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
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
; RUN: | FileCheck %s -check-prefix=RV32I
; Check indexed and unindexed, sext, zext and anyext loads
define i32 @lb(i8 *%a) nounwind {
; RV32I-LABEL: lb:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lb a1, 0(a0)
; RV32I-NEXT: lb a0, 1(a0)
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
%1 = getelementptr i8, i8* %a, i32 1
%2 = load i8, i8* %1
%3 = sext i8 %2 to i32
; the unused load will produce an anyext for selection
%4 = load volatile i8, i8* %a
ret i32 %3
}
define i32 @lh(i16 *%a) nounwind {
; RV32I-LABEL: lh:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lh a1, 0(a0)
; RV32I-NEXT: lh a0, 4(a0)
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
%1 = getelementptr i16, i16* %a, i32 2
%2 = load i16, i16* %1
%3 = sext i16 %2 to i32
; the unused load will produce an anyext for selection
%4 = load volatile i16, i16* %a
ret i32 %3
}
define i32 @lw(i32 *%a) nounwind {
; RV32I-LABEL: lw:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lw a1, 0(a0)
; RV32I-NEXT: lw a0, 12(a0)
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
%1 = getelementptr i32, i32* %a, i32 3
%2 = load i32, i32* %1
%3 = load volatile i32, i32* %a
ret i32 %2
}
define i32 @lbu(i8 *%a) nounwind {
; RV32I-LABEL: lbu:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lbu a1, 0(a0)
; RV32I-NEXT: lbu a0, 4(a0)
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
%1 = getelementptr i8, i8* %a, i32 4
%2 = load i8, i8* %1
%3 = zext i8 %2 to i32
%4 = load volatile i8, i8* %a
%5 = zext i8 %4 to i32
%6 = add i32 %3, %5
ret i32 %6
}
define i32 @lhu(i16 *%a) nounwind {
; RV32I-LABEL: lhu:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lhu a1, 0(a0)
; RV32I-NEXT: lhu a0, 10(a0)
; RV32I-NEXT: add a0, a0, a1
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
%1 = getelementptr i16, i16* %a, i32 5
%2 = load i16, i16* %1
%3 = zext i16 %2 to i32
%4 = load volatile i16, i16* %a
%5 = zext i16 %4 to i32
%6 = add i32 %3, %5
ret i32 %6
}
; Check indexed and unindexed stores
define void @sb(i8 *%a, i8 %b) nounwind {
; RV32I-LABEL: sb:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: sb a1, 6(a0)
; RV32I-NEXT: sb a1, 0(a0)
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
store i8 %b, i8* %a
%1 = getelementptr i8, i8* %a, i32 6
store i8 %b, i8* %1
ret void
}
define void @sh(i16 *%a, i16 %b) nounwind {
; RV32I-LABEL: sh:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: sh a1, 14(a0)
; RV32I-NEXT: sh a1, 0(a0)
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
store i16 %b, i16* %a
%1 = getelementptr i16, i16* %a, i32 7
store i16 %b, i16* %1
ret void
}
define void @sw(i32 *%a, i32 %b) nounwind {
; RV32I-LABEL: sw:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: sw a1, 32(a0)
; RV32I-NEXT: sw a1, 0(a0)
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
store i32 %b, i32* %a
%1 = getelementptr i32, i32* %a, i32 8
store i32 %b, i32* %1
ret void
}
; Check load and store to an i1 location
define i32 @load_sext_zext_anyext_i1(i1 *%a) nounwind {
; RV32I-LABEL: load_sext_zext_anyext_i1:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lb a1, 0(a0)
; RV32I-NEXT: lbu a1, 1(a0)
; RV32I-NEXT: lbu a0, 2(a0)
; RV32I-NEXT: sub a0, a0, a1
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
; sextload i1
%1 = getelementptr i1, i1* %a, i32 1
%2 = load i1, i1* %1
%3 = sext i1 %2 to i32
; zextload i1
%4 = getelementptr i1, i1* %a, i32 2
%5 = load i1, i1* %4
%6 = zext i1 %5 to i32
%7 = add i32 %3, %6
; extload i1 (anyext). Produced as the load is unused.
%8 = load volatile i1, i1* %a
ret i32 %7
}
define i16 @load_sext_zext_anyext_i1_i16(i1 *%a) nounwind {
; RV32I-LABEL: load_sext_zext_anyext_i1_i16:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lb a1, 0(a0)
; RV32I-NEXT: lbu a1, 1(a0)
; RV32I-NEXT: lbu a0, 2(a0)
; RV32I-NEXT: sub a0, a0, a1
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
; sextload i1
%1 = getelementptr i1, i1* %a, i32 1
%2 = load i1, i1* %1
%3 = sext i1 %2 to i16
; zextload i1
%4 = getelementptr i1, i1* %a, i32 2
%5 = load i1, i1* %4
%6 = zext i1 %5 to i16
%7 = add i16 %3, %6
; extload i1 (anyext). Produced as the load is unused.
%8 = load volatile i1, i1* %a
ret i16 %7
}
; Check load and store to a global
@G = global i32 0
define i32 @lw_sw_global(i32 %a) nounwind {
; TODO: the addi should be folded in to the lw/sw operations
; RV32I-LABEL: lw_sw_global:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lui a1, %hi(G)
; RV32I-NEXT: addi a2, a1, %lo(G)
; RV32I-NEXT: lw a1, 0(a2)
; RV32I-NEXT: sw a0, 0(a2)
; RV32I-NEXT: lui a2, %hi(G+36)
; RV32I-NEXT: addi a2, a2, %lo(G+36)
; RV32I-NEXT: lw a3, 0(a2)
; RV32I-NEXT: sw a0, 0(a2)
; RV32I-NEXT: addi a0, a1, 0
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
%1 = load volatile i32, i32* @G
store i32 %a, i32* @G
%2 = getelementptr i32, i32* @G, i32 9
%3 = load volatile i32, i32* %2
store i32 %a, i32* %2
ret i32 %1
}
; Ensure that 1 is added to the high 20 bits if bit 11 of the low part is 1
define i32 @lw_sw_constant(i32 %a) nounwind {
; TODO: the addi should be folded in to the lw/sw
; RV32I-LABEL: lw_sw_constant:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -16
; RV32I-NEXT: sw ra, 12(sp)
; RV32I-NEXT: sw s0, 8(sp)
; RV32I-NEXT: addi s0, sp, 16
; RV32I-NEXT: lui a1, 912092
; RV32I-NEXT: addi a2, a1, -273
; RV32I-NEXT: lw a1, 0(a2)
; RV32I-NEXT: sw a0, 0(a2)
; RV32I-NEXT: addi a0, a1, 0
; RV32I-NEXT: lw s0, 8(sp)
; RV32I-NEXT: lw ra, 12(sp)
; RV32I-NEXT: addi sp, sp, 16
; RV32I-NEXT: jalr zero, ra, 0
%1 = inttoptr i32 3735928559 to i32*
%2 = load volatile i32, i32* %1
store i32 %a, i32* %1
ret i32 %2
}
|
