY:.*:]]
+// X86-NEXT:    [[U_ADDR:%.*]] = alloca ptr addrspace(1), align 4
+// X86-NEXT:    store ptr addrspace(1) [[U]], ptr [[U_ADDR]], align 4
+// X86-NEXT:    [[TMP0:%.*]] = load ptr addrspace(1), ptr [[U_ADDR]], align 4
+// X86-NEXT:    call void @__clang_ocl_kern_imp_KernelOneMemberSpir(ptr addrspace(1) noundef align 8 [[TMP0]]) #[[ATTR3]]
+// X86-NEXT:    ret void
+//
+//
+// X86-LABEL: define void @__clang_ocl_kern_imp_KernelOneMemberSpir(
+// X86-SAME: ptr addrspace(1) noundef align 8 [[U:%.*]]) #[[ATTR0]] !kernel_arg_addr_space [[META14]] !kernel_arg_access_qual [[META11]] !kernel_arg_type [[META15]] !kernel_arg_base_type [[META15]] !kernel_arg_type_qual [[META13]] {
+// X86-NEXT:  [[ENTRY:.*:]]
+// X86-NEXT:    [[U_ADDR:%.*]] = alloca ptr addrspace(1), align 4
+// X86-NEXT:    [[BYVAL_TEMP:%.*]] = alloca [[STRUCT_STRUCTONEMEMBER:%.*]], align 4
+// X86-NEXT:    store ptr addrspace(1) [[U]], ptr [[U_ADDR]], align 4
+// X86-NEXT:    [[TMP0:%.*]] = load ptr addrspace(1), ptr [[U_ADDR]], align 4
+// X86-NEXT:    call void @llvm.memcpy.p0.p1.i32(ptr align 4 [[BYVAL_TEMP]], ptr addrspace(1) align 8 [[TMP0]], i32 8, i1 false)
+// X86-NEXT:    call void @FuncOneMember(ptr noundef byval([[STRUCT_STRUCTONEMEMBER]]) align 4 [[BYVAL_TEMP]]) #[[ATTR3]]
+// X86-NEXT:    ret void
+//
+//
+// X86-LABEL: define spir_kernel void @KernelLargeOneMember(
----------------
arsenm wrote:

It's super annoying that if you use include generated funcs all the checks are separated from the original function in the file 

https://github.com/llvm/llvm-project/pull/115821