vector-promotion.ll 23.7 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625
; RUN: opt < %s -sroa -S | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n8:16:32:64"

%S1 = type { i64, [42 x float] }

define i32 @test1(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @test1(
entry:
	%a = alloca [2 x <4 x i32>]
; CHECK-NOT: alloca

  %a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
  store <4 x i32> %x, <4 x i32>* %a.x
  %a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
  store <4 x i32> %y, <4 x i32>* %a.y
; CHECK-NOT: store

  %a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
  %tmp1 = load i32, i32* %a.tmp1
  %a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
  %tmp2 = load i32, i32* %a.tmp2
  %a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
  %tmp3 = load i32, i32* %a.tmp3
; CHECK-NOT: load
; CHECK:      extractelement <4 x i32> %x, i32 2
; CHECK-NEXT: extractelement <4 x i32> %y, i32 3
; CHECK-NEXT: extractelement <4 x i32> %y, i32 0

  %tmp4 = add i32 %tmp1, %tmp2
  %tmp5 = add i32 %tmp3, %tmp4
  ret i32 %tmp5
; CHECK-NEXT: add
; CHECK-NEXT: add
; CHECK-NEXT: ret
}

define i32 @test2(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @test2(
entry:
	%a = alloca [2 x <4 x i32>]
; CHECK-NOT: alloca

  %a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
  store <4 x i32> %x, <4 x i32>* %a.x
  %a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
  store <4 x i32> %y, <4 x i32>* %a.y
; CHECK-NOT: store

  %a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
  %tmp1 = load i32, i32* %a.tmp1
  %a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
  %tmp2 = load i32, i32* %a.tmp2
  %a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
  %a.tmp3.cast = bitcast i32* %a.tmp3 to <2 x i32>*
  %tmp3.vec = load <2 x i32>, <2 x i32>* %a.tmp3.cast
  %tmp3 = extractelement <2 x i32> %tmp3.vec, i32 0
; CHECK-NOT: load
; CHECK:      %[[extract1:.*]] = extractelement <4 x i32> %x, i32 2
; CHECK-NEXT: %[[extract2:.*]] = extractelement <4 x i32> %y, i32 3
; CHECK-NEXT: %[[extract3:.*]] = shufflevector <4 x i32> %y, <4 x i32> undef, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT: %[[extract4:.*]] = extractelement <2 x i32> %[[extract3]], i32 0

  %tmp4 = add i32 %tmp1, %tmp2
  %tmp5 = add i32 %tmp3, %tmp4
  ret i32 %tmp5
; CHECK-NEXT: %[[sum1:.*]] = add i32 %[[extract1]], %[[extract2]]
; CHECK-NEXT: %[[sum2:.*]] = add i32 %[[extract4]], %[[sum1]]
; CHECK-NEXT: ret i32 %[[sum2]]
}

define i32 @test3(<4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @test3(
entry:
	%a = alloca [2 x <4 x i32>]
; CHECK-NOT: alloca

  %a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
  store <4 x i32> %x, <4 x i32>* %a.x
  %a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
  store <4 x i32> %y, <4 x i32>* %a.y
; CHECK-NOT: store

  %a.y.cast = bitcast <4 x i32>* %a.y to i8*
  call void @llvm.memset.p0i8.i32(i8* %a.y.cast, i8 0, i32 16, i1 false)
; CHECK-NOT: memset

  %a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
  %a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
  call void @llvm.memset.p0i8.i32(i8* %a.tmp1.cast, i8 -1, i32 4, i1 false)
  %tmp1 = load i32, i32* %a.tmp1
  %a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
  %tmp2 = load i32, i32* %a.tmp2
  %a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
  %tmp3 = load i32, i32* %a.tmp3
; CHECK-NOT: load
; CHECK:      %[[insert:.*]] = insertelement <4 x i32> %x, i32 -1, i32 2
; CHECK-NEXT: extractelement <4 x i32> %[[insert]], i32 2
; CHECK-NEXT: extractelement <4 x i32> zeroinitializer, i32 3
; CHECK-NEXT: extractelement <4 x i32> zeroinitializer, i32 0

  %tmp4 = add i32 %tmp1, %tmp2
  %tmp5 = add i32 %tmp3, %tmp4
  ret i32 %tmp5
; CHECK-NEXT: add
; CHECK-NEXT: add
; CHECK-NEXT: ret
}

define i32 @test4(<4 x i32> %x, <4 x i32> %y, <4 x i32>* %z) {
; CHECK-LABEL: @test4(
entry:
	%a = alloca [2 x <4 x i32>]
; CHECK-NOT: alloca

  %a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
  store <4 x i32> %x, <4 x i32>* %a.x
  %a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
  store <4 x i32> %y, <4 x i32>* %a.y
; CHECK-NOT: store

  %a.y.cast = bitcast <4 x i32>* %a.y to i8*
  %z.cast = bitcast <4 x i32>* %z to i8*
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.y.cast, i8* %z.cast, i32 16, i1 false)
; CHECK-NOT: memcpy

  %a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
  %a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
  %z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2
  %z.tmp1.cast = bitcast i32* %z.tmp1 to i8*
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.tmp1.cast, i8* %z.tmp1.cast, i32 4, i1 false)
  %tmp1 = load i32, i32* %a.tmp1
  %a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
  %tmp2 = load i32, i32* %a.tmp2
  %a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
  %tmp3 = load i32, i32* %a.tmp3
; CHECK-NOT: memcpy
; CHECK:      %[[load:.*]] = load <4 x i32>, <4 x i32>* %z
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2
; CHECK-NEXT: %[[element_load:.*]] = load i32, i32* %[[gep]]
; CHECK-NEXT: %[[insert:.*]] = insertelement <4 x i32> %x, i32 %[[element_load]], i32 2
; CHECK-NEXT: extractelement <4 x i32> %[[insert]], i32 2
; CHECK-NEXT: extractelement <4 x i32> %[[load]], i32 3
; CHECK-NEXT: extractelement <4 x i32> %[[load]], i32 0

  %tmp4 = add i32 %tmp1, %tmp2
  %tmp5 = add i32 %tmp3, %tmp4
  ret i32 %tmp5
; CHECK-NEXT: add
; CHECK-NEXT: add
; CHECK-NEXT: ret
}

declare void @llvm.memcpy.p0i8.p1i8.i32(i8* nocapture, i8 addrspace(1)* nocapture, i32, i1) nounwind

; Same as test4 with a different sized address  space pointer source.
define i32 @test4_as1(<4 x i32> %x, <4 x i32> %y, <4 x i32> addrspace(1)* %z) {
; CHECK-LABEL: @test4_as1(
entry:
	%a = alloca [2 x <4 x i32>]
; CHECK-NOT: alloca

  %a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
  store <4 x i32> %x, <4 x i32>* %a.x
  %a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
  store <4 x i32> %y, <4 x i32>* %a.y
; CHECK-NOT: store

  %a.y.cast = bitcast <4 x i32>* %a.y to i8*
  %z.cast = bitcast <4 x i32> addrspace(1)* %z to i8 addrspace(1)*
  call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.y.cast, i8 addrspace(1)* %z.cast, i32 16, i1 false)
; CHECK-NOT: memcpy

  %a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
  %a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
  %z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %z, i16 0, i16 2
  %z.tmp1.cast = bitcast i32 addrspace(1)* %z.tmp1 to i8 addrspace(1)*
  call void @llvm.memcpy.p0i8.p1i8.i32(i8* %a.tmp1.cast, i8 addrspace(1)* %z.tmp1.cast, i32 4, i1 false)
  %tmp1 = load i32, i32* %a.tmp1
  %a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
  %tmp2 = load i32, i32* %a.tmp2
  %a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
  %tmp3 = load i32, i32* %a.tmp3
; CHECK-NOT: memcpy
; CHECK:      %[[load:.*]] = load <4 x i32>, <4 x i32> addrspace(1)* %z
; CHECK-NEXT: %[[gep:.*]] = getelementptr inbounds <4 x i32>, <4 x i32> addrspace(1)* %z, i64 0, i64 2
; CHECK-NEXT: %[[element_load:.*]] = load i32, i32 addrspace(1)* %[[gep]]
; CHECK-NEXT: %[[insert:.*]] = insertelement <4 x i32> %x, i32 %[[element_load]], i32 2
; CHECK-NEXT: extractelement <4 x i32> %[[insert]], i32 2
; CHECK-NEXT: extractelement <4 x i32> %[[load]], i32 3
; CHECK-NEXT: extractelement <4 x i32> %[[load]], i32 0

  %tmp4 = add i32 %tmp1, %tmp2
  %tmp5 = add i32 %tmp3, %tmp4
  ret i32 %tmp5
; CHECK-NEXT: add
; CHECK-NEXT: add
; CHECK-NEXT: ret
}

define i32 @test5(<4 x i32> %x, <4 x i32> %y, <4 x i32>* %z) {
; CHECK-LABEL: @test5(
; The same as the above, but with reversed source and destination for the
; element memcpy, and a self copy.
entry:
	%a = alloca [2 x <4 x i32>]
; CHECK-NOT: alloca

  %a.x = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0
  store <4 x i32> %x, <4 x i32>* %a.x
  %a.y = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1
  store <4 x i32> %y, <4 x i32>* %a.y
; CHECK-NOT: store

  %a.y.cast = bitcast <4 x i32>* %a.y to i8*
  %a.x.cast = bitcast <4 x i32>* %a.x to i8*
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.x.cast, i8* %a.y.cast, i32 16, i1 false)
; CHECK-NOT: memcpy

  %a.tmp1 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 0, i64 2
  %a.tmp1.cast = bitcast i32* %a.tmp1 to i8*
  %z.tmp1 = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2
  %z.tmp1.cast = bitcast i32* %z.tmp1 to i8*
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %z.tmp1.cast, i8* %a.tmp1.cast, i32 4, i1 false)
  %tmp1 = load i32, i32* %a.tmp1
  %a.tmp2 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 3
  %tmp2 = load i32, i32* %a.tmp2
  %a.tmp3 = getelementptr inbounds [2 x <4 x i32>], [2 x <4 x i32>]* %a, i64 0, i64 1, i64 0
  %tmp3 = load i32, i32* %a.tmp3
; CHECK-NOT: memcpy
; CHECK:      %[[gep:.*]] = getelementptr inbounds <4 x i32>, <4 x i32>* %z, i64 0, i64 2
; CHECK-NEXT: %[[extract:.*]] = extractelement <4 x i32> %y, i32 2
; CHECK-NEXT: store i32 %[[extract]], i32* %[[gep]]
; CHECK-NEXT: extractelement <4 x i32> %y, i32 2
; CHECK-NEXT: extractelement <4 x i32> %y, i32 3
; CHECK-NEXT: extractelement <4 x i32> %y, i32 0

  %tmp4 = add i32 %tmp1, %tmp2
  %tmp5 = add i32 %tmp3, %tmp4
  ret i32 %tmp5
; CHECK-NEXT: add
; CHECK-NEXT: add
; CHECK-NEXT: ret
}

declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i1) nounwind
declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i1) nounwind

define i64 @test6(<4 x i64> %x, <4 x i64> %y, i64 %n) {
; CHECK-LABEL: @test6(
; The old scalarrepl pass would wrongly drop the store to the second alloca.
; PR13254
  %tmp = alloca { <4 x i64>, <4 x i64> }
  %p0 = getelementptr inbounds { <4 x i64>, <4 x i64> }, { <4 x i64>, <4 x i64> }* %tmp, i32 0, i32 0
  store <4 x i64> %x, <4 x i64>* %p0
; CHECK: store <4 x i64> %x,
  %p1 = getelementptr inbounds { <4 x i64>, <4 x i64> }, { <4 x i64>, <4 x i64> }* %tmp, i32 0, i32 1
  store <4 x i64> %y, <4 x i64>* %p1
; CHECK: store <4 x i64> %y,
  %addr = getelementptr inbounds { <4 x i64>, <4 x i64> }, { <4 x i64>, <4 x i64> }* %tmp, i32 0, i32 0, i64 %n
  %res = load i64, i64* %addr, align 4
  ret i64 %res
}

define <4 x i32> @test_subvec_store() {
; CHECK-LABEL: @test_subvec_store(
entry:
  %a = alloca <4 x i32>
; CHECK-NOT: alloca

  %a.gep0 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 0
  %a.cast0 = bitcast i32* %a.gep0 to <2 x i32>*
  store <2 x i32> <i32 0, i32 0>, <2 x i32>* %a.cast0
; CHECK-NOT: store
; CHECK:     select <4 x i1> <i1 true, i1 true, i1 false, i1 false> 

  %a.gep1 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 1
  %a.cast1 = bitcast i32* %a.gep1 to <2 x i32>*
  store <2 x i32> <i32 1, i32 1>, <2 x i32>* %a.cast1
; CHECK-NEXT: select <4 x i1> <i1 false, i1 true, i1 true, i1 false>

  %a.gep2 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 2
  %a.cast2 = bitcast i32* %a.gep2 to <2 x i32>*
  store <2 x i32> <i32 2, i32 2>, <2 x i32>* %a.cast2
; CHECK-NEXT: select <4 x i1> <i1 false, i1 false, i1 true, i1 true>

  %a.gep3 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 3
  store i32 3, i32* %a.gep3
; CHECK-NEXT: insertelement <4 x i32>

  %ret = load <4 x i32>, <4 x i32>* %a

  ret <4 x i32> %ret
; CHECK-NEXT: ret <4 x i32> 
}

define <4 x i32> @test_subvec_load() {
; CHECK-LABEL: @test_subvec_load(
entry:
  %a = alloca <4 x i32>
; CHECK-NOT: alloca
  store <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32>* %a
; CHECK-NOT: store

  %a.gep0 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 0
  %a.cast0 = bitcast i32* %a.gep0 to <2 x i32>*
  %first = load <2 x i32>, <2 x i32>* %a.cast0
; CHECK-NOT: load
; CHECK:      %[[extract1:.*]] = shufflevector <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32> undef, <2 x i32> <i32 0, i32 1>

  %a.gep1 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 1
  %a.cast1 = bitcast i32* %a.gep1 to <2 x i32>*
  %second = load <2 x i32>, <2 x i32>* %a.cast1
; CHECK-NEXT: %[[extract2:.*]] = shufflevector <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32> undef, <2 x i32> <i32 1, i32 2>

  %a.gep2 = getelementptr <4 x i32>, <4 x i32>* %a, i32 0, i32 2
  %a.cast2 = bitcast i32* %a.gep2 to <2 x i32>*
  %third = load <2 x i32>, <2 x i32>* %a.cast2
; CHECK-NEXT: %[[extract3:.*]] = shufflevector <4 x i32> <i32 0, i32 1, i32 2, i32 3>, <4 x i32> undef, <2 x i32> <i32 2, i32 3>

  %tmp = shufflevector <2 x i32> %first, <2 x i32> %second, <2 x i32> <i32 0, i32 2>
  %ret = shufflevector <2 x i32> %tmp, <2 x i32> %third, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: %[[tmp:.*]] = shufflevector <2 x i32> %[[extract1]], <2 x i32> %[[extract2]], <2 x i32> <i32 0, i32 2>
; CHECK-NEXT: %[[ret:.*]] = shufflevector <2 x i32> %[[tmp]], <2 x i32> %[[extract3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>

  ret <4 x i32> %ret
; CHECK-NEXT: ret <4 x i32> %[[ret]]
}

declare void @llvm.memset.p0i32.i32(i32* nocapture, i32, i32, i1) nounwind

define <4 x float> @test_subvec_memset() {
; CHECK-LABEL: @test_subvec_memset(
entry:
  %a = alloca <4 x float>
; CHECK-NOT: alloca

  %a.gep0 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 0
  %a.cast0 = bitcast float* %a.gep0 to i8*
  call void @llvm.memset.p0i8.i32(i8* %a.cast0, i8 0, i32 8, i1 false)
; CHECK-NOT: store
; CHECK: select <4 x i1> <i1 true, i1 true, i1 false, i1 false>

  %a.gep1 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 1
  %a.cast1 = bitcast float* %a.gep1 to i8*
  call void @llvm.memset.p0i8.i32(i8* %a.cast1, i8 1, i32 8, i1 false)
; CHECK-NEXT: select <4 x i1> <i1 false, i1 true, i1 true, i1 false>

  %a.gep2 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 2
  %a.cast2 = bitcast float* %a.gep2 to i8*
  call void @llvm.memset.p0i8.i32(i8* %a.cast2, i8 3, i32 8, i1 false)
; CHECK-NEXT: select <4 x i1> <i1 false, i1 false, i1 true, i1 true>

  %a.gep3 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 3
  %a.cast3 = bitcast float* %a.gep3 to i8*
  call void @llvm.memset.p0i8.i32(i8* %a.cast3, i8 7, i32 4, i1 false)
; CHECK-NEXT: insertelement <4 x float> 

  %ret = load <4 x float>, <4 x float>* %a

  ret <4 x float> %ret
; CHECK-NEXT: ret <4 x float> 
}

define <4 x float> @test_subvec_memcpy(i8* %x, i8* %y, i8* %z, i8* %f, i8* %out) {
; CHECK-LABEL: @test_subvec_memcpy(
entry:
  %a = alloca <4 x float>
; CHECK-NOT: alloca

  %a.gep0 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 0
  %a.cast0 = bitcast float* %a.gep0 to i8*
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast0, i8* %x, i32 8, i1 false)
; CHECK:      %[[xptr:.*]] = bitcast i8* %x to <2 x float>*
; CHECK-NEXT: %[[x:.*]] = load <2 x float>, <2 x float>* %[[xptr]]
; CHECK-NEXT: %[[expand_x:.*]] = shufflevector <2 x float> %[[x]], <2 x float> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef>
; CHECK-NEXT: select <4 x i1> <i1 true, i1 true, i1 false, i1 false>  

  %a.gep1 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 1
  %a.cast1 = bitcast float* %a.gep1 to i8*
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast1, i8* %y, i32 8, i1 false)
; CHECK-NEXT: %[[yptr:.*]] = bitcast i8* %y to <2 x float>*
; CHECK-NEXT: %[[y:.*]] = load <2 x float>, <2 x float>* %[[yptr]]
; CHECK-NEXT: %[[expand_y:.*]] = shufflevector <2 x float> %[[y]], <2 x float> undef, <4 x i32> <i32 undef, i32 0, i32 1, i32 undef>
; CHECK-NEXT: select <4 x i1> <i1 false, i1 true, i1 true, i1 false>

  %a.gep2 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 2
  %a.cast2 = bitcast float* %a.gep2 to i8*
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast2, i8* %z, i32 8, i1 false)
; CHECK-NEXT: %[[zptr:.*]] = bitcast i8* %z to <2 x float>*
; CHECK-NEXT: %[[z:.*]] = load <2 x float>, <2 x float>* %[[zptr]]
; CHECK-NEXT: %[[expand_z:.*]] = shufflevector <2 x float> %[[z]], <2 x float> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 1>
; CHECK-NEXT: select <4 x i1> <i1 false, i1 false, i1 true, i1 true>

  %a.gep3 = getelementptr <4 x float>, <4 x float>* %a, i32 0, i32 3
  %a.cast3 = bitcast float* %a.gep3 to i8*
  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %a.cast3, i8* %f, i32 4, i1 false)
; CHECK-NEXT: %[[fptr:.*]] = bitcast i8* %f to float*
; CHECK-NEXT: %[[f:.*]] = load float, float* %[[fptr]]
; CHECK-NEXT: %[[insert_f:.*]] = insertelement <4 x float> 

  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %out, i8* %a.cast2, i32 8, i1 false)
; CHECK-NEXT: %[[outptr:.*]] = bitcast i8* %out to <2 x float>*
; CHECK-NEXT: %[[extract_out:.*]] = shufflevector <4 x float> %[[insert_f]], <4 x float> undef, <2 x i32> <i32 2, i32 3>
; CHECK-NEXT: store <2 x float> %[[extract_out]], <2 x float>* %[[outptr]]

  %ret = load <4 x float>, <4 x float>* %a

  ret <4 x float> %ret
; CHECK-NEXT: ret <4 x float> %[[insert_f]]
}

define i32 @PR14212() {
; CHECK-LABEL: @PR14212(
; This caused a crash when "splitting" the load of the i32 in order to promote
; the store of <3 x i8> properly. Heavily reduced from an OpenCL test case.
entry:
  %retval = alloca <3 x i8>, align 4
; CHECK-NOT: alloca

  store <3 x i8> undef, <3 x i8>* %retval, align 4
  %cast = bitcast <3 x i8>* %retval to i32*
  %load = load i32, i32* %cast, align 4
  ret i32 %load
; CHECK: ret i32
}

define <2 x i8> @PR14349.1(i32 %x) {
; CHECK: @PR14349.1
; The first testcase for broken SROA rewriting of split integer loads and
; stores due to smaller vector loads and stores. This particular test ensures
; that we can rewrite a split store of an integer to a store of a vector.
entry:
  %a = alloca i32
; CHECK-NOT: alloca

  store i32 %x, i32* %a
; CHECK-NOT: store

  %cast = bitcast i32* %a to <2 x i8>*
  %vec = load <2 x i8>, <2 x i8>* %cast
; CHECK-NOT: load

  ret <2 x i8> %vec
; CHECK: %[[trunc:.*]] = trunc i32 %x to i16
; CHECK: %[[cast:.*]] = bitcast i16 %[[trunc]] to <2 x i8>
; CHECK: ret <2 x i8> %[[cast]]
}

define i32 @PR14349.2(<2 x i8> %x) {
; CHECK: @PR14349.2
; The first testcase for broken SROA rewriting of split integer loads and
; stores due to smaller vector loads and stores. This particular test ensures
; that we can rewrite a split load of an integer to a load of a vector.
entry:
  %a = alloca i32
; CHECK-NOT: alloca

  %cast = bitcast i32* %a to <2 x i8>*
  store <2 x i8> %x, <2 x i8>* %cast
; CHECK-NOT: store

  %int = load i32, i32* %a
; CHECK-NOT: load

  ret i32 %int
; CHECK: %[[cast:.*]] = bitcast <2 x i8> %x to i16
; CHECK: %[[trunc:.*]] = zext i16 %[[cast]] to i32
; CHECK: %[[insert:.*]] = or i32 %{{.*}}, %[[trunc]]
; CHECK: ret i32 %[[insert]]
}

define i32 @test7(<2 x i32> %x, <2 x i32> %y) {
; Test that we can promote to vectors when the alloca doesn't mention any vector types.
; CHECK-LABEL: @test7(
entry:
	%a = alloca [2 x i64]
  %a.cast = bitcast [2 x i64]* %a to [2 x <2 x i32>]*
; CHECK-NOT: alloca

  %a.x = getelementptr inbounds [2 x <2 x i32>], [2 x <2 x i32>]* %a.cast, i64 0, i64 0
  store <2 x i32> %x, <2 x i32>* %a.x
  %a.y = getelementptr inbounds [2 x <2 x i32>], [2 x <2 x i32>]* %a.cast, i64 0, i64 1
  store <2 x i32> %y, <2 x i32>* %a.y
; CHECK-NOT: store

  %a.tmp1 = getelementptr inbounds [2 x <2 x i32>], [2 x <2 x i32>]* %a.cast, i64 0, i64 0, i64 1
  %tmp1 = load i32, i32* %a.tmp1
  %a.tmp2 = getelementptr inbounds [2 x <2 x i32>], [2 x <2 x i32>]* %a.cast, i64 0, i64 1, i64 1
  %tmp2 = load i32, i32* %a.tmp2
  %a.tmp3 = getelementptr inbounds [2 x <2 x i32>], [2 x <2 x i32>]* %a.cast, i64 0, i64 1, i64 0
  %tmp3 = load i32, i32* %a.tmp3
; CHECK-NOT: load
; CHECK:      extractelement <2 x i32> %x, i32 1
; CHECK-NEXT: extractelement <2 x i32> %y, i32 1
; CHECK-NEXT: extractelement <2 x i32> %y, i32 0

  %tmp4 = add i32 %tmp1, %tmp2
  %tmp5 = add i32 %tmp3, %tmp4
  ret i32 %tmp5
; CHECK-NEXT: add
; CHECK-NEXT: add
; CHECK-NEXT: ret
}

define i32 @test8(<2 x i32> %x) {
; Ensure that we can promote an alloca that doesn't mention a vector type based
; on a single store with a vector type.
; CHECK-LABEL: @test8(
entry:
	%a = alloca i64
  %a.vec = bitcast i64* %a to <2 x i32>*
  %a.i32 = bitcast i64* %a to i32*
; CHECK-NOT: alloca

  store <2 x i32> %x, <2 x i32>* %a.vec
; CHECK-NOT: store

  %tmp1 = load i32, i32* %a.i32
  %a.tmp2 = getelementptr inbounds i32, i32* %a.i32, i64 1
  %tmp2 = load i32, i32* %a.tmp2
; CHECK-NOT: load
; CHECK:      extractelement <2 x i32> %x, i32 0
; CHECK-NEXT: extractelement <2 x i32> %x, i32 1

  %tmp4 = add i32 %tmp1, %tmp2
  ret i32 %tmp4
; CHECK-NEXT: add
; CHECK-NEXT: ret
}

define <2 x i32> @test9(i32 %x, i32 %y) {
; Ensure that we can promote an alloca that doesn't mention a vector type based
; on a single load with a vector type.
; CHECK-LABEL: @test9(
entry:
	%a = alloca i64
  %a.vec = bitcast i64* %a to <2 x i32>*
  %a.i32 = bitcast i64* %a to i32*
; CHECK-NOT: alloca

  store i32 %x, i32* %a.i32
  %a.tmp2 = getelementptr inbounds i32, i32* %a.i32, i64 1
  store i32 %y, i32* %a.tmp2
; CHECK-NOT: store
; CHECK:      %[[V1:.*]] = insertelement <2 x i32> undef, i32 %x, i32 0
; CHECK-NEXT: %[[V2:.*]] = insertelement <2 x i32> %[[V1]], i32 %y, i32 1

  %result = load <2 x i32>, <2 x i32>* %a.vec
; CHECK-NOT:  load

  ret <2 x i32> %result
; CHECK-NEXT: ret <2 x i32> %[[V2]]
}

define <2 x i32> @test10(<4 x i16> %x, i32 %y) {
; If there are multiple different vector types used, we should select the one
; with the widest elements.
; CHECK-LABEL: @test10(
entry:
	%a = alloca i64
  %a.vec1 = bitcast i64* %a to <2 x i32>*
  %a.vec2 = bitcast i64* %a to <4 x i16>*
  %a.i32 = bitcast i64* %a to i32*
; CHECK-NOT: alloca

  store <4 x i16> %x, <4 x i16>* %a.vec2
  %a.tmp2 = getelementptr inbounds i32, i32* %a.i32, i64 1
  store i32 %y, i32* %a.tmp2
; CHECK-NOT: store
; CHECK:      %[[V1:.*]] = bitcast <4 x i16> %x to <2 x i32>
; CHECK-NEXT: %[[V2:.*]] = insertelement <2 x i32> %[[V1]], i32 %y, i32 1

  %result = load <2 x i32>, <2 x i32>* %a.vec1
; CHECK-NOT:  load

  ret <2 x i32> %result
; CHECK-NEXT: ret <2 x i32> %[[V2]]
}

define <2 x float> @test11(<4 x i16> %x, i32 %y) {
; If there are multiple different element types for different vector types,
; pick the integer types. This isn't really important, but seems like the best
; heuristic for making a deterministic decision.
; CHECK-LABEL: @test11(
entry:
	%a = alloca i64
  %a.vec1 = bitcast i64* %a to <2 x float>*
  %a.vec2 = bitcast i64* %a to <4 x i16>*
  %a.i32 = bitcast i64* %a to i32*
; CHECK-NOT: alloca

  store <4 x i16> %x, <4 x i16>* %a.vec2
  %a.tmp2 = getelementptr inbounds i32, i32* %a.i32, i64 1
  store i32 %y, i32* %a.tmp2
; CHECK-NOT: store
; CHECK:      %[[V1:.*]] = bitcast i32 %y to <2 x i16>
; CHECK-NEXT: %[[V2:.*]] = shufflevector <2 x i16> %[[V1]], <2 x i16> undef, <4 x i32> <i32 undef, i32 undef, i32 0, i32 1>
; CHECK-NEXT: %[[V3:.*]] = select <4 x i1> <i1 false, i1 false, i1 true, i1 true>, <4 x i16> %[[V2]], <4 x i16> %x
; CHECK-NEXT: %[[V4:.*]] = bitcast <4 x i16> %[[V3]] to <2 x float>

  %result = load <2 x float>, <2 x float>* %a.vec1
; CHECK-NOT:  load

  ret <2 x float> %result
; CHECK-NEXT: ret <2 x float> %[[V4]]
}

define <4 x float> @test12() {
; CHECK-LABEL: @test12(
  %a = alloca <3 x i32>, align 16
; CHECK-NOT: alloca

  %cast1 = bitcast <3 x i32>* %a to <4 x i32>*
  store <4 x i32> undef, <4 x i32>* %cast1, align 16
; CHECK-NOT: store

  %cast2 = bitcast <3 x i32>* %a to <3 x float>*
  %cast3 = bitcast <3 x float>* %cast2 to <4 x float>*
  %vec = load <4 x float>, <4 x float>* %cast3
; CHECK-NOT: load

; CHECK:      %[[ret:.*]] = bitcast <4 x i32> undef to <4 x float>
; CHECK-NEXT: ret <4 x float> %[[ret]]
  ret <4 x float> %vec
}