prefetch.ll
3.81 KB
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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
; RUN: llc -mtriple=thumb-eabi -mattr=-thumb2 %s -o - | FileCheck %s -check-prefix CHECK-T1
; RUN: llc -mtriple=thumb-eabi -mattr=+v7 %s -o - | FileCheck %s -check-prefix=THUMB2
; RUN: llc -mtriple=thumb-eabi -mattr=+v7 -mattr=+mp %s -o - | FileCheck %s -check-prefix=THUMB2-MP
; RUN: llc -mtriple=arm-eabi -mattr=+v7 %s -o - | FileCheck %s -check-prefix=ARM
; RUN: llc -mtriple=arm-eabi -mcpu=cortex-a9 %s -o - | FileCheck %s -check-prefix=ARM-MP
; rdar://8601536
; CHECK-T1-NOT: pld
define void @t1(i8* %ptr) nounwind {
entry:
; ARM-LABEL: t1:
; ARM-NOT: pldw [r0]
; ARM: pld [r0]
; ARM-MP-LABEL: t1:
; ARM-MP: pldw [r0]
; ARM-MP: pld [r0]
; THUMB2-LABEL: t1:
; THUMB2-NOT: pldw [r0]
; THUMB2: pld [r0]
tail call void @llvm.prefetch( i8* %ptr, i32 1, i32 3, i32 1 )
tail call void @llvm.prefetch( i8* %ptr, i32 0, i32 3, i32 1 )
ret void
}
define void @t2(i8* %ptr) nounwind {
entry:
; ARM-LABEL: t2:
; ARM: pld [r0, #1023]
; THUMB2-LABEL: t2:
; THUMB2: pld [r0, #1023]
%tmp = getelementptr i8, i8* %ptr, i32 1023
tail call void @llvm.prefetch( i8* %tmp, i32 0, i32 3, i32 1 )
ret void
}
define void @t3(i32 %base, i32 %offset) nounwind {
entry:
; ARM-LABEL: t3:
; ARM: pld [r0, r1, lsr #2]
; THUMB2-LABEL: t3:
; THUMB2: lsrs r1, r1, #2
; THUMB2: pld [r0, r1]
%tmp1 = lshr i32 %offset, 2
%tmp2 = add i32 %base, %tmp1
%tmp3 = inttoptr i32 %tmp2 to i8*
tail call void @llvm.prefetch( i8* %tmp3, i32 0, i32 3, i32 1 )
ret void
}
define void @t4(i32 %base, i32 %offset) nounwind {
entry:
; ARM-LABEL: t4:
; ARM: pld [r0, r1, lsl #2]
; THUMB2-LABEL: t4:
; THUMB2: pld [r0, r1, lsl #2]
%tmp1 = shl i32 %offset, 2
%tmp2 = add i32 %base, %tmp1
%tmp3 = inttoptr i32 %tmp2 to i8*
tail call void @llvm.prefetch( i8* %tmp3, i32 0, i32 3, i32 1 )
ret void
}
declare void @llvm.prefetch(i8*, i32, i32, i32) nounwind
define void @t5(i8* %ptr) nounwind {
entry:
; ARM-LABEL: t5:
; ARM: pli [r0]
; THUMB2-LABEL: t5:
; THUMB2: pli [r0]
tail call void @llvm.prefetch( i8* %ptr, i32 0, i32 3, i32 0 )
ret void
}
define void @t6() {
entry:
;ARM-LABEL: t6:
;ARM: pld [sp]
;ARM: pld [sp, #50]
;ARM: pld [sp, #-50]
;THUMB2-LABEL: t6:
;THUMB2: pld [sp]
;THUMB2: pld [sp, #50]
;THUMB2: pld [sp, #-50]
%red = alloca [100 x i8], align 1
%0 = getelementptr inbounds [100 x i8], [100 x i8]* %red, i32 0, i32 0
%1 = getelementptr inbounds [100 x i8], [100 x i8]* %red, i32 0, i32 50
%2 = getelementptr inbounds [100 x i8], [100 x i8]* %red, i32 0, i32 -50
call void @llvm.prefetch(i8* %0, i32 0, i32 3, i32 1)
call void @llvm.prefetch(i8* %1, i32 0, i32 3, i32 1)
call void @llvm.prefetch(i8* %2, i32 0, i32 3, i32 1)
ret void
}
define void @t7() {
entry:
;ARM-LABEL: t7:
;ARM-MP: pldw [sp]
;ARM-MP: pldw [sp, #50]
;ARM-MP: pldw [sp, #-50]
;THUMB2-MP-LABEL: t7:
;THUMB2-MP: pldw [sp]
;THUMB2-MP: pldw [sp, #50]
;THUMB2-MP: pldw [sp, #-50]
%red = alloca [100 x i8], align 1
%0 = getelementptr inbounds [100 x i8], [100 x i8]* %red, i32 0, i32 0
%1 = getelementptr inbounds [100 x i8], [100 x i8]* %red, i32 0, i32 50
%2 = getelementptr inbounds [100 x i8], [100 x i8]* %red, i32 0, i32 -50
call void @llvm.prefetch(i8* %0, i32 1, i32 3, i32 1)
call void @llvm.prefetch(i8* %1, i32 1, i32 3, i32 1)
call void @llvm.prefetch(i8* %2, i32 1, i32 3, i32 1)
ret void
}
define void @t8() {
entry:
;ARM-LABEL: t8:
;ARM: pli [sp]
;ARM: pli [sp, #50]
;ARM: pli [sp, #-50]
;THUMB2-LABEL: t8:
;THUMB2: pli [sp]
;THUMB2: pli [sp, #50]
;THUMB2: pli [sp, #-50]
%red = alloca [100 x i8], align 1
%0 = getelementptr inbounds [100 x i8], [100 x i8]* %red, i32 0, i32 0
%1 = getelementptr inbounds [100 x i8], [100 x i8]* %red, i32 0, i32 50
%2 = getelementptr inbounds [100 x i8], [100 x i8]* %red, i32 0, i32 -50
call void @llvm.prefetch(i8* %0, i32 0, i32 3, i32 0)
call void @llvm.prefetch(i8* %1, i32 0, i32 3, i32 0)
call void @llvm.prefetch(i8* %2, i32 0, i32 3, i32 0)
ret void
}