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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
| ; RUN: llc -relocation-model=static < %s -O0 -verify-machineinstrs -fast-isel -fast-isel-abort=1 -mattr=-vsx -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 | FileCheck %s --check-prefix=ELF64
; RUN: llc -relocation-model=static < %s -O0 -verify-machineinstrs -fast-isel -fast-isel-abort=1 -mattr=+vsx -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 | FileCheck %s --check-prefix=VSX
; RUN: llc -relocation-model=static < %s -O0 -verify-machineinstrs -fast-isel -fast-isel-abort=1 -mattr=spe -mtriple=powerpc-unknown-linux-gnu -mcpu=e500 | FileCheck %s --check-prefix=SPE
; This test verifies that load/store instructions are properly generated,
; and that they pass MI verification.
@a = global i8 1, align 1
@b = global i16 2, align 2
@c = global i32 4, align 4
@d = global i64 8, align 8
@e = global float 1.25, align 4
@f = global double 3.5, align 8
%struct.s = type<{ i8, i32 }>
%struct.t = type<{ i8, i64 }>
@g = global %struct.s <{ i8 1, i32 2 }>, align 1
@h = global %struct.t <{ i8 1, i64 2 }>, align 1
@i = common global [8192 x i64] zeroinitializer, align 8
; load
define i8 @t1() nounwind {
; ELF64: t1
%1 = load i8, i8* @a, align 1
; ELF64: lbz
%2 = add nsw i8 %1, 1
; ELF64: addi
ret i8 %2
}
define i16 @t2() nounwind {
; ELF64: t2
%1 = load i16, i16* @b, align 2
; ELF64: lhz
%2 = add nsw i16 %1, 1
; ELF64: addi
ret i16 %2
}
define i32 @t3() nounwind {
; ELF64: t3
%1 = load i32, i32* @c, align 4
; ELF64: lwz
%2 = add nsw i32 %1, 1
; ELF64: addi
ret i32 %2
}
define i64 @t4() nounwind {
; ELF64: t4
%1 = load i64, i64* @d, align 4
; ELF64: ld
%2 = add nsw i64 %1, 1
; ELF64: addi
ret i64 %2
}
define float @t5() nounwind {
; ELF64: t5
; SPE: t5
%1 = load float, float* @e, align 4
; ELF64: lfs
; SPE: lwz
%2 = fadd float %1, 1.0
; ELF64: fadds
; SPE: efsadd
ret float %2
}
define double @t6() nounwind {
; ELF64: t6
; SPE: t6
%1 = load double, double* @f, align 8
; ELF64: lfd
; VSX: lxsdx
; SPE: evldd
%2 = fadd double %1, 1.0
; ELF64: fadd
; VSX: xsadddp
; SPE: efdadd
ret double %2
}
; store
define void @t7(i8 %v) nounwind {
; ELF64: t7
%1 = add nsw i8 %v, 1
store i8 %1, i8* @a, align 1
; ELF64: addis
; ELF64: addi
; ELF64: addi
; ELF64: stb
ret void
}
define void @t8(i16 %v) nounwind {
; ELF64: t8
%1 = add nsw i16 %v, 1
store i16 %1, i16* @b, align 2
; ELF64: addis
; ELF64: addi
; ELF64: addi
; ELF64: sth
ret void
}
define void @t9(i32 %v) nounwind {
; ELF64: t9
%1 = add nsw i32 %v, 1
store i32 %1, i32* @c, align 4
; ELF64: addis
; ELF64: addi
; ELF64: addi
; ELF64: stw
ret void
}
define void @t10(i64 %v) nounwind {
; ELF64: t10
%1 = add nsw i64 %v, 1
store i64 %1, i64* @d, align 4
; ELF64: addis
; ELF64: addi
; ELF64: addi
; ELF64: std
ret void
}
define void @t11(float %v) nounwind {
; ELF64: t11
; SPE: t11
%1 = fadd float %v, 1.0
store float %1, float* @e, align 4
; ELF64: fadds
; ELF64: stfs
; SPE: efsadd
; SPE: stw
ret void
}
define void @t12(double %v) nounwind {
; ELF64: t12
; SPE: t12
%1 = fadd double %v, 1.0
store double %1, double* @f, align 8
; ELF64: fadd
; ELF64: stfd
; VSX: xsadddp
; VSX: stxsdx
; SPE: efdadd
; SPE: evstdd
ret void
}
;; lwa requires an offset divisible by 4, so we need lwax here.
define i64 @t13() nounwind {
; ELF64: t13
%1 = load i32, i32* getelementptr inbounds (%struct.s, %struct.s* @g, i32 0, i32 1), align 1
%2 = sext i32 %1 to i64
; ELF64: li
; ELF64: lwax
%3 = add nsw i64 %2, 1
; ELF64: addi
ret i64 %3
}
;; ld requires an offset divisible by 4, so we need ldx here.
define i64 @t14() nounwind {
; ELF64: t14
%1 = load i64, i64* getelementptr inbounds (%struct.t, %struct.t* @h, i32 0, i32 1), align 1
; ELF64: li
; ELF64: ldx
%2 = add nsw i64 %1, 1
; ELF64: addi
ret i64 %2
}
;; std requires an offset divisible by 4, so we need stdx here.
define void @t15(i64 %v) nounwind {
; ELF64: t15
%1 = add nsw i64 %v, 1
store i64 %1, i64* getelementptr inbounds (%struct.t, %struct.t* @h, i32 0, i32 1), align 1
; ELF64: addis
; ELF64: addi
; ELF64: addi
; ELF64: li
; ELF64: stdx
ret void
}
;; ld requires an offset that fits in 16 bits, so we need ldx here.
define i64 @t16() nounwind {
; ELF64: t16
%1 = load i64, i64* getelementptr inbounds ([8192 x i64], [8192 x i64]* @i, i32 0, i64 5000), align 8
; ELF64: lis
; ELF64: ori
; ELF64: ldx
%2 = add nsw i64 %1, 1
; ELF64: addi
ret i64 %2
}
;; std requires an offset that fits in 16 bits, so we need stdx here.
define void @t17(i64 %v) nounwind {
; ELF64: t17
%1 = add nsw i64 %v, 1
store i64 %1, i64* getelementptr inbounds ([8192 x i64], [8192 x i64]* @i, i32 0, i64 5000), align 8
; ELF64: addis
; ELF64: addi
; ELF64: addi
; ELF64: lis
; ELF64: ori
; ELF64: stdx
ret void
}
|