Index: llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -9065,6 +9065,17 @@
     VPBB->appendRecipe(Recipe);
     return VPBB;
   }
+
+  if (IsUniform && isa<LoadInst>(I) &&
+      !Legal->blockNeedsPredication(I->getParent()) && Range.Start.isVector()) {
+    assert(CM.foldTailByMasking() &&
+           "Uniform load is unexpectedly marked as predicated!");
+    LLVM_DEBUG(dbgs() << "LV: Replicating uniform load in predicated loop:"
+                      << *I << "\n");
+    VPBB->appendRecipe(Recipe);
+    return VPBB;
+  }
+
   LLVM_DEBUG(dbgs() << "LV: Scalarizing and predicating:" << *I << "\n");
   assert(VPBB->getSuccessors().empty() &&
          "VPBB has successors when handling predicated replication.");
Index: llvm/test/Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll
+++ llvm/test/Transforms/LoopVectorize/AArch64/tail-fold-uniform-memops.ll
@@ -5,6 +5,46 @@
 
 target triple = "aarch64-linux-gnu"
 
+; The original loop had an unconditional uniform load. Let's make sure
+; we don't artificially create new predicated blocks for the load.
+define void @uniform_load(i32* noalias %dst, i32* noalias readonly %src, i64 %n) #0 {
+; CHECK-LABEL: @uniform_load(
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[IDX:%.*]] = phi i64 [ 0, %vector.ph ], [ [[IDX_NEXT:%.*]], %vector.body ]
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x i64> poison, i64 [[IDX]], i32 0
+; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <4 x i64> [[TMP1]], <4 x i64> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add <4 x i64> [[TMP2]], <i64 0, i64 1, i64 2, i64 3>
+; CHECK-NEXT:    [[TMP3:%.*]] = add i64 [[IDX]], 0
+; CHECK-NEXT:    [[LOOP_PRED:%.*]] = icmp ule <4 x i64> [[INDUCTION]]
+; CHECK-NEXT:    [[LOAD_VAL:%.*]] = load i32, i32* %src, align 4
+; CHECK-NOT:     load i32, i32* %src, align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <4 x i32> poison, i32 [[LOAD_VAL]], i32 0
+; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <4 x i32> [[TMP4]], <4 x i32> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* %dst, i64 [[TMP3]]
+; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TMP6]], i32 0
+; CHECK-NEXT:    [[STORE_PTR:%.*]] = bitcast i32* [[TMP7]] to <4 x i32>*
+; CHECK-NEXT:    call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> [[TMP5]], <4 x i32>* [[STORE_PTR]], i32 4, <4 x i1> [[LOOP_PRED]])
+; CHECK-NEXT:    [[IDX_NEXT]] = add i64 [[IDX]], 4
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i64 [[IDX_NEXT]], %n.vec
+; CHECK-NEXT:    br i1 [[CMP]], label %middle.block, label %vector.body
+
+entry:
+  br label %for.body
+
+for.body:                                         ; preds = %entry, %for.body
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %val = load i32, i32* %src, align 4
+  %arrayidx = getelementptr inbounds i32, i32* %dst, i64 %indvars.iv
+  store i32 %val, i32* %arrayidx, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond.not = icmp eq i64 %indvars.iv.next, %n
+  br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end:                                          ; preds = %for.body, %entry
+  ret void
+}
+
+
 ; The original loop had a conditional uniform load. In this case we actually
 ; do need to perform conditional loads and so we end up using a gather instead.
 ; However, we at least ensure the mask is the overlap of the loop predicate