| 12
 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
 
 | ; Test the handling of base + 12-bit displacement addresses for large frames,
; in cases where no 20-bit form exists.  The tests here assume z10 register
; pressure, without the high words being available.
;
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z10 | \
; RUN:   FileCheck -check-prefix=CHECK-NOFP %s
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z10 -frame-pointer=all | \
; RUN:   FileCheck -check-prefix=CHECK-FP %s
; This file tests what happens when a displacement is converted from
; being relative to the start of a frame object to being relative to
; the frame itself.  In some cases the test is only possible if two
; objects are allocated.
;
; Rather than rely on a particular order for those objects, the tests
; instead allocate two objects of the same size and apply the test to
; both of them.  For consistency, all tests follow this model, even if
; one object would actually be enough.
; First check the highest in-range offset after conversion, which is 4092
; for word-addressing instructions like MVHI.
;
; The last in-range doubleword offset is 4088.  Since the frame has two
; emergency spill slots at 160(%r15), the amount that we need to allocate
; in order to put another object at offset 4088 is (4088 - 176) / 4 = 978
; words.
define void @f1() {
; CHECK-NOFP-LABEL: f1:
; CHECK-NOFP: mvhi 4092(%r15), 42
; CHECK-NOFP: br %r14
;
; CHECK-FP-LABEL: f1:
; CHECK-FP: mvhi 4092(%r11), 42
; CHECK-FP: br %r14
  %region1 = alloca [978 x i32], align 8
  %region2 = alloca [978 x i32], align 8
  %ptr1 = getelementptr inbounds [978 x i32], ptr %region1, i64 0, i64 1
  %ptr2 = getelementptr inbounds [978 x i32], ptr %region2, i64 0, i64 1
  store volatile i32 42, ptr %ptr1
  store volatile i32 42, ptr %ptr2
  ret void
}
; Test the first out-of-range offset.  We cannot use an index register here.
define void @f2() {
; CHECK-NOFP-LABEL: f2:
; CHECK-NOFP: lay %r1, 4096(%r15)
; CHECK-NOFP: mvhi 0(%r1), 42
; CHECK-NOFP: br %r14
;
; CHECK-FP-LABEL: f2:
; CHECK-FP: lay %r1, 4096(%r11)
; CHECK-FP: mvhi 0(%r1), 42
; CHECK-FP: br %r14
  %region1 = alloca [978 x i32], align 8
  %region2 = alloca [978 x i32], align 8
  %ptr1 = getelementptr inbounds [978 x i32], ptr %region1, i64 0, i64 2
  %ptr2 = getelementptr inbounds [978 x i32], ptr %region2, i64 0, i64 2
  store volatile i32 42, ptr %ptr1
  store volatile i32 42, ptr %ptr2
  ret void
}
; Test the next offset after that.
define void @f3() {
; CHECK-NOFP-LABEL: f3:
; CHECK-NOFP: lay %r1, 4096(%r15)
; CHECK-NOFP: mvhi 4(%r1), 42
; CHECK-NOFP: br %r14
;
; CHECK-FP-LABEL: f3:
; CHECK-FP: lay %r1, 4096(%r11)
; CHECK-FP: mvhi 4(%r1), 42
; CHECK-FP: br %r14
  %region1 = alloca [978 x i32], align 8
  %region2 = alloca [978 x i32], align 8
  %ptr1 = getelementptr inbounds [978 x i32], ptr %region1, i64 0, i64 3
  %ptr2 = getelementptr inbounds [978 x i32], ptr %region2, i64 0, i64 3
  store volatile i32 42, ptr %ptr1
  store volatile i32 42, ptr %ptr2
  ret void
}
; Add 4096 bytes (1024 words) to the size of each object and repeat.
define void @f4() {
; CHECK-NOFP-LABEL: f4:
; CHECK-NOFP: lay %r1, 4096(%r15)
; CHECK-NOFP: mvhi 4092(%r1), 42
; CHECK-NOFP: br %r14
;
; CHECK-FP-LABEL: f4:
; CHECK-FP: lay %r1, 4096(%r11)
; CHECK-FP: mvhi 4092(%r1), 42
; CHECK-FP: br %r14
  %region1 = alloca [2002 x i32], align 8
  %region2 = alloca [2002 x i32], align 8
  %ptr1 = getelementptr inbounds [2002 x i32], ptr %region1, i64 0, i64 1
  %ptr2 = getelementptr inbounds [2002 x i32], ptr %region2, i64 0, i64 1
  store volatile i32 42, ptr %ptr1
  store volatile i32 42, ptr %ptr2
  ret void
}
; ...as above.
define void @f5() {
; CHECK-NOFP-LABEL: f5:
; CHECK-NOFP: lay %r1, 8192(%r15)
; CHECK-NOFP: mvhi 0(%r1), 42
; CHECK-NOFP: br %r14
;
; CHECK-FP-LABEL: f5:
; CHECK-FP: lay %r1, 8192(%r11)
; CHECK-FP: mvhi 0(%r1), 42
; CHECK-FP: br %r14
  %region1 = alloca [2002 x i32], align 8
  %region2 = alloca [2002 x i32], align 8
  %ptr1 = getelementptr inbounds [2002 x i32], ptr %region1, i64 0, i64 2
  %ptr2 = getelementptr inbounds [2002 x i32], ptr %region2, i64 0, i64 2
  store volatile i32 42, ptr %ptr1
  store volatile i32 42, ptr %ptr2
  ret void
}
; ...as above.
define void @f6() {
; CHECK-NOFP-LABEL: f6:
; CHECK-NOFP: lay %r1, 8192(%r15)
; CHECK-NOFP: mvhi 4(%r1), 42
; CHECK-NOFP: br %r14
;
; CHECK-FP-LABEL: f6:
; CHECK-FP: lay %r1, 8192(%r11)
; CHECK-FP: mvhi 4(%r1), 42
; CHECK-FP: br %r14
  %region1 = alloca [2002 x i32], align 8
  %region2 = alloca [2002 x i32], align 8
  %ptr1 = getelementptr inbounds [2002 x i32], ptr %region1, i64 0, i64 3
  %ptr2 = getelementptr inbounds [2002 x i32], ptr %region2, i64 0, i64 3
  store volatile i32 42, ptr %ptr1
  store volatile i32 42, ptr %ptr2
  ret void
}
; Now try an offset of 4092 from the start of the object, with the object
; being at offset 8192.  This time we need objects of (8192 - 176) / 4 = 2004
; words.
define void @f7() {
; CHECK-NOFP-LABEL: f7:
; CHECK-NOFP: lay %r1, 8192(%r15)
; CHECK-NOFP: mvhi 4092(%r1), 42
; CHECK-NOFP: br %r14
;
; CHECK-FP-LABEL: f7:
; CHECK-FP: lay %r1, 8192(%r11)
; CHECK-FP: mvhi 4092(%r1), 42
; CHECK-FP: br %r14
  %region1 = alloca [2004 x i32], align 8
  %region2 = alloca [2004 x i32], align 8
  %ptr1 = getelementptr inbounds [2004 x i32], ptr %region1, i64 0, i64 1023
  %ptr2 = getelementptr inbounds [2004 x i32], ptr %region2, i64 0, i64 1023
  store volatile i32 42, ptr %ptr1
  store volatile i32 42, ptr %ptr2
  ret void
}
; Keep the object-relative offset the same but bump the size of the
; objects by one doubleword.
define void @f8() {
; CHECK-NOFP-LABEL: f8:
; CHECK-NOFP: lay %r1, 12288(%r15)
; CHECK-NOFP: mvhi 4(%r1), 42
; CHECK-NOFP: br %r14
;
; CHECK-FP-LABEL: f8:
; CHECK-FP: lay %r1, 12288(%r11)
; CHECK-FP: mvhi 4(%r1), 42
; CHECK-FP: br %r14
  %region1 = alloca [2006 x i32], align 8
  %region2 = alloca [2006 x i32], align 8
  %ptr1 = getelementptr inbounds [2006 x i32], ptr %region1, i64 0, i64 1023
  %ptr2 = getelementptr inbounds [2006 x i32], ptr %region2, i64 0, i64 1023
  store volatile i32 42, ptr %ptr1
  store volatile i32 42, ptr %ptr2
  ret void
}
; Check a case where the original displacement is out of range.  The backend
; should force STY to be used instead.
define void @f9() {
; CHECK-NOFP-LABEL: f9:
; CHECK-NOFP: lhi [[TMP:%r[0-5]]], 42
; CHECK-NOFP: sty [[TMP]], 12296(%r15)
; CHECK-NOFP: br %r14
;
; CHECK-FP-LABEL: f9:
; CHECK-FP: lhi [[TMP:%r[0-5]]], 42
; CHECK-FP: sty [[TMP]], 12296(%r11)
; CHECK-FP: br %r14
  %region1 = alloca [2006 x i32], align 8
  %region2 = alloca [2006 x i32], align 8
  %ptr1 = getelementptr inbounds [2006 x i32], ptr %region1, i64 0, i64 1024
  %ptr2 = getelementptr inbounds [2006 x i32], ptr %region2, i64 0, i64 1024
  store volatile i32 42, ptr %ptr1
  store volatile i32 42, ptr %ptr2
  ret void
}
; Repeat f2 in a case that needs the emergency spill slots (because all
; call-clobbered registers are live and no call-saved ones have been
; allocated).
define void @f10(ptr %vptr) {
; CHECK-NOFP-LABEL: f10:
; CHECK-NOFP: stg [[REGISTER:%r[1-9][0-4]?]], [[OFFSET:160|168]](%r15)
; CHECK-NOFP: lay [[REGISTER]], 4096(%r15)
; CHECK-NOFP: mvhi 0([[REGISTER]]), 42
; CHECK-NOFP: lg [[REGISTER]], [[OFFSET]](%r15)
; CHECK-NOFP: br %r14
;
; CHECK-FP-LABEL: f10:
; CHECK-FP: stg [[REGISTER:%r[1-9][0-4]?]], [[OFFSET:160|168]](%r11)
; CHECK-FP: lay [[REGISTER]], 4096(%r11)
; CHECK-FP: mvhi 0([[REGISTER]]), 42
; CHECK-FP: lg [[REGISTER]], [[OFFSET]](%r11)
; CHECK-FP: br %r14
  %i0 = load volatile i32, ptr %vptr
  %i1 = load volatile i32, ptr %vptr
  %i3 = load volatile i32, ptr %vptr
  %i4 = load volatile i32, ptr %vptr
  %i5 = load volatile i32, ptr %vptr
  %region1 = alloca [978 x i32], align 8
  %region2 = alloca [978 x i32], align 8
  %ptr1 = getelementptr inbounds [978 x i32], ptr %region1, i64 0, i64 2
  %ptr2 = getelementptr inbounds [978 x i32], ptr %region2, i64 0, i64 2
  store volatile i32 42, ptr %ptr1
  store volatile i32 42, ptr %ptr2
  store volatile i32 %i0, ptr %vptr
  store volatile i32 %i1, ptr %vptr
  store volatile i32 %i3, ptr %vptr
  store volatile i32 %i4, ptr %vptr
  store volatile i32 %i5, ptr %vptr
  ret void
}
; And again with maximum register pressure.  The only spill slots that the
; NOFP case needs are the emergency ones, so the offsets are the same as for f2.
; The FP case needs to spill an extra register and is too dependent on
; register allocation heuristics for a stable test.
define void @f11(ptr %vptr) {
; CHECK-NOFP-LABEL: f11:
; CHECK-NOFP: stmg %r6, %r15,
; CHECK-NOFP: stg [[REGISTER:%r[1-9][0-4]?]], [[OFFSET:160|168]](%r15)
; CHECK-NOFP: lay [[REGISTER]], 4096(%r15)
; CHECK-NOFP: mvhi 0([[REGISTER]]), 42
; CHECK-NOFP: lg [[REGISTER]], [[OFFSET]](%r15)
; CHECK-NOFP: lmg %r6, %r15,
; CHECK-NOFP: br %r14
  %i0 = load volatile i32, ptr %vptr
  %i1 = load volatile i32, ptr %vptr
  %i3 = load volatile i32, ptr %vptr
  %i4 = load volatile i32, ptr %vptr
  %i5 = load volatile i32, ptr %vptr
  %i6 = load volatile i32, ptr %vptr
  %i7 = load volatile i32, ptr %vptr
  %i8 = load volatile i32, ptr %vptr
  %i9 = load volatile i32, ptr %vptr
  %i10 = load volatile i32, ptr %vptr
  %i11 = load volatile i32, ptr %vptr
  %i12 = load volatile i32, ptr %vptr
  %i13 = load volatile i32, ptr %vptr
  %i14 = load volatile i32, ptr %vptr
  %region1 = alloca [978 x i32], align 8
  %region2 = alloca [978 x i32], align 8
  %ptr1 = getelementptr inbounds [978 x i32], ptr %region1, i64 0, i64 2
  %ptr2 = getelementptr inbounds [978 x i32], ptr %region2, i64 0, i64 2
  store volatile i32 42, ptr %ptr1
  store volatile i32 42, ptr %ptr2
  store volatile i32 %i0, ptr %vptr
  store volatile i32 %i1, ptr %vptr
  store volatile i32 %i3, ptr %vptr
  store volatile i32 %i4, ptr %vptr
  store volatile i32 %i5, ptr %vptr
  store volatile i32 %i6, ptr %vptr
  store volatile i32 %i7, ptr %vptr
  store volatile i32 %i8, ptr %vptr
  store volatile i32 %i9, ptr %vptr
  store volatile i32 %i10, ptr %vptr
  store volatile i32 %i11, ptr %vptr
  store volatile i32 %i12, ptr %vptr
  store volatile i32 %i13, ptr %vptr
  store volatile i32 %i14, ptr %vptr
  ret void
}
 |