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
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
| ; RUN: llc -relocation-model=pic -verify-machineinstrs < %s -mcpu=pwr8 \
; RUN: -mattr=+altivec -mattr=-vsx | FileCheck %s
; RUN: llc -relocation-model=pic -verify-machineinstrs < %s -mattr=+altivec \
; RUN: -mattr=-vsx | FileCheck %s
; RUN: llc -relocation-model=pic -verify-machineinstrs < %s -mcpu=pwr9 \
; RUN: -mattr=-direct-move -mattr=+altivec | FileCheck %s
; Currently VSX support is disabled for this test because we generate lxsdx
; instead of lfd, and stxsdx instead of stfd. That is a poor choice when we
; have reg+imm addressing, and is on the list of things to be fixed.
; The second run step is to ensure that -march=ppc64le is adequate to select
; the same feature set as with -mcpu=pwr8 since that is the baseline for ppc64le.
target datalayout = "e-m:e-i64:64-n32:64"
target triple = "powerpc64le-unknown-linux-gnu"
;
; Verify use of registers for float/vector aggregate return.
;
define [8 x float] @return_float([8 x float] %x) {
entry:
ret [8 x float] %x
}
; CHECK-LABEL: @return_float
; CHECK: %entry
; CHECK-NEXT: blr
define [8 x double] @return_double([8 x double] %x) {
entry:
ret [8 x double] %x
}
; CHECK-LABEL: @return_double
; CHECK: %entry
; CHECK-NEXT: blr
define [4 x ppc_fp128] @return_ppcf128([4 x ppc_fp128] %x) {
entry:
ret [4 x ppc_fp128] %x
}
; CHECK-LABEL: @return_ppcf128
; CHECK: %entry
; CHECK-NEXT: blr
define [8 x <4 x i32>] @return_v4i32([8 x <4 x i32>] %x) {
entry:
ret [8 x <4 x i32>] %x
}
; CHECK-LABEL: @return_v4i32
; CHECK: %entry
; CHECK-NEXT: blr
;
; Verify amount of space taken up by aggregates in the parameter save area.
;
define i64 @callee_float([7 x float] %a, [7 x float] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_float
; CHECK: ld 3, 96(1)
; CHECK: blr
define void @caller_float(i64 %x, [7 x float] %y) {
entry:
tail call void @test_float([7 x float] %y, [7 x float] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_float
; CHECK: std 3, 96(1)
; CHECK: bl test_float
declare void @test_float([7 x float], [7 x float], i64)
define i64 @callee_double(i64 %a, [7 x double] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_double
; CHECK: ld 3, 96(1)
; CHECK: blr
define void @caller_double(i64 %x, [7 x double] %y) {
entry:
tail call void @test_double(i64 %x, [7 x double] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_double
; CHECK: std 3, 96(1)
; CHECK: bl test_double
declare void @test_double(i64, [7 x double], i64)
define i64 @callee_ppcf128(i64 %a, [4 x ppc_fp128] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_ppcf128
; CHECK: ld 3, 104(1)
; CHECK: blr
define void @caller_ppcf128(i64 %x, [4 x ppc_fp128] %y) {
entry:
tail call void @test_ppcf128(i64 %x, [4 x ppc_fp128] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_ppcf128
; CHECK: std 3, 104(1)
; CHECK: bl test_ppcf128
declare void @test_ppcf128(i64, [4 x ppc_fp128], i64)
define i64 @callee_i64(i64 %a, [7 x i64] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_i64
; CHECK: ld 3, 96(1)
; CHECK: blr
define void @caller_i64(i64 %x, [7 x i64] %y) {
entry:
tail call void @test_i64(i64 %x, [7 x i64] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_i64
; CHECK: std 3, 96(1)
; CHECK: bl test_i64
declare void @test_i64(i64, [7 x i64], i64)
define i64 @callee_i128(i64 %a, [4 x i128] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_i128
; CHECK: ld 3, 112(1)
; CHECK: blr
define void @caller_i128(i64 %x, [4 x i128] %y) {
entry:
tail call void @test_i128(i64 %x, [4 x i128] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_i128
; CHECK: std 3, 112(1)
; CHECK: bl test_i128
declare void @test_i128(i64, [4 x i128], i64)
define i64 @callee_v4i32(i64 %a, [4 x <4 x i32>] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_v4i32
; CHECK: ld 3, 112(1)
; CHECK: blr
define void @caller_v4i32(i64 %x, [4 x <4 x i32>] %y) {
entry:
tail call void @test_v4i32(i64 %x, [4 x <4 x i32>] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_v4i32
; CHECK: std 3, 112(1)
; CHECK: bl test_v4i32
declare void @test_v4i32(i64, [4 x <4 x i32>], i64)
;
; Verify handling of floating point arguments in GPRs
;
%struct.float8 = type { [8 x float] }
%struct.float5 = type { [5 x float] }
%struct.float2 = type { [2 x float] }
@g8 = common global %struct.float8 zeroinitializer, align 4
@g5 = common global %struct.float5 zeroinitializer, align 4
@g2 = common global %struct.float2 zeroinitializer, align 4
define float @callee0([7 x float] %a, [7 x float] %b) {
entry:
%b.extract = extractvalue [7 x float] %b, 6
ret float %b.extract
}
; CHECK-LABEL: @callee0
; CHECK: stw 10, [[OFF:.*]](1)
; CHECK: lfs 1, [[OFF]](1)
; CHECK: blr
define void @caller0([7 x float] %a) {
entry:
tail call void @test0([7 x float] %a, [7 x float] %a)
ret void
}
; CHECK-LABEL: @caller0
; CHECK-DAG: fmr 8, 1
; CHECK-DAG: fmr 9, 2
; CHECK-DAG: fmr 10, 3
; CHECK-DAG: fmr 11, 4
; CHECK-DAG: fmr 12, 5
; CHECK-DAG: fmr 13, 6
; CHECK-DAG: stfs 7, [[OFF:[0-9]+]](1)
; CHECK-DAG: lwz 10, [[OFF]](1)
; CHECK: bl test0
declare void @test0([7 x float], [7 x float])
define float @callee1([8 x float] %a, [8 x float] %b) {
entry:
%b.extract = extractvalue [8 x float] %b, 7
ret float %b.extract
}
; CHECK-LABEL: @callee1
; CHECK: rldicl [[REG:[0-9]+]], 10, 32, 32
; CHECK: stw [[REG]], [[OFF:.*]](1)
; CHECK: lfs 1, [[OFF]](1)
; CHECK: blr
define void @caller1([8 x float] %a) {
entry:
tail call void @test1([8 x float] %a, [8 x float] %a)
ret void
}
; CHECK-LABEL: @caller1
; CHECK-DAG: fmr 9, 1
; CHECK-DAG: fmr 10, 2
; CHECK-DAG: fmr 11, 3
; CHECK-DAG: fmr 12, 4
; CHECK-DAG: fmr 13, 5
; CHECK-DAG: stfs 5, [[OFF0:[0-9]+]](1)
; CHECK-DAG: stfs 6, [[OFF1:[0-9]+]](1)
; CHECK-DAG: stfs 7, [[OFF2:[0-9]+]](1)
; CHECK-DAG: stfs 8, [[OFF3:[0-9]+]](1)
; CHECK-DAG: lwz 9, [[OFF0]](1)
; CHECK-DAG: lwz [[REG1:[0-9]+]], [[OFF1]](1)
; CHECK-DAG: lwz 10, [[OFF2]](1)
; CHECK-DAG: lwz [[REG3:[0-9]+]], [[OFF3]](1)
; CHECK-DAG: rldimi 9, [[REG1]], 32, 0
; CHECK-DAG: rldimi 10, [[REG3]], 32, 0
; CHECK: bl test1
declare void @test1([8 x float], [8 x float])
define float @callee2([8 x float] %a, [5 x float] %b, [2 x float] %c) {
entry:
%c.extract = extractvalue [2 x float] %c, 1
ret float %c.extract
}
; CHECK-LABEL: @callee2
; CHECK: rldicl [[REG:[0-9]+]], 10, 32, 32
; CHECK: stw [[REG]], [[OFF:.*]](1)
; CHECK: lfs 1, [[OFF]](1)
; CHECK: blr
define void @caller2() {
entry:
%0 = load [8 x float], [8 x float]* getelementptr inbounds (%struct.float8, %struct.float8* @g8, i64 0, i32 0), align 4
%1 = load [5 x float], [5 x float]* getelementptr inbounds (%struct.float5, %struct.float5* @g5, i64 0, i32 0), align 4
%2 = load [2 x float], [2 x float]* getelementptr inbounds (%struct.float2, %struct.float2* @g2, i64 0, i32 0), align 4
tail call void @test2([8 x float] %0, [5 x float] %1, [2 x float] %2)
ret void
}
; CHECK-LABEL: @caller2
; CHECK: ld {{[0-9]+}}, .LC
; CHECK-DAG: lfs 1, 0({{[0-9]+}})
; CHECK-DAG: lfs 2, 4({{[0-9]+}})
; CHECK-DAG: lfs 3, 8({{[0-9]+}})
; CHECK-DAG: lfs 4, 12({{[0-9]+}})
; CHECK-DAG: lfs 5, 16({{[0-9]+}})
; CHECK-DAG: lfs 6, 20({{[0-9]+}})
; CHECK-DAG: lfs 7, 24({{[0-9]+}})
; CHECK-DAG: lfs 8, 28({{[0-9]+}})
; CHECK-DAG: lfs 9, 0({{[0-9]+}})
; CHECK-DAG: lfs 10, 4({{[0-9]+}})
; CHECK-DAG: lfs 11, 8({{[0-9]+}})
; CHECK-DAG: lfs 12, 12({{[0-9]+}})
; CHECK-DAG: lfs 13, 16({{[0-9]+}})
; CHECK-DAG: ld 10, 0({{[0-9]+}})
; CHECK: bl test2
declare void @test2([8 x float], [5 x float], [2 x float])
define double @callee3([8 x float] %a, [5 x float] %b, double %c) {
entry:
ret double %c
}
; CHECK-LABEL: @callee3
; CHECK: std 10, [[OFF:.*]](1)
; CHECK: lfd 1, [[OFF]](1)
; CHECK: blr
define void @caller3(double %d) {
entry:
%0 = load [8 x float], [8 x float]* getelementptr inbounds (%struct.float8, %struct.float8* @g8, i64 0, i32 0), align 4
%1 = load [5 x float], [5 x float]* getelementptr inbounds (%struct.float5, %struct.float5* @g5, i64 0, i32 0), align 4
tail call void @test3([8 x float] %0, [5 x float] %1, double %d)
ret void
}
; CHECK-LABEL: @caller3
; CHECK: stfd 1, [[OFF:.*]](1)
; CHECK: ld 10, [[OFF]](1)
; CHECK: bl test3
declare void @test3([8 x float], [5 x float], double)
define float @callee4([8 x float] %a, [5 x float] %b, float %c) {
entry:
ret float %c
}
; CHECK-LABEL: @callee4
; CHECK: stw 10, [[OFF:.*]](1)
; CHECK: lfs 1, [[OFF]](1)
; CHECK: blr
define void @caller4(float %f) {
entry:
%0 = load [8 x float], [8 x float]* getelementptr inbounds (%struct.float8, %struct.float8* @g8, i64 0, i32 0), align 4
%1 = load [5 x float], [5 x float]* getelementptr inbounds (%struct.float5, %struct.float5* @g5, i64 0, i32 0), align 4
tail call void @test4([8 x float] %0, [5 x float] %1, float %f)
ret void
}
; CHECK-LABEL: @caller4
; CHECK: stfs 1, [[OFF:.*]](1)
; CHECK: lwz 10, [[OFF]](1)
; CHECK: bl test4
declare void @test4([8 x float], [5 x float], float)
|