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
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
; RUN: llc < %s -o - | FileCheck %s
; RUN: llc -mattr=+alu-lsl-fast --aarch64-enable-sink-fold=false < %s -o - | FileCheck %s -check-prefix=LSLFAST
target triple = "aarch64-linux"
declare void @g(...)
; Check that ADDWrs/ADDXrs with shift > 4 is considered relatively
; slow, thus CSE-d.
define void @f0(i1 %c0, i1 %c1, ptr %a, i64 %i) {
; CHECK-LABEL: f0:
; CHECK: // %bb.0: // %E
; CHECK-NEXT: tbz w0, #0, .LBB0_5
; CHECK-NEXT: // %bb.1: // %A
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: add x0, x2, x3, lsl #5
; CHECK-NEXT: tbz w1, #0, .LBB0_3
; CHECK-NEXT: // %bb.2: // %B
; CHECK-NEXT: bl g
; CHECK-NEXT: b .LBB0_4
; CHECK-NEXT: .LBB0_3: // %C
; CHECK-NEXT: mov x1, x0
; CHECK-NEXT: bl g
; CHECK-NEXT: .LBB0_4:
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: .LBB0_5: // %X
; CHECK-NEXT: ret
;
; LSLFAST-LABEL: f0:
; LSLFAST: // %bb.0: // %E
; LSLFAST-NEXT: tbz w0, #0, .LBB0_5
; LSLFAST-NEXT: // %bb.1: // %A
; LSLFAST-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
; LSLFAST-NEXT: .cfi_def_cfa_offset 16
; LSLFAST-NEXT: .cfi_offset w30, -16
; LSLFAST-NEXT: add x0, x2, x3, lsl #5
; LSLFAST-NEXT: tbz w1, #0, .LBB0_3
; LSLFAST-NEXT: // %bb.2: // %B
; LSLFAST-NEXT: bl g
; LSLFAST-NEXT: b .LBB0_4
; LSLFAST-NEXT: .LBB0_3: // %C
; LSLFAST-NEXT: mov x1, x0
; LSLFAST-NEXT: bl g
; LSLFAST-NEXT: .LBB0_4:
; LSLFAST-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
; LSLFAST-NEXT: .LBB0_5: // %X
; LSLFAST-NEXT: ret
E:
%p0 = getelementptr {i64, i64, i64, i64}, ptr %a, i64 %i
br i1 %c0, label %A, label %X
A:
br i1 %c1, label %B, label %C
B:
call void @g(ptr %p0)
br label %X
C:
%p1 = getelementptr {i64, i64, i64, i64}, ptr %a, i64 %i
call void @g(ptr %p1, ptr %p0)
br label %X
X:
ret void
}
; Check that ADDWrs/ADDXrs with shift <= 4 is considered relatively fast on sub-targets
; with feature +alu-lsl-fast, thus *not* CSE-d.
define void @f1(i1 %c0, i1 %c1, ptr %a, i64 %i) {
; CHECK-LABEL: f1:
; CHECK: // %bb.0: // %E
; CHECK-NEXT: tbz w0, #0, .LBB1_5
; CHECK-NEXT: // %bb.1: // %A
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: .cfi_offset w30, -16
; CHECK-NEXT: add x0, x2, x3, lsl #4
; CHECK-NEXT: tbz w1, #0, .LBB1_3
; CHECK-NEXT: // %bb.2: // %B
; CHECK-NEXT: bl g
; CHECK-NEXT: b .LBB1_4
; CHECK-NEXT: .LBB1_3: // %C
; CHECK-NEXT: mov x1, x0
; CHECK-NEXT: bl g
; CHECK-NEXT: .LBB1_4:
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: .LBB1_5: // %X
; CHECK-NEXT: ret
;
; LSLFAST-LABEL: f1:
; LSLFAST: // %bb.0: // %E
; LSLFAST-NEXT: tbz w0, #0, .LBB1_5
; LSLFAST-NEXT: // %bb.1: // %A
; LSLFAST-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
; LSLFAST-NEXT: .cfi_def_cfa_offset 16
; LSLFAST-NEXT: .cfi_offset w30, -16
; LSLFAST-NEXT: add x8, x2, x3, lsl #4
; LSLFAST-NEXT: tbz w1, #0, .LBB1_3
; LSLFAST-NEXT: // %bb.2: // %B
; LSLFAST-NEXT: mov x0, x8
; LSLFAST-NEXT: bl g
; LSLFAST-NEXT: b .LBB1_4
; LSLFAST-NEXT: .LBB1_3: // %C
; LSLFAST-NEXT: add x0, x2, x3, lsl #4
; LSLFAST-NEXT: mov x1, x8
; LSLFAST-NEXT: bl g
; LSLFAST-NEXT: .LBB1_4:
; LSLFAST-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
; LSLFAST-NEXT: .LBB1_5: // %X
; LSLFAST-NEXT: ret
E:
%p0 = getelementptr {i64, i64}, ptr %a, i64 %i
br i1 %c0, label %A, label %X
A:
br i1 %c1, label %B, label %C
B:
call void @g(ptr %p0)
br label %X
C:
%p1 = getelementptr {i64, i64}, ptr %a, i64 %i
call void @g(ptr %p1, ptr %p0)
br label %X
X:
ret void
}
|
