unordered-atomic-memcpy.ll 16.7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456
; RUN: opt -basicaa -loop-idiom < %s -S | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-unknown-linux-gnu"

;; memcpy.atomic formation (atomic load & store)
define void @test1(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test1(
; CHECK: call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %Dest, i8* align 1 %Base, i64 %Size, i32 1)
; CHECK-NOT: store
; CHECK: ret void
bb.nph:
  %Base = alloca i8, i32 10000
  %Dest = alloca i8, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar
  %DestI = getelementptr i8, i8* %Dest, i64 %indvar
  %V = load atomic i8, i8* %I.0.014 unordered, align 1
  store atomic i8 %V, i8* %DestI unordered, align 1
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation (atomic store, normal load)
define void @test2(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test2(
; CHECK: call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %Dest, i8* align 1 %Base, i64 %Size, i32 1)
; CHECK-NOT: store
; CHECK: ret void
bb.nph:
  %Base = alloca i8, i32 10000
  %Dest = alloca i8, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar
  %DestI = getelementptr i8, i8* %Dest, i64 %indvar
  %V = load i8, i8* %I.0.014, align 1
  store atomic i8 %V, i8* %DestI unordered, align 1
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation rejection (atomic store, normal load w/ no align)
define void @test2b(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test2b(
; CHECK-NOT: call void @llvm.memcpy.element.unordered.atomic
; CHECK: store
; CHECK: ret void
bb.nph:
  %Base = alloca i8, i32 10000
  %Dest = alloca i8, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar
  %DestI = getelementptr i8, i8* %Dest, i64 %indvar
  %V = load i8, i8* %I.0.014
  store atomic i8 %V, i8* %DestI unordered, align 1
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation rejection (atomic store, normal load w/ bad align)
define void @test2c(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test2c(
; CHECK-NOT: call void @llvm.memcpy.element.unordered.atomic
; CHECK: store
; CHECK: ret void
bb.nph:
  %Base = alloca i32, i32 10000
  %Dest = alloca i32, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i32, i32* %Base, i64 %indvar
  %DestI = getelementptr i32, i32* %Dest, i64 %indvar
  %V = load i32, i32* %I.0.014, align 2
  store atomic i32 %V, i32* %DestI unordered, align 4
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation rejection (atomic store w/ bad align, normal load)
define void @test2d(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test2d(
; CHECK-NOT: call void @llvm.memcpy.element.unordered.atomic
; CHECK: store
; CHECK: ret void
bb.nph:
  %Base = alloca i32, i32 10000
  %Dest = alloca i32, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i32, i32* %Base, i64 %indvar
  %DestI = getelementptr i32, i32* %Dest, i64 %indvar
  %V = load i32, i32* %I.0.014, align 4
  store atomic i32 %V, i32* %DestI unordered, align 2
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}


;; memcpy.atomic formation (normal store, atomic load)
define void @test3(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test3(
; CHECK: call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %Dest, i8* align 1 %Base, i64 %Size, i32 1)
; CHECK-NOT: store
; CHECK: ret void
bb.nph:
  %Base = alloca i8, i32 10000
  %Dest = alloca i8, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar
  %DestI = getelementptr i8, i8* %Dest, i64 %indvar
  %V = load atomic i8, i8* %I.0.014 unordered, align 1
  store i8 %V, i8* %DestI, align 1
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation rejection (normal store w/ no align, atomic load)
define void @test3b(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test3b(
; CHECK-NOT: call void @llvm.memcpy.element.unordered.atomic
; CHECK: store
; CHECK: ret void
bb.nph:
  %Base = alloca i8, i32 10000
  %Dest = alloca i8, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar
  %DestI = getelementptr i8, i8* %Dest, i64 %indvar
  %V = load atomic i8, i8* %I.0.014 unordered, align 1
  store i8 %V, i8* %DestI
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation rejection (normal store, atomic load w/ bad align)
define void @test3c(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test3c(
; CHECK-NOT: call void @llvm.memcpy.element.unordered.atomic
; CHECK: store
; CHECK: ret void
bb.nph:
  %Base = alloca i32, i32 10000
  %Dest = alloca i32, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i32, i32* %Base, i64 %indvar
  %DestI = getelementptr i32, i32* %Dest, i64 %indvar
  %V = load atomic i32, i32* %I.0.014 unordered, align 2
  store i32 %V, i32* %DestI, align 4
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation rejection (normal store w/ bad align, atomic load)
define void @test3d(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test3d(
; CHECK-NOT: call void @llvm.memcpy.element.unordered.atomic
; CHECK: store
; CHECK: ret void
bb.nph:
  %Base = alloca i32, i32 10000
  %Dest = alloca i32, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i32, i32* %Base, i64 %indvar
  %DestI = getelementptr i32, i32* %Dest, i64 %indvar
  %V = load atomic i32, i32* %I.0.014 unordered, align 4
  store i32 %V, i32* %DestI, align 2
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}


;; memcpy.atomic formation rejection (atomic load, ordered-atomic store)
define void @test4(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test4(
; CHECK-NOT: call void @llvm.memcpy.element.unordered.atomic
; CHECK: store
; CHECK: ret void
bb.nph:
  %Base = alloca i8, i32 10000
  %Dest = alloca i8, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar
  %DestI = getelementptr i8, i8* %Dest, i64 %indvar
  %V = load atomic i8, i8* %I.0.014 unordered, align 1
  store atomic i8 %V, i8* %DestI monotonic, align 1
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation rejection (ordered-atomic load, unordered-atomic store)
define void @test5(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test5(
; CHECK-NOT: call void @llvm.memcpy.element.unordered.atomic
; CHECK: store
; CHECK: ret void
bb.nph:
  %Base = alloca i8, i32 10000
  %Dest = alloca i8, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar
  %DestI = getelementptr i8, i8* %Dest, i64 %indvar
  %V = load atomic i8, i8* %I.0.014 monotonic, align 1
  store atomic i8 %V, i8* %DestI unordered, align 1
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation (atomic load & store) -- element size 2
define void @test6(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test6(
; CHECK: [[Sz:%[0-9]+]] = shl nuw i64 %Size, 1
; CHECK: call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 2 %Dest{{[0-9]*}}, i8* align 2 %Base{{[0-9]*}}, i64 [[Sz]], i32 2)
; CHECK-NOT: store
; CHECK: ret void
bb.nph:
  %Base = alloca i16, i32 10000
  %Dest = alloca i16, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i16, i16* %Base, i64 %indvar
  %DestI = getelementptr i16, i16* %Dest, i64 %indvar
  %V = load atomic i16, i16* %I.0.014 unordered, align 2
  store atomic i16 %V, i16* %DestI unordered, align 2
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation (atomic load & store) -- element size 4
define void @test7(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test7(
; CHECK: [[Sz:%[0-9]+]] = shl nuw i64 %Size, 2
; CHECK: call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 4 %Dest{{[0-9]*}}, i8* align 4 %Base{{[0-9]*}}, i64 [[Sz]], i32 4)
; CHECK-NOT: store
; CHECK: ret void
bb.nph:
  %Base = alloca i32, i32 10000
  %Dest = alloca i32, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i32, i32* %Base, i64 %indvar
  %DestI = getelementptr i32, i32* %Dest, i64 %indvar
  %V = load atomic i32, i32* %I.0.014 unordered, align 4
  store atomic i32 %V, i32* %DestI unordered, align 4
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation (atomic load & store) -- element size 8
define void @test8(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test8(
; CHECK: [[Sz:%[0-9]+]] = shl nuw i64 %Size, 3
; CHECK: call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 8 %Dest{{[0-9]*}}, i8* align 8 %Base{{[0-9]*}}, i64 [[Sz]], i32 8)
; CHECK-NOT: store
; CHECK: ret void
bb.nph:
  %Base = alloca i64, i32 10000
  %Dest = alloca i64, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i64, i64* %Base, i64 %indvar
  %DestI = getelementptr i64, i64* %Dest, i64 %indvar
  %V = load atomic i64, i64* %I.0.014 unordered, align 8
  store atomic i64 %V, i64* %DestI unordered, align 8
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation rejection (atomic load & store) -- element size 16
define void @test9(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test9(
; CHECK: [[Sz:%[0-9]+]] = shl nuw i64 %Size, 4
; CHECK: call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 16 %Dest{{[0-9]*}}, i8* align 16 %Base{{[0-9]*}}, i64 [[Sz]], i32 16)
; CHECK-NOT: store
; CHECK: ret void
bb.nph:
  %Base = alloca i128, i32 10000
  %Dest = alloca i128, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i128, i128* %Base, i64 %indvar
  %DestI = getelementptr i128, i128* %Dest, i64 %indvar
  %V = load atomic i128, i128* %I.0.014 unordered, align 16
  store atomic i128 %V, i128* %DestI unordered, align 16
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

;; memcpy.atomic formation rejection (atomic load & store) -- element size 32
define void @test10(i64 %Size) nounwind ssp {
; CHECK-LABEL: @test10(
; CHECK-NOT: call void @llvm.memcpy.element.unordered.atomic
; CHECK: store
; CHECK: ret void
bb.nph:
  %Base = alloca i256, i32 10000
  %Dest = alloca i256, i32 10000
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i256, i256* %Base, i64 %indvar
  %DestI = getelementptr i256, i256* %Dest, i64 %indvar
  %V = load atomic i256, i256* %I.0.014 unordered, align 32
  store atomic i256 %V, i256* %DestI unordered, align 32
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}



; Make sure that atomic memset doesn't get recognized by mistake
define void @test_nomemset(i8* %Base, i64 %Size) nounwind ssp {
; CHECK-LABEL: @test_nomemset(
; CHECK-NOT: call void @llvm.memset
; CHECK: store
; CHECK: ret void
bb.nph:                                           ; preds = %entry
  br label %for.body

for.body:                                         ; preds = %bb.nph, %for.body
  %indvar = phi i64 [ 0, %bb.nph ], [ %indvar.next, %for.body ]
  %I.0.014 = getelementptr i8, i8* %Base, i64 %indvar
  store atomic i8 0, i8* %I.0.014 unordered, align 1
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, %Size
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret void
}

; Verify that unordered memset_pattern isn't recognized.
; This is a replica of test11_pattern from basic.ll
define void @test_nomemset_pattern(i32* nocapture %P) nounwind ssp {
; CHECK-LABEL: @test_nomemset_pattern(
; CHECK-NEXT: entry:
; CHECK-NOT: bitcast
; CHECK-NOT: memset_pattern
; CHECK: store atomic
; CHECK: ret void
entry:
  br label %for.body

for.body:                                         ; preds = %entry, %for.body
  %indvar = phi i64 [ 0, %entry ], [ %indvar.next, %for.body ]
  %arrayidx = getelementptr i32, i32* %P, i64 %indvar
  store atomic i32 1, i32* %arrayidx unordered, align 4
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, 10000
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body
  ret void
}