aboutsummaryrefslogtreecommitdiffstats
path: root/test/CodeGen/AArch64/tailcall-explicit-sret.ll
blob: 4d80f2ac5c12133b918eda803f05e95e5206f6d5 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
; RUN: llc < %s -mtriple arm64-apple-darwin -aarch64-load-store-opt=false -asm-verbose=false | FileCheck %s
; Disable the load/store optimizer to avoid having LDP/STPs and simplify checks.

target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"

; Check that we don't try to tail-call with a non-forwarded sret parameter.
declare void @test_explicit_sret(i1024* sret) #0

; This is the only OK case, where we forward the explicit sret pointer.

; CHECK-LABEL: _test_tailcall_explicit_sret:
; CHECK-NEXT: b _test_explicit_sret
define void @test_tailcall_explicit_sret(i1024* sret %arg) #0 {
  tail call void @test_explicit_sret(i1024* %arg)
  ret void
}

; CHECK-LABEL: _test_call_explicit_sret:
; CHECK-NOT: mov  x8
; CHECK: bl _test_explicit_sret
; CHECK: ret
define void @test_call_explicit_sret(i1024* sret %arg) #0 {
  call void @test_explicit_sret(i1024* %arg)
  ret void
}

; CHECK-LABEL: _test_tailcall_explicit_sret_alloca_unused:
; CHECK: mov  x8, sp
; CHECK-NEXT: bl _test_explicit_sret
; CHECK: ret
define void @test_tailcall_explicit_sret_alloca_unused() #0 {
  %l = alloca i1024, align 8
  tail call void @test_explicit_sret(i1024* %l)
  ret void
}

; CHECK-LABEL: _test_tailcall_explicit_sret_alloca_dummyusers:
; CHECK: ldr [[PTRLOAD1:x[0-9]+]], [x0]
; CHECK: str [[PTRLOAD1]], [sp]
; CHECK: mov  x8, sp
; CHECK-NEXT: bl _test_explicit_sret
; CHECK: ret
define void @test_tailcall_explicit_sret_alloca_dummyusers(i1024* %ptr) #0 {
  %l = alloca i1024, align 8
  %r = load i1024, i1024* %ptr, align 8
  store i1024 %r, i1024* %l, align 8
  tail call void @test_explicit_sret(i1024* %l)
  ret void
}

; This is too conservative, but doesn't really happen in practice.

; CHECK-LABEL: _test_tailcall_explicit_sret_gep:
; CHECK: add  x8, x0, #128
; CHECK-NEXT: bl _test_explicit_sret
; CHECK: ret
define void @test_tailcall_explicit_sret_gep(i1024* %ptr) #0 {
  %ptr2 = getelementptr i1024, i1024* %ptr, i32 1
  tail call void @test_explicit_sret(i1024* %ptr2)
  ret void
}

; CHECK-LABEL: _test_tailcall_explicit_sret_alloca_returned:
; CHECK: mov  x[[CALLERX8NUM:[0-9]+]], x8
; CHECK: mov  x8, sp
; CHECK-NEXT: bl _test_explicit_sret
; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
; CHECK: ret
define i1024 @test_tailcall_explicit_sret_alloca_returned() #0 {
  %l = alloca i1024, align 8
  tail call void @test_explicit_sret(i1024* %l)
  %r = load i1024, i1024* %l, align 8
  ret i1024 %r
}

; CHECK-LABEL: _test_indirect_tailcall_explicit_sret_nosret_arg:
; CHECK-DAG: mov  x[[CALLERX8NUM:[0-9]+]], x8
; CHECK-DAG: mov  [[FPTR:x[0-9]+]], x0
; CHECK: mov  x0, sp
; CHECK-NEXT: blr [[FPTR]]
; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
; CHECK: ret
define void @test_indirect_tailcall_explicit_sret_nosret_arg(i1024* sret %arg, void (i1024*)* %f) #0 {
  %l = alloca i1024, align 8
  tail call void %f(i1024* %l)
  %r = load i1024, i1024* %l, align 8
  store i1024 %r, i1024* %arg, align 8
  ret void
}

; CHECK-LABEL: _test_indirect_tailcall_explicit_sret_:
; CHECK: mov  x[[CALLERX8NUM:[0-9]+]], x8
; CHECK: mov  x8, sp
; CHECK-NEXT: blr x0
; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
; CHECK: ret
define void @test_indirect_tailcall_explicit_sret_(i1024* sret %arg, i1024 ()* %f) #0 {
  %ret = tail call i1024 %f()
  store i1024 %ret, i1024* %arg, align 8
  ret void
}

attributes #0 = { nounwind }