diff --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index d2f8a3c0671069..54b8a3ee190f19 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -736,12 +736,24 @@ InstructionCost RISCVTTIImpl::getInterleavedMemoryOpCost(
       if (VTy->getElementCount().isKnownMultipleOf(Factor) &&
           TLI->isLegalInterleavedAccessType(SubVecTy, Factor, Alignment,
                                             AddressSpace, DL)) {
-        // Cost as one wide memory op + Factor * LMUL shuffle ops.
-        InstructionCost Cost =
-            getMemoryOpCost(Opcode, VTy, Alignment, AddressSpace, CostKind);
-        MVT SubVecVT = getTLI()->getValueType(DL, SubVecTy).getSimpleVT();
-        Cost += Factor * TLI->getLMULCost(SubVecVT);
-        return LT.first * Cost;
+
+        // Most available hardware today optimizes NF=2 as as one wide memory op
+        // + Factor * LMUL shuffle ops.
+        if (Factor == 2) {
+          InstructionCost Cost =
+              getMemoryOpCost(Opcode, VTy, Alignment, AddressSpace, CostKind);
+          MVT SubVecVT = getTLI()->getValueType(DL, SubVecTy).getSimpleVT();
+          Cost += Factor * TLI->getLMULCost(SubVecVT);
+          return LT.first * Cost;
+        }
+
+        // Otherwise, the cost is proportional to the number of elements (VL *
+        // Factor ops).
+        InstructionCost MemOpCost =
+            getMemoryOpCost(Opcode, VTy->getElementType(), Alignment, 0,
+                            CostKind, {TTI::OK_AnyValue, TTI::OP_None});
+        unsigned NumLoads = getEstimatedVLFor(VTy);
+        return NumLoads * MemOpCost;
       }
     }
   }
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/dead-ops-cost.ll b/llvm/test/Transforms/LoopVectorize/RISCV/dead-ops-cost.ll
index 0e55ad65cdb2c2..6724afd6ca10f4 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/dead-ops-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/dead-ops-cost.ll
@@ -410,45 +410,49 @@ define void @gather_interleave_group_with_dead_insert_pos(i64 %N, ptr noalias %s
 ; CHECK-SAME: i64 [[N:%.*]], ptr noalias [[SRC:%.*]], ptr noalias [[DST:%.*]]) #[[ATTR2]] {
 ; CHECK-NEXT:  [[ENTRY:.*]]:
 ; CHECK-NEXT:    [[SMAX:%.*]] = call i64 @llvm.smax.i64(i64 [[N]], i64 0)
-; CHECK-NEXT:    [[TMP0:%.*]] = add nuw i64 [[SMAX]], 3
-; CHECK-NEXT:    [[TMP1:%.*]] = lshr i64 [[TMP0]], 2
+; CHECK-NEXT:    [[TMP0:%.*]] = add nuw i64 [[SMAX]], 1
+; CHECK-NEXT:    [[TMP1:%.*]] = lshr i64 [[TMP0]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ule i64 [[TMP2]], 16
+; CHECK-NEXT:    [[TMP3:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP4:%.*]] = mul i64 [[TMP3]], 4
+; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], [[TMP4]]
 ; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
 ; CHECK:       [[VECTOR_PH]]:
-; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], 16
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq i64 [[N_MOD_VF]], 0
-; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP3]], i64 16, i64 [[N_MOD_VF]]
-; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP2]], [[TMP4]]
-; CHECK-NEXT:    [[IND_END:%.*]] = mul i64 [[N_VEC]], 4
+; CHECK-NEXT:    [[TMP5:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP6:%.*]] = mul i64 [[TMP5]], 4
+; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP2]], [[TMP6]]
+; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP2]], [[N_MOD_VF]]
+; CHECK-NEXT:    [[IND_END:%.*]] = mul i64 [[N_VEC]], 2
+; CHECK-NEXT:    [[TMP7:%.*]] = call i64 @llvm.vscale.i64()
+; CHECK-NEXT:    [[TMP8:%.*]] = mul i64 [[TMP7]], 4
+; CHECK-NEXT:    [[TMP9:%.*]] = call <vscale x 4 x i64> @llvm.stepvector.nxv4i64()
+; CHECK-NEXT:    [[TMP10:%.*]] = add <vscale x 4 x i64> [[TMP9]], zeroinitializer
+; CHECK-NEXT:    [[TMP11:%.*]] = mul <vscale x 4 x i64> [[TMP10]], shufflevector (<vscale x 4 x i64> insertelement (<vscale x 4 x i64> poison, i64 2, i64 0), <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer)
+; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 4 x i64> zeroinitializer, [[TMP11]]
+; CHECK-NEXT:    [[TMP12:%.*]] = mul i64 2, [[TMP8]]
+; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 4 x i64> poison, i64 [[TMP12]], i64 0
+; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 4 x i64> [[DOTSPLATINSERT]], <vscale x 4 x i64> poison, <vscale x 4 x i32> zeroinitializer
 ; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
 ; CHECK:       [[VECTOR_BODY]]:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <8 x i64> [ <i64 0, i64 4, i64 8, i64 12, i64 16, i64 20, i64 24, i64 28>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[STEP_ADD:%.*]] = add <8 x i64> [[VEC_IND]], <i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32>
-; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], 4
-; CHECK-NEXT:    [[TMP5:%.*]] = add i64 [[OFFSET_IDX]], 0
-; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[OFFSET_IDX]], 32
-; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[TMP5]]
-; CHECK-NEXT:    [[TMP8:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[TMP6]]
-; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <32 x i8>, ptr [[TMP7]], align 1
-; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <32 x i8> [[WIDE_VEC]], <32 x i8> poison, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
-; CHECK-NEXT:    [[STRIDED_VEC4:%.*]] = shufflevector <32 x i8> [[WIDE_VEC]], <32 x i8> poison, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
-; CHECK-NEXT:    [[WIDE_VEC2:%.*]] = load <32 x i8>, ptr [[TMP8]], align 1
-; CHECK-NEXT:    [[STRIDED_VEC3:%.*]] = shufflevector <32 x i8> [[WIDE_VEC2]], <32 x i8> poison, <8 x i32> <i32 0, i32 4, i32 8, i32 12, i32 16, i32 20, i32 24, i32 28>
-; CHECK-NEXT:    [[STRIDED_VEC5:%.*]] = shufflevector <32 x i8> [[WIDE_VEC2]], <32 x i8> poison, <8 x i32> <i32 1, i32 5, i32 9, i32 13, i32 17, i32 21, i32 25, i32 29>
-; CHECK-NEXT:    [[TMP11:%.*]] = zext <8 x i8> [[STRIDED_VEC4]] to <8 x i32>
-; CHECK-NEXT:    [[TMP12:%.*]] = zext <8 x i8> [[STRIDED_VEC5]] to <8 x i32>
-; CHECK-NEXT:    [[TMP13:%.*]] = getelementptr i32, ptr [[DST]], <8 x i64> [[VEC_IND]]
-; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i32, ptr [[DST]], <8 x i64> [[STEP_ADD]]
-; CHECK-NEXT:    call void @llvm.masked.scatter.v8i32.v8p0(<8 x i32> [[TMP11]], <8 x ptr> [[TMP13]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
-; CHECK-NEXT:    call void @llvm.masked.scatter.v8i32.v8p0(<8 x i32> [[TMP12]], <8 x ptr> [[TMP14]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>)
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
-; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <8 x i64> [[STEP_ADD]], <i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32, i64 32>
-; CHECK-NEXT:    [[TMP15:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP15]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
+; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 4 x i64> [ [[INDUCTION]], %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = mul i64 [[INDEX]], 2
+; CHECK-NEXT:    [[TMP13:%.*]] = add i64 [[OFFSET_IDX]], 0
+; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i8, ptr [[SRC]], i64 [[TMP13]]
+; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <vscale x 8 x i8>, ptr [[TMP14]], align 1
+; CHECK-NEXT:    [[STRIDED_VEC:%.*]] = call { <vscale x 4 x i8>, <vscale x 4 x i8> } @llvm.vector.deinterleave2.nxv8i8(<vscale x 8 x i8> [[WIDE_VEC]])
+; CHECK-NEXT:    [[TMP15:%.*]] = extractvalue { <vscale x 4 x i8>, <vscale x 4 x i8> } [[STRIDED_VEC]], 0
+; CHECK-NEXT:    [[TMP16:%.*]] = extractvalue { <vscale x 4 x i8>, <vscale x 4 x i8> } [[STRIDED_VEC]], 1
+; CHECK-NEXT:    [[TMP17:%.*]] = zext <vscale x 4 x i8> [[TMP16]] to <vscale x 4 x i32>
+; CHECK-NEXT:    [[TMP18:%.*]] = getelementptr i32, ptr [[DST]], <vscale x 4 x i64> [[VEC_IND]]
+; CHECK-NEXT:    call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> [[TMP17]], <vscale x 4 x ptr> [[TMP18]], i32 4, <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer))
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP8]]
+; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 4 x i64> [[VEC_IND]], [[DOTSPLAT]]
+; CHECK-NEXT:    [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[TMP19]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP20:![0-9]+]]
 ; CHECK:       [[MIDDLE_BLOCK]]:
-; CHECK-NEXT:    br label %[[SCALAR_PH]]
+; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 [[TMP2]], [[N_VEC]]
+; CHECK-NEXT:    br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
 ; CHECK:       [[SCALAR_PH]]:
 ; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
 ; CHECK-NEXT:    br label %[[LOOP:.*]]
@@ -462,9 +466,9 @@ define void @gather_interleave_group_with_dead_insert_pos(i64 %N, ptr noalias %s
 ; CHECK-NEXT:    [[EXT:%.*]] = zext i8 [[L_1]] to i32
 ; CHECK-NEXT:    [[GEP_DST:%.*]] = getelementptr i32, ptr [[DST]], i64 [[IV]]
 ; CHECK-NEXT:    store i32 [[EXT]], ptr [[GEP_DST]], align 4
-; CHECK-NEXT:    [[IV_NEXT]] = add nsw i64 [[IV]], 4
+; CHECK-NEXT:    [[IV_NEXT]] = add nsw i64 [[IV]], 2
 ; CHECK-NEXT:    [[EC:%.*]] = icmp slt i64 [[IV]], [[N]]
-; CHECK-NEXT:    br i1 [[EC]], label %[[LOOP]], label %[[EXIT:.*]], !llvm.loop [[LOOP21:![0-9]+]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[LOOP]], label %[[EXIT]], !llvm.loop [[LOOP21:![0-9]+]]
 ; CHECK:       [[EXIT]]:
 ; CHECK-NEXT:    ret void
 ;
@@ -481,7 +485,7 @@ loop:
   %ext  = zext i8 %l.1 to i32
   %gep.dst = getelementptr i32, ptr %dst, i64 %iv
   store i32 %ext, ptr %gep.dst, align 4
-  %iv.next = add nsw i64 %iv, 4
+  %iv.next = add nsw i64 %iv, 2
   %ec = icmp slt i64 %iv, %N
   br i1 %ec, label %loop, label %exit
 
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll
index 5a3a3e2f5b1580..2789ab484e1b66 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-accesses.ll
@@ -550,52 +550,33 @@ exit:
 define void @load_store_factor3_i64(ptr %p) {
 ; CHECK-LABEL: @load_store_factor3_i64(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    br i1 false, 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:    [[TMP6:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
-; CHECK-NEXT:    [[TMP7:%.*]] = add <vscale x 2 x i64> [[TMP6]], zeroinitializer
-; CHECK-NEXT:    [[TMP8:%.*]] = mul <vscale x 2 x i64> [[TMP7]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; CHECK-NEXT:    [[INDUCTION:%.*]] = add <vscale x 2 x i64> zeroinitializer, [[TMP8]]
-; CHECK-NEXT:    [[TMP9:%.*]] = mul i64 1, [[TMP5]]
-; CHECK-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP9]], i64 0
-; CHECK-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
 ; CHECK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 2 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[TMP10:%.*]] = mul <vscale x 2 x i64> [[VEC_IND]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 3, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr i64, ptr [[P:%.*]], <vscale x 2 x i64> [[TMP10]]
-; CHECK-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 2 x i64> @llvm.masked.gather.nxv2i64.nxv2p0(<vscale x 2 x ptr> [[TMP11]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i64> poison)
-; CHECK-NEXT:    [[TMP12:%.*]] = add <vscale x 2 x i64> [[WIDE_MASKED_GATHER]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; CHECK-NEXT:    call void @llvm.masked.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[TMP12]], <vscale x 2 x ptr> [[TMP11]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; CHECK-NEXT:    [[TMP13:%.*]] = add <vscale x 2 x i64> [[TMP10]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP14:%.*]] = getelementptr i64, ptr [[P]], <vscale x 2 x i64> [[TMP13]]
-; CHECK-NEXT:    [[WIDE_MASKED_GATHER1:%.*]] = call <vscale x 2 x i64> @llvm.masked.gather.nxv2i64.nxv2p0(<vscale x 2 x ptr> [[TMP14]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i64> poison)
-; CHECK-NEXT:    [[TMP15:%.*]] = add <vscale x 2 x i64> [[WIDE_MASKED_GATHER1]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 2, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; CHECK-NEXT:    call void @llvm.masked.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[TMP15]], <vscale x 2 x ptr> [[TMP14]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; CHECK-NEXT:    [[TMP16:%.*]] = add <vscale x 2 x i64> [[TMP13]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; CHECK-NEXT:    [[TMP17:%.*]] = getelementptr i64, ptr [[P]], <vscale x 2 x i64> [[TMP16]]
-; CHECK-NEXT:    [[WIDE_MASKED_GATHER2:%.*]] = call <vscale x 2 x i64> @llvm.masked.gather.nxv2i64.nxv2p0(<vscale x 2 x ptr> [[TMP17]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i64> poison)
-; CHECK-NEXT:    [[TMP18:%.*]] = add <vscale x 2 x i64> [[WIDE_MASKED_GATHER2]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 3, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; CHECK-NEXT:    call void @llvm.masked.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[TMP18]], <vscale x 2 x ptr> [[TMP17]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
-; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 2 x i64> [[VEC_IND]], [[DOTSPLAT]]
-; CHECK-NEXT:    [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 3
+; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP1]]
+; CHECK-NEXT:    [[WIDE_VEC:%.*]] = load <12 x i64>, ptr [[TMP2]], 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:    [[TMP4:%.*]] = add <4 x i64> [[STRIDED_VEC]], <i64 1, i64 1, i64 1, i64 1>
+; CHECK-NEXT:    [[TMP6:%.*]] = add <4 x i64> [[STRIDED_VEC1]], <i64 2, i64 2, i64 2, i64 2>
+; CHECK-NEXT:    [[TMP9:%.*]] = add <4 x i64> [[STRIDED_VEC2]], <i64 3, i64 3, i64 3, i64 3>
+; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <4 x i64> [[TMP4]], <4 x i64> [[TMP6]], <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> [[TMP9]], <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 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 [[TMP2]], align 8
+; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
+; CHECK-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
+; CHECK-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
 ; CHECK:       middle.block:
-; CHECK-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
-; CHECK-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; CHECK:       scalar.ph:
-; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
 ; CHECK-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
@@ -627,24 +608,22 @@ define void @load_store_factor3_i64(ptr %p) {
 ; FIXED-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; FIXED:       vector.body:
 ; FIXED-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; FIXED-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 0, i64 1, i64 2, i64 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
-; FIXED-NEXT:    [[TMP0:%.*]] = mul <4 x i64> [[VEC_IND]], <i64 3, i64 3, i64 3, i64 3>
-; FIXED-NEXT:    [[TMP1:%.*]] = getelementptr i64, ptr [[P:%.*]], <4 x i64> [[TMP0]]
-; FIXED-NEXT:    [[STRIDED_VEC:%.*]] = call <4 x i64> @llvm.masked.gather.v4i64.v4p0(<4 x ptr> [[TMP1]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i64> poison)
+; FIXED-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; FIXED-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 3
+; FIXED-NEXT:    [[TMP2:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP1]]
+; FIXED-NEXT:    [[WIDE_VEC:%.*]] = load <12 x i64>, ptr [[TMP2]], align 8
+; FIXED-NEXT:    [[STRIDED_VEC:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <4 x i32> <i32 0, i32 3, i32 6, i32 9>
+; FIXED-NEXT:    [[STRIDED_VEC1:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <4 x i32> <i32 1, i32 4, i32 7, i32 10>
+; FIXED-NEXT:    [[STRIDED_VEC2:%.*]] = shufflevector <12 x i64> [[WIDE_VEC]], <12 x i64> poison, <4 x i32> <i32 2, i32 5, i32 8, i32 11>
 ; FIXED-NEXT:    [[TMP4:%.*]] = add <4 x i64> [[STRIDED_VEC]], <i64 1, i64 1, i64 1, i64 1>
-; FIXED-NEXT:    call void @llvm.masked.scatter.v4i64.v4p0(<4 x i64> [[TMP4]], <4 x ptr> [[TMP1]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
-; FIXED-NEXT:    [[TMP3:%.*]] = add <4 x i64> [[TMP0]], <i64 1, i64 1, i64 1, i64 1>
-; FIXED-NEXT:    [[TMP5:%.*]] = getelementptr i64, ptr [[P]], <4 x i64> [[TMP3]]
-; FIXED-NEXT:    [[STRIDED_VEC1:%.*]] = call <4 x i64> @llvm.masked.gather.v4i64.v4p0(<4 x ptr> [[TMP5]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i64> poison)
 ; FIXED-NEXT:    [[TMP6:%.*]] = add <4 x i64> [[STRIDED_VEC1]], <i64 2, i64 2, i64 2, i64 2>
-; FIXED-NEXT:    call void @llvm.masked.scatter.v4i64.v4p0(<4 x i64> [[TMP6]], <4 x ptr> [[TMP5]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
-; FIXED-NEXT:    [[TMP8:%.*]] = add <4 x i64> [[TMP3]], <i64 1, i64 1, i64 1, i64 1>
-; FIXED-NEXT:    [[TMP7:%.*]] = getelementptr i64, ptr [[P]], <4 x i64> [[TMP8]]
-; FIXED-NEXT:    [[STRIDED_VEC2:%.*]] = call <4 x i64> @llvm.masked.gather.v4i64.v4p0(<4 x ptr> [[TMP7]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i64> poison)
 ; FIXED-NEXT:    [[TMP9:%.*]] = add <4 x i64> [[STRIDED_VEC2]], <i64 3, i64 3, i64 3, i64 3>
-; FIXED-NEXT:    call void @llvm.masked.scatter.v4i64.v4p0(<4 x i64> [[TMP9]], <4 x ptr> [[TMP7]], i32 8, <4 x i1> <i1 true, i1 true, i1 true, i1 true>)
+; FIXED-NEXT:    [[TMP11:%.*]] = shufflevector <4 x i64> [[TMP4]], <4 x i64> [[TMP6]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
+; FIXED-NEXT:    [[TMP12:%.*]] = shufflevector <4 x i64> [[TMP9]], <4 x i64> poison, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison>
+; FIXED-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>
+; FIXED-NEXT:    [[INTERLEAVED_VEC:%.*]] = shufflevector <12 x i64> [[TMP13]], <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>
+; FIXED-NEXT:    store <12 x i64> [[INTERLEAVED_VEC]], ptr [[TMP2]], align 8
 ; FIXED-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
-; FIXED-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
 ; FIXED-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
 ; FIXED-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
 ; FIXED:       middle.block:
@@ -677,52 +656,33 @@ define void @load_store_factor3_i64(ptr %p) {
 ;
 ; SCALABLE-LABEL: @load_store_factor3_i64(
 ; SCALABLE-NEXT:  entry:
-; SCALABLE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; SCALABLE-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; SCALABLE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
-; SCALABLE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; SCALABLE-NEXT:    br i1 false, 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:    [[TMP6:%.*]] = call <vscale x 2 x i64> @llvm.stepvector.nxv2i64()
-; SCALABLE-NEXT:    [[TMP7:%.*]] = add <vscale x 2 x i64> [[TMP6]], zeroinitializer
-; SCALABLE-NEXT:    [[TMP8:%.*]] = mul <vscale x 2 x i64> [[TMP7]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; SCALABLE-NEXT:    [[INDUCTION:%.*]] = add <vscale x 2 x i64> zeroinitializer, [[TMP8]]
-; SCALABLE-NEXT:    [[TMP9:%.*]] = mul i64 1, [[TMP5]]
-; SCALABLE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 2 x i64> poison, i64 [[TMP9]], i64 0
-; SCALABLE-NEXT:    [[DOTSPLAT:%.*]] = shufflevector <vscale x 2 x i64> [[DOTSPLATINSERT]], <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer
 ; SCALABLE-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; SCALABLE:       vector.body:
 ; SCALABLE-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
-; SCALABLE-NEXT:    [[VEC_IND:%.*]] = phi <vscale x 2 x i64> [ [[INDUCTION]], [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
-; SCALABLE-NEXT:    [[TMP10:%.*]] = mul <vscale x 2 x i64> [[VEC_IND]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 3, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; SCALABLE-NEXT:    [[TMP11:%.*]] = getelementptr i64, ptr [[P:%.*]], <vscale x 2 x i64> [[TMP10]]
-; SCALABLE-NEXT:    [[WIDE_MASKED_GATHER:%.*]] = call <vscale x 2 x i64> @llvm.masked.gather.nxv2i64.nxv2p0(<vscale x 2 x ptr> [[TMP11]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i64> poison)
-; SCALABLE-NEXT:    [[TMP12:%.*]] = add <vscale x 2 x i64> [[WIDE_MASKED_GATHER]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; SCALABLE-NEXT:    call void @llvm.masked.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[TMP12]], <vscale x 2 x ptr> [[TMP11]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SCALABLE-NEXT:    [[TMP13:%.*]] = add <vscale x 2 x i64> [[TMP10]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; SCALABLE-NEXT:    [[TMP14:%.*]] = getelementptr i64, ptr [[P]], <vscale x 2 x i64> [[TMP13]]
-; SCALABLE-NEXT:    [[WIDE_MASKED_GATHER1:%.*]] = call <vscale x 2 x i64> @llvm.masked.gather.nxv2i64.nxv2p0(<vscale x 2 x ptr> [[TMP14]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i64> poison)
-; SCALABLE-NEXT:    [[TMP15:%.*]] = add <vscale x 2 x i64> [[WIDE_MASKED_GATHER1]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 2, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; SCALABLE-NEXT:    call void @llvm.masked.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[TMP15]], <vscale x 2 x ptr> [[TMP14]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SCALABLE-NEXT:    [[TMP16:%.*]] = add <vscale x 2 x i64> [[TMP13]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 1, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; SCALABLE-NEXT:    [[TMP17:%.*]] = getelementptr i64, ptr [[P]], <vscale x 2 x i64> [[TMP16]]
-; SCALABLE-NEXT:    [[WIDE_MASKED_GATHER2:%.*]] = call <vscale x 2 x i64> @llvm.masked.gather.nxv2i64.nxv2p0(<vscale x 2 x ptr> [[TMP17]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer), <vscale x 2 x i64> poison)
-; SCALABLE-NEXT:    [[TMP18:%.*]] = add <vscale x 2 x i64> [[WIDE_MASKED_GATHER2]], shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> poison, i64 3, i64 0), <vscale x 2 x i64> poison, <vscale x 2 x i32> zeroinitializer)
-; SCALABLE-NEXT:    call void @llvm.masked.scatter.nxv2i64.nxv2p0(<vscale x 2 x i64> [[TMP18]], <vscale x 2 x ptr> [[TMP17]], i32 8, <vscale x 2 x i1> shufflevector (<vscale x 2 x i1> insertelement (<vscale x 2 x i1> poison, i1 true, i64 0), <vscale x 2 x i1> poison, <vscale x 2 x i32> zeroinitializer))
-; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
-; SCALABLE-NEXT:    [[VEC_IND_NEXT]] = add <vscale x 2 x i64> [[VEC_IND]], [[DOTSPLAT]]
-; SCALABLE-NEXT:    [[TMP19:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; SCALABLE-NEXT:    br i1 [[TMP19]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
+; SCALABLE-NEXT:    [[TMP0:%.*]] = add i64 [[INDEX]], 0
+; SCALABLE-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 3
+; SCALABLE-NEXT:    [[TMP2:%.*]] = getelementptr i64, ptr [[P:%.*]], i64 [[TMP1]]
+; SCALABLE-NEXT:    [[WIDE_VEC:%.*]] = load <12 x i64>, ptr [[TMP2]], 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:    [[TMP4:%.*]] = add <4 x i64> [[STRIDED_VEC]], <i64 1, i64 1, i64 1, i64 1>
+; SCALABLE-NEXT:    [[TMP6:%.*]] = add <4 x i64> [[STRIDED_VEC1]], <i64 2, i64 2, i64 2, i64 2>
+; SCALABLE-NEXT:    [[TMP9:%.*]] = add <4 x i64> [[STRIDED_VEC2]], <i64 3, i64 3, i64 3, i64 3>
+; SCALABLE-NEXT:    [[TMP11:%.*]] = shufflevector <4 x i64> [[TMP4]], <4 x i64> [[TMP6]], <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> [[TMP9]], <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 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 [[TMP2]], align 8
+; SCALABLE-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
+; SCALABLE-NEXT:    [[TMP14:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
+; SCALABLE-NEXT:    br i1 [[TMP14]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP8:![0-9]+]]
 ; SCALABLE:       middle.block:
-; SCALABLE-NEXT:    [[CMP_N:%.*]] = icmp eq i64 1024, [[N_VEC]]
-; SCALABLE-NEXT:    br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
+; SCALABLE-NEXT:    br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
 ; SCALABLE:       scalar.ph:
-; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
+; SCALABLE-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 1024, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
 ; SCALABLE-NEXT:    br label [[LOOP:%.*]]
 ; SCALABLE:       loop:
 ; SCALABLE-NEXT:    [[I:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[NEXTI:%.*]], [[LOOP]] ]
diff --git a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-cost.ll b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-cost.ll
index 20b1ac83414934..6477f14e3c6984 100644
--- a/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/RISCV/interleaved-cost.ll
@@ -49,16 +49,16 @@ define void @i8_factor_3(ptr %data, i64 %n) {
 entry:
   br label %for.body
 ; CHECK-LABEL: Checking a loop in 'i8_factor_3'
-; CHECK: Cost of 4 for VF 2: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
-; CHECK: Cost of 4 for VF 2: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
-; CHECK: Cost of 4 for VF 4: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
-; CHECK: Cost of 4 for VF 4: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
-; CHECK: Cost of 5 for VF 8: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
-; CHECK: Cost of 5 for VF 8: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
-; CHECK: Cost of 7 for VF 16: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
-; CHECK: Cost of 7 for VF 16: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
-; CHECK: Cost of 14 for VF 32: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
-; CHECK: Cost of 14 for VF 32: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; CHECK: Cost of 6 for VF 2: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; CHECK: Cost of 6 for VF 2: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; CHECK: Cost of 12 for VF 4: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; CHECK: Cost of 12 for VF 4: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; CHECK: Cost of 24 for VF 8: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; CHECK: Cost of 24 for VF 8: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; CHECK: Cost of 48 for VF 16: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; CHECK: Cost of 48 for VF 16: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
+; CHECK: Cost of 96 for VF 32: INTERLEAVE-GROUP with factor 3 at %l0, ir<%p0>
+; CHECK: Cost of 96 for VF 32: INTERLEAVE-GROUP with factor 3 at <badref>, ir<%p0>
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %p0 = getelementptr inbounds %i8.3, ptr %data, i64 %i, i32 0
@@ -86,16 +86,16 @@ define void @i8_factor_4(ptr %data, i64 %n) {
 entry:
   br label %for.body
 ; CHECK-LABEL: Checking a loop in 'i8_factor_4'
-; CHECK: Cost of 5 for VF 2: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
-; CHECK: Cost of 5 for VF 2: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
-; CHECK: Cost of 5 for VF 4: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
-; CHECK: Cost of 5 for VF 4: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
-; CHECK: Cost of 6 for VF 8: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
-; CHECK: Cost of 6 for VF 8: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
-; CHECK: Cost of 8 for VF 16: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
-; CHECK: Cost of 8 for VF 16: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
-; CHECK: Cost of 16 for VF 32: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
-; CHECK: Cost of 16 for VF 32: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; CHECK: Cost of 8 for VF 2: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; CHECK: Cost of 8 for VF 2: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; CHECK: Cost of 16 for VF 4: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; CHECK: Cost of 16 for VF 4: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; CHECK: Cost of 32 for VF 8: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; CHECK: Cost of 32 for VF 8: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; CHECK: Cost of 64 for VF 16: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; CHECK: Cost of 64 for VF 16: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
+; CHECK: Cost of 128 for VF 32: INTERLEAVE-GROUP with factor 4 at %l0, ir<%p0>
+; CHECK: Cost of 128 for VF 32: INTERLEAVE-GROUP with factor 4 at <badref>, ir<%p0>
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %p0 = getelementptr inbounds %i8.4, ptr %data, i64 %i, i32 0
@@ -127,14 +127,14 @@ define void @i8_factor_5(ptr %data, i64 %n) {
 entry:
   br label %for.body
 ; CHECK-LABEL: Checking a loop in 'i8_factor_5'
-; CHECK: Cost of 6 for VF 2: INTERLEAVE-GROUP with factor 5 at %l0, ir<%p0>
-; CHECK: Cost of 6 for VF 2: INTERLEAVE-GROUP with factor 5 at <badref>, ir<%p0>
-; CHECK: Cost of 7 for VF 4: INTERLEAVE-GROUP with factor 5 at %l0, ir<%p0>
-; CHECK: Cost of 7 for VF 4: INTERLEAVE-GROUP with factor 5 at <badref>, ir<%p0>
-; CHECK: Cost of 9 for VF 8: INTERLEAVE-GROUP with factor 5 at %l0, ir<%p0>
-; CHECK: Cost of 9 for VF 8: INTERLEAVE-GROUP with factor 5 at <badref>, ir<%p0>
-; CHECK: Cost of 13 for VF 16: INTERLEAVE-GROUP with factor 5 at %l0, ir<%p0>
-; CHECK: Cost of 13 for VF 16: INTERLEAVE-GROUP with factor 5 at <badref>, ir<%p0>
+; CHECK: Cost of 10 for VF 2: INTERLEAVE-GROUP with factor 5 at %l0, ir<%p0>
+; CHECK: Cost of 10 for VF 2: INTERLEAVE-GROUP with factor 5 at <badref>, ir<%p0>
+; CHECK: Cost of 20 for VF 4: INTERLEAVE-GROUP with factor 5 at %l0, ir<%p0>
+; CHECK: Cost of 20 for VF 4: INTERLEAVE-GROUP with factor 5 at <badref>, ir<%p0>
+; CHECK: Cost of 40 for VF 8: INTERLEAVE-GROUP with factor 5 at %l0, ir<%p0>
+; CHECK: Cost of 40 for VF 8: INTERLEAVE-GROUP with factor 5 at <badref>, ir<%p0>
+; CHECK: Cost of 80 for VF 16: INTERLEAVE-GROUP with factor 5 at %l0, ir<%p0>
+; CHECK: Cost of 80 for VF 16: INTERLEAVE-GROUP with factor 5 at <badref>, ir<%p0>
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %p0 = getelementptr inbounds %i8.5, ptr %data, i64 %i, i32 0
@@ -170,14 +170,14 @@ define void @i8_factor_6(ptr %data, i64 %n) {
 entry:
   br label %for.body
 ; CHECK-LABEL: Checking a loop in 'i8_factor_6'
-; CHECK: Cost of 7 for VF 2: INTERLEAVE-GROUP with factor 6 at %l0, ir<%p0>
-; CHECK: Cost of 7 for VF 2: INTERLEAVE-GROUP with factor 6 at <badref>, ir<%p0>
-; CHECK: Cost of 8 for VF 4: INTERLEAVE-GROUP with factor 6 at %l0, ir<%p0>
-; CHECK: Cost of 8 for VF 4: INTERLEAVE-GROUP with factor 6 at <badref>, ir<%p0>
-; CHECK: Cost of 10 for VF 8: INTERLEAVE-GROUP with factor 6 at %l0, ir<%p0>
-; CHECK: Cost of 10 for VF 8: INTERLEAVE-GROUP with factor 6 at <badref>, ir<%p0>
-; CHECK: Cost of 14 for VF 16: INTERLEAVE-GROUP with factor 6 at %l0, ir<%p0>
-; CHECK: Cost of 14 for VF 16: INTERLEAVE-GROUP with factor 6 at <badref>, ir<%p0>
+; CHECK: Cost of 12 for VF 2: INTERLEAVE-GROUP with factor 6 at %l0, ir<%p0>
+; CHECK: Cost of 12 for VF 2: INTERLEAVE-GROUP with factor 6 at <badref>, ir<%p0>
+; CHECK: Cost of 24 for VF 4: INTERLEAVE-GROUP with factor 6 at %l0, ir<%p0>
+; CHECK: Cost of 24 for VF 4: INTERLEAVE-GROUP with factor 6 at <badref>, ir<%p0>
+; CHECK: Cost of 48 for VF 8: INTERLEAVE-GROUP with factor 6 at %l0, ir<%p0>
+; CHECK: Cost of 48 for VF 8: INTERLEAVE-GROUP with factor 6 at <badref>, ir<%p0>
+; CHECK: Cost of 96 for VF 16: INTERLEAVE-GROUP with factor 6 at %l0, ir<%p0>
+; CHECK: Cost of 96 for VF 16: INTERLEAVE-GROUP with factor 6 at <badref>, ir<%p0>
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %p0 = getelementptr inbounds %i8.6, ptr %data, i64 %i, i32 0
@@ -217,14 +217,14 @@ define void @i8_factor_7(ptr %data, i64 %n) {
 entry:
   br label %for.body
 ; CHECK-LABEL: Checking a loop in 'i8_factor_7'
-; CHECK: Cost of 8 for VF 2: INTERLEAVE-GROUP with factor 7 at %l0, ir<%p0>
-; CHECK: Cost of 8 for VF 2: INTERLEAVE-GROUP with factor 7 at <badref>, ir<%p0>
-; CHECK: Cost of 9 for VF 4: INTERLEAVE-GROUP with factor 7 at %l0, ir<%p0>
-; CHECK: Cost of 9 for VF 4: INTERLEAVE-GROUP with factor 7 at <badref>, ir<%p0>
-; CHECK: Cost of 11 for VF 8: INTERLEAVE-GROUP with factor 7 at %l0, ir<%p0>
-; CHECK: Cost of 11 for VF 8: INTERLEAVE-GROUP with factor 7 at <badref>, ir<%p0>
-; CHECK: Cost of 15 for VF 16: INTERLEAVE-GROUP with factor 7 at %l0, ir<%p0>
-; CHECK: Cost of 15 for VF 16: INTERLEAVE-GROUP with factor 7 at <badref>, ir<%p0>
+; CHECK: Cost of 14 for VF 2: INTERLEAVE-GROUP with factor 7 at %l0, ir<%p0>
+; CHECK: Cost of 14 for VF 2: INTERLEAVE-GROUP with factor 7 at <badref>, ir<%p0>
+; CHECK: Cost of 28 for VF 4: INTERLEAVE-GROUP with factor 7 at %l0, ir<%p0>
+; CHECK: Cost of 28 for VF 4: INTERLEAVE-GROUP with factor 7 at <badref>, ir<%p0>
+; CHECK: Cost of 56 for VF 8: INTERLEAVE-GROUP with factor 7 at %l0, ir<%p0>
+; CHECK: Cost of 56 for VF 8: INTERLEAVE-GROUP with factor 7 at <badref>, ir<%p0>
+; CHECK: Cost of 112 for VF 16: INTERLEAVE-GROUP with factor 7 at %l0, ir<%p0>
+; CHECK: Cost of 112 for VF 16: INTERLEAVE-GROUP with factor 7 at <badref>, ir<%p0>
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %p0 = getelementptr inbounds %i8.7, ptr %data, i64 %i, i32 0
@@ -268,14 +268,14 @@ define void @i8_factor_8(ptr %data, i64 %n) {
 entry:
   br label %for.body
 ; CHECK-LABEL: Checking a loop in 'i8_factor_8'
-; CHECK: Cost of 9 for VF 2: INTERLEAVE-GROUP with factor 8 at %l0, ir<%p0>
-; CHECK: Cost of 9 for VF 2: INTERLEAVE-GROUP with factor 8 at <badref>, ir<%p0>
-; CHECK: Cost of 10 for VF 4: INTERLEAVE-GROUP with factor 8 at %l0, ir<%p0>
-; CHECK: Cost of 10 for VF 4: INTERLEAVE-GROUP with factor 8 at <badref>, ir<%p0>
-; CHECK: Cost of 12 for VF 8: INTERLEAVE-GROUP with factor 8 at %l0, ir<%p0>
-; CHECK: Cost of 12 for VF 8: INTERLEAVE-GROUP with factor 8 at <badref>, ir<%p0>
-; CHECK: Cost of 16 for VF 16: INTERLEAVE-GROUP with factor 8 at %l0, ir<%p0>
-; CHECK: Cost of 16 for VF 16: INTERLEAVE-GROUP with factor 8 at <badref>, ir<%p0>
+; CHECK: Cost of 16 for VF 2: INTERLEAVE-GROUP with factor 8 at %l0, ir<%p0>
+; CHECK: Cost of 16 for VF 2: INTERLEAVE-GROUP with factor 8 at <badref>, ir<%p0>
+; CHECK: Cost of 32 for VF 4: INTERLEAVE-GROUP with factor 8 at %l0, ir<%p0>
+; CHECK: Cost of 32 for VF 4: INTERLEAVE-GROUP with factor 8 at <badref>, ir<%p0>
+; CHECK: Cost of 64 for VF 8: INTERLEAVE-GROUP with factor 8 at %l0, ir<%p0>
+; CHECK: Cost of 64 for VF 8: INTERLEAVE-GROUP with factor 8 at <badref>, ir<%p0>
+; CHECK: Cost of 128 for VF 16: INTERLEAVE-GROUP with factor 8 at %l0, ir<%p0>
+; CHECK: Cost of 128 for VF 16: INTERLEAVE-GROUP with factor 8 at <badref>, ir<%p0>
 for.body:
   %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
   %p0 = getelementptr inbounds %i8.8, ptr %data, i64 %i, i32 0