[LoopVectorize] Extract the last lane from a uniform store

[kmclaughlin]

Summary

Changes VPReplicateRecipe to extract the last lane from an unconditional,
uniform store instruction. collectLoopUniforms will also add stores to
the list of uniform instructions where Legal->isUniformMemOp is true.

setCostBasedWideningDecision now sets the widening decision for
all uniform memory ops to Scalarize, where previously GatherScatter
may have been chosen for scalable stores.

This fixes an assert ("Cannot yet scalarize uniform stores") in
setCostBasedWideningDecision when we have a loop containing a
uniform i1 store and a scalable VF, which we cannot create a scatter for.

[sdesmalen]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

7479–7480

This condition is always true, because it is enclosed by if (Legal->isUniformMemOp(I))

9821

This code needs a comment with rationale for extracting the last lane.

9822

While it is a concrete problem for scalable vectors, I don't think this is necessarily specific to scalable vectors and so we may want to do the same thing for fixed-width vectors. I'd expect other passes to remove the redundant scalar stores that are currently created, but it would be nice if those would not be generated in the first place.

9822

I would expect isScalarAfterVectorization to be set to true when the memory address is uniform and that to be used instead of '!IsUniform && isUniformMemOp(*I). Can you check whether this can be used instead?

[kmclaughlin]

• Removed redundant Legal->isUniformMemOp(I) check from setCostBasedWideningDecision
• Added a comment to VPReplicateRecipe::execute
• Removed the State.VF.isScalable() check from VPReplicateRecipe::execute & updated the tests affected by this change. Also added a test of uniform stores for fixed-width.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9822

Hi @sdesmalen, I've removed State.VF.isScalable() and added a new test for fixed-width to LoopVectorize/uniform-store.ll. There were also a few existing tests with uniform stores affected by this change which have been updated.

9822

I tried removing !IsUniform && isUniformMemOp(*I) and replacing it with isScalarAfterVectorization, though this returns false for the instruction here and we continue on to hit the "Can't scalarize a scalable vector" assert below.

[kmclaughlin]

• Removed the uniform-store.ll test added in the previous revision.

[kmclaughlin]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9822

@sdesmalen I think you're right that isScalarAfterVectorization should be true for the store instruction and I've created D113034 (which changes collectLoopUniforms to also consider uniform stores) to address this.
I think we still need to check isUniformMemOp here though, since Scalars collects more than just uniform instructions and we only want to generate the last lane for uniform stores.

[fhahn]

I think the title needs updating after the latest update (remove SVE).

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9822

If D113034 would be landed first, shouldn't IsUniform be set correctly? Ideally the uniform information should be explicit in the recipe and Legal should not be accessed during codegen.

[kmclaughlin]

• Merged with D113034, which makes changes to collectLoopUniforms to collect uniform store instructions.

[kmclaughlin]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9822

Hi @fhahn, I don't think D113034 could be landed first since it requires changes from this patch to generate the last lane for stores? Since these patches are closely related I've merged them here so that I don't need to access Legal from VPReplicateRecipe.

[david-arm]

The changes look good to me @kmclaughlin! I'll look through the remaining non-aarch64 tests later today. I had a couple of minor comments so far ...

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

9824

This change looks sensible to me, since I think we mark unrolled scalar stores as uniform.

llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-store.ll

29

Perhaps it's worth deleting the CHECK lines from middle.block onwards as they don't add much value?

llvm/test/Transforms/LoopVectorize/AArch64/sve-uniform-store.ll

5

I wonder if it's perhaps worth moving these tests into sve-inv-store.ll, since they're testing the same thing?

[david-arm]

llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll

85

Hi @kmclaughlin, I don't think this looks right sadly. I wonder if now we're marking the store as uniform that you've exposed an existing bug in collectLoopUniforms or somewhere else like handleReplication? It looks like we're also now treating the the load as uniform, which is wrong in this case because we still want to do the vector load and store out the last lane. I'd expected something like:

[[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP22]], align 4
[[TMP23:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], <i32 1, i32 1, i32 1, i32 1>
[[TMP27:%.*]] = extractelement <4 x i32> [[TMP23]], i32 3
store i32 [[TMP27]], i32* [[ARRAYIDX7_US]], align 4

[fhahn]

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

5480

Unfortunately this is incorrect now. The worklist currently relies on instructions only demanding the first lane, and this is used to propagate this property later on, using: if all users of an operand demand the first lane only, the operand itself also only needs to compute the first lane. I added a clarifying comment in b4992dbb21ff9159285ae0aec73f3d760344b0e5

Adding stores violates that. You should probably be able to work around that by adding them to Uniforms without adding them to the worklist. It might be worth calling out that entries in Uniforms may demand the first or last lane.

[kmclaughlin]

• Add store instructions to the Uniforms list in collectLoopUniforms, instead of the worklist. Added more comments to clarify that instructions in Uniforms may demand the first or last lane.
• Moved the new tests in sve-uniform-store.ll into sve-inv-store.ll.
• Removed the CHECK lines from middle.block from @inv_store_i16

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

5480

Thank you for adding a comment to addToWorklistIfAllowed, @fhahn. I've changed this so that store instructions are only added to Uniforms as suggested and added some comments which I hope makes this clear.

llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll

85

Thanks @david-arm, the load instruction was incorrectly being marked as uniform here. I think now that I've changed collectLoopUniforms so that stores are not added to the worklist, the output of this test looks as expected?

[david-arm]

LGTM! It looks like you've addressed all the review comments here. Thanks @kmclaughlin!

[fhahn]

LGTM, thanks!

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

5483

nit: perhaps throw in an only (e.g. we instead add these to Uniforms only). Otherwise it may sound like the other instructions won't get added to Uniforms, which they will eventually.

[sdesmalen]

Nice improvement @kmclaughlin, thanks for addressing my comments.

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

5481–5482

nit: Should the comment on line 5443 be updated?

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

void LoopVectorizationCostModel::collectLoopUniforms(ElementCount VF) {
   if (Cmp && TheLoop->contains(Cmp) && Cmp->hasOneUse())
     addToWorklistIfAllowed(Cmp);
 
   auto isUniformDecision = [&](Instruction *I, ElementCount VF) {
     InstWidening WideningDecision = getWideningDecision(I, VF);
     assert(WideningDecision != CM_Unknown &&
            "Widening decision should be ready at this moment");
 
-    // A uniform memory op is itself uniform.  We exclude uniform stores
-    // here as they demand the last lane, not the first one.
-    if (isa<LoadInst>(I) && Legal->isUniformMemOp(*I)) {
+    // A uniform memory op is itself uniform.
+    if (Legal->isUniformMemOp(*I)) {
       assert(WideningDecision == CM_Scalarize);
       return true;
     }
 
     return (WideningDecision == CM_Widen ||
             WideningDecision == CM_Widen_Reverse ||
             WideningDecision == CM_Interleave);
   };
for (auto &I : *BB) {
         continue;
       }
 
       // If there's no pointer operand, there's nothing to do.
       auto *Ptr = getLoadStorePointerOperand(&I);
       if (!Ptr)
         continue;
 
-      // A uniform memory op is itself uniform.  We exclude uniform stores
-      // here as they demand the last lane, not the first one.
-      if (isa<LoadInst>(I) && Legal->isUniformMemOp(I))
+      // A uniform memory op is itself uniform.
+      if (Legal->isUniformMemOp(I))
         addToWorklistIfAllowed(&I);
 
       if (isUniformDecision(&I, VF)) {
         assert(isVectorizedMemAccessUse(&I, Ptr) && "consistency check");
         HasUniformUse.insert(Ptr);
       }
     }
 
   // Add to the worklist any operands which have *only* uniform (e.g. lane 0
   // demanding) users.  Since loops are assumed to be in LCSSA form, this
   // disallows uses outside the loop as well.
for (Instruction &I : *BB) {
       // invariant-store-vectorization.ll).
       if (isa<StoreInst>(&I) && isScalarWithPredication(&I))
         NumPredStores++;
 
       if (Legal->isUniformMemOp(I)) {
         // TODO: Avoid replicating loads and stores instead of
         // relying on instcombine to remove them.
         // Load: Scalar load + broadcast
         // Store: Scalar store + isLoopInvariantStoreValue ? 0 : extract
-        InstructionCost Cost;
-        if (isa<StoreInst>(&I) && VF.isScalable() &&
-            isLegalGatherOrScatter(&I)) {
-          Cost = getGatherScatterCost(&I, VF);
-          setWideningDecision(&I, VF, CM_GatherScatter, Cost);
-        } else {
-          assert((isa<LoadInst>(&I) || !VF.isScalable()) &&
-                 "Cannot yet scalarize uniform stores");
-          Cost = getUniformMemOpCost(&I, VF);
-          setWideningDecision(&I, VF, CM_Scalarize, Cost);
-        }
+        InstructionCost Cost = getUniformMemOpCost(&I, VF);
         continue;
       }
 
       // We assume that widening is the best solution when possible.
       if (memoryInstructionCanBeWidened(&I, VF)) {
         InstructionCost Cost = getConsecutiveMemOpCost(&I, VF);
         int ConsecutiveStride = Legal->isConsecutivePtr(
             getLoadStoreType(&I), getLoadStorePointerOperand(&I));
if (AlsoPack && State.VF.isVector()) {
             VectorType::get(getUnderlyingValue()->getType(), State.VF));
         State.set(this, Poison, State.Instance->Part);
       }
       State.ILV->packScalarIntoVectorValue(this, *State.Instance, State);
     }
     return;
   }
 
+  // If the instruction is a store to a uniform address, we only need to
+  // generate the last lane for the last UF part.
+  Instruction *I = getUnderlyingInstr();
+  if (State.VF.isVector() && IsUniform && isa<StoreInst>(I)) {
+    VPLane Lane = VPLane::getLastLaneForVF(State.VF);
+    State.ILV->scalarizeInstruction(
+        I, this, *this, VPIteration(State.UF - 1, Lane), IsPredicated, State);
+    return;
+  }
+
   // Generate scalar instances for all VF lanes of all UF parts, unless the
   // instruction is uniform inwhich case generate only the first lane for each
   // of the UF parts.
   unsigned EndLane = IsUniform ? 1 : State.VF.getKnownMinValue();
   assert((!State.VF.isScalable() || IsUniform) &&
          "Can't scalarize a scalable vector");
   for (unsigned Part = 0; Part < State.UF; ++Part)
     for (unsigned Lane = 0; Lane < EndLane; ++Lane)
-      State.ILV->scalarizeInstruction(getUnderlyingInstr(), this, *this,
-                                      VPIteration(Part, Lane), IsPredicated,
-                                      State);
+      State.ILV->scalarizeInstruction(I, this, *this, VPIteration(Part, Lane),
+                                      IsPredicated, State);
 }
 
 void VPBranchOnMaskRecipe::execute(VPTransformState &State) {
   assert(State.Instance && "Branch on Mask works only on single instance.");
 
   unsigned Part = State.Instance->Part;
   unsigned Lane = State.Instance->Lane.getKnownLane();
 

llvm/test/Transforms/LoopVectorize/AArch64/sve-inv-store.ll

 ; RUN: opt -loop-vectorize -scalable-vectorization=on -S < %s | FileCheck %s
 
 target triple = "aarch64-unknown-linux-gnu"
 
 define void @inv_store_i16(i16* noalias %dst, i16* noalias readonly %src, i64 %N) #0 {
 ; CHECK-LABEL: @inv_store_i16(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N:%.*]], [[TMP1]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
-; CHECK:         %[[TMP1:.*]] = insertelement <vscale x 4 x i16*> poison, i16* %dst, i32 0
-; CHECK-NEXT:    %[[SPLAT_PTRS:.*]] = shufflevector <vscale x 4 x i16*> %[[TMP1]], <vscale x 4 x i16*> poison, <vscale x 4 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[N]], [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
-; CHECK:         %[[VECLOAD:.*]] = load <vscale x 4 x i16>, <vscale x 4 x i16>* %{{.*}}, align 2
-; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i16.nxv4p0i16(<vscale x 4 x i16> %[[VECLOAD]], <vscale x 4 x i16*> %[[SPLAT_PTRS]], i32 2
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i16, i16* [[SRC:%.*]], i64 [[TMP4]]
+; CHECK-NEXT:    [[TMP6:%.*]] = load i16, i16* [[TMP5]], align 2
+; CHECK-NEXT:    store i16 [[TMP6]], i16* [[DST:%.*]], align 2
+; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP8]]
+; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       middle.block:
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_INC24:%.*]], label [[SCALAR_PH]]
+; CHECK:       scalar.ph:
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    br label [[FOR_BODY14:%.*]]
+; CHECK:       for.body14:
+; CHECK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY14]] ]
+; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i16, i16* [[SRC]], i64 [[INDVARS_IV]]
+; CHECK-NEXT:    [[LD:%.*]] = load i16, i16* [[ARRAYIDX]], align 2
+; CHECK-NEXT:    store i16 [[LD]], i16* [[DST]], align 2
+; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], [[N]]
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_INC24]], label [[FOR_BODY14]], !llvm.loop [[LOOP3:![0-9]+]]
+; CHECK:       for.inc24:
+; CHECK-NEXT:    ret void
+;
 entry:
   br label %for.body14
 
 for.body14:                                       ; preds = %for.body14, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body14 ]
   %arrayidx = getelementptr inbounds i16, i16* %src, i64 %indvars.iv
   %ld = load i16, i16* %arrayidx
   store i16 %ld, i16* %dst, align 2

llvm/test/Transforms/LoopVectorize/AArch64/sve-uniform-store.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -loop-vectorize -scalable-vectorization=preferred -mattr=+sve -S < %s | FileCheck %s
+target triple = "aarch64-unknown-linux-gnu"
+
+define void @uniform_store_i1(i1* noalias %dst, i64* noalias %start, i64 %N) {
+; CHECK-LABEL: @uniform_store_i1(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[N:%.*]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP2:%.*]] = mul i64 [[TMP1]], 4
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], [[TMP2]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], [[TMP4]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
+; CHECK-NEXT:    [[IND_END:%.*]] = getelementptr i64, i64* [[START:%.*]], i64 [[N_VEC]]
+; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i64, i64* [[START]], i64 [[TMP5]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP7:%.*]] = mul i64 [[TMP6]], 2
+; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[TMP7]], 0
+; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], [[TMP8]]
+; CHECK-NEXT:    [[NEXT_GEP2:%.*]] = getelementptr i64, i64* [[START]], i64 [[TMP9]]
+; CHECK-NEXT:    [[TMP10:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP11:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP12:%.*]] = mul i64 [[TMP11]], 2
+; CHECK-NEXT:    [[TMP13:%.*]] = add i64 [[TMP12]], 0
+; CHECK-NEXT:    [[TMP14:%.*]] = mul i64 [[TMP13]], 1
+; CHECK-NEXT:    [[TMP15:%.*]] = add i64 [[INDEX]], [[TMP14]]
+; CHECK-NEXT:    [[TMP16:%.*]] = getelementptr i64, i64* [[NEXT_GEP]], i32 0
+; CHECK-NEXT:    [[TMP17:%.*]] = bitcast i64* [[TMP16]] to <vscale x 2 x i64>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, <vscale x 2 x i64>* [[TMP17]], align 4
+; CHECK-NEXT:    [[TMP18:%.*]] = call i32 @llvm.vscale.i32()
+; CHECK-NEXT:    [[TMP19:%.*]] = mul i32 [[TMP18]], 2
+; CHECK-NEXT:    [[TMP20:%.*]] = getelementptr i64, i64* [[NEXT_GEP]], i32 [[TMP19]]
+; CHECK-NEXT:    [[TMP21:%.*]] = bitcast i64* [[TMP20]] to <vscale x 2 x i64>*
+; CHECK-NEXT:    [[WIDE_LOAD3:%.*]] = load <vscale x 2 x i64>, <vscale x 2 x i64>* [[TMP21]], align 4
+; CHECK-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i64, i64* [[NEXT_GEP]], i64 1
+; CHECK-NEXT:    [[TMP23:%.*]] = getelementptr inbounds i64, i64* [[NEXT_GEP2]], i64 1
+; CHECK-NEXT:    [[TMP24:%.*]] = icmp eq i64* [[TMP22]], [[START]]
+; CHECK-NEXT:    [[TMP25:%.*]] = icmp eq i64* [[TMP23]], [[START]]
+; CHECK-NEXT:    store i1 [[TMP25]], i1* [[DST:%.*]], align 1
+; CHECK-NEXT:    [[TMP26:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP27:%.*]] = mul i64 [[TMP26]], 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP27]]
+; CHECK-NEXT:    [[TMP28:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP28]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
+;
+entry:
+  br label %for.body
+
+for.body:
+  %first.sroa = phi i64* [ %incdec.ptr, %for.body ], [ %start, %entry ]
+  %iv = phi i64 [ %iv.next, %for.body ], [ 0, %entry ]
+  %iv.next = add i64 %iv, 1
+  %0 = load i64, i64* %first.sroa
+  %incdec.ptr = getelementptr inbounds i64, i64* %first.sroa, i64 1
+  %cmp.not = icmp eq i64* %incdec.ptr, %start
+  store i1 %cmp.not, i1* %dst
+  %cmp = icmp ult i64 %iv, %N
+  br i1 %cmp, label %for.body, label %end
+
+end:
+  ret void
+}
+
+; Ensure conditional i1 stores do not vectorize
+define void @cond_store_i1(i1* noalias %dst, i8* noalias %start, i32 %cond, i64 %N) {
+; CHECK-LABEL: @cond_store_i1(
+; CHECK-NOT:   vector.body
+;
+entry:
+  br label %for.body
+
+for.body:
+  %first.sroa = phi i8* [ %incdec.ptr, %if.end ], [ null, %entry ]
+  %incdec.ptr = getelementptr inbounds i8, i8* %first.sroa, i64 1
+  %0 = load i8, i8* %incdec.ptr
+  %tobool.not = icmp eq i8 %0, 10
+  br i1 %tobool.not, label %if.end, label %if.then
+
+if.then:
+  %cmp.store = icmp eq i8* %start, %incdec.ptr
+  store i1 %cmp.store, i1* %dst
+  br label %if.end
+
+if.end:
+  %cmp.not = icmp eq i8* %incdec.ptr, %start
+  br i1 %cmp.not, label %for.end, label %for.body
+
+for.end:
+  ret void
+}

llvm/test/Transforms/LoopVectorize/X86/cost-model-assert.ll

 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s  -loop-vectorize -S | FileCheck %s
+; RUN: opt < %s  -loop-vectorize -force-vector-width=4 -S | FileCheck %s
 
 ; This is a bugpoint reduction of a test from PR43582:
 ; https://bugs.llvm.org/show_bug.cgi?id=43582
 
 ; ...but it's over-simplifying the underlying question:
 ; TODO: Should this be vectorized rather than allowing the backend to load combine?
 ;       The original code is a bswap pattern.
 

 ; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
 ; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 8
 ; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], 8
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP2]], [[N_MOD_VF]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[N_VEC]], 4
 ; CHECK-NEXT:    [[IND_END:%.*]] = getelementptr i8, i8* null, i64 [[TMP3]]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i8> poison, i8 [[X:%.*]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT]], <4 x i8> poison, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT2:%.*]] = insertelement <4 x i8> poison, i8 [[X]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT3:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT2]], <4 x i8> poison, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
 ; CHECK-NEXT:    [[NEXT_GEP:%.*]] = getelementptr i8, i8* null, i64 [[TMP5]]
 ; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP7:%.*]] = mul i64 [[TMP6]], 4
 ; CHECK-NEXT:    [[NEXT_GEP1:%.*]] = getelementptr i8, i8* null, i64 [[TMP7]]
-; CHECK-NEXT:    [[TMP8:%.*]] = zext <4 x i8> [[BROADCAST_SPLAT]] to <4 x i32>
-; CHECK-NEXT:    [[TMP9:%.*]] = zext <4 x i8> [[BROADCAST_SPLAT3]] to <4 x i32>
-; CHECK-NEXT:    [[TMP10:%.*]] = shl nuw <4 x i32> [[TMP8]], <i32 24, i32 24, i32 24, i32 24>
-; CHECK-NEXT:    [[TMP11:%.*]] = shl nuw <4 x i32> [[TMP9]], <i32 24, i32 24, i32 24, i32 24>
+; CHECK-NEXT:    [[TMP8:%.*]] = zext i8 [[X:%.*]] to i32
+; CHECK-NEXT:    [[TMP9:%.*]] = zext i8 [[X]] to i32
+; CHECK-NEXT:    [[TMP10:%.*]] = shl nuw i32 [[TMP8]], 24
+; CHECK-NEXT:    [[TMP11:%.*]] = shl nuw i32 [[TMP9]], 24
 ; CHECK-NEXT:    [[TMP12:%.*]] = load i8, i8* [[P:%.*]], align 1, !tbaa [[TBAA1:![0-9]+]]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT4:%.*]] = insertelement <4 x i8> poison, i8 [[TMP12]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT5:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT4]], <4 x i8> poison, <4 x i32> zeroinitializer
 ; CHECK-NEXT:    [[TMP13:%.*]] = load i8, i8* [[P]], align 1, !tbaa [[TBAA1]]
-; CHECK-NEXT:    [[BROADCAST_SPLATINSERT6:%.*]] = insertelement <4 x i8> poison, i8 [[TMP13]], i32 0
-; CHECK-NEXT:    [[BROADCAST_SPLAT7:%.*]] = shufflevector <4 x i8> [[BROADCAST_SPLATINSERT6]], <4 x i8> poison, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP14:%.*]] = zext <4 x i8> [[BROADCAST_SPLAT5]] to <4 x i32>
-; CHECK-NEXT:    [[TMP15:%.*]] = zext <4 x i8> [[BROADCAST_SPLAT7]] to <4 x i32>
-; CHECK-NEXT:    [[TMP16:%.*]] = shl nuw nsw <4 x i32> [[TMP14]], <i32 16, i32 16, i32 16, i32 16>
-; CHECK-NEXT:    [[TMP17:%.*]] = shl nuw nsw <4 x i32> [[TMP15]], <i32 16, i32 16, i32 16, i32 16>
-; CHECK-NEXT:    [[TMP18:%.*]] = or <4 x i32> [[TMP16]], [[TMP10]]
-; CHECK-NEXT:    [[TMP19:%.*]] = or <4 x i32> [[TMP17]], [[TMP11]]
+; CHECK-NEXT:    [[TMP14:%.*]] = zext i8 [[TMP12]] to i32
+; CHECK-NEXT:    [[TMP15:%.*]] = zext i8 [[TMP13]] to i32
+; CHECK-NEXT:    [[TMP16:%.*]] = shl nuw nsw i32 [[TMP14]], 16
+; CHECK-NEXT:    [[TMP17:%.*]] = shl nuw nsw i32 [[TMP15]], 16
+; CHECK-NEXT:    [[TMP18:%.*]] = or i32 [[TMP16]], [[TMP10]]
+; CHECK-NEXT:    [[TMP19:%.*]] = or i32 [[TMP17]], [[TMP11]]
 ; CHECK-NEXT:    [[TMP20:%.*]] = load i8, i8* undef, align 1, !tbaa [[TBAA1]]
 ; CHECK-NEXT:    [[TMP21:%.*]] = load i8, i8* undef, align 1, !tbaa [[TBAA1]]
-; CHECK-NEXT:    [[TMP22:%.*]] = or <4 x i32> [[TMP18]], zeroinitializer
-; CHECK-NEXT:    [[TMP23:%.*]] = or <4 x i32> [[TMP19]], zeroinitializer
-; CHECK-NEXT:    [[TMP24:%.*]] = or <4 x i32> [[TMP22]], zeroinitializer
-; CHECK-NEXT:    [[TMP25:%.*]] = or <4 x i32> [[TMP23]], zeroinitializer
-; CHECK-NEXT:    [[TMP26:%.*]] = extractelement <4 x i32> [[TMP24]], i32 0
-; CHECK-NEXT:    store i32 [[TMP26]], i32* undef, align 4, !tbaa [[TBAA4:![0-9]+]]
-; CHECK-NEXT:    [[TMP27:%.*]] = extractelement <4 x i32> [[TMP24]], i32 1
-; CHECK-NEXT:    store i32 [[TMP27]], i32* undef, align 4, !tbaa [[TBAA4]]
-; CHECK-NEXT:    [[TMP28:%.*]] = extractelement <4 x i32> [[TMP24]], i32 2
-; CHECK-NEXT:    store i32 [[TMP28]], i32* undef, align 4, !tbaa [[TBAA4]]
-; CHECK-NEXT:    [[TMP29:%.*]] = extractelement <4 x i32> [[TMP24]], i32 3
-; CHECK-NEXT:    store i32 [[TMP29]], i32* undef, align 4, !tbaa [[TBAA4]]
-; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <4 x i32> [[TMP25]], i32 0
-; CHECK-NEXT:    store i32 [[TMP30]], i32* undef, align 4, !tbaa [[TBAA4]]
-; CHECK-NEXT:    [[TMP31:%.*]] = extractelement <4 x i32> [[TMP25]], i32 1
-; CHECK-NEXT:    store i32 [[TMP31]], i32* undef, align 4, !tbaa [[TBAA4]]
-; CHECK-NEXT:    [[TMP32:%.*]] = extractelement <4 x i32> [[TMP25]], i32 2
-; CHECK-NEXT:    store i32 [[TMP32]], i32* undef, align 4, !tbaa [[TBAA4]]
-; CHECK-NEXT:    [[TMP33:%.*]] = extractelement <4 x i32> [[TMP25]], i32 3
-; CHECK-NEXT:    store i32 [[TMP33]], i32* undef, align 4, !tbaa [[TBAA4]]
+; CHECK-NEXT:    [[TMP22:%.*]] = shl nuw nsw i32 undef, 8
+; CHECK-NEXT:    [[TMP23:%.*]] = shl nuw nsw i32 undef, 8
+; CHECK-NEXT:    [[TMP24:%.*]] = or i32 [[TMP18]], [[TMP22]]
+; CHECK-NEXT:    [[TMP25:%.*]] = or i32 [[TMP19]], [[TMP23]]
+; CHECK-NEXT:    [[TMP26:%.*]] = zext i8 undef to i32
+; CHECK-NEXT:    [[TMP27:%.*]] = zext i8 undef to i32
+; CHECK-NEXT:    [[TMP28:%.*]] = or i32 [[TMP24]], [[TMP26]]
+; CHECK-NEXT:    [[TMP29:%.*]] = or i32 [[TMP25]], [[TMP27]]
+; CHECK-NEXT:    store i32 [[TMP29]], i32* undef, align 4, !tbaa [[TBAA4:![0-9]+]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
-; CHECK-NEXT:    [[TMP34:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP34]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK-NEXT:    [[TMP30:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP30]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP2]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[SW_EPILOG:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i8* [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ null, [[IF_THEN]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY68:%.*]]
 ; CHECK:       for.body68:
 ; CHECK-NEXT:    [[P_359:%.*]] = phi i8* [ [[ADD_PTR86:%.*]], [[FOR_BODY68]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
 ; CHECK-NEXT:    [[CONV70:%.*]] = zext i8 [[X]] to i32
 ; CHECK-NEXT:    [[SHL71:%.*]] = shl nuw i32 [[CONV70]], 24
-; CHECK-NEXT:    [[TMP35:%.*]] = load i8, i8* [[P]], align 1, !tbaa [[TBAA1]]
-; CHECK-NEXT:    [[CONV73:%.*]] = zext i8 [[TMP35]] to i32
+; CHECK-NEXT:    [[TMP31:%.*]] = load i8, i8* [[P]], align 1, !tbaa [[TBAA1]]
+; CHECK-NEXT:    [[CONV73:%.*]] = zext i8 [[TMP31]] to i32
 ; CHECK-NEXT:    [[SHL74:%.*]] = shl nuw nsw i32 [[CONV73]], 16
 ; CHECK-NEXT:    [[OR75:%.*]] = or i32 [[SHL74]], [[SHL71]]
-; CHECK-NEXT:    [[TMP36:%.*]] = load i8, i8* undef, align 1, !tbaa [[TBAA1]]
+; CHECK-NEXT:    [[TMP32:%.*]] = load i8, i8* undef, align 1, !tbaa [[TBAA1]]
 ; CHECK-NEXT:    [[SHL78:%.*]] = shl nuw nsw i32 undef, 8
 ; CHECK-NEXT:    [[OR79:%.*]] = or i32 [[OR75]], [[SHL78]]
 ; CHECK-NEXT:    [[CONV81:%.*]] = zext i8 undef to i32
 ; CHECK-NEXT:    [[OR83:%.*]] = or i32 [[OR79]], [[CONV81]]
 ; CHECK-NEXT:    store i32 [[OR83]], i32* undef, align 4, !tbaa [[TBAA4]]
 ; CHECK-NEXT:    [[ADD_PTR86]] = getelementptr inbounds i8, i8* [[P_359]], i64 4
 ; CHECK-NEXT:    [[CMP66:%.*]] = icmp ult i8* [[ADD_PTR86]], undef
 ; CHECK-NEXT:    br i1 [[CMP66]], label [[FOR_BODY68]], label [[SW_EPILOG]], !llvm.loop [[LOOP8:![0-9]+]]

llvm/test/Transforms/LoopVectorize/X86/illegal-parallel-loop-uniform-write.ll

 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP16:%.*]] = trunc i64 [[INDEX]] to i32
 ; CHECK-NEXT:    [[TMP17:%.*]] = add i32 [[TMP16]], 0
 ; CHECK-NEXT:    [[TMP18:%.*]] = add i32 [[ADD_US]], [[TMP17]]
 ; CHECK-NEXT:    [[TMP19:%.*]] = sext i32 [[TMP18]] to i64
 ; CHECK-NEXT:    [[TMP20:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[TMP19]]
-; CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[TMP20]], i32 0
-; CHECK-NEXT:    [[TMP22:%.*]] = bitcast i32* [[TMP21]] to <4 x i32>*
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP22]], align 4
-; CHECK-NEXT:    [[TMP23:%.*]] = add nsw <4 x i32> [[WIDE_LOAD]], <i32 1, i32 1, i32 1, i32 1>
-; CHECK-NEXT:    [[TMP24:%.*]] = extractelement <4 x i32> [[TMP23]], i32 0
-; CHECK-NEXT:    store i32 [[TMP24]], i32* [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
-; CHECK-NEXT:    [[TMP25:%.*]] = extractelement <4 x i32> [[TMP23]], i32 1
-; CHECK-NEXT:    store i32 [[TMP25]], i32* [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
-; CHECK-NEXT:    [[TMP26:%.*]] = extractelement <4 x i32> [[TMP23]], i32 2
-; CHECK-NEXT:    store i32 [[TMP26]], i32* [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
-; CHECK-NEXT:    [[TMP27:%.*]] = extractelement <4 x i32> [[TMP23]], i32 3
-; CHECK-NEXT:    store i32 [[TMP27]], i32* [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
+; CHECK-NEXT:    [[TMP21:%.*]] = load i32, i32* [[TMP20]], align 4, !llvm.mem.parallel_loop_access !0
+; CHECK-NEXT:    [[TMP22:%.*]] = add nsw i32 [[TMP21]], 1
+; CHECK-NEXT:    store i32 [[TMP22]], i32* [[ARRAYIDX7_US]], align 4, !llvm.mem.parallel_loop_access !0
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; CHECK-NEXT:    [[TMP28:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP28]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-NEXT:    [[TMP23:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP23]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP3]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END_US]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[FOR_BODY3_LR_PH_US]] ], [ 0, [[VECTOR_SCEVCHECK]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY3_US]]
 ; CHECK:       for.end15.loopexit:
 ; CHECK-NEXT:    br label [[FOR_END15]]

llvm/test/Transforms/LoopVectorize/X86/uniform_mem_op.ll

 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 8
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 12
 ; CHECK-NEXT:    store i32 0, i32* [[ADDR:%.*]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
-; CHECK-NEXT:    store i32 0, i32* [[ADDR]], align 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
 ; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096
 ; CHECK-NEXT:    br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 4097, 4096
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[LOOPEXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 4096, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]

 define void @uniform_store_varying_value(i32* align(4) %addr) {
 ; CHECK-LABEL: @uniform_store_varying_value(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[VEC_IND4:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT9:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[STEP_ADD:%.*]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
-; CHECK-NEXT:    [[STEP_ADD1:%.*]] = add <4 x i64> [[STEP_ADD]], <i64 4, i64 4, i64 4, i64 4>
-; CHECK-NEXT:    [[STEP_ADD2:%.*]] = add <4 x i64> [[STEP_ADD1]], <i64 4, i64 4, i64 4, i64 4>
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
-; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 1
-; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 2
-; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 3
-; CHECK-NEXT:    [[TMP4:%.*]] = add i64 [[INDEX]], 4
-; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[INDEX]], 5
-; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 6
-; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[INDEX]], 7
-; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[INDEX]], 8
-; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[INDEX]], 9
-; CHECK-NEXT:    [[TMP10:%.*]] = add i64 [[INDEX]], 10
-; CHECK-NEXT:    [[TMP11:%.*]] = add i64 [[INDEX]], 11
-; CHECK-NEXT:    [[TMP12:%.*]] = add i64 [[INDEX]], 12
-; CHECK-NEXT:    [[TMP13:%.*]] = add i64 [[INDEX]], 13
-; CHECK-NEXT:    [[TMP14:%.*]] = add i64 [[INDEX]], 14
-; CHECK-NEXT:    [[TMP15:%.*]] = add i64 [[INDEX]], 15
-; CHECK-NEXT:    [[STEP_ADD5:%.*]] = add <4 x i32> [[VEC_IND4]], <i32 4, i32 4, i32 4, i32 4>
-; CHECK-NEXT:    [[STEP_ADD6:%.*]] = add <4 x i32> [[STEP_ADD5]], <i32 4, i32 4, i32 4, i32 4>
-; CHECK-NEXT:    [[STEP_ADD7:%.*]] = add <4 x i32> [[STEP_ADD6]], <i32 4, i32 4, i32 4, i32 4>
-; CHECK-NEXT:    [[TMP16:%.*]] = extractelement <4 x i32> [[VEC_IND4]], i32 0
-; CHECK-NEXT:    store i32 [[TMP16]], i32* [[ADDR:%.*]], align 4
-; CHECK-NEXT:    [[TMP17:%.*]] = extractelement <4 x i32> [[VEC_IND4]], i32 1
-; CHECK-NEXT:    store i32 [[TMP17]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP18:%.*]] = extractelement <4 x i32> [[VEC_IND4]], i32 2
-; CHECK-NEXT:    store i32 [[TMP18]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP19:%.*]] = extractelement <4 x i32> [[VEC_IND4]], i32 3
-; CHECK-NEXT:    store i32 [[TMP19]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP20:%.*]] = extractelement <4 x i32> [[STEP_ADD5]], i32 0
-; CHECK-NEXT:    store i32 [[TMP20]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP21:%.*]] = extractelement <4 x i32> [[STEP_ADD5]], i32 1
-; CHECK-NEXT:    store i32 [[TMP21]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP22:%.*]] = extractelement <4 x i32> [[STEP_ADD5]], i32 2
-; CHECK-NEXT:    store i32 [[TMP22]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP23:%.*]] = extractelement <4 x i32> [[STEP_ADD5]], i32 3
-; CHECK-NEXT:    store i32 [[TMP23]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP24:%.*]] = extractelement <4 x i32> [[STEP_ADD6]], i32 0
-; CHECK-NEXT:    store i32 [[TMP24]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP25:%.*]] = extractelement <4 x i32> [[STEP_ADD6]], i32 1
-; CHECK-NEXT:    store i32 [[TMP25]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP26:%.*]] = extractelement <4 x i32> [[STEP_ADD6]], i32 2
-; CHECK-NEXT:    store i32 [[TMP26]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP27:%.*]] = extractelement <4 x i32> [[STEP_ADD6]], i32 3
-; CHECK-NEXT:    store i32 [[TMP27]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP28:%.*]] = extractelement <4 x i32> [[STEP_ADD7]], i32 0
-; CHECK-NEXT:    store i32 [[TMP28]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP29:%.*]] = extractelement <4 x i32> [[STEP_ADD7]], i32 1
-; CHECK-NEXT:    store i32 [[TMP29]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP30:%.*]] = extractelement <4 x i32> [[STEP_ADD7]], i32 2
-; CHECK-NEXT:    store i32 [[TMP30]], i32* [[ADDR]], align 4
-; CHECK-NEXT:    [[TMP31:%.*]] = extractelement <4 x i32> [[STEP_ADD7]], i32 3
-; CHECK-NEXT:    store i32 [[TMP31]], i32* [[ADDR]], align 4
+; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 8
+; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 12
+; CHECK-NEXT:    [[TMP4:%.*]] = trunc i64 [[INDEX]] to i32
+; CHECK-NEXT:    [[TMP5:%.*]] = add i32 [[TMP4]], 0
+; CHECK-NEXT:    [[TMP6:%.*]] = add i32 [[TMP4]], 4
+; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[TMP4]], 8
+; CHECK-NEXT:    [[TMP8:%.*]] = add i32 [[TMP4]], 12
+; CHECK-NEXT:    store i32 [[TMP8]], i32* [[ADDR:%.*]], align 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
-; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[STEP_ADD2]], <i64 4, i64 4, i64 4, i64 4>
-; CHECK-NEXT:    [[VEC_IND_NEXT9]] = add <4 x i32> [[STEP_ADD7]], <i32 4, i32 4, i32 4, i32 4>
-; CHECK-NEXT:    [[TMP32:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096
-; CHECK-NEXT:    br i1 [[TMP32]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
+; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096
+; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP10:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 4097, 4096
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[LOOPEXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 4096, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]

 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP1:%.*]] = add i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 8
 ; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[INDEX]], 12
 ; CHECK-NEXT:    [[TMP4:%.*]] = load i32, i32* [[A]], align 4, !alias.scope !12
 ; CHECK-NEXT:    [[TMP5:%.*]] = load i32, i32* [[A]], align 4, !alias.scope !12
 ; CHECK-NEXT:    [[TMP6:%.*]] = load i32, i32* [[A]], align 4, !alias.scope !12
 ; CHECK-NEXT:    [[TMP7:%.*]] = load i32, i32* [[A]], align 4, !alias.scope !12
-; CHECK-NEXT:    store i32 [[TMP4]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP4]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP4]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP4]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP5]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP5]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP5]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP5]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP6]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP6]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP6]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP6]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP7]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP7]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
-; CHECK-NEXT:    store i32 [[TMP7]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
 ; CHECK-NEXT:    store i32 [[TMP7]], i32* [[B]], align 4, !alias.scope !15, !noalias !12
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
 ; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 4096
 ; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP17:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 4097, 4096
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[LOOPEXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:

llvm/test/Transforms/LoopVectorize/invariant-store-vectorization-2.ll

 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDEX]]
 ; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
 ; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[TMP1]], align 8, !alias.scope !0, !noalias !3
 ; CHECK-NEXT:    [[DOTNOT:%.*]] = icmp eq <4 x i32> [[WIDE_LOAD]], [[BROADCAST_SPLAT]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>*
 ; CHECK-NEXT:    store <4 x i32> [[BROADCAST_SPLAT8]], <4 x i32>* [[TMP2]], align 4, !alias.scope !0, !noalias !3
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <4 x i1> [[DOTNOT]], <4 x i32> [[BROADCAST_SPLAT8]], <4 x i32> [[BROADCAST_SPLAT]]
-; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i32> [[PREDPHI]], i32 3
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i32> [[PREDPHI]], i32 0
 ; CHECK-NEXT:    store i32 [[TMP3]], i32* [[A]], align 4, !alias.scope !3
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[SMAX6]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:

 ; CHECK-NEXT:    [[BOUND0:%.*]] = icmp ugt i32* [[SCEVGEP4]], [[B]]
 ; CHECK-NEXT:    [[BOUND1:%.*]] = icmp ugt i32* [[SCEVGEP]], [[A]]
 ; CHECK-NEXT:    [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
 ; CHECK-NEXT:    br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[N_VEC:%.*]] = and i64 [[SMAX6]], 9223372036854775804
 ; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[NTRUNC]], i32 0
 ; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i1> undef, i1 [[CMP]], i32 3
-; CHECK-NEXT:    [[BROADCAST_SPLAT10:%.*]] = insertelement <4 x i32> poison, i32 [[K]], i32 3
-; CHECK-NEXT:    [[PREDPHI:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[BROADCAST_SPLAT]], <4 x i32> [[BROADCAST_SPLAT10]]
-; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i32> [[PREDPHI]], i32 3
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT7:%.*]] = insertelement <4 x i1> poison, i1 [[CMP]], i32 0
+; CHECK-NEXT:    [[BROADCAST_SPLATINSERT9:%.*]] = insertelement <4 x i32> poison, i32 [[K]], i32 0
+; CHECK-NEXT:    [[PREDPHI:%.*]] = select <4 x i1> [[BROADCAST_SPLATINSERT7]], <4 x i32> [[BROADCAST_SPLAT]], <4 x i32> [[BROADCAST_SPLATINSERT9]]
+; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <4 x i32> [[PREDPHI]], i32 0
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDEX]]
-; CHECK-NEXT:    [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
-; CHECK-NEXT:    store <4 x i32> [[BROADCAST_SPLAT]], <4 x i32>* [[TMP3]], align 4, !alias.scope !8, !noalias !11
-; CHECK-NEXT:    store i32 [[TMP1]], i32* [[A]], align 4, !alias.scope !11
+; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[B]], i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i32* [[TMP1]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[BROADCAST_SPLAT]], <4 x i32>* [[TMP2]], align 4, !alias.scope !8, !noalias !11
+; CHECK-NEXT:    store i32 [[TMP0]], i32* [[A]], align 4, !alias.scope !11
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
+; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP3]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP13:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[SMAX6]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ], [ 0, [[VECTOR_MEMCHECK]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[I_NEXT:%.*]], [[LATCH:%.*]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]

llvm/test/Transforms/LoopVectorize/pr44488-predication.ll

 ; CHECK-NEXT:    [[TMP11:%.*]] = srem i16 5786, [[TMP2]]
 ; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <2 x i16> [[TMP9]], i16 [[TMP11]], i32 1
 ; CHECK-NEXT:    br label [[PRED_SREM_CONTINUE4]]
 ; CHECK:       pred.srem.continue4:
 ; CHECK-NEXT:    [[TMP13:%.*]] = phi <2 x i16> [ [[TMP9]], [[PRED_SREM_CONTINUE]] ], [ [[TMP12]], [[PRED_SREM_IF3]] ]
 ; CHECK-NEXT:    [[PREDPHI:%.*]] = select <2 x i1> [[TMP4]], <2 x i16> <i16 5786, i16 5786>, <2 x i16> [[TMP13]]
 ; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <2 x i16> [[PREDPHI]], i32 0
 ; CHECK-NEXT:    store i16 [[TMP14]], i16* @v_39, align 1
-; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <2 x i16> [[PREDPHI]], i32 1
-; CHECK-NEXT:    store i16 [[TMP15]], i16* @v_39, align 1
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 2
-; CHECK-NEXT:    [[TMP16:%.*]] = icmp eq i32 [[INDEX_NEXT]], 12
-; CHECK-NEXT:    br i1 [[TMP16]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
+; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i32 [[INDEX_NEXT]], 12
+; CHECK-NEXT:    br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 12, 12
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i16 [ 111, [[MIDDLE_BLOCK]] ], [ 99, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[I_07:%.*]] = phi i16 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INC7:%.*]], [[FOR_LATCH:%.*]] ]
 ; CHECK-NEXT:    [[LV:%.*]] = load i16, i16* @v_38, align 1
 ; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i16 [[LV]], 32767
 ; CHECK-NEXT:    br i1 [[CMP1]], label [[COND_END:%.*]], label [[COND_END]]
 ; CHECK:       cond.end:
 ; CHECK-NEXT:    [[CMP2:%.*]] = icmp eq i16 [[LV]], 0
 ; CHECK-NEXT:    br i1 [[CMP2]], label [[FOR_LATCH]], label [[COND_FALSE4:%.*]]
 ; CHECK:       cond.false4:
 ; CHECK-NEXT:    [[REM:%.*]] = srem i16 5786, [[LV]]
 ; CHECK-NEXT:    br label [[FOR_LATCH]]
 ; CHECK:       for.latch:
 ; CHECK-NEXT:    [[COND6:%.*]] = phi i16 [ [[REM]], [[COND_FALSE4]] ], [ 5786, [[COND_END]] ]
 ; CHECK-NEXT:    store i16 [[COND6]], i16* @v_39, align 1
 ; CHECK-NEXT:    [[INC7]] = add nsw i16 [[I_07]], 1
 ; CHECK-NEXT:    [[CMP:%.*]] = icmp slt i16 [[INC7]], 111
-; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[EXIT]], [[LOOP2:!llvm.loop !.*]]
+; CHECK-NEXT:    br i1 [[CMP]], label [[FOR_BODY]], label [[EXIT]], !llvm.loop [[LOOP2:![0-9]+]]
 ; CHECK:       exit:
 ; CHECK-NEXT:    [[RV:%.*]] = load i16, i16* @v_39, align 1
 ; CHECK-NEXT:    ret i16 [[RV]]
 ;
 entry:
   br label %for.body
 
 for.body:                                         ; preds = %entry, %for.latch

llvm/test/Transforms/LoopVectorize/pr47343-expander-lcssa-after-cfg-update.ll

 ; CHECK-NEXT:    [[BOUND1:%.*]] = icmp ult i8* [[TMP1]], bitcast (i32* getelementptr inbounds (i32, i32* @f.e, i64 1) to i8*)
 ; CHECK-NEXT:    [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
 ; CHECK-NEXT:    br i1 [[FOUND_CONFLICT]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i32 [[INDEX]], 0
-; CHECK-NEXT:    store i32 0, i32* @f.e, align 1, !alias.scope !0, !noalias !3
-; CHECK-NEXT:    store i32 0, i32* @f.e, align 1, !alias.scope !0, !noalias !3
-; CHECK-NEXT:    store i8 10, i8* [[TMP0]], align 1
+; CHECK-NEXT:    [[TMP3:%.*]] = zext i1 false to i32
+; CHECK-NEXT:    store i32 [[TMP3]], i32* @f.e, align 1, !alias.scope !0, !noalias !3
 ; CHECK-NEXT:    store i8 10, i8* [[TMP0]], align 1
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 2
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq i32 [[INDEX_NEXT]], 500
-; CHECK-NEXT:    br i1 [[TMP3]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-NEXT:    [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], 500
+; CHECK-NEXT:    br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i32 500, 500
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i32 [ 500, [[MIDDLE_BLOCK]] ], [ 0, [[LOOP_PREHEADER]] ], [ 0, [[VECTOR_MEMCHECK]] ]
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[IV_NEXT:%.*]], [[LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]

llvm/test/Transforms/LoopVectorize/skeleton-lcssa-crash.ll

 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 2
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP2:%.*]] = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = add nuw nsw i64 [[TMP2]], 1
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr inbounds i16, i16* [[L_1]], i64 [[TMP3]]
-; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i16, i16* [[TMP4]], i32 0
-; CHECK-NEXT:    [[TMP6:%.*]] = bitcast i16* [[TMP5]] to <2 x i16>*
-; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i16>, <2 x i16>* [[TMP6]], align 2, !alias.scope !0
-; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i16, i16* [[L_2]], i64 0
-; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x i16> [[WIDE_LOAD]], i32 0
-; CHECK-NEXT:    store i16 [[TMP8]], i16* [[TMP7]], align 2, !alias.scope !3, !noalias !0
-; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <2 x i16> [[WIDE_LOAD]], i32 1
-; CHECK-NEXT:    store i16 [[TMP9]], i16* [[TMP7]], align 2, !alias.scope !3, !noalias !0
+; CHECK-NEXT:    [[TMP5:%.*]] = load i16, i16* [[TMP4]], align 2, !alias.scope !0
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i16, i16* [[L_2]], i64 0
+; CHECK-NEXT:    store i16 [[TMP5]], i16* [[TMP6]], align 2, !alias.scope !3, !noalias !0
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
-; CHECK-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
+; CHECK-NEXT:    [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP7]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
 ; CHECK:       middle.block:
 ; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[N_VEC]]
 ; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT_LOOPEXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[LOOP_3_PREHEADER]] ], [ 0, [[VECTOR_MEMCHECK]] ]
 ; CHECK-NEXT:    br label [[LOOP_3:%.*]]
 ; CHECK:       inner.latch:
 ; CHECK-NEXT:    [[C_4:%.*]] = call i1 @cond()