diff --git a/llvm/include/llvm/Analysis/VectorUtils.h b/llvm/include/llvm/Analysis/VectorUtils.h
index 52fe6f6cf43f2..53ba1e8f77791 100644
--- a/llvm/include/llvm/Analysis/VectorUtils.h
+++ b/llvm/include/llvm/Analysis/VectorUtils.h
@@ -176,6 +176,12 @@ LLVM_ABI bool isVectorIntrinsicWithStructReturnOverloadAtField(
 LLVM_ABI Intrinsic::ID
 getVectorIntrinsicIDForCall(const CallInst *CI, const TargetLibraryInfo *TLI);
 
+/// Returns the corresponding llvm.vector.interleaveN intrinsic for factor N.
+LLVM_ABI Intrinsic::ID getInterleaveIntrinsicID(unsigned Factor);
+
+/// Returns the corresponding llvm.vector.deinterleaveN intrinsic for factor N.
+LLVM_ABI Intrinsic::ID getDeinterleaveIntrinsicID(unsigned Factor);
+
 /// Given a vector and an element number, see if the scalar value is
 /// already around as a register, for example if it were inserted then extracted
 /// from the vector.
diff --git a/llvm/lib/Analysis/VectorUtils.cpp b/llvm/lib/Analysis/VectorUtils.cpp
index 968fd2f8c5d7f..63fccee63c0ae 100644
--- a/llvm/lib/Analysis/VectorUtils.cpp
+++ b/llvm/lib/Analysis/VectorUtils.cpp
@@ -240,6 +240,30 @@ Intrinsic::ID llvm::getVectorIntrinsicIDForCall(const CallInst *CI,
   return Intrinsic::not_intrinsic;
 }
 
+struct InterleaveIntrinsic {
+  Intrinsic::ID Interleave, Deinterleave;
+};
+
+static InterleaveIntrinsic InterleaveIntrinsics[] = {
+    {Intrinsic::vector_interleave2, Intrinsic::vector_deinterleave2},
+    {Intrinsic::vector_interleave3, Intrinsic::vector_deinterleave3},
+    {Intrinsic::vector_interleave4, Intrinsic::vector_deinterleave4},
+    {Intrinsic::vector_interleave5, Intrinsic::vector_deinterleave5},
+    {Intrinsic::vector_interleave6, Intrinsic::vector_deinterleave6},
+    {Intrinsic::vector_interleave7, Intrinsic::vector_deinterleave7},
+    {Intrinsic::vector_interleave8, Intrinsic::vector_deinterleave8},
+};
+
+Intrinsic::ID llvm::getInterleaveIntrinsicID(unsigned Factor) {
+  assert(Factor >= 2 && Factor <= 8 && "Unexpected factor");
+  return InterleaveIntrinsics[Factor - 2].Interleave;
+}
+
+Intrinsic::ID llvm::getDeinterleaveIntrinsicID(unsigned Factor) {
+  assert(Factor >= 2 && Factor <= 8 && "Unexpected factor");
+  return InterleaveIntrinsics[Factor - 2].Deinterleave;
+}
+
 /// Given a vector and an element number, see if the scalar value is
 /// already around as a register, for example if it were inserted then extracted
 /// from the vector.
diff --git a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
index acd37a5ae0720..0232ac421aeda 100644
--- a/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
+++ b/llvm/lib/Target/AArch64/AArch64TargetTransformInfo.cpp
@@ -4583,6 +4583,13 @@ InstructionCost AArch64TTIImpl::getInterleavedMemoryOpCost(
   if (VecTy->isScalableTy() && !ST->hasSVE())
     return InstructionCost::getInvalid();
 
+  // Scalable VFs will emit vector.[de]interleave intrinsics, and currently we
+  // only have lowering for power-of-2 factors.
+  // TODO: Add lowering for vector.[de]interleave3 intrinsics and support in
+  // InterleavedAccessPass for ld3/st3
+  if (VecTy->isScalableTy() && !isPowerOf2_32(Factor))
+    return InstructionCost::getInvalid();
+
   // Vectorization for masked interleaved accesses is only enabled for scalable
   // VF.
   if (!VecTy->isScalableTy() && (UseMaskForCond || UseMaskForGaps))
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 427c1460fcfc9..93c158dc860ad 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -3167,10 +3167,9 @@ bool LoopVectorizationCostModel::interleavedAccessCanBeWidened(
   if (hasIrregularType(ScalarTy, DL))
     return false;
 
-  // For scalable vectors, the only interleave factor currently supported
-  // must be power of 2 since we require the (de)interleave2 intrinsics
-  // instead of shufflevectors.
-  if (VF.isScalable() && !isPowerOf2_32(InterleaveFactor))
+  // For scalable vectors, the interleave factors must be <= 8 since we require
+  // the (de)interleaveN intrinsics instead of shufflevectors.
+  if (VF.isScalable() && InterleaveFactor > 8)
     return false;
 
   // If the group involves a non-integral pointer, we may not be able to
@@ -8709,10 +8708,9 @@ VPlanPtr LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes(
       bool Result = (VF.isVector() && // Query is illegal for VF == 1
                      CM.getWideningDecision(IG->getInsertPos(), VF) ==
                          LoopVectorizationCostModel::CM_Interleave);
-      // For scalable vectors, the only interleave factor currently supported
-      // must be power of 2 since we require the (de)interleave2 intrinsics
-      // instead of shufflevectors.
-      assert((!Result || !VF.isScalable() || isPowerOf2_32(IG->getFactor())) &&
+      // For scalable vectors, the interleave factors must be <= 8 since we
+      // require the (de)interleaveN intrinsics instead of shufflevectors.
+      assert((!Result || !VF.isScalable() || IG->getFactor() <= 8) &&
              "Unsupported interleave factor for scalable vectors");
       return Result;
     };
diff --git a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
index 62b99d98a2b5e..aa6b13c217bd1 100644
--- a/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
+++ b/llvm/lib/Transforms/Vectorize/VPlanRecipes.cpp
@@ -3294,21 +3294,13 @@ static Value *interleaveVectors(IRBuilderBase &Builder, ArrayRef<Value *> Vals,
   // Scalable vectors cannot use arbitrary shufflevectors (only splats), so
   // must use intrinsics to interleave.
   if (VecTy->isScalableTy()) {
-    assert(isPowerOf2_32(Factor) && "Unsupported interleave factor for "
-                                    "scalable vectors, must be power of 2");
-    SmallVector<Value *> InterleavingValues(Vals);
-    // When interleaving, the number of values will be shrunk until we have the
-    // single final interleaved value.
-    auto *InterleaveTy = cast<VectorType>(InterleavingValues[0]->getType());
-    for (unsigned Midpoint = Factor / 2; Midpoint > 0; Midpoint /= 2) {
-      InterleaveTy = VectorType::getDoubleElementsVectorType(InterleaveTy);
-      for (unsigned I = 0; I < Midpoint; ++I)
-        InterleavingValues[I] = Builder.CreateIntrinsic(
-            InterleaveTy, Intrinsic::vector_interleave2,
-            {InterleavingValues[I], InterleavingValues[Midpoint + I]},
-            /*FMFSource=*/nullptr, Name);
-    }
-    return InterleavingValues[0];
+    assert(Factor <= 8 && "Unsupported interleave factor for scalable vectors");
+    VectorType *InterleaveTy =
+        VectorType::get(VecTy->getElementType(),
+                        VecTy->getElementCount().multiplyCoefficientBy(Factor));
+    return Builder.CreateIntrinsic(InterleaveTy,
+                                   getInterleaveIntrinsicID(Factor), Vals,
+                                   /*FMFSource=*/nullptr, Name);
   }
 
   // Fixed length. Start by concatenating all vectors into a wide vector.
@@ -3394,7 +3386,7 @@ void VPInterleaveRecipe::execute(VPTransformState &State) {
                           &InterleaveFactor](Value *MaskForGaps) -> Value * {
     if (State.VF.isScalable()) {
       assert(!MaskForGaps && "Interleaved groups with gaps are not supported.");
-      assert(isPowerOf2_32(InterleaveFactor) &&
+      assert(InterleaveFactor <= 8 &&
              "Unsupported deinterleave factor for scalable vectors");
       auto *ResBlockInMask = State.get(BlockInMask);
       SmallVector<Value *> Ops(InterleaveFactor, ResBlockInMask);
@@ -3438,43 +3430,18 @@ void VPInterleaveRecipe::execute(VPTransformState &State) {
     ArrayRef<VPValue *> VPDefs = definedValues();
     const DataLayout &DL = State.CFG.PrevBB->getDataLayout();
     if (VecTy->isScalableTy()) {
-      assert(isPowerOf2_32(InterleaveFactor) &&
-             "Unsupported deinterleave factor for scalable vectors");
-
       // Scalable vectors cannot use arbitrary shufflevectors (only splats),
       // so must use intrinsics to deinterleave.
-      SmallVector<Value *> DeinterleavedValues(InterleaveFactor);
-      DeinterleavedValues[0] = NewLoad;
-      // For the case of InterleaveFactor > 2, we will have to do recursive
-      // deinterleaving, because the current available deinterleave intrinsic
-      // supports only Factor of 2, otherwise it will bailout after first
-      // iteration.
-      // When deinterleaving, the number of values will double until we
-      // have "InterleaveFactor".
-      for (unsigned NumVectors = 1; NumVectors < InterleaveFactor;
-           NumVectors *= 2) {
-        // Deinterleave the elements within the vector
-        SmallVector<Value *> TempDeinterleavedValues(NumVectors);
-        for (unsigned I = 0; I < NumVectors; ++I) {
-          auto *DiTy = DeinterleavedValues[I]->getType();
-          TempDeinterleavedValues[I] = State.Builder.CreateIntrinsic(
-              Intrinsic::vector_deinterleave2, DiTy, DeinterleavedValues[I],
-              /*FMFSource=*/nullptr, "strided.vec");
-        }
-        // Extract the deinterleaved values:
-        for (unsigned I = 0; I < 2; ++I)
-          for (unsigned J = 0; J < NumVectors; ++J)
-            DeinterleavedValues[NumVectors * I + J] =
-                State.Builder.CreateExtractValue(TempDeinterleavedValues[J], I);
-      }
+      assert(InterleaveFactor <= 8 &&
+             "Unsupported deinterleave factor for scalable vectors");
+      Value *Deinterleave = State.Builder.CreateIntrinsic(
+          getDeinterleaveIntrinsicID(InterleaveFactor), NewLoad->getType(),
+          NewLoad,
+          /*FMFSource=*/nullptr, "strided.vec");
 
-#ifndef NDEBUG
-      for (Value *Val : DeinterleavedValues)
-        assert(Val && "NULL Deinterleaved Value");
-#endif
       for (unsigned I = 0, J = 0; I < InterleaveFactor; ++I) {
         Instruction *Member = Group->getMember(I);
-        Value *StridedVec = DeinterleavedValues[I];
+        Value *StridedVec = State.Builder.CreateExtractValue(Deinterleave, I);
         if (!Member) {
           // This value is not needed as it's not used
           cast<Instruction>(StridedVec)->eraseFromParent();
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-accesses.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-accesses.ll
index 6861644fc9969..77e713256d247 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-accesses.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-accesses.ll
@@ -375,8 +375,8 @@ define void @test_reversed_load2_store2(ptr noalias nocapture readonly %A, ptr n
 ; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 8 x i32>, ptr [[TMP9]], align 4
 ; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> [[WIDE_VEC]])
 ; CHECK-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 0
-; CHECK-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 1
 ; CHECK-NEXT:    [[REVERSE:%.*]] = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> [[TMP10]])
+; CHECK-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 1
 ; CHECK-NEXT:    [[REVERSE1:%.*]] = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> [[TMP11]])
 ; CHECK-NEXT:    [[TMP12:%.*]] = add nsw <vscale x 4 x i32> [[REVERSE]], [[VEC_IND]]
 ; CHECK-NEXT:    [[TMP13:%.*]] = sub nsw <vscale x 4 x i32> [[REVERSE1]], [[VEC_IND]]
@@ -1479,34 +1479,24 @@ define void @interleave_deinterleave(ptr writeonly noalias %dst, ptr readonly %a
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP6:%.*]] = getelementptr inbounds [[STRUCT_XYZT:%.*]], ptr [[A:%.*]], i64 [[INDEX]]
 ; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 16 x i32>, ptr [[TMP6]], align 4
-; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> [[WIDE_VEC]])
-; CHECK-NEXT:    [[TMP7:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[STRIDED_VEC]], 0
-; CHECK-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[STRIDED_VEC]], 1
-; CHECK-NEXT:    [[STRIDED_VEC6:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> [[TMP7]])
-; CHECK-NEXT:    [[STRIDED_VEC7:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> [[TMP8]])
-; CHECK-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC6]], 0
-; CHECK-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC7]], 0
-; CHECK-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC6]], 1
-; CHECK-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC7]], 1
+; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave4.nxv16i32(<vscale x 16 x i32> [[WIDE_VEC]])
+; CHECK-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 0
+; CHECK-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 1
+; CHECK-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 2
+; CHECK-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 3
 ; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr inbounds [[STRUCT_XYZT]], ptr [[B:%.*]], i64 [[INDEX]]
 ; CHECK-NEXT:    [[WIDE_VEC8:%.*]] = load <vscale x 16 x i32>, ptr [[TMP13]], align 4
-; CHECK-NEXT:    [[STRIDED_VEC9:%.*]] = call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> [[WIDE_VEC8]])
-; CHECK-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[STRIDED_VEC9]], 0
-; CHECK-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[STRIDED_VEC9]], 1
-; CHECK-NEXT:    [[STRIDED_VEC10:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> [[TMP14]])
-; CHECK-NEXT:    [[STRIDED_VEC11:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> [[TMP15]])
-; CHECK-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC10]], 0
-; CHECK-NEXT:    [[TMP17:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC11]], 0
-; CHECK-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC10]], 1
-; CHECK-NEXT:    [[TMP19:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC11]], 1
+; CHECK-NEXT:    [[STRIDED_VEC2:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave4.nxv16i32(<vscale x 16 x i32> [[WIDE_VEC8]])
+; CHECK-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC2]], 0
+; CHECK-NEXT:    [[TMP17:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC2]], 1
+; CHECK-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC2]], 2
+; CHECK-NEXT:    [[TMP19:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC2]], 3
 ; CHECK-NEXT:    [[TMP20:%.*]] = add nsw <vscale x 4 x i32> [[TMP16]], [[TMP9]]
 ; CHECK-NEXT:    [[TMP21:%.*]] = getelementptr inbounds [[STRUCT_XYZT]], ptr [[DST:%.*]], i64 [[INDEX]]
 ; CHECK-NEXT:    [[TMP22:%.*]] = sub nsw <vscale x 4 x i32> [[TMP10]], [[TMP17]]
 ; CHECK-NEXT:    [[TMP23:%.*]] = shl <vscale x 4 x i32> [[TMP11]], [[TMP18]]
 ; CHECK-NEXT:    [[TMP24:%.*]] = ashr <vscale x 4 x i32> [[TMP12]], [[TMP19]]
-; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 8 x i32> @llvm.vector.interleave2.nxv8i32(<vscale x 4 x i32> [[TMP20]], <vscale x 4 x i32> [[TMP23]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC12:%.*]] = call <vscale x 8 x i32> @llvm.vector.interleave2.nxv8i32(<vscale x 4 x i32> [[TMP22]], <vscale x 4 x i32> [[TMP24]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC13:%.*]] = call <vscale x 16 x i32> @llvm.vector.interleave2.nxv16i32(<vscale x 8 x i32> [[INTERLEAVED_VEC]], <vscale x 8 x i32> [[INTERLEAVED_VEC12]])
+; CHECK-NEXT:    [[INTERLEAVED_VEC13:%.*]] = call <vscale x 16 x i32> @llvm.vector.interleave4.nxv16i32(<vscale x 4 x i32> [[TMP20]], <vscale x 4 x i32> [[TMP22]], <vscale x 4 x i32> [[TMP23]], <vscale x 4 x i32> [[TMP24]])
 ; CHECK-NEXT:    store <vscale x 16 x i32> [[INTERLEAVED_VEC13]], ptr [[TMP21]], align 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
 ; CHECK-NEXT:    [[TMP25:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
@@ -1595,18 +1585,14 @@ define void @interleave_deinterleave_reverse(ptr noalias nocapture readonly %A,
 ; CHECK-NEXT:    [[TMP9:%.*]] = sext i32 [[TMP8]] to i64
 ; CHECK-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, ptr [[TMP5]], i64 [[TMP9]]
 ; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 16 x i32>, ptr [[TMP10]], align 4
-; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 8 x i32>, <vscale x 8 x i32> } @llvm.vector.deinterleave2.nxv16i32(<vscale x 16 x i32> [[WIDE_VEC]])
-; CHECK-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[STRIDED_VEC]], 0
-; CHECK-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } [[STRIDED_VEC]], 1
-; CHECK-NEXT:    [[STRIDED_VEC1:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> [[TMP11]])
-; CHECK-NEXT:    [[STRIDED_VEC2:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> [[TMP12]])
-; CHECK-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC1]], 0
-; CHECK-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC2]], 0
-; CHECK-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC1]], 1
-; CHECK-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC2]], 1
+; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave4.nxv16i32(<vscale x 16 x i32> [[WIDE_VEC]])
+; CHECK-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 0
 ; CHECK-NEXT:    [[REVERSE:%.*]] = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> [[TMP13]])
+; CHECK-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 1
 ; CHECK-NEXT:    [[REVERSE3:%.*]] = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> [[TMP14]])
+; CHECK-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 2
 ; CHECK-NEXT:    [[REVERSE4:%.*]] = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> [[TMP15]])
+; CHECK-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 3
 ; CHECK-NEXT:    [[REVERSE5:%.*]] = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> [[TMP16]])
 ; CHECK-NEXT:    [[TMP17:%.*]] = add nsw <vscale x 4 x i32> [[REVERSE]], [[VEC_IND]]
 ; CHECK-NEXT:    [[TMP18:%.*]] = sub nsw <vscale x 4 x i32> [[REVERSE3]], [[VEC_IND]]
@@ -1622,9 +1608,7 @@ define void @interleave_deinterleave_reverse(ptr noalias nocapture readonly %A,
 ; CHECK-NEXT:    [[REVERSE7:%.*]] = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> [[TMP18]])
 ; CHECK-NEXT:    [[REVERSE8:%.*]] = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> [[TMP19]])
 ; CHECK-NEXT:    [[REVERSE9:%.*]] = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> [[TMP20]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 8 x i32> @llvm.vector.interleave2.nxv8i32(<vscale x 4 x i32> [[REVERSE6]], <vscale x 4 x i32> [[REVERSE8]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC10:%.*]] = call <vscale x 8 x i32> @llvm.vector.interleave2.nxv8i32(<vscale x 4 x i32> [[REVERSE7]], <vscale x 4 x i32> [[REVERSE9]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC11:%.*]] = call <vscale x 16 x i32> @llvm.vector.interleave2.nxv16i32(<vscale x 8 x i32> [[INTERLEAVED_VEC]], <vscale x 8 x i32> [[INTERLEAVED_VEC10]])
+; CHECK-NEXT:    [[INTERLEAVED_VEC11:%.*]] = call <vscale x 16 x i32> @llvm.vector.interleave4.nxv16i32(<vscale x 4 x i32> [[REVERSE6]], <vscale x 4 x i32> [[REVERSE7]], <vscale x 4 x i32> [[REVERSE8]], <vscale x 4 x i32> [[REVERSE9]])
 ; CHECK-NEXT:    store <vscale x 16 x i32> [[INTERLEAVED_VEC11]], ptr [[TMP26]], align 4
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP1]]
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i32> [[VEC_IND]], [[DOTSPLAT]]
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-masked-accesses.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-masked-accesses.ll
index 469faf67a71b3..3567aff0ace4e 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-masked-accesses.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/sve-interleaved-masked-accesses.ll
@@ -469,36 +469,26 @@ define dso_local void @masked_strided_factor4(ptr noalias nocapture readonly %p,
 ; SCALAR_TAIL_FOLDING-NEXT:    [[TMP8:%.*]] = shl i32 [[INDEX]], 2
 ; SCALAR_TAIL_FOLDING-NEXT:    [[TMP9:%.*]] = sext i32 [[TMP8]] to i64
 ; SCALAR_TAIL_FOLDING-NEXT:    [[TMP10:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP9]]
-; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK:%.*]] = call <vscale x 32 x i1> @llvm.vector.interleave2.nxv32i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK1:%.*]] = call <vscale x 32 x i1> @llvm.vector.interleave2.nxv32i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK2:%.*]] = call <vscale x 64 x i1> @llvm.vector.interleave2.nxv64i1(<vscale x 32 x i1> [[INTERLEAVED_MASK]], <vscale x 32 x i1> [[INTERLEAVED_MASK1]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[WIDE_MASKED_VEC:%.*]] = call <vscale x 64 x i8> @llvm.masked.load.nxv64i8.p0(ptr [[TMP10]], i32 1, <vscale x 64 x i1> [[INTERLEAVED_MASK2]], <vscale x 64 x i8> poison)
-; SCALAR_TAIL_FOLDING-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 32 x i8>, <vscale x 32 x i8> } @llvm.vector.deinterleave2.nxv64i8(<vscale x 64 x i8> [[WIDE_MASKED_VEC]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 32 x i8>, <vscale x 32 x i8> } [[STRIDED_VEC]], 0
-; SCALAR_TAIL_FOLDING-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 32 x i8>, <vscale x 32 x i8> } [[STRIDED_VEC]], 1
-; SCALAR_TAIL_FOLDING-NEXT:    [[STRIDED_VEC3:%.*]] = call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.vector.deinterleave2.nxv32i8(<vscale x 32 x i8> [[TMP11]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[STRIDED_VEC4:%.*]] = call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.vector.deinterleave2.nxv32i8(<vscale x 32 x i8> [[TMP12]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC3]], 0
-; SCALAR_TAIL_FOLDING-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC4]], 0
-; SCALAR_TAIL_FOLDING-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC3]], 1
-; SCALAR_TAIL_FOLDING-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC4]], 1
+; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK:%.*]] = call <vscale x 64 x i1> @llvm.vector.interleave4.nxv64i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
+; SCALAR_TAIL_FOLDING-NEXT:    [[WIDE_MASKED_VEC:%.*]] = call <vscale x 64 x i8> @llvm.masked.load.nxv64i8.p0(ptr [[TMP10]], i32 1, <vscale x 64 x i1> [[INTERLEAVED_MASK]], <vscale x 64 x i8> poison)
+; SCALAR_TAIL_FOLDING-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.vector.deinterleave4.nxv64i8(<vscale x 64 x i8> [[WIDE_MASKED_VEC]])
+; SCALAR_TAIL_FOLDING-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC]], 0
+; SCALAR_TAIL_FOLDING-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC]], 1
+; SCALAR_TAIL_FOLDING-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC]], 2
+; SCALAR_TAIL_FOLDING-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC]], 3
+; SCALAR_TAIL_FOLDING-NEXT:    [[TMP15:%.*]] = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> [[TMP11]], <vscale x 16 x i8> [[TMP12]])
+; SCALAR_TAIL_FOLDING-NEXT:    [[TMP16:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP15]]
 ; SCALAR_TAIL_FOLDING-NEXT:    [[TMP17:%.*]] = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> [[TMP13]], <vscale x 16 x i8> [[TMP14]])
 ; SCALAR_TAIL_FOLDING-NEXT:    [[TMP18:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP17]]
-; SCALAR_TAIL_FOLDING-NEXT:    [[TMP19:%.*]] = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> [[TMP15]], <vscale x 16 x i8> [[TMP16]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[TMP20:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP19]]
-; SCALAR_TAIL_FOLDING-NEXT:    [[TMP21:%.*]] = sext i32 [[TMP8]] to i64
-; SCALAR_TAIL_FOLDING-NEXT:    [[TMP22:%.*]] = getelementptr i8, ptr [[Q]], i64 [[TMP21]]
-; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 32 x i8> @llvm.vector.interleave2.nxv32i8(<vscale x 16 x i8> [[TMP17]], <vscale x 16 x i8> [[TMP19]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_VEC5:%.*]] = call <vscale x 32 x i8> @llvm.vector.interleave2.nxv32i8(<vscale x 16 x i8> [[TMP18]], <vscale x 16 x i8> [[TMP20]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_VEC6:%.*]] = call <vscale x 64 x i8> @llvm.vector.interleave2.nxv64i8(<vscale x 32 x i8> [[INTERLEAVED_VEC]], <vscale x 32 x i8> [[INTERLEAVED_VEC5]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK7:%.*]] = call <vscale x 32 x i1> @llvm.vector.interleave2.nxv32i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK8:%.*]] = call <vscale x 32 x i1> @llvm.vector.interleave2.nxv32i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
-; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK9:%.*]] = call <vscale x 64 x i1> @llvm.vector.interleave2.nxv64i1(<vscale x 32 x i1> [[INTERLEAVED_MASK7]], <vscale x 32 x i1> [[INTERLEAVED_MASK8]])
-; SCALAR_TAIL_FOLDING-NEXT:    call void @llvm.masked.store.nxv64i8.p0(<vscale x 64 x i8> [[INTERLEAVED_VEC6]], ptr [[TMP22]], i32 1, <vscale x 64 x i1> [[INTERLEAVED_MASK9]])
+; SCALAR_TAIL_FOLDING-NEXT:    [[TMP19:%.*]] = sext i32 [[TMP8]] to i64
+; SCALAR_TAIL_FOLDING-NEXT:    [[TMP20:%.*]] = getelementptr i8, ptr [[Q]], i64 [[TMP19]]
+; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 64 x i8> @llvm.vector.interleave4.nxv64i8(<vscale x 16 x i8> [[TMP15]], <vscale x 16 x i8> [[TMP16]], <vscale x 16 x i8> [[TMP17]], <vscale x 16 x i8> [[TMP18]])
+; SCALAR_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK1:%.*]] = call <vscale x 64 x i1> @llvm.vector.interleave4.nxv64i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
+; SCALAR_TAIL_FOLDING-NEXT:    call void @llvm.masked.store.nxv64i8.p0(<vscale x 64 x i8> [[INTERLEAVED_VEC]], ptr [[TMP20]], i32 1, <vscale x 64 x i1> [[INTERLEAVED_MASK1]])
 ; SCALAR_TAIL_FOLDING-NEXT:    [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP5]]
 ; SCALAR_TAIL_FOLDING-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 16 x i32> [[VEC_IND]], [[DOTSPLAT]]
-; SCALAR_TAIL_FOLDING-NEXT:    [[TMP23:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; SCALAR_TAIL_FOLDING-NEXT:    br i1 [[TMP23]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; SCALAR_TAIL_FOLDING-NEXT:    [[TMP21:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
+; SCALAR_TAIL_FOLDING-NEXT:    br i1 [[TMP21]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
 ; SCALAR_TAIL_FOLDING:       middle.block:
 ; SCALAR_TAIL_FOLDING-NEXT:    [[CMP_N:%.*]] = icmp eq i32 [[N_MOD_VF]], 0
 ; SCALAR_TAIL_FOLDING-NEXT:    br i1 [[CMP_N]], label [[FOR_END:%.*]], label [[SCALAR_PH]]
@@ -531,37 +521,27 @@ define dso_local void @masked_strided_factor4(ptr noalias nocapture readonly %p,
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP8:%.*]] = shl i32 [[INDEX]], 2
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP9:%.*]] = sext i32 [[TMP8]] to i64
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP10:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP9]]
-; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK:%.*]] = call <vscale x 32 x i1> @llvm.vector.interleave2.nxv32i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK1:%.*]] = call <vscale x 32 x i1> @llvm.vector.interleave2.nxv32i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK2:%.*]] = call <vscale x 64 x i1> @llvm.vector.interleave2.nxv64i1(<vscale x 32 x i1> [[INTERLEAVED_MASK]], <vscale x 32 x i1> [[INTERLEAVED_MASK1]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[WIDE_MASKED_VEC:%.*]] = call <vscale x 64 x i8> @llvm.masked.load.nxv64i8.p0(ptr [[TMP10]], i32 1, <vscale x 64 x i1> [[INTERLEAVED_MASK2]], <vscale x 64 x i8> poison)
-; PREDICATED_TAIL_FOLDING-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 32 x i8>, <vscale x 32 x i8> } @llvm.vector.deinterleave2.nxv64i8(<vscale x 64 x i8> [[WIDE_MASKED_VEC]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 32 x i8>, <vscale x 32 x i8> } [[STRIDED_VEC]], 0
-; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 32 x i8>, <vscale x 32 x i8> } [[STRIDED_VEC]], 1
-; PREDICATED_TAIL_FOLDING-NEXT:    [[STRIDED_VEC3:%.*]] = call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.vector.deinterleave2.nxv32i8(<vscale x 32 x i8> [[TMP11]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[STRIDED_VEC4:%.*]] = call { <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.vector.deinterleave2.nxv32i8(<vscale x 32 x i8> [[TMP12]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC3]], 0
-; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC4]], 0
-; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC3]], 1
-; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC4]], 1
+; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK:%.*]] = call <vscale x 64 x i1> @llvm.vector.interleave4.nxv64i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
+; PREDICATED_TAIL_FOLDING-NEXT:    [[WIDE_MASKED_VEC:%.*]] = call <vscale x 64 x i8> @llvm.masked.load.nxv64i8.p0(ptr [[TMP10]], i32 1, <vscale x 64 x i1> [[INTERLEAVED_MASK]], <vscale x 64 x i8> poison)
+; PREDICATED_TAIL_FOLDING-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } @llvm.vector.deinterleave4.nxv64i8(<vscale x 64 x i8> [[WIDE_MASKED_VEC]])
+; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC]], 0
+; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC]], 1
+; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC]], 2
+; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8> } [[STRIDED_VEC]], 3
+; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP15:%.*]] = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> [[TMP11]], <vscale x 16 x i8> [[TMP12]])
+; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP16:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP15]]
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP17:%.*]] = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> [[TMP13]], <vscale x 16 x i8> [[TMP14]])
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP18:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP17]]
-; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP19:%.*]] = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> [[TMP15]], <vscale x 16 x i8> [[TMP16]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP20:%.*]] = sub <vscale x 16 x i8> zeroinitializer, [[TMP19]]
-; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP21:%.*]] = sext i32 [[TMP8]] to i64
-; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP22:%.*]] = getelementptr i8, ptr [[Q]], i64 [[TMP21]]
-; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 32 x i8> @llvm.vector.interleave2.nxv32i8(<vscale x 16 x i8> [[TMP17]], <vscale x 16 x i8> [[TMP19]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_VEC5:%.*]] = call <vscale x 32 x i8> @llvm.vector.interleave2.nxv32i8(<vscale x 16 x i8> [[TMP18]], <vscale x 16 x i8> [[TMP20]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_VEC6:%.*]] = call <vscale x 64 x i8> @llvm.vector.interleave2.nxv64i8(<vscale x 32 x i8> [[INTERLEAVED_VEC]], <vscale x 32 x i8> [[INTERLEAVED_VEC5]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK7:%.*]] = call <vscale x 32 x i1> @llvm.vector.interleave2.nxv32i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK8:%.*]] = call <vscale x 32 x i1> @llvm.vector.interleave2.nxv32i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
-; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK9:%.*]] = call <vscale x 64 x i1> @llvm.vector.interleave2.nxv64i1(<vscale x 32 x i1> [[INTERLEAVED_MASK7]], <vscale x 32 x i1> [[INTERLEAVED_MASK8]])
-; PREDICATED_TAIL_FOLDING-NEXT:    call void @llvm.masked.store.nxv64i8.p0(<vscale x 64 x i8> [[INTERLEAVED_VEC6]], ptr [[TMP22]], i32 1, <vscale x 64 x i1> [[INTERLEAVED_MASK9]])
+; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP19:%.*]] = sext i32 [[TMP8]] to i64
+; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP20:%.*]] = getelementptr i8, ptr [[Q]], i64 [[TMP19]]
+; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 64 x i8> @llvm.vector.interleave4.nxv64i8(<vscale x 16 x i8> [[TMP15]], <vscale x 16 x i8> [[TMP16]], <vscale x 16 x i8> [[TMP17]], <vscale x 16 x i8> [[TMP18]])
+; PREDICATED_TAIL_FOLDING-NEXT:    [[INTERLEAVED_MASK1:%.*]] = call <vscale x 64 x i1> @llvm.vector.interleave4.nxv64i1(<vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]], <vscale x 16 x i1> [[TMP7]])
+; PREDICATED_TAIL_FOLDING-NEXT:    call void @llvm.masked.store.nxv64i8.p0(<vscale x 64 x i8> [[INTERLEAVED_VEC]], ptr [[TMP20]], i32 1, <vscale x 64 x i1> [[INTERLEAVED_MASK1]])
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[INDEX_NEXT]] = add i32 [[INDEX]], [[TMP1]]
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[ACTIVE_LANE_MASK_NEXT]] = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 [[INDEX]], i32 [[TMP4]])
 ; PREDICATED_TAIL_FOLDING-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 16 x i32> [[VEC_IND]], [[DOTSPLAT]]
-; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP23:%.*]] = extractelement <vscale x 16 x i1> [[ACTIVE_LANE_MASK_NEXT]], i64 0
-; PREDICATED_TAIL_FOLDING-NEXT:    br i1 [[TMP23]], label [[VECTOR_BODY]], label [[MIDDLE_BLOCK:%.*]], !llvm.loop [[LOOP8:![0-9]+]]
+; PREDICATED_TAIL_FOLDING-NEXT:    [[TMP21:%.*]] = extractelement <vscale x 16 x i1> [[ACTIVE_LANE_MASK_NEXT]], i64 0
+; PREDICATED_TAIL_FOLDING-NEXT:    br i1 [[TMP21]], label [[VECTOR_BODY]], label [[MIDDLE_BLOCK:%.*]], !llvm.loop [[LOOP8:![0-9]+]]
 ; PREDICATED_TAIL_FOLDING:       middle.block:
 ; PREDICATED_TAIL_FOLDING-NEXT:    br label [[FOR_END:%.*]]
 ; PREDICATED_TAIL_FOLDING:       scalar.ph:
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll
index feb3b6d42b658..61a3e3561ad98 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll
@@ -354,32 +354,40 @@ exit:
 define void @load_store_factor3_i32(ptr %p) {
 ; CHECK-LABEL: @load_store_factor3_i32(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP7:%.*]] = mul i64 [[TMP6]], 4
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP7]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = mul i64 [[INDEX]], 3
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP0]]
-; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <24 x i32>, ptr [[TMP1]], align 4
-; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <24 x i32> [[WIDE_VEC]], <24 x i32> poison, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
-; CHECK-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <24 x i32> [[WIDE_VEC]], <24 x i32> poison, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
-; CHECK-NEXT:    [[STRIDED_VEC2:%.*]] = shufflevector <24 x i32> [[WIDE_VEC]], <24 x i32> poison, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
-; CHECK-NEXT:    [[TMP2:%.*]] = add <8 x i32> [[STRIDED_VEC]], splat (i32 1)
-; CHECK-NEXT:    [[TMP3:%.*]] = add <8 x i32> [[STRIDED_VEC1]], splat (i32 2)
-; CHECK-NEXT:    [[TMP4:%.*]] = add <8 x i32> [[STRIDED_VEC2]], splat (i32 3)
-; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <8 x i32> [[TMP2]], <8 x i32> [[TMP3]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <8 x i32> [[TMP4]], <8 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT:    [[TMP7:%.*]] = shufflevector <16 x i32> [[TMP5]], <16 x i32> [[TMP6]], <24 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
-; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <24 x i32> [[TMP7]], <24 x i32> poison, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>
-; CHECK-NEXT:    store <24 x i32> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 4
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
-; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 12 x i32>, ptr [[TMP1]], align 4
+; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave3.nxv12i32(<vscale x 12 x i32> [[WIDE_VEC]])
+; CHECK-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 0
+; CHECK-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 1
+; CHECK-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 2
+; CHECK-NEXT:    [[TMP11:%.*]] = add <vscale x 4 x i32> [[TMP8]], splat (i32 1)
+; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 4 x i32> [[TMP9]], splat (i32 2)
+; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 4 x i32> [[TMP10]], splat (i32 3)
+; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 12 x i32> @llvm.vector.interleave3.nxv12i32(<vscale x 4 x i32> [[TMP11]], <vscale x 4 x i32> [[TMP12]], <vscale x 4 x i32> [[TMP13]])
+; CHECK-NEXT:    store <vscale x 12 x i32> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 4
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
@@ -458,32 +466,40 @@ define void @load_store_factor3_i32(ptr %p) {
 ;
 ; SCALABLE-LABEL: @load_store_factor3_i32(
 ; SCALABLE-NEXT:  entry:
-; SCALABLE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; SCALABLE-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[TMP7:%.*]] = mul i64 [[TMP6]], 4
+; SCALABLE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP7]]
+; SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; SCALABLE:       vector.ph:
+; SCALABLE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
+; SCALABLE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; SCALABLE-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; SCALABLE-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 4
 ; SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; SCALABLE:       vector.body:
 ; SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; SCALABLE-NEXT:    [[TMP0:%.*]] = mul i64 [[INDEX]], 3
 ; SCALABLE-NEXT:    [[TMP1:%.*]] = getelementptr i32, ptr [[P:%.*]], i64 [[TMP0]]
-; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <24 x i32>, ptr [[TMP1]], align 4
-; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <24 x i32> [[WIDE_VEC]], <24 x i32> poison, <8 x i32> <i32 0, i32 3, i32 6, i32 9, i32 12, i32 15, i32 18, i32 21>
-; SCALABLE-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <24 x i32> [[WIDE_VEC]], <24 x i32> poison, <8 x i32> <i32 1, i32 4, i32 7, i32 10, i32 13, i32 16, i32 19, i32 22>
-; SCALABLE-NEXT:    [[STRIDED_VEC2:%.*]] = shufflevector <24 x i32> [[WIDE_VEC]], <24 x i32> poison, <8 x i32> <i32 2, i32 5, i32 8, i32 11, i32 14, i32 17, i32 20, i32 23>
-; SCALABLE-NEXT:    [[TMP2:%.*]] = add <8 x i32> [[STRIDED_VEC]], splat (i32 1)
-; SCALABLE-NEXT:    [[TMP3:%.*]] = add <8 x i32> [[STRIDED_VEC1]], splat (i32 2)
-; SCALABLE-NEXT:    [[TMP4:%.*]] = add <8 x i32> [[STRIDED_VEC2]], splat (i32 3)
-; SCALABLE-NEXT:    [[TMP5:%.*]] = shufflevector <8 x i32> [[TMP2]], <8 x i32> [[TMP3]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
-; SCALABLE-NEXT:    [[TMP6:%.*]] = shufflevector <8 x i32> [[TMP4]], <8 x i32> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; SCALABLE-NEXT:    [[TMP7:%.*]] = shufflevector <16 x i32> [[TMP5]], <16 x i32> [[TMP6]], <24 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <24 x i32> [[TMP7]], <24 x i32> poison, <24 x i32> <i32 0, i32 8, i32 16, i32 1, i32 9, i32 17, i32 2, i32 10, i32 18, i32 3, i32 11, i32 19, i32 4, i32 12, i32 20, i32 5, i32 13, i32 21, i32 6, i32 14, i32 22, i32 7, i32 15, i32 23>
-; SCALABLE-NEXT:    store <24 x i32> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 4
-; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
-; SCALABLE-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; SCALABLE-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
+; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 12 x i32>, ptr [[TMP1]], align 4
+; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } @llvm.vector.deinterleave3.nxv12i32(<vscale x 12 x i32> [[WIDE_VEC]])
+; SCALABLE-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 0
+; SCALABLE-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 1
+; SCALABLE-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } [[STRIDED_VEC]], 2
+; SCALABLE-NEXT:    [[TMP11:%.*]] = add <vscale x 4 x i32> [[TMP8]], splat (i32 1)
+; SCALABLE-NEXT:    [[TMP12:%.*]] = add <vscale x 4 x i32> [[TMP9]], splat (i32 2)
+; SCALABLE-NEXT:    [[TMP13:%.*]] = add <vscale x 4 x i32> [[TMP10]], splat (i32 3)
+; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 12 x i32> @llvm.vector.interleave3.nxv12i32(<vscale x 4 x i32> [[TMP11]], <vscale x 4 x i32> [[TMP12]], <vscale x 4 x i32> [[TMP13]])
+; SCALABLE-NEXT:    store <vscale x 12 x i32> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 4
+; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; SCALABLE-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; SCALABLE-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP6:![0-9]+]]
 ; SCALABLE:       middle.block:
-; SCALABLE-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; SCALABLE:       scalar.ph:
-; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; SCALABLE-NEXT:    br label [[LOOP:%.*]]
 ; SCALABLE:       loop:
 ; SCALABLE-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
@@ -541,32 +557,40 @@ exit:
 define void @load_store_factor3_i64(ptr %p) {
 ; CHECK-LABEL: @load_store_factor3_i64(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP7:%.*]] = mul i64 [[TMP6]], 2
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP7]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 2
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = mul i64 [[INDEX]], 3
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
-; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <12 x i64>, ptr [[TMP1]], align 8
-; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
-; CHECK-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
-; CHECK-NEXT:    [[STRIDED_VEC2:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
-; CHECK-NEXT:    [[TMP2:%.*]] = add <4 x i64> [[STRIDED_VEC]], splat (i64 1)
-; CHECK-NEXT:    [[TMP3:%.*]] = add <4 x i64> [[STRIDED_VEC1]], splat (i64 2)
-; CHECK-NEXT:    [[TMP4:%.*]] = add <4 x i64> [[STRIDED_VEC2]], splat (i64 3)
-; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <4 x i64> [[TMP2]], <4 x i64> [[TMP3]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <4 x i64> [[TMP4]], <4 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT:    [[TMP7:%.*]] = shufflevector <8 x i64> [[TMP5]], <8 x i64> [[TMP6]], <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
-; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <12 x i64> [[TMP7]], <12 x i64> poison, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
-; CHECK-NEXT:    store <12 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; CHECK-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; CHECK-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 6 x i64>, ptr [[TMP1]], align 8
+; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave3.nxv6i64(<vscale x 6 x i64> [[WIDE_VEC]])
+; CHECK-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 0
+; CHECK-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 1
+; CHECK-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 2
+; CHECK-NEXT:    [[TMP11:%.*]] = add <vscale x 2 x i64> [[TMP8]], splat (i64 1)
+; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 2 x i64> [[TMP9]], splat (i64 2)
+; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 2 x i64> [[TMP10]], splat (i64 3)
+; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 6 x i64> @llvm.vector.interleave3.nxv6i64(<vscale x 2 x i64> [[TMP11]], <vscale x 2 x i64> [[TMP12]], <vscale x 2 x i64> [[TMP13]])
+; CHECK-NEXT:    store <vscale x 6 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
@@ -645,32 +669,40 @@ define void @load_store_factor3_i64(ptr %p) {
 ;
 ; SCALABLE-LABEL: @load_store_factor3_i64(
 ; SCALABLE-NEXT:  entry:
-; SCALABLE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; SCALABLE-NEXT:    [[TMP6:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[TMP7:%.*]] = mul i64 [[TMP6]], 2
+; SCALABLE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP7]]
+; SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; SCALABLE:       vector.ph:
+; SCALABLE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
+; SCALABLE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP3]]
+; SCALABLE-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; SCALABLE-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 2
 ; SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; SCALABLE:       vector.body:
 ; SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; SCALABLE-NEXT:    [[TMP0:%.*]] = mul i64 [[INDEX]], 3
 ; SCALABLE-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
-; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <12 x i64>, ptr [[TMP1]], align 8
-; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
-; SCALABLE-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
-; SCALABLE-NEXT:    [[STRIDED_VEC2:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
-; SCALABLE-NEXT:    [[TMP2:%.*]] = add <4 x i64> [[STRIDED_VEC]], splat (i64 1)
-; SCALABLE-NEXT:    [[TMP3:%.*]] = add <4 x i64> [[STRIDED_VEC1]], splat (i64 2)
-; SCALABLE-NEXT:    [[TMP4:%.*]] = add <4 x i64> [[STRIDED_VEC2]], splat (i64 3)
-; SCALABLE-NEXT:    [[TMP5:%.*]] = shufflevector <4 x i64> [[TMP2]], <4 x i64> [[TMP3]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; SCALABLE-NEXT:    [[TMP6:%.*]] = shufflevector <4 x i64> [[TMP4]], <4 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
-; SCALABLE-NEXT:    [[TMP7:%.*]] = shufflevector <8 x i64> [[TMP5]], <8 x i64> [[TMP6]], <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <12 x i64> [[TMP7]], <12 x i64> poison, <12 x i32> <i32 0, i32 4, i32 8, i32 1, i32 5, i32 9, i32 2, i32 6, i32 10, i32 3, i32 7, i32 11>
-; SCALABLE-NEXT:    store <12 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
-; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; SCALABLE-NEXT:    [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; SCALABLE-NEXT:    br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 6 x i64>, ptr [[TMP1]], align 8
+; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave3.nxv6i64(<vscale x 6 x i64> [[WIDE_VEC]])
+; SCALABLE-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 0
+; SCALABLE-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 1
+; SCALABLE-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 2
+; SCALABLE-NEXT:    [[TMP11:%.*]] = add <vscale x 2 x i64> [[TMP8]], splat (i64 1)
+; SCALABLE-NEXT:    [[TMP12:%.*]] = add <vscale x 2 x i64> [[TMP9]], splat (i64 2)
+; SCALABLE-NEXT:    [[TMP13:%.*]] = add <vscale x 2 x i64> [[TMP10]], splat (i64 3)
+; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 6 x i64> @llvm.vector.interleave3.nxv6i64(<vscale x 2 x i64> [[TMP11]], <vscale x 2 x i64> [[TMP12]], <vscale x 2 x i64> [[TMP13]])
+; SCALABLE-NEXT:    store <vscale x 6 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
+; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
+; SCALABLE-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; SCALABLE-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
 ; SCALABLE:       middle.block:
-; SCALABLE-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; SCALABLE:       scalar.ph:
-; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; SCALABLE-NEXT:    br label [[LOOP:%.*]]
 ; SCALABLE:       loop:
 ; SCALABLE-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
@@ -745,22 +777,16 @@ define void @load_store_factor4(ptr %p) {
 ; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP6]]
 ; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 8 x i64>, ptr [[TMP7]], align 8
-; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> [[WIDE_VEC]])
-; CHECK-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } [[STRIDED_VEC]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } [[STRIDED_VEC]], 1
-; CHECK-NEXT:    [[STRIDED_VEC1:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> [[TMP8]])
-; CHECK-NEXT:    [[STRIDED_VEC2:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> [[TMP9]])
-; CHECK-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC1]], 0
-; CHECK-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC2]], 0
-; CHECK-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC1]], 1
-; CHECK-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC2]], 1
+; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave4.nxv8i64(<vscale x 8 x i64> [[WIDE_VEC]])
+; CHECK-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 0
+; CHECK-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 1
+; CHECK-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 2
+; CHECK-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 3
 ; CHECK-NEXT:    [[TMP14:%.*]] = add <vscale x 2 x i64> [[TMP10]], splat (i64 1)
 ; CHECK-NEXT:    [[TMP15:%.*]] = add <vscale x 2 x i64> [[TMP11]], splat (i64 2)
 ; CHECK-NEXT:    [[TMP16:%.*]] = add <vscale x 2 x i64> [[TMP12]], splat (i64 3)
 ; CHECK-NEXT:    [[TMP17:%.*]] = add <vscale x 2 x i64> [[TMP13]], splat (i64 4)
-; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64> [[TMP14]], <vscale x 2 x i64> [[TMP16]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC3:%.*]] = call <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64> [[TMP15]], <vscale x 2 x i64> [[TMP17]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC4:%.*]] = call <vscale x 8 x i64> @llvm.vector.interleave2.nxv8i64(<vscale x 4 x i64> [[INTERLEAVED_VEC]], <vscale x 4 x i64> [[INTERLEAVED_VEC3]])
+; CHECK-NEXT:    [[INTERLEAVED_VEC4:%.*]] = call <vscale x 8 x i64> @llvm.vector.interleave4.nxv8i64(<vscale x 2 x i64> [[TMP14]], <vscale x 2 x i64> [[TMP15]], <vscale x 2 x i64> [[TMP16]], <vscale x 2 x i64> [[TMP17]])
 ; CHECK-NEXT:    store <vscale x 8 x i64> [[INTERLEAVED_VEC4]], ptr [[TMP7]], align 8
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
 ; CHECK-NEXT:    [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
@@ -877,22 +903,16 @@ define void @load_store_factor4(ptr %p) {
 ; SCALABLE-NEXT:    [[TMP6:%.*]] = mul i64 [[INDEX]], 4
 ; SCALABLE-NEXT:    [[TMP7:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP6]]
 ; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 8 x i64>, ptr [[TMP7]], align 8
-; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> [[WIDE_VEC]])
-; SCALABLE-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } [[STRIDED_VEC]], 0
-; SCALABLE-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } [[STRIDED_VEC]], 1
-; SCALABLE-NEXT:    [[STRIDED_VEC1:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> [[TMP8]])
-; SCALABLE-NEXT:    [[STRIDED_VEC2:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> [[TMP9]])
-; SCALABLE-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC1]], 0
-; SCALABLE-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC2]], 0
-; SCALABLE-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC1]], 1
-; SCALABLE-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC2]], 1
+; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave4.nxv8i64(<vscale x 8 x i64> [[WIDE_VEC]])
+; SCALABLE-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 0
+; SCALABLE-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 1
+; SCALABLE-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 2
+; SCALABLE-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC]], 3
 ; SCALABLE-NEXT:    [[TMP14:%.*]] = add <vscale x 2 x i64> [[TMP10]], splat (i64 1)
 ; SCALABLE-NEXT:    [[TMP15:%.*]] = add <vscale x 2 x i64> [[TMP11]], splat (i64 2)
 ; SCALABLE-NEXT:    [[TMP16:%.*]] = add <vscale x 2 x i64> [[TMP12]], splat (i64 3)
 ; SCALABLE-NEXT:    [[TMP17:%.*]] = add <vscale x 2 x i64> [[TMP13]], splat (i64 4)
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64> [[TMP14]], <vscale x 2 x i64> [[TMP16]])
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC3:%.*]] = call <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64> [[TMP15]], <vscale x 2 x i64> [[TMP17]])
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC4:%.*]] = call <vscale x 8 x i64> @llvm.vector.interleave2.nxv8i64(<vscale x 4 x i64> [[INTERLEAVED_VEC]], <vscale x 4 x i64> [[INTERLEAVED_VEC3]])
+; SCALABLE-NEXT:    [[INTERLEAVED_VEC4:%.*]] = call <vscale x 8 x i64> @llvm.vector.interleave4.nxv8i64(<vscale x 2 x i64> [[TMP14]], <vscale x 2 x i64> [[TMP15]], <vscale x 2 x i64> [[TMP16]], <vscale x 2 x i64> [[TMP17]])
 ; SCALABLE-NEXT:    store <vscale x 8 x i64> [[INTERLEAVED_VEC4]], ptr [[TMP7]], align 8
 ; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
 ; SCALABLE-NEXT:    [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
@@ -970,38 +990,41 @@ exit:
 define void @load_store_factor5(ptr %p) {
 ; CHECK-LABEL: @load_store_factor5(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP3]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = mul i64 [[INDEX]], 5
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
-; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <10 x i64>, ptr [[TMP1]], align 8
-; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <10 x i64> [[WIDE_VEC]], <10 x i64> poison, <2 x i32> <i32 0, i32 5>
-; CHECK-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <10 x i64> [[WIDE_VEC]], <10 x i64> poison, <2 x i32> <i32 1, i32 6>
-; CHECK-NEXT:    [[STRIDED_VEC2:%.*]] = shufflevector <10 x i64> [[WIDE_VEC]], <10 x i64> poison, <2 x i32> <i32 2, i32 7>
-; CHECK-NEXT:    [[STRIDED_VEC3:%.*]] = shufflevector <10 x i64> [[WIDE_VEC]], <10 x i64> poison, <2 x i32> <i32 3, i32 8>
-; CHECK-NEXT:    [[STRIDED_VEC4:%.*]] = shufflevector <10 x i64> [[WIDE_VEC]], <10 x i64> poison, <2 x i32> <i32 4, i32 9>
-; CHECK-NEXT:    [[TMP2:%.*]] = add <2 x i64> [[STRIDED_VEC]], splat (i64 1)
-; CHECK-NEXT:    [[TMP3:%.*]] = add <2 x i64> [[STRIDED_VEC1]], splat (i64 2)
-; CHECK-NEXT:    [[TMP4:%.*]] = add <2 x i64> [[STRIDED_VEC2]], splat (i64 3)
-; CHECK-NEXT:    [[TMP5:%.*]] = add <2 x i64> [[STRIDED_VEC3]], splat (i64 4)
-; CHECK-NEXT:    [[TMP6:%.*]] = add <2 x i64> [[STRIDED_VEC4]], splat (i64 5)
-; CHECK-NEXT:    [[TMP7:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <2 x i64> [[TMP4]], <2 x i64> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP9:%.*]] = shufflevector <4 x i64> [[TMP7]], <4 x i64> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    [[TMP10:%.*]] = shufflevector <2 x i64> [[TMP6]], <2 x i64> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <8 x i64> [[TMP9]], <8 x i64> [[TMP10]], <10 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9>
-; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <10 x i64> [[TMP11]], <10 x i64> poison, <10 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 1, i32 3, i32 5, i32 7, i32 9>
-; CHECK-NEXT:    store <10 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
-; CHECK-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; CHECK-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 5 x i64>, ptr [[TMP1]], align 8
+; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave5.nxv5i64(<vscale x 5 x i64> [[WIDE_VEC]])
+; CHECK-NEXT:    [[TMP5:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 0
+; CHECK-NEXT:    [[TMP6:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 1
+; CHECK-NEXT:    [[TMP7:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 2
+; CHECK-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 3
+; CHECK-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 4
+; CHECK-NEXT:    [[TMP10:%.*]] = add <vscale x 1 x i64> [[TMP5]], splat (i64 1)
+; CHECK-NEXT:    [[TMP11:%.*]] = add <vscale x 1 x i64> [[TMP6]], splat (i64 2)
+; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 1 x i64> [[TMP7]], splat (i64 3)
+; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 1 x i64> [[TMP8]], splat (i64 4)
+; CHECK-NEXT:    [[TMP14:%.*]] = add <vscale x 1 x i64> [[TMP9]], splat (i64 5)
+; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 5 x i64> @llvm.vector.interleave5.nxv5i64(<vscale x 1 x i64> [[TMP10]], <vscale x 1 x i64> [[TMP11]], <vscale x 1 x i64> [[TMP12]], <vscale x 1 x i64> [[TMP13]], <vscale x 1 x i64> [[TMP14]])
+; CHECK-NEXT:    store <vscale x 5 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
+; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
@@ -1106,38 +1129,41 @@ define void @load_store_factor5(ptr %p) {
 ;
 ; SCALABLE-LABEL: @load_store_factor5(
 ; SCALABLE-NEXT:  entry:
-; SCALABLE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; SCALABLE-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP3]]
+; SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; SCALABLE:       vector.ph:
+; SCALABLE-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; SCALABLE-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; SCALABLE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; SCALABLE:       vector.body:
 ; SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; SCALABLE-NEXT:    [[TMP0:%.*]] = mul i64 [[INDEX]], 5
 ; SCALABLE-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
-; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <10 x i64>, ptr [[TMP1]], align 8
-; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <10 x i64> [[WIDE_VEC]], <10 x i64> poison, <2 x i32> <i32 0, i32 5>
-; SCALABLE-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <10 x i64> [[WIDE_VEC]], <10 x i64> poison, <2 x i32> <i32 1, i32 6>
-; SCALABLE-NEXT:    [[STRIDED_VEC2:%.*]] = shufflevector <10 x i64> [[WIDE_VEC]], <10 x i64> poison, <2 x i32> <i32 2, i32 7>
-; SCALABLE-NEXT:    [[STRIDED_VEC3:%.*]] = shufflevector <10 x i64> [[WIDE_VEC]], <10 x i64> poison, <2 x i32> <i32 3, i32 8>
-; SCALABLE-NEXT:    [[STRIDED_VEC4:%.*]] = shufflevector <10 x i64> [[WIDE_VEC]], <10 x i64> poison, <2 x i32> <i32 4, i32 9>
-; SCALABLE-NEXT:    [[TMP2:%.*]] = add <2 x i64> [[STRIDED_VEC]], splat (i64 1)
-; SCALABLE-NEXT:    [[TMP3:%.*]] = add <2 x i64> [[STRIDED_VEC1]], splat (i64 2)
-; SCALABLE-NEXT:    [[TMP4:%.*]] = add <2 x i64> [[STRIDED_VEC2]], splat (i64 3)
-; SCALABLE-NEXT:    [[TMP5:%.*]] = add <2 x i64> [[STRIDED_VEC3]], splat (i64 4)
-; SCALABLE-NEXT:    [[TMP6:%.*]] = add <2 x i64> [[STRIDED_VEC4]], splat (i64 5)
-; SCALABLE-NEXT:    [[TMP7:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; SCALABLE-NEXT:    [[TMP8:%.*]] = shufflevector <2 x i64> [[TMP4]], <2 x i64> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; SCALABLE-NEXT:    [[TMP9:%.*]] = shufflevector <4 x i64> [[TMP7]], <4 x i64> [[TMP8]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; SCALABLE-NEXT:    [[TMP10:%.*]] = shufflevector <2 x i64> [[TMP6]], <2 x i64> poison, <8 x i32> <i32 0, i32 1, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
-; SCALABLE-NEXT:    [[TMP11:%.*]] = shufflevector <8 x i64> [[TMP9]], <8 x i64> [[TMP10]], <10 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9>
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <10 x i64> [[TMP11]], <10 x i64> poison, <10 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 1, i32 3, i32 5, i32 7, i32 9>
-; SCALABLE-NEXT:    store <10 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
-; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
-; SCALABLE-NEXT:    [[TMP12:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; SCALABLE-NEXT:    br i1 [[TMP12]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
+; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 5 x i64>, ptr [[TMP1]], align 8
+; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave5.nxv5i64(<vscale x 5 x i64> [[WIDE_VEC]])
+; SCALABLE-NEXT:    [[TMP5:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 0
+; SCALABLE-NEXT:    [[TMP6:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 1
+; SCALABLE-NEXT:    [[TMP7:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 2
+; SCALABLE-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 3
+; SCALABLE-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 4
+; SCALABLE-NEXT:    [[TMP10:%.*]] = add <vscale x 1 x i64> [[TMP5]], splat (i64 1)
+; SCALABLE-NEXT:    [[TMP11:%.*]] = add <vscale x 1 x i64> [[TMP6]], splat (i64 2)
+; SCALABLE-NEXT:    [[TMP12:%.*]] = add <vscale x 1 x i64> [[TMP7]], splat (i64 3)
+; SCALABLE-NEXT:    [[TMP13:%.*]] = add <vscale x 1 x i64> [[TMP8]], splat (i64 4)
+; SCALABLE-NEXT:    [[TMP14:%.*]] = add <vscale x 1 x i64> [[TMP9]], splat (i64 5)
+; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 5 x i64> @llvm.vector.interleave5.nxv5i64(<vscale x 1 x i64> [[TMP10]], <vscale x 1 x i64> [[TMP11]], <vscale x 1 x i64> [[TMP12]], <vscale x 1 x i64> [[TMP13]], <vscale x 1 x i64> [[TMP14]])
+; SCALABLE-NEXT:    store <vscale x 5 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
+; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
+; SCALABLE-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; SCALABLE-NEXT:    br i1 [[TMP15]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP12:![0-9]+]]
 ; SCALABLE:       middle.block:
-; SCALABLE-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; SCALABLE:       scalar.ph:
-; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; SCALABLE-NEXT:    br label [[LOOP:%.*]]
 ; SCALABLE:       loop:
 ; SCALABLE-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
@@ -1217,41 +1243,43 @@ exit:
 define void @load_store_factor6(ptr %p) {
 ; CHECK-LABEL: @load_store_factor6(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP3]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = mul i64 [[INDEX]], 6
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
-; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <12 x i64>, ptr [[TMP1]], align 8
-; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 0, i32 6>
-; CHECK-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 1, i32 7>
-; CHECK-NEXT:    [[STRIDED_VEC2:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 2, i32 8>
-; CHECK-NEXT:    [[STRIDED_VEC3:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 3, i32 9>
-; CHECK-NEXT:    [[STRIDED_VEC4:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 4, i32 10>
-; CHECK-NEXT:    [[STRIDED_VEC5:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 5, i32 11>
-; CHECK-NEXT:    [[TMP2:%.*]] = add <2 x i64> [[STRIDED_VEC]], splat (i64 1)
-; CHECK-NEXT:    [[TMP3:%.*]] = add <2 x i64> [[STRIDED_VEC1]], splat (i64 2)
-; CHECK-NEXT:    [[TMP4:%.*]] = add <2 x i64> [[STRIDED_VEC2]], splat (i64 3)
-; CHECK-NEXT:    [[TMP5:%.*]] = add <2 x i64> [[STRIDED_VEC3]], splat (i64 4)
-; CHECK-NEXT:    [[TMP6:%.*]] = add <2 x i64> [[STRIDED_VEC4]], splat (i64 5)
-; CHECK-NEXT:    [[TMP7:%.*]] = add <2 x i64> [[STRIDED_VEC5]], splat (i64 6)
-; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP9:%.*]] = shufflevector <2 x i64> [[TMP4]], <2 x i64> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP10:%.*]] = shufflevector <2 x i64> [[TMP6]], <2 x i64> [[TMP7]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <4 x i64> [[TMP8]], <4 x i64> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    [[TMP12:%.*]] = shufflevector <4 x i64> [[TMP10]], <4 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
-; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <8 x i64> [[TMP11]], <8 x i64> [[TMP12]], <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
-; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <12 x i64> [[TMP13]], <12 x i64> poison, <12 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 1, i32 3, i32 5, i32 7, i32 9, i32 11>
-; CHECK-NEXT:    store <12 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
-; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
+; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 6 x i64>, ptr [[TMP1]], align 8
+; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave6.nxv6i64(<vscale x 6 x i64> [[WIDE_VEC]])
+; CHECK-NEXT:    [[TMP5:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 0
+; CHECK-NEXT:    [[TMP6:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 1
+; CHECK-NEXT:    [[TMP7:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 2
+; CHECK-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 3
+; CHECK-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 4
+; CHECK-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 5
+; CHECK-NEXT:    [[TMP11:%.*]] = add <vscale x 1 x i64> [[TMP5]], splat (i64 1)
+; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 1 x i64> [[TMP6]], splat (i64 2)
+; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 1 x i64> [[TMP7]], splat (i64 3)
+; CHECK-NEXT:    [[TMP14:%.*]] = add <vscale x 1 x i64> [[TMP8]], splat (i64 4)
+; CHECK-NEXT:    [[TMP15:%.*]] = add <vscale x 1 x i64> [[TMP9]], splat (i64 5)
+; CHECK-NEXT:    [[TMP16:%.*]] = add <vscale x 1 x i64> [[TMP10]], splat (i64 6)
+; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 6 x i64> @llvm.vector.interleave6.nxv6i64(<vscale x 1 x i64> [[TMP11]], <vscale x 1 x i64> [[TMP12]], <vscale x 1 x i64> [[TMP13]], <vscale x 1 x i64> [[TMP14]], <vscale x 1 x i64> [[TMP15]], <vscale x 1 x i64> [[TMP16]])
+; CHECK-NEXT:    store <vscale x 6 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
+; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
@@ -1369,41 +1397,43 @@ define void @load_store_factor6(ptr %p) {
 ;
 ; SCALABLE-LABEL: @load_store_factor6(
 ; SCALABLE-NEXT:  entry:
-; SCALABLE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; SCALABLE-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP3]]
+; SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; SCALABLE:       vector.ph:
+; SCALABLE-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; SCALABLE-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; SCALABLE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; SCALABLE:       vector.body:
 ; SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; SCALABLE-NEXT:    [[TMP0:%.*]] = mul i64 [[INDEX]], 6
 ; SCALABLE-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
-; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <12 x i64>, ptr [[TMP1]], align 8
-; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 0, i32 6>
-; SCALABLE-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 1, i32 7>
-; SCALABLE-NEXT:    [[STRIDED_VEC2:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 2, i32 8>
-; SCALABLE-NEXT:    [[STRIDED_VEC3:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 3, i32 9>
-; SCALABLE-NEXT:    [[STRIDED_VEC4:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 4, i32 10>
-; SCALABLE-NEXT:    [[STRIDED_VEC5:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <2 x i32> <i32 5, i32 11>
-; SCALABLE-NEXT:    [[TMP2:%.*]] = add <2 x i64> [[STRIDED_VEC]], splat (i64 1)
-; SCALABLE-NEXT:    [[TMP3:%.*]] = add <2 x i64> [[STRIDED_VEC1]], splat (i64 2)
-; SCALABLE-NEXT:    [[TMP4:%.*]] = add <2 x i64> [[STRIDED_VEC2]], splat (i64 3)
-; SCALABLE-NEXT:    [[TMP5:%.*]] = add <2 x i64> [[STRIDED_VEC3]], splat (i64 4)
-; SCALABLE-NEXT:    [[TMP6:%.*]] = add <2 x i64> [[STRIDED_VEC4]], splat (i64 5)
-; SCALABLE-NEXT:    [[TMP7:%.*]] = add <2 x i64> [[STRIDED_VEC5]], splat (i64 6)
-; SCALABLE-NEXT:    [[TMP8:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; SCALABLE-NEXT:    [[TMP9:%.*]] = shufflevector <2 x i64> [[TMP4]], <2 x i64> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; SCALABLE-NEXT:    [[TMP10:%.*]] = shufflevector <2 x i64> [[TMP6]], <2 x i64> [[TMP7]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; SCALABLE-NEXT:    [[TMP11:%.*]] = shufflevector <4 x i64> [[TMP8]], <4 x i64> [[TMP9]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; SCALABLE-NEXT:    [[TMP12:%.*]] = shufflevector <4 x i64> [[TMP10]], <4 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
-; SCALABLE-NEXT:    [[TMP13:%.*]] = shufflevector <8 x i64> [[TMP11]], <8 x i64> [[TMP12]], <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <12 x i64> [[TMP13]], <12 x i64> poison, <12 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 1, i32 3, i32 5, i32 7, i32 9, i32 11>
-; SCALABLE-NEXT:    store <12 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
-; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
-; SCALABLE-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; SCALABLE-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
+; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 6 x i64>, ptr [[TMP1]], align 8
+; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave6.nxv6i64(<vscale x 6 x i64> [[WIDE_VEC]])
+; SCALABLE-NEXT:    [[TMP5:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 0
+; SCALABLE-NEXT:    [[TMP6:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 1
+; SCALABLE-NEXT:    [[TMP7:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 2
+; SCALABLE-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 3
+; SCALABLE-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 4
+; SCALABLE-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 5
+; SCALABLE-NEXT:    [[TMP11:%.*]] = add <vscale x 1 x i64> [[TMP5]], splat (i64 1)
+; SCALABLE-NEXT:    [[TMP12:%.*]] = add <vscale x 1 x i64> [[TMP6]], splat (i64 2)
+; SCALABLE-NEXT:    [[TMP13:%.*]] = add <vscale x 1 x i64> [[TMP7]], splat (i64 3)
+; SCALABLE-NEXT:    [[TMP14:%.*]] = add <vscale x 1 x i64> [[TMP8]], splat (i64 4)
+; SCALABLE-NEXT:    [[TMP15:%.*]] = add <vscale x 1 x i64> [[TMP9]], splat (i64 5)
+; SCALABLE-NEXT:    [[TMP16:%.*]] = add <vscale x 1 x i64> [[TMP10]], splat (i64 6)
+; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 6 x i64> @llvm.vector.interleave6.nxv6i64(<vscale x 1 x i64> [[TMP11]], <vscale x 1 x i64> [[TMP12]], <vscale x 1 x i64> [[TMP13]], <vscale x 1 x i64> [[TMP14]], <vscale x 1 x i64> [[TMP15]], <vscale x 1 x i64> [[TMP16]])
+; SCALABLE-NEXT:    store <vscale x 6 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
+; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
+; SCALABLE-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; SCALABLE-NEXT:    br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP14:![0-9]+]]
 ; SCALABLE:       middle.block:
-; SCALABLE-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; SCALABLE:       scalar.ph:
-; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; SCALABLE-NEXT:    br label [[LOOP:%.*]]
 ; SCALABLE:       loop:
 ; SCALABLE-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
@@ -1494,45 +1524,45 @@ exit:
 define void @load_store_factor7(ptr %p) {
 ; CHECK-LABEL: @load_store_factor7(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP3]]
+; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
+; CHECK-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; CHECK-NEXT:    [[TMP0:%.*]] = mul i64 [[INDEX]], 7
 ; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
-; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <14 x i64>, ptr [[TMP1]], align 8
-; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 0, i32 7>
-; CHECK-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 1, i32 8>
-; CHECK-NEXT:    [[STRIDED_VEC2:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 2, i32 9>
-; CHECK-NEXT:    [[STRIDED_VEC3:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 3, i32 10>
-; CHECK-NEXT:    [[STRIDED_VEC4:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 4, i32 11>
-; CHECK-NEXT:    [[STRIDED_VEC5:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 5, i32 12>
-; CHECK-NEXT:    [[STRIDED_VEC6:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 6, i32 13>
-; CHECK-NEXT:    [[TMP2:%.*]] = add <2 x i64> [[STRIDED_VEC]], splat (i64 1)
-; CHECK-NEXT:    [[TMP3:%.*]] = add <2 x i64> [[STRIDED_VEC1]], splat (i64 2)
-; CHECK-NEXT:    [[TMP4:%.*]] = add <2 x i64> [[STRIDED_VEC2]], splat (i64 3)
-; CHECK-NEXT:    [[TMP5:%.*]] = add <2 x i64> [[STRIDED_VEC3]], splat (i64 4)
-; CHECK-NEXT:    [[TMP6:%.*]] = add <2 x i64> [[STRIDED_VEC4]], splat (i64 5)
-; CHECK-NEXT:    [[TMP7:%.*]] = add <2 x i64> [[STRIDED_VEC5]], splat (i64 6)
-; CHECK-NEXT:    [[TMP8:%.*]] = add <2 x i64> [[STRIDED_VEC6]], splat (i64 7)
-; CHECK-NEXT:    [[TMP9:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP10:%.*]] = shufflevector <2 x i64> [[TMP4]], <2 x i64> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <2 x i64> [[TMP6]], <2 x i64> [[TMP7]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; CHECK-NEXT:    [[TMP12:%.*]] = shufflevector <4 x i64> [[TMP9]], <4 x i64> [[TMP10]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <2 x i64> [[TMP8]], <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
-; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <4 x i64> [[TMP11]], <4 x i64> [[TMP13]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
-; CHECK-NEXT:    [[TMP15:%.*]] = shufflevector <6 x i64> [[TMP14]], <6 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 poison, i32 poison>
-; CHECK-NEXT:    [[TMP16:%.*]] = shufflevector <8 x i64> [[TMP12]], <8 x i64> [[TMP15]], <14 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13>
-; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <14 x i64> [[TMP16]], <14 x i64> poison, <14 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13>
-; CHECK-NEXT:    store <14 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
-; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; CHECK-NEXT:    br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
+; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 7 x i64>, ptr [[TMP1]], align 8
+; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave7.nxv7i64(<vscale x 7 x i64> [[WIDE_VEC]])
+; CHECK-NEXT:    [[TMP5:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 0
+; CHECK-NEXT:    [[TMP6:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 1
+; CHECK-NEXT:    [[TMP7:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 2
+; CHECK-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 3
+; CHECK-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 4
+; CHECK-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 5
+; CHECK-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 6
+; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 1 x i64> [[TMP5]], splat (i64 1)
+; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 1 x i64> [[TMP6]], splat (i64 2)
+; CHECK-NEXT:    [[TMP14:%.*]] = add <vscale x 1 x i64> [[TMP7]], splat (i64 3)
+; CHECK-NEXT:    [[TMP15:%.*]] = add <vscale x 1 x i64> [[TMP8]], splat (i64 4)
+; CHECK-NEXT:    [[TMP16:%.*]] = add <vscale x 1 x i64> [[TMP9]], splat (i64 5)
+; CHECK-NEXT:    [[TMP17:%.*]] = add <vscale x 1 x i64> [[TMP10]], splat (i64 6)
+; CHECK-NEXT:    [[TMP18:%.*]] = add <vscale x 1 x i64> [[TMP11]], splat (i64 7)
+; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 7 x i64> @llvm.vector.interleave7.nxv7i64(<vscale x 1 x i64> [[TMP12]], <vscale x 1 x i64> [[TMP13]], <vscale x 1 x i64> [[TMP14]], <vscale x 1 x i64> [[TMP15]], <vscale x 1 x i64> [[TMP16]], <vscale x 1 x i64> [[TMP17]], <vscale x 1 x i64> [[TMP18]])
+; CHECK-NEXT:    store <vscale x 7 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
+; CHECK-NEXT:    [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
@@ -1664,45 +1694,45 @@ define void @load_store_factor7(ptr %p) {
 ;
 ; SCALABLE-LABEL: @load_store_factor7(
 ; SCALABLE-NEXT:  entry:
-; SCALABLE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; SCALABLE-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP3]]
+; SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; SCALABLE:       vector.ph:
+; SCALABLE-NEXT:    [[TMP4:%.*]] = call i64 @llvm.vscale.i64()
+; SCALABLE-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1024, [[TMP4]]
+; SCALABLE-NEXT:    [[N_VEC:%.*]] = sub i64 1024, [[N_MOD_VF]]
+; SCALABLE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; SCALABLE:       vector.body:
 ; SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; SCALABLE-NEXT:    [[TMP0:%.*]] = mul i64 [[INDEX]], 7
 ; SCALABLE-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP0]]
-; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <14 x i64>, ptr [[TMP1]], align 8
-; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 0, i32 7>
-; SCALABLE-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 1, i32 8>
-; SCALABLE-NEXT:    [[STRIDED_VEC2:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 2, i32 9>
-; SCALABLE-NEXT:    [[STRIDED_VEC3:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 3, i32 10>
-; SCALABLE-NEXT:    [[STRIDED_VEC4:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 4, i32 11>
-; SCALABLE-NEXT:    [[STRIDED_VEC5:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 5, i32 12>
-; SCALABLE-NEXT:    [[STRIDED_VEC6:%.*]] = shufflevector <14 x i64> [[WIDE_VEC]], <14 x i64> poison, <2 x i32> <i32 6, i32 13>
-; SCALABLE-NEXT:    [[TMP2:%.*]] = add <2 x i64> [[STRIDED_VEC]], splat (i64 1)
-; SCALABLE-NEXT:    [[TMP3:%.*]] = add <2 x i64> [[STRIDED_VEC1]], splat (i64 2)
-; SCALABLE-NEXT:    [[TMP4:%.*]] = add <2 x i64> [[STRIDED_VEC2]], splat (i64 3)
-; SCALABLE-NEXT:    [[TMP5:%.*]] = add <2 x i64> [[STRIDED_VEC3]], splat (i64 4)
-; SCALABLE-NEXT:    [[TMP6:%.*]] = add <2 x i64> [[STRIDED_VEC4]], splat (i64 5)
-; SCALABLE-NEXT:    [[TMP7:%.*]] = add <2 x i64> [[STRIDED_VEC5]], splat (i64 6)
-; SCALABLE-NEXT:    [[TMP8:%.*]] = add <2 x i64> [[STRIDED_VEC6]], splat (i64 7)
-; SCALABLE-NEXT:    [[TMP9:%.*]] = shufflevector <2 x i64> [[TMP2]], <2 x i64> [[TMP3]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; SCALABLE-NEXT:    [[TMP10:%.*]] = shufflevector <2 x i64> [[TMP4]], <2 x i64> [[TMP5]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; SCALABLE-NEXT:    [[TMP11:%.*]] = shufflevector <2 x i64> [[TMP6]], <2 x i64> [[TMP7]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
-; SCALABLE-NEXT:    [[TMP12:%.*]] = shufflevector <4 x i64> [[TMP9]], <4 x i64> [[TMP10]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
-; SCALABLE-NEXT:    [[TMP13:%.*]] = shufflevector <2 x i64> [[TMP8]], <2 x i64> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
-; SCALABLE-NEXT:    [[TMP14:%.*]] = shufflevector <4 x i64> [[TMP11]], <4 x i64> [[TMP13]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
-; SCALABLE-NEXT:    [[TMP15:%.*]] = shufflevector <6 x i64> [[TMP14]], <6 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 poison, i32 poison>
-; SCALABLE-NEXT:    [[TMP16:%.*]] = shufflevector <8 x i64> [[TMP12]], <8 x i64> [[TMP15]], <14 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13>
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <14 x i64> [[TMP16]], <14 x i64> poison, <14 x i32> <i32 0, i32 2, i32 4, i32 6, i32 8, i32 10, i32 12, i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13>
-; SCALABLE-NEXT:    store <14 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
-; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
-; SCALABLE-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
-; SCALABLE-NEXT:    br i1 [[TMP17]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
+; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 7 x i64>, ptr [[TMP1]], align 8
+; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave7.nxv7i64(<vscale x 7 x i64> [[WIDE_VEC]])
+; SCALABLE-NEXT:    [[TMP5:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 0
+; SCALABLE-NEXT:    [[TMP6:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 1
+; SCALABLE-NEXT:    [[TMP7:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 2
+; SCALABLE-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 3
+; SCALABLE-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 4
+; SCALABLE-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 5
+; SCALABLE-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 6
+; SCALABLE-NEXT:    [[TMP12:%.*]] = add <vscale x 1 x i64> [[TMP5]], splat (i64 1)
+; SCALABLE-NEXT:    [[TMP13:%.*]] = add <vscale x 1 x i64> [[TMP6]], splat (i64 2)
+; SCALABLE-NEXT:    [[TMP14:%.*]] = add <vscale x 1 x i64> [[TMP7]], splat (i64 3)
+; SCALABLE-NEXT:    [[TMP15:%.*]] = add <vscale x 1 x i64> [[TMP8]], splat (i64 4)
+; SCALABLE-NEXT:    [[TMP16:%.*]] = add <vscale x 1 x i64> [[TMP9]], splat (i64 5)
+; SCALABLE-NEXT:    [[TMP17:%.*]] = add <vscale x 1 x i64> [[TMP10]], splat (i64 6)
+; SCALABLE-NEXT:    [[TMP18:%.*]] = add <vscale x 1 x i64> [[TMP11]], splat (i64 7)
+; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 7 x i64> @llvm.vector.interleave7.nxv7i64(<vscale x 1 x i64> [[TMP12]], <vscale x 1 x i64> [[TMP13]], <vscale x 1 x i64> [[TMP14]], <vscale x 1 x i64> [[TMP15]], <vscale x 1 x i64> [[TMP16]], <vscale x 1 x i64> [[TMP17]], <vscale x 1 x i64> [[TMP18]])
+; SCALABLE-NEXT:    store <vscale x 7 x i64> [[INTERLEAVED_VEC]], ptr [[TMP1]], align 8
+; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
+; SCALABLE-NEXT:    [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; SCALABLE-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP16:![0-9]+]]
 ; SCALABLE:       middle.block:
-; SCALABLE-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
+; SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; SCALABLE:       scalar.ph:
-; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; SCALABLE-NEXT:    br label [[LOOP:%.*]]
 ; SCALABLE:       loop:
 ; SCALABLE-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
@@ -1818,27 +1848,15 @@ define void @load_store_factor8(ptr %p) {
 ; CHECK-NEXT:    [[TMP3:%.*]] = shl i64 [[INDEX]], 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP3]]
 ; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 8 x i64>, ptr [[TMP4]], align 8
-; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> [[WIDE_VEC]])
-; CHECK-NEXT:    [[TMP5:%.*]] = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } [[STRIDED_VEC]], 0
-; CHECK-NEXT:    [[TMP6:%.*]] = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } [[STRIDED_VEC]], 1
-; CHECK-NEXT:    [[STRIDED_VEC1:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> [[TMP5]])
-; CHECK-NEXT:    [[STRIDED_VEC2:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> [[TMP6]])
-; CHECK-NEXT:    [[TMP7:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC1]], 0
-; CHECK-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC2]], 0
-; CHECK-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC1]], 1
-; CHECK-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC2]], 1
-; CHECK-NEXT:    [[STRIDED_VEC3:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> [[TMP7]])
-; CHECK-NEXT:    [[STRIDED_VEC4:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> [[TMP8]])
-; CHECK-NEXT:    [[STRIDED_VEC5:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> [[TMP9]])
-; CHECK-NEXT:    [[STRIDED_VEC6:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> [[TMP10]])
-; CHECK-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC3]], 0
-; CHECK-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC4]], 0
-; CHECK-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC5]], 0
-; CHECK-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC6]], 0
-; CHECK-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC3]], 1
-; CHECK-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC4]], 1
-; CHECK-NEXT:    [[TMP17:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC5]], 1
-; CHECK-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC6]], 1
+; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave8.nxv8i64(<vscale x 8 x i64> [[WIDE_VEC]])
+; CHECK-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 0
+; CHECK-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 1
+; CHECK-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 2
+; CHECK-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 3
+; CHECK-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 4
+; CHECK-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 5
+; CHECK-NEXT:    [[TMP17:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 6
+; CHECK-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 7
 ; CHECK-NEXT:    [[TMP19:%.*]] = add <vscale x 1 x i64> [[TMP11]], splat (i64 1)
 ; CHECK-NEXT:    [[TMP20:%.*]] = add <vscale x 1 x i64> [[TMP12]], splat (i64 2)
 ; CHECK-NEXT:    [[TMP21:%.*]] = add <vscale x 1 x i64> [[TMP13]], splat (i64 3)
@@ -1847,13 +1865,7 @@ define void @load_store_factor8(ptr %p) {
 ; CHECK-NEXT:    [[TMP24:%.*]] = add <vscale x 1 x i64> [[TMP16]], splat (i64 6)
 ; CHECK-NEXT:    [[TMP25:%.*]] = add <vscale x 1 x i64> [[TMP17]], splat (i64 7)
 ; CHECK-NEXT:    [[TMP26:%.*]] = add <vscale x 1 x i64> [[TMP18]], splat (i64 8)
-; CHECK-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64> [[TMP19]], <vscale x 1 x i64> [[TMP23]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC7:%.*]] = call <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64> [[TMP20]], <vscale x 1 x i64> [[TMP24]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC8:%.*]] = call <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64> [[TMP21]], <vscale x 1 x i64> [[TMP25]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC9:%.*]] = call <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64> [[TMP22]], <vscale x 1 x i64> [[TMP26]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC10:%.*]] = call <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64> [[INTERLEAVED_VEC]], <vscale x 2 x i64> [[INTERLEAVED_VEC8]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC11:%.*]] = call <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64> [[INTERLEAVED_VEC7]], <vscale x 2 x i64> [[INTERLEAVED_VEC9]])
-; CHECK-NEXT:    [[INTERLEAVED_VEC12:%.*]] = call <vscale x 8 x i64> @llvm.vector.interleave2.nxv8i64(<vscale x 4 x i64> [[INTERLEAVED_VEC10]], <vscale x 4 x i64> [[INTERLEAVED_VEC11]])
+; CHECK-NEXT:    [[INTERLEAVED_VEC12:%.*]] = call <vscale x 8 x i64> @llvm.vector.interleave8.nxv8i64(<vscale x 1 x i64> [[TMP19]], <vscale x 1 x i64> [[TMP20]], <vscale x 1 x i64> [[TMP21]], <vscale x 1 x i64> [[TMP22]], <vscale x 1 x i64> [[TMP23]], <vscale x 1 x i64> [[TMP24]], <vscale x 1 x i64> [[TMP25]], <vscale x 1 x i64> [[TMP26]])
 ; CHECK-NEXT:    store <vscale x 8 x i64> [[INTERLEAVED_VEC12]], ptr [[TMP4]], align 8
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
 ; CHECK-NEXT:    [[TMP27:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
@@ -2019,27 +2031,15 @@ define void @load_store_factor8(ptr %p) {
 ; SCALABLE-NEXT:    [[TMP3:%.*]] = shl i64 [[INDEX]], 3
 ; SCALABLE-NEXT:    [[TMP4:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP3]]
 ; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 8 x i64>, ptr [[TMP4]], align 8
-; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i64>, <vscale x 4 x i64> } @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> [[WIDE_VEC]])
-; SCALABLE-NEXT:    [[TMP5:%.*]] = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } [[STRIDED_VEC]], 0
-; SCALABLE-NEXT:    [[TMP6:%.*]] = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } [[STRIDED_VEC]], 1
-; SCALABLE-NEXT:    [[STRIDED_VEC1:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> [[TMP5]])
-; SCALABLE-NEXT:    [[STRIDED_VEC2:%.*]] = call { <vscale x 2 x i64>, <vscale x 2 x i64> } @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> [[TMP6]])
-; SCALABLE-NEXT:    [[TMP7:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC1]], 0
-; SCALABLE-NEXT:    [[TMP8:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC2]], 0
-; SCALABLE-NEXT:    [[TMP9:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC1]], 1
-; SCALABLE-NEXT:    [[TMP10:%.*]] = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } [[STRIDED_VEC2]], 1
-; SCALABLE-NEXT:    [[STRIDED_VEC3:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> [[TMP7]])
-; SCALABLE-NEXT:    [[STRIDED_VEC4:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> [[TMP8]])
-; SCALABLE-NEXT:    [[STRIDED_VEC5:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> [[TMP9]])
-; SCALABLE-NEXT:    [[STRIDED_VEC6:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave2.nxv2i64(<vscale x 2 x i64> [[TMP10]])
-; SCALABLE-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC3]], 0
-; SCALABLE-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC4]], 0
-; SCALABLE-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC5]], 0
-; SCALABLE-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC6]], 0
-; SCALABLE-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC3]], 1
-; SCALABLE-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC4]], 1
-; SCALABLE-NEXT:    [[TMP17:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC5]], 1
-; SCALABLE-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC6]], 1
+; SCALABLE-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } @llvm.vector.deinterleave8.nxv8i64(<vscale x 8 x i64> [[WIDE_VEC]])
+; SCALABLE-NEXT:    [[TMP11:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 0
+; SCALABLE-NEXT:    [[TMP12:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 1
+; SCALABLE-NEXT:    [[TMP13:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 2
+; SCALABLE-NEXT:    [[TMP14:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 3
+; SCALABLE-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 4
+; SCALABLE-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 5
+; SCALABLE-NEXT:    [[TMP17:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 6
+; SCALABLE-NEXT:    [[TMP18:%.*]] = extractvalue { <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64>, <vscale x 1 x i64> } [[STRIDED_VEC]], 7
 ; SCALABLE-NEXT:    [[TMP19:%.*]] = add <vscale x 1 x i64> [[TMP11]], splat (i64 1)
 ; SCALABLE-NEXT:    [[TMP20:%.*]] = add <vscale x 1 x i64> [[TMP12]], splat (i64 2)
 ; SCALABLE-NEXT:    [[TMP21:%.*]] = add <vscale x 1 x i64> [[TMP13]], splat (i64 3)
@@ -2048,13 +2048,7 @@ define void @load_store_factor8(ptr %p) {
 ; SCALABLE-NEXT:    [[TMP24:%.*]] = add <vscale x 1 x i64> [[TMP16]], splat (i64 6)
 ; SCALABLE-NEXT:    [[TMP25:%.*]] = add <vscale x 1 x i64> [[TMP17]], splat (i64 7)
 ; SCALABLE-NEXT:    [[TMP26:%.*]] = add <vscale x 1 x i64> [[TMP18]], splat (i64 8)
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC:%.*]] = call <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64> [[TMP19]], <vscale x 1 x i64> [[TMP23]])
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC7:%.*]] = call <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64> [[TMP20]], <vscale x 1 x i64> [[TMP24]])
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC8:%.*]] = call <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64> [[TMP21]], <vscale x 1 x i64> [[TMP25]])
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC9:%.*]] = call <vscale x 2 x i64> @llvm.vector.interleave2.nxv2i64(<vscale x 1 x i64> [[TMP22]], <vscale x 1 x i64> [[TMP26]])
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC10:%.*]] = call <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64> [[INTERLEAVED_VEC]], <vscale x 2 x i64> [[INTERLEAVED_VEC8]])
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC11:%.*]] = call <vscale x 4 x i64> @llvm.vector.interleave2.nxv4i64(<vscale x 2 x i64> [[INTERLEAVED_VEC7]], <vscale x 2 x i64> [[INTERLEAVED_VEC9]])
-; SCALABLE-NEXT:    [[INTERLEAVED_VEC12:%.*]] = call <vscale x 8 x i64> @llvm.vector.interleave2.nxv8i64(<vscale x 4 x i64> [[INTERLEAVED_VEC10]], <vscale x 4 x i64> [[INTERLEAVED_VEC11]])
+; SCALABLE-NEXT:    [[INTERLEAVED_VEC12:%.*]] = call <vscale x 8 x i64> @llvm.vector.interleave8.nxv8i64(<vscale x 1 x i64> [[TMP19]], <vscale x 1 x i64> [[TMP20]], <vscale x 1 x i64> [[TMP21]], <vscale x 1 x i64> [[TMP22]], <vscale x 1 x i64> [[TMP23]], <vscale x 1 x i64> [[TMP24]], <vscale x 1 x i64> [[TMP25]], <vscale x 1 x i64> [[TMP26]])
 ; SCALABLE-NEXT:    store <vscale x 8 x i64> [[INTERLEAVED_VEC12]], ptr [[TMP4]], align 8
 ; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP2]]
 ; SCALABLE-NEXT:    [[TMP27:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]