diff --git a/llvm/lib/Target/RISCV/RISCVInterleavedAccess.cpp b/llvm/lib/Target/RISCV/RISCVInterleavedAccess.cpp
index 39603b92cc2f7..4beca19c611dd 100644
--- a/llvm/lib/Target/RISCV/RISCVInterleavedAccess.cpp
+++ b/llvm/lib/Target/RISCV/RISCVInterleavedAccess.cpp
@@ -264,12 +264,6 @@ bool RISCVTargetLowering::lowerDeinterleaveIntrinsicToLoad(
                                      {ResVTy, PtrTy, XLenTy},
                                      {LI->getPointerOperand(), Mask, VL});
   } else {
-    static const Intrinsic::ID IntrIds[] = {
-        Intrinsic::riscv_vlseg2, Intrinsic::riscv_vlseg3,
-        Intrinsic::riscv_vlseg4, Intrinsic::riscv_vlseg5,
-        Intrinsic::riscv_vlseg6, Intrinsic::riscv_vlseg7,
-        Intrinsic::riscv_vlseg8};
-
     unsigned SEW = DL.getTypeSizeInBits(ResVTy->getElementType());
     unsigned NumElts = ResVTy->getElementCount().getKnownMinValue();
     Type *VecTupTy = TargetExtType::get(
@@ -277,13 +271,23 @@ bool RISCVTargetLowering::lowerDeinterleaveIntrinsicToLoad(
         ScalableVectorType::get(Type::getInt8Ty(LI->getContext()),
                                 NumElts * SEW / 8),
         Factor);
-
     Value *VL = Constant::getAllOnesValue(XLenTy);
+    Value *Mask = Builder.getAllOnesMask(ResVTy->getElementCount());
+
+    Function *VlsegNFunc = Intrinsic::getOrInsertDeclaration(
+        LI->getModule(), ScalableVlsegIntrIds[Factor - 2],
+        {VecTupTy, PtrTy, Mask->getType(), VL->getType()});
 
-    Value *Vlseg = Builder.CreateIntrinsic(
-        IntrIds[Factor - 2], {VecTupTy, PtrTy, XLenTy},
-        {PoisonValue::get(VecTupTy), LI->getPointerOperand(), VL,
-         ConstantInt::get(XLenTy, Log2_64(SEW))});
+    Value *Operands[] = {
+        PoisonValue::get(VecTupTy),
+        LI->getPointerOperand(),
+        Mask,
+        VL,
+        ConstantInt::get(XLenTy,
+                         RISCVVType::TAIL_AGNOSTIC | RISCVVType::MASK_AGNOSTIC),
+        ConstantInt::get(XLenTy, Log2_64(SEW))};
+
+    CallInst *Vlseg = Builder.CreateCall(VlsegNFunc, Operands);
 
     SmallVector<Type *, 2> AggrTypes{Factor, ResVTy};
     Return = PoisonValue::get(StructType::get(LI->getContext(), AggrTypes));
@@ -338,12 +342,6 @@ bool RISCVTargetLowering::lowerInterleaveIntrinsicToStore(
 
     Builder.CreateCall(VssegNFunc, Ops);
   } else {
-    static const Intrinsic::ID IntrIds[] = {
-        Intrinsic::riscv_vsseg2, Intrinsic::riscv_vsseg3,
-        Intrinsic::riscv_vsseg4, Intrinsic::riscv_vsseg5,
-        Intrinsic::riscv_vsseg6, Intrinsic::riscv_vsseg7,
-        Intrinsic::riscv_vsseg8};
-
     unsigned SEW = DL.getTypeSizeInBits(InVTy->getElementType());
     unsigned NumElts = InVTy->getElementCount().getKnownMinValue();
     Type *VecTupTy = TargetExtType::get(
@@ -352,10 +350,8 @@ bool RISCVTargetLowering::lowerInterleaveIntrinsicToStore(
                                 NumElts * SEW / 8),
         Factor);
 
-    Function *VssegNFunc = Intrinsic::getOrInsertDeclaration(
-        SI->getModule(), IntrIds[Factor - 2], {VecTupTy, PtrTy, XLenTy});
-
     Value *VL = Constant::getAllOnesValue(XLenTy);
+    Value *Mask = Builder.getAllOnesMask(InVTy->getElementCount());
 
     Value *StoredVal = PoisonValue::get(VecTupTy);
     for (unsigned i = 0; i < Factor; ++i)
@@ -363,8 +359,14 @@ bool RISCVTargetLowering::lowerInterleaveIntrinsicToStore(
           Intrinsic::riscv_tuple_insert, {VecTupTy, InVTy},
           {StoredVal, InterleaveValues[i], Builder.getInt32(i)});
 
-    Builder.CreateCall(VssegNFunc, {StoredVal, SI->getPointerOperand(), VL,
-                                    ConstantInt::get(XLenTy, Log2_64(SEW))});
+    Function *VssegNFunc = Intrinsic::getOrInsertDeclaration(
+        SI->getModule(), ScalableVssegIntrIds[Factor - 2],
+        {VecTupTy, PtrTy, Mask->getType(), VL->getType()});
+
+    Value *Operands[] = {StoredVal, SI->getPointerOperand(), Mask, VL,
+                         ConstantInt::get(XLenTy, Log2_64(SEW))};
+
+    Builder.CreateCall(VssegNFunc, Operands);
   }
 
   return true;
@@ -468,14 +470,12 @@ bool RISCVTargetLowering::lowerInterleavedVPLoad(
                                 NumElts * SEW / 8),
         Factor);
 
-    Value *PoisonVal = PoisonValue::get(VecTupTy);
-
     Function *VlsegNFunc = Intrinsic::getOrInsertDeclaration(
         Load->getModule(), ScalableVlsegIntrIds[Factor - 2],
         {VecTupTy, PtrTy, Mask->getType(), EVL->getType()});
 
     Value *Operands[] = {
-        PoisonVal,
+        PoisonValue::get(VecTupTy),
         Load->getArgOperand(0),
         Mask,
         EVL,
diff --git a/llvm/test/Transforms/InterleavedAccess/RISCV/addrspace.ll b/llvm/test/Transforms/InterleavedAccess/RISCV/addrspace.ll
index 8d156cfd4e526..f8e4ce9548147 100644
--- a/llvm/test/Transforms/InterleavedAccess/RISCV/addrspace.ll
+++ b/llvm/test/Transforms/InterleavedAccess/RISCV/addrspace.ll
@@ -20,7 +20,7 @@ define void @load_factor2(ptr addrspace(1) %ptr) {
 define void @load_factor2_vscale(ptr addrspace(1) %ptr) {
 ; CHECK-LABEL: define void @load_factor2_vscale(
 ; CHECK-SAME: ptr addrspace(1) [[PTR:%.*]]) #[[ATTR0]] {
-; CHECK-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 32 x i8>, 2) @llvm.riscv.vlseg2.triscv.vector.tuple_nxv32i8_2t.p1.i64(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) poison, ptr addrspace(1) [[PTR]], i64 -1, i64 5)
+; CHECK-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 32 x i8>, 2) @llvm.riscv.vlseg2.mask.triscv.vector.tuple_nxv32i8_2t.p1.nxv8i1.i64(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) poison, ptr addrspace(1) [[PTR]], <vscale x 8 x i1> splat (i1 true), i64 -1, i64 3, i64 5)
 ; CHECK-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i32> @llvm.riscv.tuple.extract.nxv8i32.triscv.vector.tuple_nxv32i8_2t(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) [[TMP1]], i32 0)
 ; CHECK-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } poison, <vscale x 8 x i32> [[TMP2]], 0
 ; CHECK-NEXT:    [[TMP4:%.*]] = call <vscale x 8 x i32> @llvm.riscv.tuple.extract.nxv8i32.triscv.vector.tuple_nxv32i8_2t(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) [[TMP1]], i32 1)
diff --git a/llvm/test/Transforms/InterleavedAccess/RISCV/interleaved-accesses.ll b/llvm/test/Transforms/InterleavedAccess/RISCV/interleaved-accesses.ll
index 72c1f22032bb7..672e94962da6d 100644
--- a/llvm/test/Transforms/InterleavedAccess/RISCV/interleaved-accesses.ll
+++ b/llvm/test/Transforms/InterleavedAccess/RISCV/interleaved-accesses.ll
@@ -25,7 +25,7 @@ define void @load_factor2(ptr %ptr) {
 
 define void @load_factor2_vscale(ptr %ptr) {
 ; RV32-LABEL: @load_factor2_vscale(
-; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 32 x i8>, 2) @llvm.riscv.vlseg2.triscv.vector.tuple_nxv32i8_2t.p0.i32(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 32 x i8>, 2) @llvm.riscv.vlseg2.mask.triscv.vector.tuple_nxv32i8_2t.p0.nxv8i1.i32(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) poison, ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i32 -1, i32 3, i32 5)
 ; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i32> @llvm.riscv.tuple.extract.nxv8i32.triscv.vector.tuple_nxv32i8_2t(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) [[TMP1]], i32 0)
 ; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } poison, <vscale x 8 x i32> [[TMP2]], 0
 ; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 8 x i32> @llvm.riscv.tuple.extract.nxv8i32.triscv.vector.tuple_nxv32i8_2t(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) [[TMP1]], i32 1)
@@ -35,7 +35,7 @@ define void @load_factor2_vscale(ptr %ptr) {
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @load_factor2_vscale(
-; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 32 x i8>, 2) @llvm.riscv.vlseg2.triscv.vector.tuple_nxv32i8_2t.p0.i64(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 32 x i8>, 2) @llvm.riscv.vlseg2.mask.triscv.vector.tuple_nxv32i8_2t.p0.nxv8i1.i64(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) poison, ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i64 -1, i64 3, i64 5)
 ; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 8 x i32> @llvm.riscv.tuple.extract.nxv8i32.triscv.vector.tuple_nxv32i8_2t(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) [[TMP1]], i32 0)
 ; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 8 x i32>, <vscale x 8 x i32> } poison, <vscale x 8 x i32> [[TMP2]], 0
 ; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 8 x i32> @llvm.riscv.tuple.extract.nxv8i32.triscv.vector.tuple_nxv32i8_2t(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) [[TMP1]], i32 1)
@@ -75,7 +75,7 @@ define void @load_factor3(ptr %ptr) {
 
 define void @load_factor3_vscale(ptr %ptr) {
 ; RV32-LABEL: @load_factor3_vscale(
-; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 3) @llvm.riscv.vlseg3.triscv.vector.tuple_nxv8i8_3t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 3) @llvm.riscv.vlseg3.mask.triscv.vector.tuple_nxv8i8_3t.p0.nxv2i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) poison, ptr [[PTR:%.*]], <vscale x 2 x i1> splat (i1 true), i32 -1, i32 3, i32 5)
 ; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_3t(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP1]], i32 0)
 ; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
 ; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_3t(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP1]], i32 1)
@@ -88,7 +88,7 @@ define void @load_factor3_vscale(ptr %ptr) {
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @load_factor3_vscale(
-; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 3) @llvm.riscv.vlseg3.triscv.vector.tuple_nxv8i8_3t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 3) @llvm.riscv.vlseg3.mask.triscv.vector.tuple_nxv8i8_3t.p0.nxv2i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) poison, ptr [[PTR:%.*]], <vscale x 2 x i1> splat (i1 true), i64 -1, i64 3, i64 5)
 ; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_3t(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP1]], i32 0)
 ; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
 ; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_3t(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP1]], i32 1)
@@ -135,7 +135,7 @@ define void @load_factor4(ptr %ptr) {
 
 define void @load_factor4_vscale(ptr %ptr) {
 ; RV32-LABEL: @load_factor4_vscale(
-; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 16 x i8>, 4) @llvm.riscv.vlseg4.triscv.vector.tuple_nxv16i8_4t.p0.i32(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 16 x i8>, 4) @llvm.riscv.vlseg4.mask.triscv.vector.tuple_nxv16i8_4t.p0.nxv4i1.i32(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) poison, ptr [[PTR:%.*]], <vscale x 4 x i1> splat (i1 true), i32 -1, i32 3, i32 5)
 ; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 0)
 ; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } poison, <vscale x 4 x i32> [[TMP2]], 0
 ; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 1)
@@ -151,7 +151,7 @@ define void @load_factor4_vscale(ptr %ptr) {
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @load_factor4_vscale(
-; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 16 x i8>, 4) @llvm.riscv.vlseg4.triscv.vector.tuple_nxv16i8_4t.p0.i64(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 16 x i8>, 4) @llvm.riscv.vlseg4.mask.triscv.vector.tuple_nxv16i8_4t.p0.nxv4i1.i64(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) poison, ptr [[PTR:%.*]], <vscale x 4 x i1> splat (i1 true), i64 -1, i64 3, i64 5)
 ; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 0)
 ; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32> } poison, <vscale x 4 x i32> [[TMP2]], 0
 ; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_4t(target("riscv.vector.tuple", <vscale x 16 x i8>, 4) [[TMP1]], i32 1)
@@ -205,7 +205,7 @@ define void @load_factor5(ptr %ptr) {
 
 define void @load_factor5_vscale(ptr %ptr) {
 ; RV32-LABEL: @load_factor5_vscale(
-; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 5) @llvm.riscv.vlseg5.triscv.vector.tuple_nxv8i8_5t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 5) @llvm.riscv.vlseg5.mask.triscv.vector.tuple_nxv8i8_5t.p0.nxv2i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) poison, ptr [[PTR:%.*]], <vscale x 2 x i1> splat (i1 true), i32 -1, i32 3, i32 5)
 ; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_5t(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP1]], i32 0)
 ; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
 ; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_5t(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP1]], i32 1)
@@ -224,7 +224,7 @@ define void @load_factor5_vscale(ptr %ptr) {
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @load_factor5_vscale(
-; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 5) @llvm.riscv.vlseg5.triscv.vector.tuple_nxv8i8_5t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 5) @llvm.riscv.vlseg5.mask.triscv.vector.tuple_nxv8i8_5t.p0.nxv2i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) poison, ptr [[PTR:%.*]], <vscale x 2 x i1> splat (i1 true), i64 -1, i64 3, i64 5)
 ; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_5t(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP1]], i32 0)
 ; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
 ; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_5t(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP1]], i32 1)
@@ -285,7 +285,7 @@ define void @load_factor6(ptr %ptr) {
 
 define void @load_factor6_vscale(ptr %ptr) {
 ; RV32-LABEL: @load_factor6_vscale(
-; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.vlseg6.triscv.vector.tuple_nxv8i8_6t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.vlseg6.mask.triscv.vector.tuple_nxv8i8_6t.p0.nxv2i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) poison, ptr [[PTR:%.*]], <vscale x 2 x i1> splat (i1 true), i32 -1, i32 3, i32 5)
 ; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 0)
 ; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
 ; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 1)
@@ -307,7 +307,7 @@ define void @load_factor6_vscale(ptr %ptr) {
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @load_factor6_vscale(
-; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.vlseg6.triscv.vector.tuple_nxv8i8_6t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.vlseg6.mask.triscv.vector.tuple_nxv8i8_6t.p0.nxv2i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) poison, ptr [[PTR:%.*]], <vscale x 2 x i1> splat (i1 true), i64 -1, i64 3, i64 5)
 ; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 0)
 ; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
 ; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_6t(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP1]], i32 1)
@@ -375,7 +375,7 @@ define void @load_factor7(ptr %ptr) {
 
 define void @load_factor7_vscale(ptr %ptr) {
 ; RV32-LABEL: @load_factor7_vscale(
-; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 7) @llvm.riscv.vlseg7.triscv.vector.tuple_nxv8i8_7t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 7) @llvm.riscv.vlseg7.mask.triscv.vector.tuple_nxv8i8_7t.p0.nxv2i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) poison, ptr [[PTR:%.*]], <vscale x 2 x i1> splat (i1 true), i32 -1, i32 3, i32 5)
 ; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_7t(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP1]], i32 0)
 ; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
 ; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_7t(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP1]], i32 1)
@@ -400,7 +400,7 @@ define void @load_factor7_vscale(ptr %ptr) {
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @load_factor7_vscale(
-; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 7) @llvm.riscv.vlseg7.triscv.vector.tuple_nxv8i8_7t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 7) @llvm.riscv.vlseg7.mask.triscv.vector.tuple_nxv8i8_7t.p0.nxv2i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) poison, ptr [[PTR:%.*]], <vscale x 2 x i1> splat (i1 true), i64 -1, i64 3, i64 5)
 ; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_7t(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP1]], i32 0)
 ; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
 ; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_7t(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP1]], i32 1)
@@ -475,7 +475,7 @@ define void @load_factor8(ptr %ptr) {
 
 define void @load_factor8_vscale(ptr %ptr) {
 ; RV32-LABEL: @load_factor8_vscale(
-; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.vlseg8.triscv.vector.tuple_nxv8i8_8t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, ptr [[PTR:%.*]], i32 -1, i32 5)
+; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.vlseg8.mask.triscv.vector.tuple_nxv8i8_8t.p0.nxv2i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, ptr [[PTR:%.*]], <vscale x 2 x i1> splat (i1 true), i32 -1, i32 3, i32 5)
 ; RV32-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 0)
 ; RV32-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
 ; RV32-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 1)
@@ -503,7 +503,7 @@ define void @load_factor8_vscale(ptr %ptr) {
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @load_factor8_vscale(
-; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.vlseg8.triscv.vector.tuple_nxv8i8_8t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, ptr [[PTR:%.*]], i64 -1, i64 5)
+; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.vlseg8.mask.triscv.vector.tuple_nxv8i8_8t.p0.nxv2i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) poison, ptr [[PTR:%.*]], <vscale x 2 x i1> splat (i1 true), i64 -1, i64 3, i64 5)
 ; RV64-NEXT:    [[TMP2:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 0)
 ; RV64-NEXT:    [[TMP3:%.*]] = insertvalue { <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32>, <vscale x 2 x i32> } poison, <vscale x 2 x i32> [[TMP2]], 0
 ; RV64-NEXT:    [[TMP4:%.*]] = call <vscale x 2 x i32> @llvm.riscv.tuple.extract.nxv2i32.triscv.vector.tuple_nxv8i8_8t(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP1]], i32 1)
@@ -566,13 +566,13 @@ define void @store_factor2_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV32-LABEL: @store_factor2_vscale(
 ; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_2t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
 ; RV32-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_2t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
-; RV32-NEXT:    call void @llvm.riscv.vsseg2.triscv.vector.tuple_nxv8i8_2t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) [[TMP2]], ptr [[PTR:%.*]], i32 -1, i32 3)
+; RV32-NEXT:    call void @llvm.riscv.vsseg2.mask.triscv.vector.tuple_nxv8i8_2t.p0.nxv8i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) [[TMP2]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i32 -1, i32 3)
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @store_factor2_vscale(
 ; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_2t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
 ; RV64-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_2t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
-; RV64-NEXT:    call void @llvm.riscv.vsseg2.triscv.vector.tuple_nxv8i8_2t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) [[TMP2]], ptr [[PTR:%.*]], i64 -1, i64 3)
+; RV64-NEXT:    call void @llvm.riscv.vsseg2.mask.triscv.vector.tuple_nxv8i8_2t.p0.nxv8i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 2) [[TMP2]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i64 -1, i64 3)
 ; RV64-NEXT:    ret void
 ;
   %interleaved.vec = call <vscale x 16 x i8> @llvm.vector.interleave2.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1)
@@ -611,14 +611,14 @@ define void @store_factor3_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV32-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 3) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_3t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
 ; RV32-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 3) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_3t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
 ; RV32-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 3) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_3t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
-; RV32-NEXT:    call void @llvm.riscv.vsseg3.triscv.vector.tuple_nxv8i8_3t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP3]], ptr [[PTR:%.*]], i32 -1, i32 3)
+; RV32-NEXT:    call void @llvm.riscv.vsseg3.mask.triscv.vector.tuple_nxv8i8_3t.p0.nxv8i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP3]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i32 -1, i32 3)
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @store_factor3_vscale(
 ; RV64-NEXT:    [[TMP1:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 3) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_3t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) poison, <vscale x 8 x i8> [[V0:%.*]], i32 0)
 ; RV64-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 3) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_3t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
 ; RV64-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 3) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_3t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
-; RV64-NEXT:    call void @llvm.riscv.vsseg3.triscv.vector.tuple_nxv8i8_3t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP3]], ptr [[PTR:%.*]], i64 -1, i64 3)
+; RV64-NEXT:    call void @llvm.riscv.vsseg3.mask.triscv.vector.tuple_nxv8i8_3t.p0.nxv8i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 3) [[TMP3]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i64 -1, i64 3)
 ; RV64-NEXT:    ret void
 ;
   %interleaved.vec = call <vscale x 24 x i8> @llvm.vector.interleave3.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2)
@@ -660,7 +660,7 @@ define void @store_factor4_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV32-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
 ; RV32-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
 ; RV32-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
-; RV32-NEXT:    call void @llvm.riscv.vsseg4.triscv.vector.tuple_nxv8i8_4t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP4]], ptr [[PTR:%.*]], i32 -1, i32 3)
+; RV32-NEXT:    call void @llvm.riscv.vsseg4.mask.triscv.vector.tuple_nxv8i8_4t.p0.nxv8i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP4]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i32 -1, i32 3)
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @store_factor4_vscale(
@@ -668,7 +668,7 @@ define void @store_factor4_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV64-NEXT:    [[TMP2:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP1]], <vscale x 8 x i8> [[V1:%.*]], i32 1)
 ; RV64-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
 ; RV64-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 4) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_4t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
-; RV64-NEXT:    call void @llvm.riscv.vsseg4.triscv.vector.tuple_nxv8i8_4t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP4]], ptr [[PTR:%.*]], i64 -1, i64 3)
+; RV64-NEXT:    call void @llvm.riscv.vsseg4.mask.triscv.vector.tuple_nxv8i8_4t.p0.nxv8i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 4) [[TMP4]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i64 -1, i64 3)
 ; RV64-NEXT:    ret void
 ;
   %interleaved.vec = call <vscale x 32 x i8> @llvm.vector.interleave4.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3)
@@ -683,7 +683,7 @@ define void @store_factor5_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV32-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 5) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_5t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
 ; RV32-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 5) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_5t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
 ; RV32-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 5) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_5t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP4]], <vscale x 8 x i8> [[V4:%.*]], i32 4)
-; RV32-NEXT:    call void @llvm.riscv.vsseg5.triscv.vector.tuple_nxv8i8_5t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP5]], ptr [[PTR:%.*]], i32 -1, i32 3)
+; RV32-NEXT:    call void @llvm.riscv.vsseg5.mask.triscv.vector.tuple_nxv8i8_5t.p0.nxv8i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP5]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i32 -1, i32 3)
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @store_factor5_vscale(
@@ -692,7 +692,7 @@ define void @store_factor5_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV64-NEXT:    [[TMP3:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 5) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_5t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP2]], <vscale x 8 x i8> [[V2:%.*]], i32 2)
 ; RV64-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 5) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_5t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
 ; RV64-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 5) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_5t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP4]], <vscale x 8 x i8> [[V4:%.*]], i32 4)
-; RV64-NEXT:    call void @llvm.riscv.vsseg5.triscv.vector.tuple_nxv8i8_5t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP5]], ptr [[PTR:%.*]], i64 -1, i64 3)
+; RV64-NEXT:    call void @llvm.riscv.vsseg5.mask.triscv.vector.tuple_nxv8i8_5t.p0.nxv8i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) [[TMP5]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i64 -1, i64 3)
 ; RV64-NEXT:    ret void
 ;
   %interleaved.vec = call <vscale x 40 x i8> @llvm.vector.interleave5.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3, <vscale x 8 x i8> %v4)
@@ -780,7 +780,7 @@ define void @store_factor6_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV32-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
 ; RV32-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP4]], <vscale x 8 x i8> [[V4:%.*]], i32 4)
 ; RV32-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP5]], <vscale x 8 x i8> [[V5:%.*]], i32 5)
-; RV32-NEXT:    call void @llvm.riscv.vsseg6.triscv.vector.tuple_nxv8i8_6t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP6]], ptr [[PTR:%.*]], i32 -1, i32 3)
+; RV32-NEXT:    call void @llvm.riscv.vsseg6.mask.triscv.vector.tuple_nxv8i8_6t.p0.nxv8i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP6]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i32 -1, i32 3)
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @store_factor6_vscale(
@@ -790,7 +790,7 @@ define void @store_factor6_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV64-NEXT:    [[TMP4:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP3]], <vscale x 8 x i8> [[V3:%.*]], i32 3)
 ; RV64-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP4]], <vscale x 8 x i8> [[V4:%.*]], i32 4)
 ; RV64-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 6) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_6t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP5]], <vscale x 8 x i8> [[V5:%.*]], i32 5)
-; RV64-NEXT:    call void @llvm.riscv.vsseg6.triscv.vector.tuple_nxv8i8_6t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP6]], ptr [[PTR:%.*]], i64 -1, i64 3)
+; RV64-NEXT:    call void @llvm.riscv.vsseg6.mask.triscv.vector.tuple_nxv8i8_6t.p0.nxv8i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 6) [[TMP6]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i64 -1, i64 3)
 ; RV64-NEXT:    ret void
 ;
   %interleaved.vec = call <vscale x 48 x i8> @llvm.vector.interleave6.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3, <vscale x 8 x i8> %v4, <vscale x 8 x i8> %v5)
@@ -807,7 +807,7 @@ define void @store_factor7_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV32-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 7) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_7t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP4]], <vscale x 8 x i8> [[V4:%.*]], i32 4)
 ; RV32-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 7) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_7t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP5]], <vscale x 8 x i8> [[V5:%.*]], i32 5)
 ; RV32-NEXT:    [[TMP7:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 7) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_7t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP6]], <vscale x 8 x i8> [[V6:%.*]], i32 6)
-; RV32-NEXT:    call void @llvm.riscv.vsseg7.triscv.vector.tuple_nxv8i8_7t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP7]], ptr [[PTR:%.*]], i32 -1, i32 3)
+; RV32-NEXT:    call void @llvm.riscv.vsseg7.mask.triscv.vector.tuple_nxv8i8_7t.p0.nxv8i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP7]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i32 -1, i32 3)
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @store_factor7_vscale(
@@ -818,7 +818,7 @@ define void @store_factor7_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV64-NEXT:    [[TMP5:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 7) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_7t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP4]], <vscale x 8 x i8> [[V4:%.*]], i32 4)
 ; RV64-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 7) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_7t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP5]], <vscale x 8 x i8> [[V5:%.*]], i32 5)
 ; RV64-NEXT:    [[TMP7:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 7) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_7t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP6]], <vscale x 8 x i8> [[V6:%.*]], i32 6)
-; RV64-NEXT:    call void @llvm.riscv.vsseg7.triscv.vector.tuple_nxv8i8_7t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP7]], ptr [[PTR:%.*]], i64 -1, i64 3)
+; RV64-NEXT:    call void @llvm.riscv.vsseg7.mask.triscv.vector.tuple_nxv8i8_7t.p0.nxv8i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 7) [[TMP7]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i64 -1, i64 3)
 ; RV64-NEXT:    ret void
 ;
   %interleaved.vec = call <vscale x 56 x i8> @llvm.vector.interleave7.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3, <vscale x 8 x i8> %v4, <vscale x 8 x i8> %v5, <vscale x 8 x i8> %v6)
@@ -836,7 +836,7 @@ define void @store_factor8_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV32-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP5]], <vscale x 8 x i8> [[V5:%.*]], i32 5)
 ; RV32-NEXT:    [[TMP7:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP6]], <vscale x 8 x i8> [[V6:%.*]], i32 6)
 ; RV32-NEXT:    [[TMP8:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP7]], <vscale x 8 x i8> [[V7:%.*]], i32 7)
-; RV32-NEXT:    call void @llvm.riscv.vsseg8.triscv.vector.tuple_nxv8i8_8t.p0.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP8]], ptr [[PTR:%.*]], i32 -1, i32 3)
+; RV32-NEXT:    call void @llvm.riscv.vsseg8.mask.triscv.vector.tuple_nxv8i8_8t.p0.nxv8i1.i32(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP8]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i32 -1, i32 3)
 ; RV32-NEXT:    ret void
 ;
 ; RV64-LABEL: @store_factor8_vscale(
@@ -848,7 +848,7 @@ define void @store_factor8_vscale(ptr %ptr, <vscale x 8 x i8> %v0, <vscale x 8 x
 ; RV64-NEXT:    [[TMP6:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP5]], <vscale x 8 x i8> [[V5:%.*]], i32 5)
 ; RV64-NEXT:    [[TMP7:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP6]], <vscale x 8 x i8> [[V6:%.*]], i32 6)
 ; RV64-NEXT:    [[TMP8:%.*]] = call target("riscv.vector.tuple", <vscale x 8 x i8>, 8) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv8i8_8t.nxv8i8(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP7]], <vscale x 8 x i8> [[V7:%.*]], i32 7)
-; RV64-NEXT:    call void @llvm.riscv.vsseg8.triscv.vector.tuple_nxv8i8_8t.p0.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP8]], ptr [[PTR:%.*]], i64 -1, i64 3)
+; RV64-NEXT:    call void @llvm.riscv.vsseg8.mask.triscv.vector.tuple_nxv8i8_8t.p0.nxv8i1.i64(target("riscv.vector.tuple", <vscale x 8 x i8>, 8) [[TMP8]], ptr [[PTR:%.*]], <vscale x 8 x i1> splat (i1 true), i64 -1, i64 3)
 ; RV64-NEXT:    ret void
 ;
   %interleaved.vec = call <vscale x 64 x i8> @llvm.vector.interleave8.nxv8i8(<vscale x 8 x i8> %v0, <vscale x 8 x i8> %v1, <vscale x 8 x i8> %v2, <vscale x 8 x i8> %v3, <vscale x 8 x i8> %v4, <vscale x 8 x i8> %v5, <vscale x 8 x i8> %v6, <vscale x 8 x i8> %v7)