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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -verify -iroutliner -ir-outlining-no-cost < %s | FileCheck %s
; This has two compatible regions based on function attributes. We have
; attributes that should be transferred only if it is on all of the regions.
; This includes the attributes, no-nans-fp-math,
; no-signed-zeros-fp-math, less-precise-fpmad, unsafe-fp-math, and
; no-infs-fp-math. Only when each instance of similarity has these attributes
; can we say that the outlined function can have these attributes since that
; is the more general case for these attributes.
define void @outline_attrs1() #0 {
; CHECK-LABEL: @outline_attrs1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[C:%.*]] = alloca i32, align 4
; CHECK-NEXT: call void @outlined_ir_func_1(i32* [[A]], i32* [[B]], i32* [[C]])
; CHECK-NEXT: ret void
;
entry:
%a = alloca i32, align 4
%b = alloca i32, align 4
%c = alloca i32, align 4
store i32 2, i32* %a, align 4
store i32 3, i32* %b, align 4
store i32 4, i32* %c, align 4
%al = load i32, i32* %a
%bl = load i32, i32* %b
%cl = load i32, i32* %c
ret void
}
define void @outline_attrs2() #0 {
; CHECK-LABEL: @outline_attrs2(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT: [[C:%.*]] = alloca i32, align 4
; CHECK-NEXT: call void @outlined_ir_func_1(i32* [[A]], i32* [[B]], i32* [[C]])
; CHECK-NEXT: ret void
;
entry:
%a = alloca i32, align 4
%b = alloca i32, align 4
%c = alloca i32, align 4
store i32 2, i32* %a, align 4
store i32 3, i32* %b, align 4
store i32 4, i32* %c, align 4
%al = load i32, i32* %a
%bl = load i32, i32* %b
%cl = load i32, i32* %c
ret void
}
define void @outline_attrs3() #0 {
; CHECK-LABEL: @outline_attrs3(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A:%.*]] = alloca float, align 4
; CHECK-NEXT: [[B:%.*]] = alloca float, align 4
; CHECK-NEXT: [[C:%.*]] = alloca float, align 4
; CHECK-NEXT: call void @outlined_ir_func_0(float* [[A]], float* [[B]], float* [[C]])
; CHECK-NEXT: ret void
;
entry:
%a = alloca float, align 4
%b = alloca float, align 4
%c = alloca float, align 4
store float 2.0, float* %a, align 4
store float 3.0, float* %b, align 4
store float 4.0, float* %c, align 4
%al = load float, float* %a
%bl = load float, float* %b
%cl = load float, float* %c
%0 = fmul float %al, %bl
ret void
}
define void @outline_attrs4() {
; CHECK-LABEL: @outline_attrs4(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[A:%.*]] = alloca float, align 4
; CHECK-NEXT: [[B:%.*]] = alloca float, align 4
; CHECK-NEXT: [[C:%.*]] = alloca float, align 4
; CHECK-NEXT: call void @outlined_ir_func_0(float* [[A]], float* [[B]], float* [[C]])
; CHECK-NEXT: ret void
;
entry:
%a = alloca float, align 4
%b = alloca float, align 4
%c = alloca float, align 4
store float 2.0, float* %a, align 4
store float 3.0, float* %b, align 4
store float 4.0, float* %c, align 4
%al = load float, float* %a
%bl = load float, float* %b
%cl = load float, float* %c
%0 = fmul float %al, %bl
ret void
}
attributes #0 = { "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" "less-precise-fpmad"="true"
"unsafe-fp-math"="true" "no-infs-fp-math"="true"}
; CHECK: define internal void @outlined_ir_func_0(float* [[ARG0:%.*]], float* [[ARG1:%.*]], float* [[ARG2:%.*]]) [[ATTR1:#[0-9]+]] {
; CHECK: entry_to_outline:
; CHECK-NEXT: store float 2.000000e+00, float* [[ARG0]], align 4
; CHECK-NEXT: store float 3.000000e+00, float* [[ARG1]], align 4
; CHECK-NEXT: store float 4.000000e+00, float* [[ARG2]], align 4
; CHECK-NEXT: [[AL:%.*]] = load float, float* [[ARG0]], align 4
; CHECK-NEXT: [[BL:%.*]] = load float, float* [[ARG1]], align 4
; CHECK-NEXT: [[CL:%.*]] = load float, float* [[ARG2]], align 4
; CHECK: define internal void @outlined_ir_func_1(i32* [[ARG0:%.*]], i32* [[ARG1:%.*]], i32* [[ARG2:%.*]]) [[ATTR:#[0-9]+]] {
; CHECK: entry_to_outline:
; CHECK-NEXT: store i32 2, i32* [[ARG0]], align 4
; CHECK-NEXT: store i32 3, i32* [[ARG1]], align 4
; CHECK-NEXT: store i32 4, i32* [[ARG2]], align 4
; CHECK-NEXT: [[AL:%.*]] = load i32, i32* [[ARG0]], align 4
; CHECK-NEXT: [[BL:%.*]] = load i32, i32* [[ARG1]], align 4
; CHECK-NEXT: [[CL:%.*]] = load i32, i32* [[ARG2]], align 4
; CHECK: attributes [[ATTR1]] = { minsize optsize "less-precise-fpmad"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "unsafe-fp-math"="false" }
; CHECK: attributes [[ATTR]] = { minsize optsize "less-precise-fpmad"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" "unsafe-fp-math"="true" }
|
