diff --git a/clang/include/clang/Basic/riscv_vector.td b/clang/include/clang/Basic/riscv_vector.td
--- a/clang/include/clang/Basic/riscv_vector.td
+++ b/clang/include/clang/Basic/riscv_vector.td
@@ -173,20 +173,13 @@
   // This builtin has a granted vector length parameter.
   bit HasVL = true;
 
-  // There are several cases for specifying tail policy.
-  // 1. Add tail policy argument to masked intrinsics. It may have the maskedoff
-  //    argument or not.
-  //  * Have the maskedoff argument: (HasPolicy = true, HasMaskedOffOperand = true)
-  //    Ex: vadd_vv_i8m1_mt(mask, maskedoff, op1, op2, vl, ta);
-  //  * Do not have the maskedoff argument: (HasPolicy = true, HasMaskedOffOperand = false)
-  //    Ex: vmacc_vv_i8m1_mt(mask, vd, vs1, vs2, vl, ta);
-  // 2. Add dest argument for no mask intrinsics. (TODO)
-  //    Ex: vmv_v_x_i8m1_t(dest, src, vl);
-  // 3. Always tail agnostic. (HasPolicy = false)
-  //    Ex: vmseq_vv_i8m1_b8_m(mask, maskedoff, op1, op2, vl);
-  // The tail policy argument is located at the last position.
+  // The masked intrinsic IR have the policy operand.
+  // The policy argument is located at the last position.
   bit HasPolicy = true;
 
+  // The nomask intrinsic IR have the passthru operand.
+  bit HasNoMaskPolicy = false;
+
   // This builtin supports non-masked function overloading api.
   // All masked operations support overloading api.
   bit HasNoMaskedOverloaded = true;
@@ -1290,6 +1283,8 @@
                           cast<llvm::VectorType>(ResultType)->getElementType(),
                           Ops[1]->getType()};
         Ops.insert(Ops.begin() + 1, llvm::Constant::getNullValue(IntrinsicTypes[1]));
+        // insert undef passthru
+        Ops.insert(Ops.begin(), llvm::UndefValue::get(ResultType));
         break;
       }
       }],
@@ -1321,6 +1316,8 @@
                           Ops[1]->getType()};
         Ops.insert(Ops.begin() + 1,
                    llvm::Constant::getAllOnesValue(IntrinsicTypes[1]));
+        // insert undef passthru
+        Ops.insert(Ops.begin(), llvm::UndefValue::get(ResultType));
         break;
       }
       }],
@@ -1369,6 +1366,8 @@
         IntrinsicTypes = {ResultType,
                           Ops[0]->getType(), Ops[1]->getType()};
         Ops.insert(Ops.begin() + 1, Ops[0]);
+        // insert undef passthru
+        Ops.insert(Ops.begin(), llvm::UndefValue::get(ResultType));
         break;
       }
       }],
@@ -1402,6 +1401,8 @@
                           cast<llvm::VectorType>(Ops[0]->getType())->getElementType(),
                           Ops[1]->getType()};
         Ops.insert(Ops.begin() + 1, llvm::Constant::getNullValue(IntrinsicTypes[2]));
+        // insert undef passthru
+        Ops.insert(Ops.begin(), llvm::UndefValue::get(ResultType));
         break;
       }
       }],
@@ -1438,6 +1439,8 @@
                           Ops[1]->getType(),
                           Ops[1]->getType()};
         Ops.insert(Ops.begin() + 1, llvm::Constant::getNullValue(IntrinsicTypes[2]));
+        // insert undef passthru
+        Ops.insert(Ops.begin(), llvm::UndefValue::get(ResultType));
         break;
       }
       }],
@@ -1583,15 +1586,18 @@
 
 // 12. Vector Integer Arithmetic Instructions
 // 12.1. Vector Single-Width Integer Add and Subtract
+let HasNoMaskPolicy = true in {
 defm vadd : RVVIntBinBuiltinSet;
 defm vsub : RVVIntBinBuiltinSet;
 defm vrsub : RVVOutOp1BuiltinSet<"vrsub", "csil",
                                  [["vx", "v", "vve"],
                                   ["vx", "Uv", "UvUvUe"]]>;
+}
 defm vneg_v : RVVPseudoUnaryBuiltin<"vrsub", "csil">;
 
 // 12.2. Vector Widening Integer Add/Subtract
 // Widening unsigned integer add/subtract, 2*SEW = SEW +/- SEW
+let HasNoMaskPolicy = true in {
 defm vwaddu : RVVUnsignedWidenBinBuiltinSet;
 defm vwsubu : RVVUnsignedWidenBinBuiltinSet;
 // Widening signed integer add/subtract, 2*SEW = SEW +/- SEW
@@ -1603,6 +1609,7 @@
 // Widening signed integer add/subtract, 2*SEW = 2*SEW +/- SEW
 defm vwadd : RVVSignedWidenOp0BinBuiltinSet;
 defm vwsub : RVVSignedWidenOp0BinBuiltinSet;
+}
 defm vwcvtu_x_x_v : RVVPseudoVWCVTBuiltin<"vwaddu", "vwcvtu_x", "csi",
                                           [["Uw", "UwUv"]]>;
 defm vwcvt_x_x_v : RVVPseudoVWCVTBuiltin<"vwadd", "vwcvt_x", "csi",
@@ -1633,12 +1640,15 @@
 }
 
 // 12.5. Vector Bitwise Logical Instructions
+let HasNoMaskPolicy = true in {
 defm vand : RVVIntBinBuiltinSet;
 defm vxor : RVVIntBinBuiltinSet;
 defm vor : RVVIntBinBuiltinSet;
+}
 defm vnot_v : RVVPseudoVNotBuiltin<"vxor", "csil">;
 
 // 12.6. Vector Single-Width Bit Shift Instructions
+let HasNoMaskPolicy = true in {
 defm vsll : RVVShiftBuiltinSet;
 defm vsrl : RVVUnsignedShiftBuiltinSet;
 defm vsra : RVVSignedShiftBuiltinSet;
@@ -1646,6 +1656,7 @@
 // 12.7. Vector Narrowing Integer Right Shift Instructions
 defm vnsrl : RVVUnsignedNShiftBuiltinSet;
 defm vnsra : RVVSignedNShiftBuiltinSet;
+}
 defm vncvt_x_x_w : RVVPseudoVNCVTBuiltin<"vnsrl", "vncvt_x", "csi",
                                          [["v", "vw"],
                                           ["Uv", "UvUw"]]>;
@@ -1665,6 +1676,7 @@
 }
 
 // 12.9. Vector Integer Min/Max Instructions
+let HasNoMaskPolicy = true in {
 defm vminu : RVVUnsignedBinBuiltinSet;
 defm vmin : RVVSignedBinBuiltinSet;
 defm vmaxu : RVVUnsignedBinBuiltinSet;
@@ -1685,9 +1697,10 @@
 defm vdiv : RVVSignedBinBuiltinSet;
 defm vremu : RVVUnsignedBinBuiltinSet;
 defm vrem : RVVSignedBinBuiltinSet;
+}
 
 // 12.12. Vector Widening Integer Multiply Instructions
-let Log2LMUL = [-3, -2, -1, 0, 1, 2] in {
+let Log2LMUL = [-3, -2, -1, 0, 1, 2], HasNoMaskPolicy = true in {
 defm vwmul : RVVOutOp0Op1BuiltinSet<"vwmul", "csi",
                                     [["vv", "w", "wvv"],
                                      ["vx", "w", "wve"]]>;
@@ -1753,6 +1766,7 @@
 
 // 13. Vector Fixed-Point Arithmetic Instructions
 // 13.1. Vector Single-Width Saturating Add and Subtract
+let HasNoMaskPolicy = true in {
 defm vsaddu : RVVUnsignedBinBuiltinSet;
 defm vsadd : RVVSignedBinBuiltinSet;
 defm vssubu : RVVUnsignedBinBuiltinSet;
@@ -1802,6 +1816,7 @@
                                        [["vv", "w", "wvv"],
                                         ["vf", "w", "wve"]]>;
 }
+}
 
 // 14.6. Vector Single-Width Floating-Point Fused Multiply-Add Instructions
 let HasPolicy = false in {
@@ -1831,6 +1846,7 @@
 def vfrec7 : RVVFloatingUnaryVVBuiltin;
 
 // 14.11. Vector Floating-Point MIN/MAX Instructions
+let HasNoMaskPolicy = true in {
 defm vfmin : RVVFloatingBinBuiltinSet;
 defm vfmax : RVVFloatingBinBuiltinSet;
 
@@ -1838,6 +1854,7 @@
 defm vfsgnj  : RVVFloatingBinBuiltinSet;
 defm vfsgnjn : RVVFloatingBinBuiltinSet;
 defm vfsgnjx : RVVFloatingBinBuiltinSet;
+}
 defm vfneg_v : RVVPseudoVFUnaryBuiltin<"vfsgnjn", "xfd">;
 defm vfabs_v : RVVPseudoVFUnaryBuiltin<"vfsgnjx", "xfd">;
 
@@ -2011,6 +2028,7 @@
 }
 
 // 17.3.3. Vector Slide1up Instructions
+let HasNoMaskPolicy = true in {
 defm vslide1up : RVVSlideOneBuiltinSet;
 defm vfslide1up : RVVFloatingBinVFBuiltinSet;
 
@@ -2033,6 +2051,7 @@
                                  [["vx", "Uv", "UvUvz"]]>;
 defm vrgatherei16 : RVVOutBuiltinSet<"vrgatherei16_vv", "csil",
                                      [["vv", "Uv", "UvUv(Log2EEW:4)Uv"]]>;
+}
 
 // 17.5. Vector Compress Instruction
 let HasMask = false, HasPolicy = false,
diff --git a/clang/test/CodeGen/RISCV/rvv-intrinsics/vadd.c b/clang/test/CodeGen/RISCV/rvv-intrinsics/vadd.c
--- a/clang/test/CodeGen/RISCV/rvv-intrinsics/vadd.c
+++ b/clang/test/CodeGen/RISCV/rvv-intrinsics/vadd.c
@@ -7,7 +7,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i8mf8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.nxv1i8.i64(<vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.nxv1i8.i64(<vscale x 1 x i8> undef, <vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i8> [[TMP0]]
 //
 vint8mf8_t test_vadd_vv_i8mf8(vint8mf8_t op1, vint8mf8_t op2, size_t vl) {
@@ -16,7 +16,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i8mf8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.i8.i64(<vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.i8.i64(<vscale x 1 x i8> undef, <vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i8> [[TMP0]]
 //
 vint8mf8_t test_vadd_vx_i8mf8(vint8mf8_t op1, int8_t op2, size_t vl) {
@@ -25,7 +25,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i8mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.nxv2i8.i64(<vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.nxv2i8.i64(<vscale x 2 x i8> undef, <vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i8> [[TMP0]]
 //
 vint8mf4_t test_vadd_vv_i8mf4(vint8mf4_t op1, vint8mf4_t op2, size_t vl) {
@@ -34,7 +34,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i8mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.i8.i64(<vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.i8.i64(<vscale x 2 x i8> undef, <vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i8> [[TMP0]]
 //
 vint8mf4_t test_vadd_vx_i8mf4(vint8mf4_t op1, int8_t op2, size_t vl) {
@@ -43,7 +43,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i8mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.nxv4i8.i64(<vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.nxv4i8.i64(<vscale x 4 x i8> undef, <vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i8> [[TMP0]]
 //
 vint8mf2_t test_vadd_vv_i8mf2(vint8mf2_t op1, vint8mf2_t op2, size_t vl) {
@@ -52,7 +52,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i8mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.i8.i64(<vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.i8.i64(<vscale x 4 x i8> undef, <vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i8> [[TMP0]]
 //
 vint8mf2_t test_vadd_vx_i8mf2(vint8mf2_t op1, int8_t op2, size_t vl) {
@@ -61,7 +61,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i8m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.nxv8i8.i64(<vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.nxv8i8.i64(<vscale x 8 x i8> undef, <vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i8> [[TMP0]]
 //
 vint8m1_t test_vadd_vv_i8m1(vint8m1_t op1, vint8m1_t op2, size_t vl) {
@@ -70,7 +70,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i8m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.i8.i64(<vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.i8.i64(<vscale x 8 x i8> undef, <vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i8> [[TMP0]]
 //
 vint8m1_t test_vadd_vx_i8m1(vint8m1_t op1, int8_t op2, size_t vl) {
@@ -79,7 +79,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i8m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.nxv16i8.i64(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.nxv16i8.i64(<vscale x 16 x i8> undef, <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
 //
 vint8m2_t test_vadd_vv_i8m2(vint8m2_t op1, vint8m2_t op2, size_t vl) {
@@ -88,7 +88,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i8m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.i8.i64(<vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.i8.i64(<vscale x 16 x i8> undef, <vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
 //
 vint8m2_t test_vadd_vx_i8m2(vint8m2_t op1, int8_t op2, size_t vl) {
@@ -97,7 +97,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i8m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.nxv32i8.i64(<vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.nxv32i8.i64(<vscale x 32 x i8> undef, <vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i8> [[TMP0]]
 //
 vint8m4_t test_vadd_vv_i8m4(vint8m4_t op1, vint8m4_t op2, size_t vl) {
@@ -106,7 +106,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i8m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.i8.i64(<vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.i8.i64(<vscale x 32 x i8> undef, <vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i8> [[TMP0]]
 //
 vint8m4_t test_vadd_vx_i8m4(vint8m4_t op1, int8_t op2, size_t vl) {
@@ -115,7 +115,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i8m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.nxv64i8.i64(<vscale x 64 x i8> [[OP1:%.*]], <vscale x 64 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.nxv64i8.i64(<vscale x 64 x i8> undef, <vscale x 64 x i8> [[OP1:%.*]], <vscale x 64 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
 //
 vint8m8_t test_vadd_vv_i8m8(vint8m8_t op1, vint8m8_t op2, size_t vl) {
@@ -124,7 +124,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i8m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.i8.i64(<vscale x 64 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.i8.i64(<vscale x 64 x i8> undef, <vscale x 64 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
 //
 vint8m8_t test_vadd_vx_i8m8(vint8m8_t op1, int8_t op2, size_t vl) {
@@ -133,7 +133,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.nxv1i16.i64(<vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.nxv1i16.i64(<vscale x 1 x i16> undef, <vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vint16mf4_t test_vadd_vv_i16mf4(vint16mf4_t op1, vint16mf4_t op2, size_t vl) {
@@ -142,7 +142,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.i16.i64(<vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.i16.i64(<vscale x 1 x i16> undef, <vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vint16mf4_t test_vadd_vx_i16mf4(vint16mf4_t op1, int16_t op2, size_t vl) {
@@ -151,7 +151,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.nxv2i16.i64(<vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.nxv2i16.i64(<vscale x 2 x i16> undef, <vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vint16mf2_t test_vadd_vv_i16mf2(vint16mf2_t op1, vint16mf2_t op2, size_t vl) {
@@ -160,7 +160,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.i16.i64(<vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.i16.i64(<vscale x 2 x i16> undef, <vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vint16mf2_t test_vadd_vx_i16mf2(vint16mf2_t op1, int16_t op2, size_t vl) {
@@ -169,7 +169,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.nxv4i16.i64(<vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.nxv4i16.i64(<vscale x 4 x i16> undef, <vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vint16m1_t test_vadd_vv_i16m1(vint16m1_t op1, vint16m1_t op2, size_t vl) {
@@ -178,7 +178,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.i16.i64(<vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.i16.i64(<vscale x 4 x i16> undef, <vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vint16m1_t test_vadd_vx_i16m1(vint16m1_t op1, int16_t op2, size_t vl) {
@@ -187,7 +187,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.nxv8i16.i64(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.nxv8i16.i64(<vscale x 8 x i16> undef, <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vint16m2_t test_vadd_vv_i16m2(vint16m2_t op1, vint16m2_t op2, size_t vl) {
@@ -196,7 +196,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.i16.i64(<vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.i16.i64(<vscale x 8 x i16> undef, <vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vint16m2_t test_vadd_vx_i16m2(vint16m2_t op1, int16_t op2, size_t vl) {
@@ -205,7 +205,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.nxv16i16.i64(<vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.nxv16i16.i64(<vscale x 16 x i16> undef, <vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vint16m4_t test_vadd_vv_i16m4(vint16m4_t op1, vint16m4_t op2, size_t vl) {
@@ -214,7 +214,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.i16.i64(<vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.i16.i64(<vscale x 16 x i16> undef, <vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vint16m4_t test_vadd_vx_i16m4(vint16m4_t op1, int16_t op2, size_t vl) {
@@ -223,7 +223,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.nxv32i16.i64(<vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.nxv32i16.i64(<vscale x 32 x i16> undef, <vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vint16m8_t test_vadd_vv_i16m8(vint16m8_t op1, vint16m8_t op2, size_t vl) {
@@ -232,7 +232,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.i16.i64(<vscale x 32 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.i16.i64(<vscale x 32 x i16> undef, <vscale x 32 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vint16m8_t test_vadd_vx_i16m8(vint16m8_t op1, int16_t op2, size_t vl) {
@@ -241,7 +241,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.nxv1i32.i64(<vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.nxv1i32.i64(<vscale x 1 x i32> undef, <vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vint32mf2_t test_vadd_vv_i32mf2(vint32mf2_t op1, vint32mf2_t op2, size_t vl) {
@@ -250,7 +250,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.i32.i64(<vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.i32.i64(<vscale x 1 x i32> undef, <vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vint32mf2_t test_vadd_vx_i32mf2(vint32mf2_t op1, int32_t op2, size_t vl) {
@@ -259,7 +259,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.nxv2i32.i64(<vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.nxv2i32.i64(<vscale x 2 x i32> undef, <vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vint32m1_t test_vadd_vv_i32m1(vint32m1_t op1, vint32m1_t op2, size_t vl) {
@@ -268,7 +268,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.i32.i64(<vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.i32.i64(<vscale x 2 x i32> undef, <vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vint32m1_t test_vadd_vx_i32m1(vint32m1_t op1, int32_t op2, size_t vl) {
@@ -277,7 +277,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.nxv4i32.i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.nxv4i32.i64(<vscale x 4 x i32> undef, <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vint32m2_t test_vadd_vv_i32m2(vint32m2_t op1, vint32m2_t op2, size_t vl) {
@@ -286,7 +286,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.i32.i64(<vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.i32.i64(<vscale x 4 x i32> undef, <vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vint32m2_t test_vadd_vx_i32m2(vint32m2_t op1, int32_t op2, size_t vl) {
@@ -295,7 +295,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.nxv8i32.i64(<vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.nxv8i32.i64(<vscale x 8 x i32> undef, <vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vint32m4_t test_vadd_vv_i32m4(vint32m4_t op1, vint32m4_t op2, size_t vl) {
@@ -304,7 +304,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.i32.i64(<vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.i32.i64(<vscale x 8 x i32> undef, <vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vint32m4_t test_vadd_vx_i32m4(vint32m4_t op1, int32_t op2, size_t vl) {
@@ -313,7 +313,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.nxv16i32.i64(<vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.nxv16i32.i64(<vscale x 16 x i32> undef, <vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vint32m8_t test_vadd_vv_i32m8(vint32m8_t op1, vint32m8_t op2, size_t vl) {
@@ -322,7 +322,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.i32.i64(<vscale x 16 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.i32.i64(<vscale x 16 x i32> undef, <vscale x 16 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vint32m8_t test_vadd_vx_i32m8(vint32m8_t op1, int32_t op2, size_t vl) {
@@ -331,7 +331,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.nxv1i64.i64(<vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.nxv1i64.i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vint64m1_t test_vadd_vv_i64m1(vint64m1_t op1, vint64m1_t op2, size_t vl) {
@@ -340,7 +340,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.i64.i64(<vscale x 1 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.i64.i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vint64m1_t test_vadd_vx_i64m1(vint64m1_t op1, int64_t op2, size_t vl) {
@@ -349,7 +349,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.nxv2i64.i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.nxv2i64.i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vint64m2_t test_vadd_vv_i64m2(vint64m2_t op1, vint64m2_t op2, size_t vl) {
@@ -358,7 +358,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.i64.i64(<vscale x 2 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.i64.i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vint64m2_t test_vadd_vx_i64m2(vint64m2_t op1, int64_t op2, size_t vl) {
@@ -367,7 +367,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.nxv4i64.i64(<vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.nxv4i64.i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vint64m4_t test_vadd_vv_i64m4(vint64m4_t op1, vint64m4_t op2, size_t vl) {
@@ -376,7 +376,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.i64.i64(<vscale x 4 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.i64.i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vint64m4_t test_vadd_vx_i64m4(vint64m4_t op1, int64_t op2, size_t vl) {
@@ -385,7 +385,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_i64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.nxv8i64.i64(<vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.nxv8i64.i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vint64m8_t test_vadd_vv_i64m8(vint64m8_t op1, vint64m8_t op2, size_t vl) {
@@ -394,7 +394,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_i64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.i64.i64(<vscale x 8 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.i64.i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vint64m8_t test_vadd_vx_i64m8(vint64m8_t op1, int64_t op2, size_t vl) {
@@ -403,7 +403,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u8mf8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.nxv1i8.i64(<vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.nxv1i8.i64(<vscale x 1 x i8> undef, <vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i8> [[TMP0]]
 //
 vuint8mf8_t test_vadd_vv_u8mf8(vuint8mf8_t op1, vuint8mf8_t op2, size_t vl) {
@@ -412,7 +412,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u8mf8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.i8.i64(<vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.i8.i64(<vscale x 1 x i8> undef, <vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i8> [[TMP0]]
 //
 vuint8mf8_t test_vadd_vx_u8mf8(vuint8mf8_t op1, uint8_t op2, size_t vl) {
@@ -421,7 +421,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u8mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.nxv2i8.i64(<vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.nxv2i8.i64(<vscale x 2 x i8> undef, <vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i8> [[TMP0]]
 //
 vuint8mf4_t test_vadd_vv_u8mf4(vuint8mf4_t op1, vuint8mf4_t op2, size_t vl) {
@@ -430,7 +430,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u8mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.i8.i64(<vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i8> @llvm.riscv.vadd.nxv2i8.i8.i64(<vscale x 2 x i8> undef, <vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i8> [[TMP0]]
 //
 vuint8mf4_t test_vadd_vx_u8mf4(vuint8mf4_t op1, uint8_t op2, size_t vl) {
@@ -439,7 +439,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u8mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.nxv4i8.i64(<vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.nxv4i8.i64(<vscale x 4 x i8> undef, <vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i8> [[TMP0]]
 //
 vuint8mf2_t test_vadd_vv_u8mf2(vuint8mf2_t op1, vuint8mf2_t op2, size_t vl) {
@@ -448,7 +448,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u8mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.i8.i64(<vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i8> @llvm.riscv.vadd.nxv4i8.i8.i64(<vscale x 4 x i8> undef, <vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i8> [[TMP0]]
 //
 vuint8mf2_t test_vadd_vx_u8mf2(vuint8mf2_t op1, uint8_t op2, size_t vl) {
@@ -457,7 +457,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u8m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.nxv8i8.i64(<vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.nxv8i8.i64(<vscale x 8 x i8> undef, <vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i8> [[TMP0]]
 //
 vuint8m1_t test_vadd_vv_u8m1(vuint8m1_t op1, vuint8m1_t op2, size_t vl) {
@@ -466,7 +466,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u8m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.i8.i64(<vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i8> @llvm.riscv.vadd.nxv8i8.i8.i64(<vscale x 8 x i8> undef, <vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i8> [[TMP0]]
 //
 vuint8m1_t test_vadd_vx_u8m1(vuint8m1_t op1, uint8_t op2, size_t vl) {
@@ -475,7 +475,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u8m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.nxv16i8.i64(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.nxv16i8.i64(<vscale x 16 x i8> undef, <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
 //
 vuint8m2_t test_vadd_vv_u8m2(vuint8m2_t op1, vuint8m2_t op2, size_t vl) {
@@ -484,7 +484,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u8m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.i8.i64(<vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i8> @llvm.riscv.vadd.nxv16i8.i8.i64(<vscale x 16 x i8> undef, <vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i8> [[TMP0]]
 //
 vuint8m2_t test_vadd_vx_u8m2(vuint8m2_t op1, uint8_t op2, size_t vl) {
@@ -493,7 +493,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u8m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.nxv32i8.i64(<vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.nxv32i8.i64(<vscale x 32 x i8> undef, <vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i8> [[TMP0]]
 //
 vuint8m4_t test_vadd_vv_u8m4(vuint8m4_t op1, vuint8m4_t op2, size_t vl) {
@@ -502,7 +502,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u8m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.i8.i64(<vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i8> @llvm.riscv.vadd.nxv32i8.i8.i64(<vscale x 32 x i8> undef, <vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i8> [[TMP0]]
 //
 vuint8m4_t test_vadd_vx_u8m4(vuint8m4_t op1, uint8_t op2, size_t vl) {
@@ -511,7 +511,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u8m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.nxv64i8.i64(<vscale x 64 x i8> [[OP1:%.*]], <vscale x 64 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.nxv64i8.i64(<vscale x 64 x i8> undef, <vscale x 64 x i8> [[OP1:%.*]], <vscale x 64 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
 //
 vuint8m8_t test_vadd_vv_u8m8(vuint8m8_t op1, vuint8m8_t op2, size_t vl) {
@@ -520,7 +520,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u8m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.i8.i64(<vscale x 64 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 64 x i8> @llvm.riscv.vadd.nxv64i8.i8.i64(<vscale x 64 x i8> undef, <vscale x 64 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 64 x i8> [[TMP0]]
 //
 vuint8m8_t test_vadd_vx_u8m8(vuint8m8_t op1, uint8_t op2, size_t vl) {
@@ -529,7 +529,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.nxv1i16.i64(<vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.nxv1i16.i64(<vscale x 1 x i16> undef, <vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vuint16mf4_t test_vadd_vv_u16mf4(vuint16mf4_t op1, vuint16mf4_t op2, size_t vl) {
@@ -538,7 +538,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.i16.i64(<vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vadd.nxv1i16.i16.i64(<vscale x 1 x i16> undef, <vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vuint16mf4_t test_vadd_vx_u16mf4(vuint16mf4_t op1, uint16_t op2, size_t vl) {
@@ -547,7 +547,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.nxv2i16.i64(<vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.nxv2i16.i64(<vscale x 2 x i16> undef, <vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vuint16mf2_t test_vadd_vv_u16mf2(vuint16mf2_t op1, vuint16mf2_t op2, size_t vl) {
@@ -556,7 +556,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.i16.i64(<vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vadd.nxv2i16.i16.i64(<vscale x 2 x i16> undef, <vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vuint16mf2_t test_vadd_vx_u16mf2(vuint16mf2_t op1, uint16_t op2, size_t vl) {
@@ -565,7 +565,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.nxv4i16.i64(<vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.nxv4i16.i64(<vscale x 4 x i16> undef, <vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vuint16m1_t test_vadd_vv_u16m1(vuint16m1_t op1, vuint16m1_t op2, size_t vl) {
@@ -574,7 +574,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.i16.i64(<vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vadd.nxv4i16.i16.i64(<vscale x 4 x i16> undef, <vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vuint16m1_t test_vadd_vx_u16m1(vuint16m1_t op1, uint16_t op2, size_t vl) {
@@ -583,7 +583,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.nxv8i16.i64(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.nxv8i16.i64(<vscale x 8 x i16> undef, <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vuint16m2_t test_vadd_vv_u16m2(vuint16m2_t op1, vuint16m2_t op2, size_t vl) {
@@ -592,7 +592,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.i16.i64(<vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vadd.nxv8i16.i16.i64(<vscale x 8 x i16> undef, <vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vuint16m2_t test_vadd_vx_u16m2(vuint16m2_t op1, uint16_t op2, size_t vl) {
@@ -601,7 +601,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.nxv16i16.i64(<vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.nxv16i16.i64(<vscale x 16 x i16> undef, <vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vuint16m4_t test_vadd_vv_u16m4(vuint16m4_t op1, vuint16m4_t op2, size_t vl) {
@@ -610,7 +610,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.i16.i64(<vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vadd.nxv16i16.i16.i64(<vscale x 16 x i16> undef, <vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vuint16m4_t test_vadd_vx_u16m4(vuint16m4_t op1, uint16_t op2, size_t vl) {
@@ -619,7 +619,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.nxv32i16.i64(<vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.nxv32i16.i64(<vscale x 32 x i16> undef, <vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vuint16m8_t test_vadd_vv_u16m8(vuint16m8_t op1, vuint16m8_t op2, size_t vl) {
@@ -628,7 +628,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.i16.i64(<vscale x 32 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vadd.nxv32i16.i16.i64(<vscale x 32 x i16> undef, <vscale x 32 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vuint16m8_t test_vadd_vx_u16m8(vuint16m8_t op1, uint16_t op2, size_t vl) {
@@ -637,7 +637,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.nxv1i32.i64(<vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.nxv1i32.i64(<vscale x 1 x i32> undef, <vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vuint32mf2_t test_vadd_vv_u32mf2(vuint32mf2_t op1, vuint32mf2_t op2, size_t vl) {
@@ -646,7 +646,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.i32.i64(<vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vadd.nxv1i32.i32.i64(<vscale x 1 x i32> undef, <vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vuint32mf2_t test_vadd_vx_u32mf2(vuint32mf2_t op1, uint32_t op2, size_t vl) {
@@ -655,7 +655,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.nxv2i32.i64(<vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.nxv2i32.i64(<vscale x 2 x i32> undef, <vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vuint32m1_t test_vadd_vv_u32m1(vuint32m1_t op1, vuint32m1_t op2, size_t vl) {
@@ -664,7 +664,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.i32.i64(<vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vadd.nxv2i32.i32.i64(<vscale x 2 x i32> undef, <vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vuint32m1_t test_vadd_vx_u32m1(vuint32m1_t op1, uint32_t op2, size_t vl) {
@@ -673,7 +673,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.nxv4i32.i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.nxv4i32.i64(<vscale x 4 x i32> undef, <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vuint32m2_t test_vadd_vv_u32m2(vuint32m2_t op1, vuint32m2_t op2, size_t vl) {
@@ -682,7 +682,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.i32.i64(<vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vadd.nxv4i32.i32.i64(<vscale x 4 x i32> undef, <vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vuint32m2_t test_vadd_vx_u32m2(vuint32m2_t op1, uint32_t op2, size_t vl) {
@@ -691,7 +691,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.nxv8i32.i64(<vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.nxv8i32.i64(<vscale x 8 x i32> undef, <vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vuint32m4_t test_vadd_vv_u32m4(vuint32m4_t op1, vuint32m4_t op2, size_t vl) {
@@ -700,7 +700,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.i32.i64(<vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vadd.nxv8i32.i32.i64(<vscale x 8 x i32> undef, <vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vuint32m4_t test_vadd_vx_u32m4(vuint32m4_t op1, uint32_t op2, size_t vl) {
@@ -709,7 +709,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.nxv16i32.i64(<vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.nxv16i32.i64(<vscale x 16 x i32> undef, <vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vuint32m8_t test_vadd_vv_u32m8(vuint32m8_t op1, vuint32m8_t op2, size_t vl) {
@@ -718,7 +718,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.i32.i64(<vscale x 16 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vadd.nxv16i32.i32.i64(<vscale x 16 x i32> undef, <vscale x 16 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vuint32m8_t test_vadd_vx_u32m8(vuint32m8_t op1, uint32_t op2, size_t vl) {
@@ -727,7 +727,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.nxv1i64.i64(<vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.nxv1i64.i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vuint64m1_t test_vadd_vv_u64m1(vuint64m1_t op1, vuint64m1_t op2, size_t vl) {
@@ -736,7 +736,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.i64.i64(<vscale x 1 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vadd.nxv1i64.i64.i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vuint64m1_t test_vadd_vx_u64m1(vuint64m1_t op1, uint64_t op2, size_t vl) {
@@ -745,7 +745,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.nxv2i64.i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.nxv2i64.i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vuint64m2_t test_vadd_vv_u64m2(vuint64m2_t op1, vuint64m2_t op2, size_t vl) {
@@ -754,7 +754,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.i64.i64(<vscale x 2 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vadd.nxv2i64.i64.i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vuint64m2_t test_vadd_vx_u64m2(vuint64m2_t op1, uint64_t op2, size_t vl) {
@@ -763,7 +763,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.nxv4i64.i64(<vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.nxv4i64.i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vuint64m4_t test_vadd_vv_u64m4(vuint64m4_t op1, vuint64m4_t op2, size_t vl) {
@@ -772,7 +772,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.i64.i64(<vscale x 4 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vadd.nxv4i64.i64.i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vuint64m4_t test_vadd_vx_u64m4(vuint64m4_t op1, uint64_t op2, size_t vl) {
@@ -781,7 +781,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vv_u64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.nxv8i64.i64(<vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.nxv8i64.i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i64> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vuint64m8_t test_vadd_vv_u64m8(vuint64m8_t op1, vuint64m8_t op2, size_t vl) {
@@ -790,7 +790,7 @@
 
 // CHECK-RV64-LABEL: @test_vadd_vx_u64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.i64.i64(<vscale x 8 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vadd.nxv8i64.i64.i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> [[OP1:%.*]], i64 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vuint64m8_t test_vadd_vx_u64m8(vuint64m8_t op1, uint64_t op2, size_t vl) {
diff --git a/clang/test/CodeGen/RISCV/rvv-intrinsics/vwadd.c b/clang/test/CodeGen/RISCV/rvv-intrinsics/vwadd.c
--- a/clang/test/CodeGen/RISCV/rvv-intrinsics/vwadd.c
+++ b/clang/test/CodeGen/RISCV/rvv-intrinsics/vwadd.c
@@ -6,7 +6,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwadd.nxv1i16.nxv1i8.nxv1i8.i64(<vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwadd.nxv1i16.nxv1i8.nxv1i8.i64(<vscale x 1 x i16> undef, <vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vint16mf4_t test_vwadd_vv_i16mf4(vint8mf8_t op1, vint8mf8_t op2, size_t vl) {
@@ -15,7 +15,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwadd.nxv1i16.nxv1i8.i8.i64(<vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwadd.nxv1i16.nxv1i8.i8.i64(<vscale x 1 x i16> undef, <vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vint16mf4_t test_vwadd_vx_i16mf4(vint8mf8_t op1, int8_t op2, size_t vl) {
@@ -24,7 +24,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwadd.w.nxv1i16.nxv1i8.i64(<vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwadd.w.nxv1i16.nxv1i8.i64(<vscale x 1 x i16> undef, <vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vint16mf4_t test_vwadd_wv_i16mf4(vint16mf4_t op1, vint8mf8_t op2, size_t vl) {
@@ -33,7 +33,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwadd.w.nxv1i16.i8.i64(<vscale x 1 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwadd.w.nxv1i16.i8.i64(<vscale x 1 x i16> undef, <vscale x 1 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vint16mf4_t test_vwadd_wx_i16mf4(vint16mf4_t op1, int8_t op2, size_t vl) {
@@ -42,7 +42,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwadd.nxv2i16.nxv2i8.nxv2i8.i64(<vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwadd.nxv2i16.nxv2i8.nxv2i8.i64(<vscale x 2 x i16> undef, <vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vint16mf2_t test_vwadd_vv_i16mf2(vint8mf4_t op1, vint8mf4_t op2, size_t vl) {
@@ -51,7 +51,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwadd.nxv2i16.nxv2i8.i8.i64(<vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwadd.nxv2i16.nxv2i8.i8.i64(<vscale x 2 x i16> undef, <vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vint16mf2_t test_vwadd_vx_i16mf2(vint8mf4_t op1, int8_t op2, size_t vl) {
@@ -60,7 +60,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwadd.w.nxv2i16.nxv2i8.i64(<vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwadd.w.nxv2i16.nxv2i8.i64(<vscale x 2 x i16> undef, <vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vint16mf2_t test_vwadd_wv_i16mf2(vint16mf2_t op1, vint8mf4_t op2, size_t vl) {
@@ -69,7 +69,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwadd.w.nxv2i16.i8.i64(<vscale x 2 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwadd.w.nxv2i16.i8.i64(<vscale x 2 x i16> undef, <vscale x 2 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vint16mf2_t test_vwadd_wx_i16mf2(vint16mf2_t op1, int8_t op2, size_t vl) {
@@ -78,7 +78,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwadd.nxv4i16.nxv4i8.nxv4i8.i64(<vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwadd.nxv4i16.nxv4i8.nxv4i8.i64(<vscale x 4 x i16> undef, <vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vint16m1_t test_vwadd_vv_i16m1(vint8mf2_t op1, vint8mf2_t op2, size_t vl) {
@@ -87,7 +87,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwadd.nxv4i16.nxv4i8.i8.i64(<vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwadd.nxv4i16.nxv4i8.i8.i64(<vscale x 4 x i16> undef, <vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vint16m1_t test_vwadd_vx_i16m1(vint8mf2_t op1, int8_t op2, size_t vl) {
@@ -96,7 +96,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwadd.w.nxv4i16.nxv4i8.i64(<vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwadd.w.nxv4i16.nxv4i8.i64(<vscale x 4 x i16> undef, <vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vint16m1_t test_vwadd_wv_i16m1(vint16m1_t op1, vint8mf2_t op2, size_t vl) {
@@ -105,7 +105,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwadd.w.nxv4i16.i8.i64(<vscale x 4 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwadd.w.nxv4i16.i8.i64(<vscale x 4 x i16> undef, <vscale x 4 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vint16m1_t test_vwadd_wx_i16m1(vint16m1_t op1, int8_t op2, size_t vl) {
@@ -114,7 +114,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwadd.nxv8i16.nxv8i8.nxv8i8.i64(<vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwadd.nxv8i16.nxv8i8.nxv8i8.i64(<vscale x 8 x i16> undef, <vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vint16m2_t test_vwadd_vv_i16m2(vint8m1_t op1, vint8m1_t op2, size_t vl) {
@@ -123,7 +123,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwadd.nxv8i16.nxv8i8.i8.i64(<vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwadd.nxv8i16.nxv8i8.i8.i64(<vscale x 8 x i16> undef, <vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vint16m2_t test_vwadd_vx_i16m2(vint8m1_t op1, int8_t op2, size_t vl) {
@@ -132,7 +132,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwadd.w.nxv8i16.nxv8i8.i64(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwadd.w.nxv8i16.nxv8i8.i64(<vscale x 8 x i16> undef, <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vint16m2_t test_vwadd_wv_i16m2(vint16m2_t op1, vint8m1_t op2, size_t vl) {
@@ -141,7 +141,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwadd.w.nxv8i16.i8.i64(<vscale x 8 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwadd.w.nxv8i16.i8.i64(<vscale x 8 x i16> undef, <vscale x 8 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vint16m2_t test_vwadd_wx_i16m2(vint16m2_t op1, int8_t op2, size_t vl) {
@@ -150,7 +150,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwadd.nxv16i16.nxv16i8.nxv16i8.i64(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwadd.nxv16i16.nxv16i8.nxv16i8.i64(<vscale x 16 x i16> undef, <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vint16m4_t test_vwadd_vv_i16m4(vint8m2_t op1, vint8m2_t op2, size_t vl) {
@@ -159,7 +159,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwadd.nxv16i16.nxv16i8.i8.i64(<vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwadd.nxv16i16.nxv16i8.i8.i64(<vscale x 16 x i16> undef, <vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vint16m4_t test_vwadd_vx_i16m4(vint8m2_t op1, int8_t op2, size_t vl) {
@@ -168,7 +168,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwadd.w.nxv16i16.nxv16i8.i64(<vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwadd.w.nxv16i16.nxv16i8.i64(<vscale x 16 x i16> undef, <vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vint16m4_t test_vwadd_wv_i16m4(vint16m4_t op1, vint8m2_t op2, size_t vl) {
@@ -177,7 +177,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwadd.w.nxv16i16.i8.i64(<vscale x 16 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwadd.w.nxv16i16.i8.i64(<vscale x 16 x i16> undef, <vscale x 16 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vint16m4_t test_vwadd_wx_i16m4(vint16m4_t op1, int8_t op2, size_t vl) {
@@ -186,7 +186,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwadd.nxv32i16.nxv32i8.nxv32i8.i64(<vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwadd.nxv32i16.nxv32i8.nxv32i8.i64(<vscale x 32 x i16> undef, <vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vint16m8_t test_vwadd_vv_i16m8(vint8m4_t op1, vint8m4_t op2, size_t vl) {
@@ -195,7 +195,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwadd.nxv32i16.nxv32i8.i8.i64(<vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwadd.nxv32i16.nxv32i8.i8.i64(<vscale x 32 x i16> undef, <vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vint16m8_t test_vwadd_vx_i16m8(vint8m4_t op1, int8_t op2, size_t vl) {
@@ -204,7 +204,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwadd.w.nxv32i16.nxv32i8.i64(<vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwadd.w.nxv32i16.nxv32i8.i64(<vscale x 32 x i16> undef, <vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vint16m8_t test_vwadd_wv_i16m8(vint16m8_t op1, vint8m4_t op2, size_t vl) {
@@ -213,7 +213,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwadd.w.nxv32i16.i8.i64(<vscale x 32 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwadd.w.nxv32i16.i8.i64(<vscale x 32 x i16> undef, <vscale x 32 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vint16m8_t test_vwadd_wx_i16m8(vint16m8_t op1, int8_t op2, size_t vl) {
@@ -222,7 +222,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwadd.nxv1i32.nxv1i16.nxv1i16.i64(<vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwadd.nxv1i32.nxv1i16.nxv1i16.i64(<vscale x 1 x i32> undef, <vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vint32mf2_t test_vwadd_vv_i32mf2(vint16mf4_t op1, vint16mf4_t op2, size_t vl) {
@@ -231,7 +231,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwadd.nxv1i32.nxv1i16.i16.i64(<vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwadd.nxv1i32.nxv1i16.i16.i64(<vscale x 1 x i32> undef, <vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vint32mf2_t test_vwadd_vx_i32mf2(vint16mf4_t op1, int16_t op2, size_t vl) {
@@ -240,7 +240,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwadd.w.nxv1i32.nxv1i16.i64(<vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwadd.w.nxv1i32.nxv1i16.i64(<vscale x 1 x i32> undef, <vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vint32mf2_t test_vwadd_wv_i32mf2(vint32mf2_t op1, vint16mf4_t op2, size_t vl) {
@@ -249,7 +249,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwadd.w.nxv1i32.i16.i64(<vscale x 1 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwadd.w.nxv1i32.i16.i64(<vscale x 1 x i32> undef, <vscale x 1 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vint32mf2_t test_vwadd_wx_i32mf2(vint32mf2_t op1, int16_t op2, size_t vl) {
@@ -258,7 +258,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwadd.nxv2i32.nxv2i16.nxv2i16.i64(<vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwadd.nxv2i32.nxv2i16.nxv2i16.i64(<vscale x 2 x i32> undef, <vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vint32m1_t test_vwadd_vv_i32m1(vint16mf2_t op1, vint16mf2_t op2, size_t vl) {
@@ -267,7 +267,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwadd.nxv2i32.nxv2i16.i16.i64(<vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwadd.nxv2i32.nxv2i16.i16.i64(<vscale x 2 x i32> undef, <vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vint32m1_t test_vwadd_vx_i32m1(vint16mf2_t op1, int16_t op2, size_t vl) {
@@ -276,7 +276,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwadd.w.nxv2i32.nxv2i16.i64(<vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwadd.w.nxv2i32.nxv2i16.i64(<vscale x 2 x i32> undef, <vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vint32m1_t test_vwadd_wv_i32m1(vint32m1_t op1, vint16mf2_t op2, size_t vl) {
@@ -285,7 +285,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwadd.w.nxv2i32.i16.i64(<vscale x 2 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwadd.w.nxv2i32.i16.i64(<vscale x 2 x i32> undef, <vscale x 2 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vint32m1_t test_vwadd_wx_i32m1(vint32m1_t op1, int16_t op2, size_t vl) {
@@ -294,7 +294,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwadd.nxv4i32.nxv4i16.nxv4i16.i64(<vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwadd.nxv4i32.nxv4i16.nxv4i16.i64(<vscale x 4 x i32> undef, <vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vint32m2_t test_vwadd_vv_i32m2(vint16m1_t op1, vint16m1_t op2, size_t vl) {
@@ -303,7 +303,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwadd.nxv4i32.nxv4i16.i16.i64(<vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwadd.nxv4i32.nxv4i16.i16.i64(<vscale x 4 x i32> undef, <vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vint32m2_t test_vwadd_vx_i32m2(vint16m1_t op1, int16_t op2, size_t vl) {
@@ -312,7 +312,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwadd.w.nxv4i32.nxv4i16.i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwadd.w.nxv4i32.nxv4i16.i64(<vscale x 4 x i32> undef, <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vint32m2_t test_vwadd_wv_i32m2(vint32m2_t op1, vint16m1_t op2, size_t vl) {
@@ -321,7 +321,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwadd.w.nxv4i32.i16.i64(<vscale x 4 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwadd.w.nxv4i32.i16.i64(<vscale x 4 x i32> undef, <vscale x 4 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vint32m2_t test_vwadd_wx_i32m2(vint32m2_t op1, int16_t op2, size_t vl) {
@@ -330,7 +330,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwadd.nxv8i32.nxv8i16.nxv8i16.i64(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwadd.nxv8i32.nxv8i16.nxv8i16.i64(<vscale x 8 x i32> undef, <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vint32m4_t test_vwadd_vv_i32m4(vint16m2_t op1, vint16m2_t op2, size_t vl) {
@@ -339,7 +339,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwadd.nxv8i32.nxv8i16.i16.i64(<vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwadd.nxv8i32.nxv8i16.i16.i64(<vscale x 8 x i32> undef, <vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vint32m4_t test_vwadd_vx_i32m4(vint16m2_t op1, int16_t op2, size_t vl) {
@@ -348,7 +348,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwadd.w.nxv8i32.nxv8i16.i64(<vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwadd.w.nxv8i32.nxv8i16.i64(<vscale x 8 x i32> undef, <vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vint32m4_t test_vwadd_wv_i32m4(vint32m4_t op1, vint16m2_t op2, size_t vl) {
@@ -357,7 +357,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwadd.w.nxv8i32.i16.i64(<vscale x 8 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwadd.w.nxv8i32.i16.i64(<vscale x 8 x i32> undef, <vscale x 8 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vint32m4_t test_vwadd_wx_i32m4(vint32m4_t op1, int16_t op2, size_t vl) {
@@ -366,7 +366,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwadd.nxv16i32.nxv16i16.nxv16i16.i64(<vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwadd.nxv16i32.nxv16i16.nxv16i16.i64(<vscale x 16 x i32> undef, <vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vint32m8_t test_vwadd_vv_i32m8(vint16m4_t op1, vint16m4_t op2, size_t vl) {
@@ -375,7 +375,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwadd.nxv16i32.nxv16i16.i16.i64(<vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwadd.nxv16i32.nxv16i16.i16.i64(<vscale x 16 x i32> undef, <vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vint32m8_t test_vwadd_vx_i32m8(vint16m4_t op1, int16_t op2, size_t vl) {
@@ -384,7 +384,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwadd.w.nxv16i32.nxv16i16.i64(<vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwadd.w.nxv16i32.nxv16i16.i64(<vscale x 16 x i32> undef, <vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vint32m8_t test_vwadd_wv_i32m8(vint32m8_t op1, vint16m4_t op2, size_t vl) {
@@ -393,7 +393,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwadd.w.nxv16i32.i16.i64(<vscale x 16 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwadd.w.nxv16i32.i16.i64(<vscale x 16 x i32> undef, <vscale x 16 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vint32m8_t test_vwadd_wx_i32m8(vint32m8_t op1, int16_t op2, size_t vl) {
@@ -402,7 +402,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwadd.nxv1i64.nxv1i32.nxv1i32.i64(<vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwadd.nxv1i64.nxv1i32.nxv1i32.i64(<vscale x 1 x i64> undef, <vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vint64m1_t test_vwadd_vv_i64m1(vint32mf2_t op1, vint32mf2_t op2, size_t vl) {
@@ -411,7 +411,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwadd.nxv1i64.nxv1i32.i32.i64(<vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwadd.nxv1i64.nxv1i32.i32.i64(<vscale x 1 x i64> undef, <vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vint64m1_t test_vwadd_vx_i64m1(vint32mf2_t op1, int32_t op2, size_t vl) {
@@ -420,7 +420,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwadd.w.nxv1i64.nxv1i32.i64(<vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwadd.w.nxv1i64.nxv1i32.i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vint64m1_t test_vwadd_wv_i64m1(vint64m1_t op1, vint32mf2_t op2, size_t vl) {
@@ -429,7 +429,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwadd.w.nxv1i64.i32.i64(<vscale x 1 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwadd.w.nxv1i64.i32.i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vint64m1_t test_vwadd_wx_i64m1(vint64m1_t op1, int32_t op2, size_t vl) {
@@ -438,7 +438,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwadd.nxv2i64.nxv2i32.nxv2i32.i64(<vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwadd.nxv2i64.nxv2i32.nxv2i32.i64(<vscale x 2 x i64> undef, <vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vint64m2_t test_vwadd_vv_i64m2(vint32m1_t op1, vint32m1_t op2, size_t vl) {
@@ -447,7 +447,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwadd.nxv2i64.nxv2i32.i32.i64(<vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwadd.nxv2i64.nxv2i32.i32.i64(<vscale x 2 x i64> undef, <vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vint64m2_t test_vwadd_vx_i64m2(vint32m1_t op1, int32_t op2, size_t vl) {
@@ -456,7 +456,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwadd.w.nxv2i64.nxv2i32.i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwadd.w.nxv2i64.nxv2i32.i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vint64m2_t test_vwadd_wv_i64m2(vint64m2_t op1, vint32m1_t op2, size_t vl) {
@@ -465,7 +465,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwadd.w.nxv2i64.i32.i64(<vscale x 2 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwadd.w.nxv2i64.i32.i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vint64m2_t test_vwadd_wx_i64m2(vint64m2_t op1, int32_t op2, size_t vl) {
@@ -474,7 +474,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwadd.nxv4i64.nxv4i32.nxv4i32.i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwadd.nxv4i64.nxv4i32.nxv4i32.i64(<vscale x 4 x i64> undef, <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vint64m4_t test_vwadd_vv_i64m4(vint32m2_t op1, vint32m2_t op2, size_t vl) {
@@ -483,7 +483,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwadd.nxv4i64.nxv4i32.i32.i64(<vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwadd.nxv4i64.nxv4i32.i32.i64(<vscale x 4 x i64> undef, <vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vint64m4_t test_vwadd_vx_i64m4(vint32m2_t op1, int32_t op2, size_t vl) {
@@ -492,7 +492,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwadd.w.nxv4i64.nxv4i32.i64(<vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwadd.w.nxv4i64.nxv4i32.i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vint64m4_t test_vwadd_wv_i64m4(vint64m4_t op1, vint32m2_t op2, size_t vl) {
@@ -501,7 +501,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwadd.w.nxv4i64.i32.i64(<vscale x 4 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwadd.w.nxv4i64.i32.i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vint64m4_t test_vwadd_wx_i64m4(vint64m4_t op1, int32_t op2, size_t vl) {
@@ -510,7 +510,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vv_i64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwadd.nxv8i64.nxv8i32.nxv8i32.i64(<vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwadd.nxv8i64.nxv8i32.nxv8i32.i64(<vscale x 8 x i64> undef, <vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vint64m8_t test_vwadd_vv_i64m8(vint32m4_t op1, vint32m4_t op2, size_t vl) {
@@ -519,7 +519,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_vx_i64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwadd.nxv8i64.nxv8i32.i32.i64(<vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwadd.nxv8i64.nxv8i32.i32.i64(<vscale x 8 x i64> undef, <vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vint64m8_t test_vwadd_vx_i64m8(vint32m4_t op1, int32_t op2, size_t vl) {
@@ -528,7 +528,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wv_i64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwadd.w.nxv8i64.nxv8i32.i64(<vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwadd.w.nxv8i64.nxv8i32.i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vint64m8_t test_vwadd_wv_i64m8(vint64m8_t op1, vint32m4_t op2, size_t vl) {
@@ -537,7 +537,7 @@
 
 // CHECK-RV64-LABEL: @test_vwadd_wx_i64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwadd.w.nxv8i64.i32.i64(<vscale x 8 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwadd.w.nxv8i64.i32.i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vint64m8_t test_vwadd_wx_i64m8(vint64m8_t op1, int32_t op2, size_t vl) {
@@ -546,7 +546,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwaddu.nxv1i16.nxv1i8.nxv1i8.i64(<vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwaddu.nxv1i16.nxv1i8.nxv1i8.i64(<vscale x 1 x i16> undef, <vscale x 1 x i8> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vuint16mf4_t test_vwaddu_vv_u16mf4(vuint8mf8_t op1, vuint8mf8_t op2,
@@ -556,7 +556,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwaddu.nxv1i16.nxv1i8.i8.i64(<vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwaddu.nxv1i16.nxv1i8.i8.i64(<vscale x 1 x i16> undef, <vscale x 1 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vuint16mf4_t test_vwaddu_vx_u16mf4(vuint8mf8_t op1, uint8_t op2, size_t vl) {
@@ -565,7 +565,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwaddu.w.nxv1i16.nxv1i8.i64(<vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwaddu.w.nxv1i16.nxv1i8.i64(<vscale x 1 x i16> undef, <vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vuint16mf4_t test_vwaddu_wv_u16mf4(vuint16mf4_t op1, vuint8mf8_t op2,
@@ -575,7 +575,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u16mf4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwaddu.w.nxv1i16.i8.i64(<vscale x 1 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i16> @llvm.riscv.vwaddu.w.nxv1i16.i8.i64(<vscale x 1 x i16> undef, <vscale x 1 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i16> [[TMP0]]
 //
 vuint16mf4_t test_vwaddu_wx_u16mf4(vuint16mf4_t op1, uint8_t op2, size_t vl) {
@@ -584,7 +584,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwaddu.nxv2i16.nxv2i8.nxv2i8.i64(<vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwaddu.nxv2i16.nxv2i8.nxv2i8.i64(<vscale x 2 x i16> undef, <vscale x 2 x i8> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vuint16mf2_t test_vwaddu_vv_u16mf2(vuint8mf4_t op1, vuint8mf4_t op2,
@@ -594,7 +594,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwaddu.nxv2i16.nxv2i8.i8.i64(<vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwaddu.nxv2i16.nxv2i8.i8.i64(<vscale x 2 x i16> undef, <vscale x 2 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vuint16mf2_t test_vwaddu_vx_u16mf2(vuint8mf4_t op1, uint8_t op2, size_t vl) {
@@ -603,7 +603,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwaddu.w.nxv2i16.nxv2i8.i64(<vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwaddu.w.nxv2i16.nxv2i8.i64(<vscale x 2 x i16> undef, <vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vuint16mf2_t test_vwaddu_wv_u16mf2(vuint16mf2_t op1, vuint8mf4_t op2,
@@ -613,7 +613,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u16mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwaddu.w.nxv2i16.i8.i64(<vscale x 2 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i16> @llvm.riscv.vwaddu.w.nxv2i16.i8.i64(<vscale x 2 x i16> undef, <vscale x 2 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i16> [[TMP0]]
 //
 vuint16mf2_t test_vwaddu_wx_u16mf2(vuint16mf2_t op1, uint8_t op2, size_t vl) {
@@ -622,7 +622,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwaddu.nxv4i16.nxv4i8.nxv4i8.i64(<vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwaddu.nxv4i16.nxv4i8.nxv4i8.i64(<vscale x 4 x i16> undef, <vscale x 4 x i8> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vuint16m1_t test_vwaddu_vv_u16m1(vuint8mf2_t op1, vuint8mf2_t op2, size_t vl) {
@@ -631,7 +631,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwaddu.nxv4i16.nxv4i8.i8.i64(<vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwaddu.nxv4i16.nxv4i8.i8.i64(<vscale x 4 x i16> undef, <vscale x 4 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vuint16m1_t test_vwaddu_vx_u16m1(vuint8mf2_t op1, uint8_t op2, size_t vl) {
@@ -640,7 +640,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwaddu.w.nxv4i16.nxv4i8.i64(<vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwaddu.w.nxv4i16.nxv4i8.i64(<vscale x 4 x i16> undef, <vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vuint16m1_t test_vwaddu_wv_u16m1(vuint16m1_t op1, vuint8mf2_t op2, size_t vl) {
@@ -649,7 +649,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u16m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwaddu.w.nxv4i16.i8.i64(<vscale x 4 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i16> @llvm.riscv.vwaddu.w.nxv4i16.i8.i64(<vscale x 4 x i16> undef, <vscale x 4 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i16> [[TMP0]]
 //
 vuint16m1_t test_vwaddu_wx_u16m1(vuint16m1_t op1, uint8_t op2, size_t vl) {
@@ -658,7 +658,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwaddu.nxv8i16.nxv8i8.nxv8i8.i64(<vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwaddu.nxv8i16.nxv8i8.nxv8i8.i64(<vscale x 8 x i16> undef, <vscale x 8 x i8> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vuint16m2_t test_vwaddu_vv_u16m2(vuint8m1_t op1, vuint8m1_t op2, size_t vl) {
@@ -667,7 +667,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwaddu.nxv8i16.nxv8i8.i8.i64(<vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwaddu.nxv8i16.nxv8i8.i8.i64(<vscale x 8 x i16> undef, <vscale x 8 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vuint16m2_t test_vwaddu_vx_u16m2(vuint8m1_t op1, uint8_t op2, size_t vl) {
@@ -676,7 +676,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwaddu.w.nxv8i16.nxv8i8.i64(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwaddu.w.nxv8i16.nxv8i8.i64(<vscale x 8 x i16> undef, <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vuint16m2_t test_vwaddu_wv_u16m2(vuint16m2_t op1, vuint8m1_t op2, size_t vl) {
@@ -685,7 +685,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u16m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwaddu.w.nxv8i16.i8.i64(<vscale x 8 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i16> @llvm.riscv.vwaddu.w.nxv8i16.i8.i64(<vscale x 8 x i16> undef, <vscale x 8 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i16> [[TMP0]]
 //
 vuint16m2_t test_vwaddu_wx_u16m2(vuint16m2_t op1, uint8_t op2, size_t vl) {
@@ -694,7 +694,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwaddu.nxv16i16.nxv16i8.nxv16i8.i64(<vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwaddu.nxv16i16.nxv16i8.nxv16i8.i64(<vscale x 16 x i16> undef, <vscale x 16 x i8> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vuint16m4_t test_vwaddu_vv_u16m4(vuint8m2_t op1, vuint8m2_t op2, size_t vl) {
@@ -703,7 +703,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwaddu.nxv16i16.nxv16i8.i8.i64(<vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwaddu.nxv16i16.nxv16i8.i8.i64(<vscale x 16 x i16> undef, <vscale x 16 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vuint16m4_t test_vwaddu_vx_u16m4(vuint8m2_t op1, uint8_t op2, size_t vl) {
@@ -712,7 +712,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwaddu.w.nxv16i16.nxv16i8.i64(<vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwaddu.w.nxv16i16.nxv16i8.i64(<vscale x 16 x i16> undef, <vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vuint16m4_t test_vwaddu_wv_u16m4(vuint16m4_t op1, vuint8m2_t op2, size_t vl) {
@@ -721,7 +721,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u16m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwaddu.w.nxv16i16.i8.i64(<vscale x 16 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i16> @llvm.riscv.vwaddu.w.nxv16i16.i8.i64(<vscale x 16 x i16> undef, <vscale x 16 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i16> [[TMP0]]
 //
 vuint16m4_t test_vwaddu_wx_u16m4(vuint16m4_t op1, uint8_t op2, size_t vl) {
@@ -730,7 +730,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwaddu.nxv32i16.nxv32i8.nxv32i8.i64(<vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwaddu.nxv32i16.nxv32i8.nxv32i8.i64(<vscale x 32 x i16> undef, <vscale x 32 x i8> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vuint16m8_t test_vwaddu_vv_u16m8(vuint8m4_t op1, vuint8m4_t op2, size_t vl) {
@@ -739,7 +739,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwaddu.nxv32i16.nxv32i8.i8.i64(<vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwaddu.nxv32i16.nxv32i8.i8.i64(<vscale x 32 x i16> undef, <vscale x 32 x i8> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vuint16m8_t test_vwaddu_vx_u16m8(vuint8m4_t op1, uint8_t op2, size_t vl) {
@@ -748,7 +748,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwaddu.w.nxv32i16.nxv32i8.i64(<vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwaddu.w.nxv32i16.nxv32i8.i64(<vscale x 32 x i16> undef, <vscale x 32 x i16> [[OP1:%.*]], <vscale x 32 x i8> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vuint16m8_t test_vwaddu_wv_u16m8(vuint16m8_t op1, vuint8m4_t op2, size_t vl) {
@@ -757,7 +757,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u16m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwaddu.w.nxv32i16.i8.i64(<vscale x 32 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 32 x i16> @llvm.riscv.vwaddu.w.nxv32i16.i8.i64(<vscale x 32 x i16> undef, <vscale x 32 x i16> [[OP1:%.*]], i8 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 32 x i16> [[TMP0]]
 //
 vuint16m8_t test_vwaddu_wx_u16m8(vuint16m8_t op1, uint8_t op2, size_t vl) {
@@ -766,7 +766,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwaddu.nxv1i32.nxv1i16.nxv1i16.i64(<vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwaddu.nxv1i32.nxv1i16.nxv1i16.i64(<vscale x 1 x i32> undef, <vscale x 1 x i16> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vuint32mf2_t test_vwaddu_vv_u32mf2(vuint16mf4_t op1, vuint16mf4_t op2,
@@ -776,7 +776,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwaddu.nxv1i32.nxv1i16.i16.i64(<vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwaddu.nxv1i32.nxv1i16.i16.i64(<vscale x 1 x i32> undef, <vscale x 1 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vuint32mf2_t test_vwaddu_vx_u32mf2(vuint16mf4_t op1, uint16_t op2, size_t vl) {
@@ -785,7 +785,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwaddu.w.nxv1i32.nxv1i16.i64(<vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwaddu.w.nxv1i32.nxv1i16.i64(<vscale x 1 x i32> undef, <vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vuint32mf2_t test_vwaddu_wv_u32mf2(vuint32mf2_t op1, vuint16mf4_t op2,
@@ -795,7 +795,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u32mf2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwaddu.w.nxv1i32.i16.i64(<vscale x 1 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i32> @llvm.riscv.vwaddu.w.nxv1i32.i16.i64(<vscale x 1 x i32> undef, <vscale x 1 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i32> [[TMP0]]
 //
 vuint32mf2_t test_vwaddu_wx_u32mf2(vuint32mf2_t op1, uint16_t op2, size_t vl) {
@@ -804,7 +804,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwaddu.nxv2i32.nxv2i16.nxv2i16.i64(<vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwaddu.nxv2i32.nxv2i16.nxv2i16.i64(<vscale x 2 x i32> undef, <vscale x 2 x i16> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vuint32m1_t test_vwaddu_vv_u32m1(vuint16mf2_t op1, vuint16mf2_t op2,
@@ -814,7 +814,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwaddu.nxv2i32.nxv2i16.i16.i64(<vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwaddu.nxv2i32.nxv2i16.i16.i64(<vscale x 2 x i32> undef, <vscale x 2 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vuint32m1_t test_vwaddu_vx_u32m1(vuint16mf2_t op1, uint16_t op2, size_t vl) {
@@ -823,7 +823,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwaddu.w.nxv2i32.nxv2i16.i64(<vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwaddu.w.nxv2i32.nxv2i16.i64(<vscale x 2 x i32> undef, <vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vuint32m1_t test_vwaddu_wv_u32m1(vuint32m1_t op1, vuint16mf2_t op2, size_t vl) {
@@ -832,7 +832,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u32m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwaddu.w.nxv2i32.i16.i64(<vscale x 2 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i32> @llvm.riscv.vwaddu.w.nxv2i32.i16.i64(<vscale x 2 x i32> undef, <vscale x 2 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i32> [[TMP0]]
 //
 vuint32m1_t test_vwaddu_wx_u32m1(vuint32m1_t op1, uint16_t op2, size_t vl) {
@@ -841,7 +841,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwaddu.nxv4i32.nxv4i16.nxv4i16.i64(<vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwaddu.nxv4i32.nxv4i16.nxv4i16.i64(<vscale x 4 x i32> undef, <vscale x 4 x i16> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vuint32m2_t test_vwaddu_vv_u32m2(vuint16m1_t op1, vuint16m1_t op2, size_t vl) {
@@ -850,7 +850,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwaddu.nxv4i32.nxv4i16.i16.i64(<vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwaddu.nxv4i32.nxv4i16.i16.i64(<vscale x 4 x i32> undef, <vscale x 4 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vuint32m2_t test_vwaddu_vx_u32m2(vuint16m1_t op1, uint16_t op2, size_t vl) {
@@ -859,7 +859,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwaddu.w.nxv4i32.nxv4i16.i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwaddu.w.nxv4i32.nxv4i16.i64(<vscale x 4 x i32> undef, <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vuint32m2_t test_vwaddu_wv_u32m2(vuint32m2_t op1, vuint16m1_t op2, size_t vl) {
@@ -868,7 +868,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u32m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwaddu.w.nxv4i32.i16.i64(<vscale x 4 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i32> @llvm.riscv.vwaddu.w.nxv4i32.i16.i64(<vscale x 4 x i32> undef, <vscale x 4 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i32> [[TMP0]]
 //
 vuint32m2_t test_vwaddu_wx_u32m2(vuint32m2_t op1, uint16_t op2, size_t vl) {
@@ -877,7 +877,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwaddu.nxv8i32.nxv8i16.nxv8i16.i64(<vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwaddu.nxv8i32.nxv8i16.nxv8i16.i64(<vscale x 8 x i32> undef, <vscale x 8 x i16> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vuint32m4_t test_vwaddu_vv_u32m4(vuint16m2_t op1, vuint16m2_t op2, size_t vl) {
@@ -886,7 +886,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwaddu.nxv8i32.nxv8i16.i16.i64(<vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwaddu.nxv8i32.nxv8i16.i16.i64(<vscale x 8 x i32> undef, <vscale x 8 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vuint32m4_t test_vwaddu_vx_u32m4(vuint16m2_t op1, uint16_t op2, size_t vl) {
@@ -895,7 +895,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwaddu.w.nxv8i32.nxv8i16.i64(<vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwaddu.w.nxv8i32.nxv8i16.i64(<vscale x 8 x i32> undef, <vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vuint32m4_t test_vwaddu_wv_u32m4(vuint32m4_t op1, vuint16m2_t op2, size_t vl) {
@@ -904,7 +904,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u32m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwaddu.w.nxv8i32.i16.i64(<vscale x 8 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i32> @llvm.riscv.vwaddu.w.nxv8i32.i16.i64(<vscale x 8 x i32> undef, <vscale x 8 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i32> [[TMP0]]
 //
 vuint32m4_t test_vwaddu_wx_u32m4(vuint32m4_t op1, uint16_t op2, size_t vl) {
@@ -913,7 +913,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwaddu.nxv16i32.nxv16i16.nxv16i16.i64(<vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwaddu.nxv16i32.nxv16i16.nxv16i16.i64(<vscale x 16 x i32> undef, <vscale x 16 x i16> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vuint32m8_t test_vwaddu_vv_u32m8(vuint16m4_t op1, vuint16m4_t op2, size_t vl) {
@@ -922,7 +922,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwaddu.nxv16i32.nxv16i16.i16.i64(<vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwaddu.nxv16i32.nxv16i16.i16.i64(<vscale x 16 x i32> undef, <vscale x 16 x i16> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vuint32m8_t test_vwaddu_vx_u32m8(vuint16m4_t op1, uint16_t op2, size_t vl) {
@@ -931,7 +931,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwaddu.w.nxv16i32.nxv16i16.i64(<vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwaddu.w.nxv16i32.nxv16i16.i64(<vscale x 16 x i32> undef, <vscale x 16 x i32> [[OP1:%.*]], <vscale x 16 x i16> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vuint32m8_t test_vwaddu_wv_u32m8(vuint32m8_t op1, vuint16m4_t op2, size_t vl) {
@@ -940,7 +940,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u32m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwaddu.w.nxv16i32.i16.i64(<vscale x 16 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 16 x i32> @llvm.riscv.vwaddu.w.nxv16i32.i16.i64(<vscale x 16 x i32> undef, <vscale x 16 x i32> [[OP1:%.*]], i16 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 16 x i32> [[TMP0]]
 //
 vuint32m8_t test_vwaddu_wx_u32m8(vuint32m8_t op1, uint16_t op2, size_t vl) {
@@ -949,7 +949,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwaddu.nxv1i64.nxv1i32.nxv1i32.i64(<vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwaddu.nxv1i64.nxv1i32.nxv1i32.i64(<vscale x 1 x i64> undef, <vscale x 1 x i32> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vuint64m1_t test_vwaddu_vv_u64m1(vuint32mf2_t op1, vuint32mf2_t op2,
@@ -959,7 +959,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwaddu.nxv1i64.nxv1i32.i32.i64(<vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwaddu.nxv1i64.nxv1i32.i32.i64(<vscale x 1 x i64> undef, <vscale x 1 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vuint64m1_t test_vwaddu_vx_u64m1(vuint32mf2_t op1, uint32_t op2, size_t vl) {
@@ -968,7 +968,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwaddu.w.nxv1i64.nxv1i32.i64(<vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwaddu.w.nxv1i64.nxv1i32.i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> [[OP1:%.*]], <vscale x 1 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vuint64m1_t test_vwaddu_wv_u64m1(vuint64m1_t op1, vuint32mf2_t op2, size_t vl) {
@@ -977,7 +977,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u64m1(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwaddu.w.nxv1i64.i32.i64(<vscale x 1 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 1 x i64> @llvm.riscv.vwaddu.w.nxv1i64.i32.i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 1 x i64> [[TMP0]]
 //
 vuint64m1_t test_vwaddu_wx_u64m1(vuint64m1_t op1, uint32_t op2, size_t vl) {
@@ -986,7 +986,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwaddu.nxv2i64.nxv2i32.nxv2i32.i64(<vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwaddu.nxv2i64.nxv2i32.nxv2i32.i64(<vscale x 2 x i64> undef, <vscale x 2 x i32> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vuint64m2_t test_vwaddu_vv_u64m2(vuint32m1_t op1, vuint32m1_t op2, size_t vl) {
@@ -995,7 +995,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwaddu.nxv2i64.nxv2i32.i32.i64(<vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwaddu.nxv2i64.nxv2i32.i32.i64(<vscale x 2 x i64> undef, <vscale x 2 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vuint64m2_t test_vwaddu_vx_u64m2(vuint32m1_t op1, uint32_t op2, size_t vl) {
@@ -1004,7 +1004,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwaddu.w.nxv2i64.nxv2i32.i64(<vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwaddu.w.nxv2i64.nxv2i32.i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> [[OP1:%.*]], <vscale x 2 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vuint64m2_t test_vwaddu_wv_u64m2(vuint64m2_t op1, vuint32m1_t op2, size_t vl) {
@@ -1013,7 +1013,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u64m2(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwaddu.w.nxv2i64.i32.i64(<vscale x 2 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 2 x i64> @llvm.riscv.vwaddu.w.nxv2i64.i32.i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 2 x i64> [[TMP0]]
 //
 vuint64m2_t test_vwaddu_wx_u64m2(vuint64m2_t op1, uint32_t op2, size_t vl) {
@@ -1022,7 +1022,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwaddu.nxv4i64.nxv4i32.nxv4i32.i64(<vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwaddu.nxv4i64.nxv4i32.nxv4i32.i64(<vscale x 4 x i64> undef, <vscale x 4 x i32> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vuint64m4_t test_vwaddu_vv_u64m4(vuint32m2_t op1, vuint32m2_t op2, size_t vl) {
@@ -1031,7 +1031,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwaddu.nxv4i64.nxv4i32.i32.i64(<vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwaddu.nxv4i64.nxv4i32.i32.i64(<vscale x 4 x i64> undef, <vscale x 4 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vuint64m4_t test_vwaddu_vx_u64m4(vuint32m2_t op1, uint32_t op2, size_t vl) {
@@ -1040,7 +1040,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwaddu.w.nxv4i64.nxv4i32.i64(<vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwaddu.w.nxv4i64.nxv4i32.i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> [[OP1:%.*]], <vscale x 4 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vuint64m4_t test_vwaddu_wv_u64m4(vuint64m4_t op1, vuint32m2_t op2, size_t vl) {
@@ -1049,7 +1049,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u64m4(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwaddu.w.nxv4i64.i32.i64(<vscale x 4 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 4 x i64> @llvm.riscv.vwaddu.w.nxv4i64.i32.i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 4 x i64> [[TMP0]]
 //
 vuint64m4_t test_vwaddu_wx_u64m4(vuint64m4_t op1, uint32_t op2, size_t vl) {
@@ -1058,7 +1058,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vv_u64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwaddu.nxv8i64.nxv8i32.nxv8i32.i64(<vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwaddu.nxv8i64.nxv8i32.nxv8i32.i64(<vscale x 8 x i64> undef, <vscale x 8 x i32> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vuint64m8_t test_vwaddu_vv_u64m8(vuint32m4_t op1, vuint32m4_t op2, size_t vl) {
@@ -1067,7 +1067,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_vx_u64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwaddu.nxv8i64.nxv8i32.i32.i64(<vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwaddu.nxv8i64.nxv8i32.i32.i64(<vscale x 8 x i64> undef, <vscale x 8 x i32> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vuint64m8_t test_vwaddu_vx_u64m8(vuint32m4_t op1, uint32_t op2, size_t vl) {
@@ -1076,7 +1076,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wv_u64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwaddu.w.nxv8i64.nxv8i32.i64(<vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwaddu.w.nxv8i64.nxv8i32.i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> [[OP1:%.*]], <vscale x 8 x i32> [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vuint64m8_t test_vwaddu_wv_u64m8(vuint64m8_t op1, vuint32m4_t op2, size_t vl) {
@@ -1085,7 +1085,7 @@
 
 // CHECK-RV64-LABEL: @test_vwaddu_wx_u64m8(
 // CHECK-RV64-NEXT:  entry:
-// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwaddu.w.nxv8i64.i32.i64(<vscale x 8 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
+// CHECK-RV64-NEXT:    [[TMP0:%.*]] = call <vscale x 8 x i64> @llvm.riscv.vwaddu.w.nxv8i64.i32.i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> [[OP1:%.*]], i32 [[OP2:%.*]], i64 [[VL:%.*]])
 // CHECK-RV64-NEXT:    ret <vscale x 8 x i64> [[TMP0]]
 //
 vuint64m8_t test_vwaddu_wx_u64m8(vuint64m8_t op1, uint32_t op2, size_t vl) {
diff --git a/clang/utils/TableGen/RISCVVEmitter.cpp b/clang/utils/TableGen/RISCVVEmitter.cpp
--- a/clang/utils/TableGen/RISCVVEmitter.cpp
+++ b/clang/utils/TableGen/RISCVVEmitter.cpp
@@ -162,6 +162,7 @@
   bool IsMask;
   bool HasVL;
   bool HasPolicy;
+  bool HasNoMaskPolicy;
   bool HasNoMaskedOverloaded;
   bool HasAutoDef; // There is automiatic definition in header
   std::string ManualCodegen;
@@ -177,8 +178,8 @@
   RVVIntrinsic(StringRef Name, StringRef Suffix, StringRef MangledName,
                StringRef MangledSuffix, StringRef IRName, bool IsMask,
                bool HasMaskedOffOperand, bool HasVL, bool HasPolicy,
-               bool HasNoMaskedOverloaded, bool HasAutoDef,
-               StringRef ManualCodegen, const RVVTypes &Types,
+               bool HasNoMaskPolicy, bool HasNoMaskedOverloaded,
+               bool HasAutoDef, StringRef ManualCodegen, const RVVTypes &Types,
                const std::vector<int64_t> &IntrinsicTypes,
                const std::vector<StringRef> &RequiredFeatures, unsigned NF);
   ~RVVIntrinsic() = default;
@@ -188,6 +189,7 @@
   StringRef getMangledName() const { return MangledName; }
   bool hasVL() const { return HasVL; }
   bool hasPolicy() const { return HasPolicy; }
+  bool hasNoMaskPolicy() const { return HasNoMaskPolicy; }
   bool hasNoMaskedOverloaded() const { return HasNoMaskedOverloaded; }
   bool hasManualCodegen() const { return !ManualCodegen.empty(); }
   bool hasAutoDef() const { return HasAutoDef; }
@@ -766,16 +768,15 @@
 //===----------------------------------------------------------------------===//
 // RVVIntrinsic implementation
 //===----------------------------------------------------------------------===//
-RVVIntrinsic::RVVIntrinsic(StringRef NewName, StringRef Suffix,
-                           StringRef NewMangledName, StringRef MangledSuffix,
-                           StringRef IRName, bool IsMask,
-                           bool HasMaskedOffOperand, bool HasVL, bool HasPolicy,
-                           bool HasNoMaskedOverloaded, bool HasAutoDef,
-                           StringRef ManualCodegen, const RVVTypes &OutInTypes,
-                           const std::vector<int64_t> &NewIntrinsicTypes,
-                           const std::vector<StringRef> &RequiredFeatures,
-                           unsigned NF)
+RVVIntrinsic::RVVIntrinsic(
+    StringRef NewName, StringRef Suffix, StringRef NewMangledName,
+    StringRef MangledSuffix, StringRef IRName, bool IsMask,
+    bool HasMaskedOffOperand, bool HasVL, bool HasPolicy, bool HasNoMaskPolicy,
+    bool HasNoMaskedOverloaded, bool HasAutoDef, StringRef ManualCodegen,
+    const RVVTypes &OutInTypes, const std::vector<int64_t> &NewIntrinsicTypes,
+    const std::vector<StringRef> &RequiredFeatures, unsigned NF)
     : IRName(IRName), IsMask(IsMask), HasVL(HasVL), HasPolicy(HasPolicy),
+      HasNoMaskPolicy(HasNoMaskPolicy),
       HasNoMaskedOverloaded(HasNoMaskedOverloaded), HasAutoDef(HasAutoDef),
       ManualCodegen(ManualCodegen.str()), NF(NF) {
 
@@ -823,7 +824,7 @@
   // IntrinsicTypes is nonmasked version index. Need to update it
   // if there is maskedoff operand (It is always in first operand).
   IntrinsicTypes = NewIntrinsicTypes;
-  if (IsMask && HasMaskedOffOperand) {
+  if ((IsMask && HasMaskedOffOperand) || (!IsMask && HasNoMaskPolicy)) {
     for (auto &I : IntrinsicTypes) {
       if (I >= 0)
         I += NF;
@@ -860,6 +861,9 @@
     } else {
       OS << "  std::rotate(Ops.begin(), Ops.begin() + 1, Ops.end());\n";
     }
+  } else if (hasNoMaskPolicy()) {
+    OS << "  Ops.push_back(llvm::UndefValue::get(ResultType));\n";
+    OS << "  std::rotate(Ops.rbegin(), Ops.rbegin() + 1,  Ops.rend());\n";
   }
 
   OS << "  IntrinsicTypes = {";
@@ -1107,6 +1111,8 @@
       PrintFatalError("Builtin with same name has different HasPolicy");
     else if (P.first->second->hasPolicy() != Def->hasPolicy())
       PrintFatalError("Builtin with same name has different HasPolicy");
+    else if (P.first->second->hasNoMaskPolicy() != Def->hasNoMaskPolicy())
+      PrintFatalError("Builtin with same name has different HasNoMaskPolicy");
     else if (P.first->second->getIntrinsicTypes() != Def->getIntrinsicTypes())
       PrintFatalError("Builtin with same name has different IntrinsicTypes");
   }
@@ -1154,6 +1160,7 @@
     bool HasMaskedOffOperand = R->getValueAsBit("HasMaskedOffOperand");
     bool HasVL = R->getValueAsBit("HasVL");
     bool HasPolicy = R->getValueAsBit("HasPolicy");
+    bool HasNoMaskPolicy = R->getValueAsBit("HasNoMaskPolicy");
     bool HasNoMaskedOverloaded = R->getValueAsBit("HasNoMaskedOverloaded");
     std::vector<int64_t> Log2LMULList = R->getValueAsListOfInts("Log2LMUL");
     StringRef ManualCodegen = R->getValueAsString("ManualCodegen");
@@ -1228,8 +1235,8 @@
         Out.push_back(std::make_unique<RVVIntrinsic>(
             Name, SuffixStr, MangledName, MangledSuffixStr, IRName,
             /*IsMask=*/false, /*HasMaskedOffOperand=*/false, HasVL, HasPolicy,
-            HasNoMaskedOverloaded, HasAutoDef, ManualCodegen, Types.getValue(),
-            IntrinsicTypes, RequiredFeatures, NF));
+            HasNoMaskPolicy, HasNoMaskedOverloaded, HasAutoDef, ManualCodegen,
+            Types.getValue(), IntrinsicTypes, RequiredFeatures, NF));
         if (HasMask) {
           // Create a mask intrinsic
           Optional<RVVTypes> MaskTypes =
@@ -1237,8 +1244,9 @@
           Out.push_back(std::make_unique<RVVIntrinsic>(
               Name, SuffixStr, MangledName, MangledSuffixStr, IRNameMask,
               /*IsMask=*/true, HasMaskedOffOperand, HasVL, HasPolicy,
-              HasNoMaskedOverloaded, HasAutoDef, ManualCodegenMask,
-              MaskTypes.getValue(), IntrinsicTypes, RequiredFeatures, NF));
+              HasNoMaskPolicy, HasNoMaskedOverloaded, HasAutoDef,
+              ManualCodegenMask, MaskTypes.getValue(), IntrinsicTypes,
+              RequiredFeatures, NF));
         }
       } // end for Log2LMULList
     }   // end for TypeRange
diff --git a/llvm/include/llvm/IR/IntrinsicsRISCV.td b/llvm/include/llvm/IR/IntrinsicsRISCV.td
--- a/llvm/include/llvm/IR/IntrinsicsRISCV.td
+++ b/llvm/include/llvm/IR/IntrinsicsRISCV.td
@@ -372,12 +372,13 @@
     let VLOperand = 2;
   }
   // For destination vector type is the same as first and second source vector.
-  // Input: (vector_in, int_vector_in, vl)
+  // Input: (passthru, vector_in, int_vector_in, vl)
   class RISCVRGatherVVNoMask
         : Intrinsic<[llvm_anyvector_ty],
-                    [LLVMMatchType<0>, LLVMVectorOfBitcastsToInt<0>, llvm_anyint_ty],
+                    [LLVMMatchType<0>, LLVMMatchType<0>,
+                     LLVMVectorOfBitcastsToInt<0>, llvm_anyint_ty],
                     [IntrNoMem]>, RISCVVIntrinsic {
-    let VLOperand = 2;
+    let VLOperand = 3;
   }
   // For destination vector type is the same as first and second source vector.
   // Input: (vector_in, vector_in, int_vector_in, vl, ta)
@@ -389,13 +390,14 @@
                     [ImmArg<ArgIndex<5>>, IntrNoMem]>, RISCVVIntrinsic {
     let VLOperand = 4;
   }
-  // Input: (vector_in, int16_vector_in, vl)
+  // Input: (passthru, vector_in, int16_vector_in, vl)
   class RISCVRGatherEI16VVNoMask
         : Intrinsic<[llvm_anyvector_ty],
-                    [LLVMMatchType<0>, LLVMScalarOrSameVectorWidth<0, llvm_i16_ty>,
+                    [LLVMMatchType<0>, LLVMMatchType<0>,
+                     LLVMScalarOrSameVectorWidth<0, llvm_i16_ty>,
                      llvm_anyint_ty],
                     [IntrNoMem]>, RISCVVIntrinsic {
-    let VLOperand = 2;
+    let VLOperand = 3;
   }
   // For destination vector type is the same as first and second source vector.
   // Input: (vector_in, vector_in, int16_vector_in, vl, ta)
@@ -410,12 +412,13 @@
   }
   // For destination vector type is the same as first source vector, and the
   // second operand is XLen.
-  // Input: (vector_in, xlen_in, vl)
+  // Input: (passthru, vector_in, xlen_in, vl)
   class RISCVGatherVXNoMask
         : Intrinsic<[llvm_anyvector_ty],
-                    [LLVMMatchType<0>, llvm_anyint_ty, LLVMMatchType<1>],
+                    [LLVMMatchType<0>, LLVMMatchType<0>, llvm_anyint_ty, 
+                     LLVMMatchType<1>],
                     [IntrNoMem]>, RISCVVIntrinsic {
-    let VLOperand = 2;
+    let VLOperand = 3;
   }
   // For destination vector type is the same as first source vector (with mask).
   // Second operand is XLen.
@@ -429,13 +432,14 @@
     let VLOperand = 4;
   }
   // For destination vector type is the same as first source vector.
-  // Input: (vector_in, vector_in/scalar_in, vl)
+  // Input: (passthru, vector_in, vector_in/scalar_in, vl)
   class RISCVBinaryAAXNoMask
         : Intrinsic<[llvm_anyvector_ty],
-                    [LLVMMatchType<0>, llvm_any_ty, llvm_anyint_ty],
+                    [LLVMMatchType<0>, LLVMMatchType<0>, llvm_any_ty,
+                     llvm_anyint_ty],
                     [IntrNoMem]>, RISCVVIntrinsic {
-    let SplatOperand = 1;
-    let VLOperand = 2;
+    let SplatOperand = 2;
+    let VLOperand = 3;
   }
   // For destination vector type is the same as first source vector (with mask).
   // Input: (maskedoff, vector_in, vector_in/scalar_in, mask, vl, ta)
@@ -450,12 +454,13 @@
   }
   // For destination vector type is the same as first source vector. The
   // second source operand must match the destination type or be an XLen scalar.
-  // Input: (vector_in, vector_in/scalar_in, vl)
+  // Input: (passthru, vector_in, vector_in/scalar_in, vl)
   class RISCVBinaryAAShiftNoMask
         : Intrinsic<[llvm_anyvector_ty],
-                    [LLVMMatchType<0>, llvm_any_ty, llvm_anyint_ty],
+                    [LLVMMatchType<0>, LLVMMatchType<0>, llvm_any_ty,
+                     llvm_anyint_ty],
                     [IntrNoMem]>, RISCVVIntrinsic {
-    let VLOperand = 2;
+    let VLOperand = 3;
   }
   // For destination vector type is the same as first source vector (with mask).
   // The second source operand must match the destination type or be an XLen scalar.
@@ -469,13 +474,14 @@
     let VLOperand = 4;
   }
   // For destination vector type is NOT the same as first source vector.
-  // Input: (vector_in, vector_in/scalar_in, vl)
+  // Input: (passthru, vector_in, vector_in/scalar_in, vl)
   class RISCVBinaryABXNoMask
         : Intrinsic<[llvm_anyvector_ty],
-                    [llvm_anyvector_ty, llvm_any_ty, llvm_anyint_ty],
+                    [LLVMMatchType<0>, llvm_anyvector_ty, llvm_any_ty,
+                     llvm_anyint_ty],
                     [IntrNoMem]>, RISCVVIntrinsic {
-    let SplatOperand = 1;
-    let VLOperand = 2;
+    let SplatOperand = 2;
+    let VLOperand = 3;
   }
   // For destination vector type is NOT the same as first source vector (with mask).
   // Input: (maskedoff, vector_in, vector_in/scalar_in, mask, vl, ta)
@@ -490,12 +496,13 @@
   }
   // For destination vector type is NOT the same as first source vector. The
   // second source operand must match the destination type or be an XLen scalar.
-  // Input: (vector_in, vector_in/scalar_in, vl)
+  // Input: (passthru, vector_in, vector_in/scalar_in, vl)
   class RISCVBinaryABShiftNoMask
         : Intrinsic<[llvm_anyvector_ty],
-                    [llvm_anyvector_ty, llvm_any_ty, llvm_anyint_ty],
+                    [LLVMMatchType<0>, llvm_anyvector_ty, llvm_any_ty,
+                     llvm_anyint_ty],
                     [IntrNoMem]>, RISCVVIntrinsic {
-    let VLOperand = 2;
+    let VLOperand = 3;
   }
   // For destination vector type is NOT the same as first source vector (with mask).
   // The second source operand must match the destination type or be an XLen scalar.
@@ -584,13 +591,14 @@
   }
   // For Saturating binary operations.
   // The destination vector type is the same as first source vector.
-  // Input: (vector_in, vector_in/scalar_in, vl)
+  // Input: (passthru, vector_in, vector_in/scalar_in, vl)
   class RISCVSaturatingBinaryAAXNoMask
         : Intrinsic<[llvm_anyvector_ty],
-                    [LLVMMatchType<0>, llvm_any_ty, llvm_anyint_ty],
+                    [LLVMMatchType<0>, LLVMMatchType<0>, llvm_any_ty,
+                     llvm_anyint_ty],
                     [IntrNoMem, IntrHasSideEffects]>, RISCVVIntrinsic {
-    let SplatOperand = 1;
-    let VLOperand = 2;
+    let SplatOperand = 2;
+    let VLOperand = 3;
   }
   // For Saturating binary operations with mask.
   // The destination vector type is the same as first source vector.
@@ -607,12 +615,13 @@
   // For Saturating binary operations.
   // The destination vector type is the same as first source vector.
   // The second source operand matches the destination type or is an XLen scalar.
-  // Input: (vector_in, vector_in/scalar_in, vl)
+  // Input: (passthru, vector_in, vector_in/scalar_in, vl)
   class RISCVSaturatingBinaryAAShiftNoMask
         : Intrinsic<[llvm_anyvector_ty],
-                    [LLVMMatchType<0>, llvm_any_ty, llvm_anyint_ty],
+                    [LLVMMatchType<0>, LLVMMatchType<0>, llvm_any_ty,
+                     llvm_anyint_ty],
                     [IntrNoMem, IntrHasSideEffects]>, RISCVVIntrinsic {
-    let VLOperand = 2;
+    let VLOperand = 3;
   }
   // For Saturating binary operations with mask.
   // The destination vector type is the same as first source vector.
@@ -629,12 +638,13 @@
   // For Saturating binary operations.
   // The destination vector type is NOT the same as first source vector.
   // The second source operand matches the destination type or is an XLen scalar.
-  // Input: (vector_in, vector_in/scalar_in, vl)
+  // Input: (passthru, vector_in, vector_in/scalar_in, vl)
   class RISCVSaturatingBinaryABShiftNoMask
         : Intrinsic<[llvm_anyvector_ty],
-                    [llvm_anyvector_ty, llvm_any_ty, llvm_anyint_ty],
+                    [LLVMMatchType<0>, llvm_anyvector_ty, llvm_any_ty,
+                     llvm_anyint_ty],
                     [IntrNoMem, IntrHasSideEffects]>, RISCVVIntrinsic {
-    let VLOperand = 2;
+    let VLOperand = 3;
   }
   // For Saturating binary operations with mask.
   // The destination vector type is NOT the same as first source vector (with mask).
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.h b/llvm/lib/Target/RISCV/RISCVISelLowering.h
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.h
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.h
@@ -158,9 +158,9 @@
   // and the fifth the VL.
   VSLIDEUP_VL,
   VSLIDEDOWN_VL,
-  // Matches the semantics of vslide1up/slide1down. The first operand is the
-  // source vector, the second is the XLenVT scalar value. The third and fourth
-  // operands are the mask and VL operands.
+  // Matches the semantics of vslide1up/slide1down. The first operand is
+  // passthru operand, the second is source vector, third is the XLenVT scalar
+  // value. The fourth and fifth operands are the mask and VL operands.
   VSLIDE1UP_VL,
   VSLIDE1DOWN_VL,
   // Matches the semantics of the vid.v instruction, with a mask and VL
diff --git a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
--- a/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelLowering.cpp
@@ -4250,10 +4250,12 @@
     ValInVec = DAG.getNode(RISCVISD::VMV_V_X_VL, DL, I32ContainerVT, Zero,
                            InsertI64VL);
     // First slide in the hi value, then the lo in underneath it.
-    ValInVec = DAG.getNode(RISCVISD::VSLIDE1UP_VL, DL, I32ContainerVT, ValInVec,
-                           ValHi, I32Mask, InsertI64VL);
-    ValInVec = DAG.getNode(RISCVISD::VSLIDE1UP_VL, DL, I32ContainerVT, ValInVec,
-                           ValLo, I32Mask, InsertI64VL);
+    ValInVec = DAG.getNode(RISCVISD::VSLIDE1UP_VL, DL, I32ContainerVT,
+                           DAG.getUNDEF(I32ContainerVT), ValInVec, ValHi,
+                           I32Mask, InsertI64VL);
+    ValInVec = DAG.getNode(RISCVISD::VSLIDE1UP_VL, DL, I32ContainerVT,
+                           DAG.getUNDEF(I32ContainerVT), ValInVec, ValLo,
+                           I32Mask, InsertI64VL);
     // Bitcast back to the right container type.
     ValInVec = DAG.getBitcast(ContainerVT, ValInVec);
   }
@@ -4495,8 +4497,7 @@
     // We need to special case these when the scalar is larger than XLen.
     unsigned NumOps = Op.getNumOperands();
     bool IsMasked = NumOps == 7;
-    unsigned OpOffset = IsMasked ? 1 : 0;
-    SDValue Scalar = Op.getOperand(2 + OpOffset);
+    SDValue Scalar = Op.getOperand(3);
     if (Scalar.getValueType().bitsLE(XLenVT))
       break;
 
@@ -4511,7 +4512,7 @@
 
     // Convert the vector source to the equivalent nxvXi32 vector.
     MVT I32VT = MVT::getVectorVT(MVT::i32, VT.getVectorElementCount() * 2);
-    SDValue Vec = DAG.getBitcast(I32VT, Op.getOperand(1 + OpOffset));
+    SDValue Vec = DAG.getBitcast(I32VT, Op.getOperand(2));
 
     SDValue ScalarLo = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, MVT::i32, Scalar,
                                    DAG.getConstant(0, DL, XLenVT));
@@ -4528,17 +4529,32 @@
 
     // Shift the two scalar parts in using SEW=32 slide1up/slide1down
     // instructions.
-    if (IntNo == Intrinsic::riscv_vslide1up ||
-        IntNo == Intrinsic::riscv_vslide1up_mask) {
-      Vec = DAG.getNode(RISCVISD::VSLIDE1UP_VL, DL, I32VT, Vec, ScalarHi,
-                        I32Mask, I32VL);
-      Vec = DAG.getNode(RISCVISD::VSLIDE1UP_VL, DL, I32VT, Vec, ScalarLo,
-                        I32Mask, I32VL);
+    if (!IsMasked) {
+      SDValue passthru = DAG.getBitcast(I32VT, Op.getOperand(1));
+      if (IntNo == Intrinsic::riscv_vslide1up) {
+        Vec = DAG.getNode(RISCVISD::VSLIDE1UP_VL, DL, I32VT, passthru, Vec,
+                          ScalarHi, I32Mask, I32VL);
+        Vec = DAG.getNode(RISCVISD::VSLIDE1UP_VL, DL, I32VT, passthru, Vec,
+                          ScalarLo, I32Mask, I32VL);
+      } else {
+        Vec = DAG.getNode(RISCVISD::VSLIDE1DOWN_VL, DL, I32VT, passthru, Vec,
+                          ScalarLo, I32Mask, I32VL);
+        Vec = DAG.getNode(RISCVISD::VSLIDE1DOWN_VL, DL, I32VT, passthru, Vec,
+                          ScalarHi, I32Mask, I32VL);
+      }
     } else {
-      Vec = DAG.getNode(RISCVISD::VSLIDE1DOWN_VL, DL, I32VT, Vec, ScalarLo,
-                        I32Mask, I32VL);
-      Vec = DAG.getNode(RISCVISD::VSLIDE1DOWN_VL, DL, I32VT, Vec, ScalarHi,
-                        I32Mask, I32VL);
+      SDValue Undef = DAG.getUNDEF(I32VT);
+      if (IntNo == Intrinsic::riscv_vslide1up_mask) {
+        Vec = DAG.getNode(RISCVISD::VSLIDE1UP_VL, DL, I32VT, Undef, Vec,
+                          ScalarHi, I32Mask, I32VL);
+        Vec = DAG.getNode(RISCVISD::VSLIDE1UP_VL, DL, I32VT, Undef, Vec,
+                          ScalarLo, I32Mask, I32VL);
+      } else {
+        Vec = DAG.getNode(RISCVISD::VSLIDE1DOWN_VL, DL, I32VT, Undef, Vec,
+                          ScalarLo, I32Mask, I32VL);
+        Vec = DAG.getNode(RISCVISD::VSLIDE1DOWN_VL, DL, I32VT, Undef, Vec,
+                          ScalarHi, I32Mask, I32VL);
+      }
     }
 
     // Convert back to nxvXi64.
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoVPseudos.td
@@ -982,6 +982,24 @@
   let BaseInstr = !cast<Instruction>(PseudoToVInst<NAME>.VInst);
 }
 
+class VPseudoBinaryNoMaskTU<VReg RetClass,
+                            VReg Op1Class,
+                            DAGOperand Op2Class,
+                            string Constraint> :
+        Pseudo<(outs RetClass:$rd),
+               (ins RetClass:$merge, Op1Class:$rs2, Op2Class:$rs1, AVL:$vl, ixlenimm:$sew), []>,
+        RISCVVPseudo {
+  let mayLoad = 0;
+  let mayStore = 0;
+  let hasSideEffects = 0;
+  let Constraints = Join<[Constraint, "$rd = $merge"], ",">.ret;
+  let HasVLOp = 1;
+  let HasSEWOp = 1;
+  let HasDummyMask = 1;
+  let HasMergeOp = 1;
+  let BaseInstr = !cast<Instruction>(PseudoToVInst<NAME>.VInst);
+}
+
 // Special version of VPseudoBinaryNoMask where we pretend the first source is
 // tied to the destination.
 // This allows maskedoff and rs2 to be the same register.
@@ -1003,6 +1021,25 @@
   let BaseInstr = !cast<Instruction>(PseudoToVInst<NAME>.VInst);
 }
 
+class VPseudoTiedBinaryNoMaskTU<VReg RetClass,
+                                DAGOperand Op2Class,
+                                string Constraint> :
+        Pseudo<(outs RetClass:$rd),
+               (ins RetClass:$merge, Op2Class:$rs1, AVL:$vl, ixlenimm:$sew), []>,
+        RISCVVPseudo {
+  let mayLoad = 0;
+  let mayStore = 0;
+  let hasSideEffects = 0;
+  let Constraints = Join<[Constraint, "$rd = $merge"], ",">.ret;
+  let HasVLOp = 1;
+  let HasSEWOp = 1;
+  let HasMergeOp = 0; // Merge is also rs2.
+  let HasDummyMask = 1;
+  let ForceTailAgnostic = 1;
+  let isConvertibleToThreeAddress = 1;
+  let BaseInstr = !cast<Instruction>(PseudoToVInst<NAME>.VInst);
+}
+
 class VPseudoIStoreNoMask<VReg StClass, VReg IdxClass, int EEW, bits<3> LMUL,
                           bit Ordered>:
       Pseudo<(outs),
@@ -1638,6 +1675,8 @@
   let VLMul = MInfo.value in {
     def "_" # MInfo.MX : VPseudoBinaryNoMask<RetClass, Op1Class, Op2Class,
                                              Constraint>;
+    def "_" # MInfo.MX # "_TU" : VPseudoBinaryNoMaskTU<RetClass, Op1Class, Op2Class,
+                                                       Constraint>;
     def "_" # MInfo.MX # "_MASK" : VPseudoBinaryMaskTA<RetClass, Op1Class, Op2Class,
                                                        Constraint>;
   }
@@ -1666,6 +1705,8 @@
   let VLMul = lmul.value in {
     def "_" # lmul.MX # "_" # emul.MX : VPseudoBinaryNoMask<RetClass, Op1Class, Op2Class,
                                                             Constraint>;
+    def "_" # lmul.MX # "_" # emul.MX # "_TU": VPseudoBinaryNoMaskTU<RetClass, Op1Class, Op2Class,
+                                                                     Constraint>;
     def "_" # lmul.MX # "_" # emul.MX # "_MASK" : VPseudoBinaryMaskTA<RetClass, Op1Class, Op2Class,
                                                                       Constraint>;
   }
@@ -1678,6 +1719,8 @@
   let VLMul = MInfo.value in {
     def "_" # MInfo.MX # "_TIED": VPseudoTiedBinaryNoMask<RetClass, Op2Class,
                                                           Constraint>;
+    def "_" # MInfo.MX # "_TIED_TU": VPseudoTiedBinaryNoMaskTU<RetClass, Op2Class,
+                                                               Constraint>;
     def "_" # MInfo.MX # "_MASK_TIED" : VPseudoTiedBinaryMask<RetClass, Op2Class,
                                                          Constraint>;
   }
@@ -2792,14 +2835,14 @@
                    (mask_type VR:$rs2),
                    GPR:$vl, sew)>;
 
-class VPatBinaryNoMask<string intrinsic_name,
-                       string inst,
-                       ValueType result_type,
-                       ValueType op1_type,
-                       ValueType op2_type,
-                       int sew,
-                       VReg op1_reg_class,
-                       DAGOperand op2_kind> :
+class VPatBinaryM<string intrinsic_name,
+                  string inst,
+                  ValueType result_type,
+                  ValueType op1_type,
+                  ValueType op2_type,
+                  int sew,
+                  VReg op1_reg_class,
+                  DAGOperand op2_kind> :
   Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
                    (op1_type op1_reg_class:$rs1),
                    (op2_type op2_kind:$rs2),
@@ -2809,6 +2852,44 @@
                    (op2_type op2_kind:$rs2),
                    GPR:$vl, sew)>;
 
+class VPatBinaryNoMaskTA<string intrinsic_name,
+                         string inst,
+                         ValueType result_type,
+                         ValueType op1_type,
+                         ValueType op2_type,
+                         int sew,
+                         VReg op1_reg_class,
+                         DAGOperand op2_kind> :
+  Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
+                   (result_type (undef)),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   VLOpFrag)),
+                   (!cast<Instruction>(inst)
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   GPR:$vl, sew)>;
+
+class VPatBinaryNoMaskTU<string intrinsic_name,
+                         string inst,
+                         ValueType result_type,
+                         ValueType op1_type,
+                         ValueType op2_type,
+                         int sew,
+                         VReg result_reg_class,
+                         VReg op1_reg_class,
+                         DAGOperand op2_kind> :
+  Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   VLOpFrag)),
+                   (!cast<Instruction>(inst#"_TU")
+                   (result_type result_reg_class:$merge),
+                   (op1_type op1_reg_class:$rs1),
+                   (op2_type op2_kind:$rs2),
+                   GPR:$vl, sew)>;
+
 // Same as above but source operands are swapped.
 class VPatBinaryNoMaskSwapped<string intrinsic_name,
                               string inst,
@@ -2902,6 +2983,7 @@
                            VReg result_reg_class,
                            DAGOperand op2_kind> :
   Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
+                   (result_type (undef)),
                    (result_type result_reg_class:$rs1),
                    (op2_type op2_kind:$rs2),
                    VLOpFrag)),
@@ -2910,6 +2992,23 @@
                    (op2_type op2_kind:$rs2),
                    GPR:$vl, sew)>;
 
+class VPatTiedBinaryNoMaskTU<string intrinsic_name,
+                             string inst,
+                             ValueType result_type,
+                             ValueType op2_type,
+                             int sew,
+                             VReg result_reg_class,
+                             DAGOperand op2_kind> :
+  Pat<(result_type (!cast<Intrinsic>(intrinsic_name)
+                   (result_type result_reg_class:$merge),
+                   (result_type result_reg_class:$merge),
+                   (op2_type op2_kind:$rs2),
+                   VLOpFrag)),
+                   (!cast<Instruction>(inst#"_TIED_TU")
+                   (result_type result_reg_class:$merge),
+                   (op2_type op2_kind:$rs2),
+                   GPR:$vl, sew)>;
+
 class VPatTiedBinaryMask<string intrinsic_name,
                          string inst,
                          ValueType result_type,
@@ -3094,7 +3193,7 @@
                         GPR:$vl, mti.Log2SEW)>;
 }
 
-multiclass VPatBinary<string intrinsic,
+multiclass VPatBinaryM<string intrinsic,
                       string inst,
                       ValueType result_type,
                       ValueType op1_type,
@@ -3105,8 +3204,8 @@
                       VReg op1_reg_class,
                       DAGOperand op2_kind>
 {
-  def : VPatBinaryNoMask<intrinsic, inst, result_type, op1_type, op2_type,
-                         sew, op1_reg_class, op2_kind>;
+  def : VPatBinaryM<intrinsic, inst, result_type, op1_type, op2_type,
+                    sew, op1_reg_class, op2_kind>;
   def : VPatBinaryMask<intrinsic, inst, result_type, op1_type, op2_type,
                        mask_type, sew, result_reg_class, op1_reg_class,
                        op2_kind>;
@@ -3123,8 +3222,10 @@
                         VReg op1_reg_class,
                         DAGOperand op2_kind>
 {
-  def : VPatBinaryNoMask<intrinsic, inst, result_type, op1_type, op2_type,
-                         sew, op1_reg_class, op2_kind>;
+  def : VPatBinaryNoMaskTA<intrinsic, inst, result_type, op1_type, op2_type,
+                           sew, op1_reg_class, op2_kind>;
+  def : VPatBinaryNoMaskTU<intrinsic, inst, result_type, op1_type, op2_type,
+                           sew, result_reg_class, op1_reg_class, op2_kind>;
   def : VPatBinaryMaskTA<intrinsic, inst, result_type, op1_type, op2_type,
                          mask_type, sew, result_reg_class, op1_reg_class,
                          op2_kind>;
@@ -3296,9 +3397,9 @@
 
 multiclass VPatBinaryM_MM<string intrinsic, string instruction> {
   foreach mti = AllMasks in
-    def : VPatBinaryNoMask<intrinsic, instruction # "_MM_" # mti.LMul.MX,
-                           mti.Mask, mti.Mask, mti.Mask,
-                           mti.Log2SEW, VR, VR>;
+    def : VPatBinaryM<intrinsic, instruction # "_MM_" # mti.LMul.MX,
+                      mti.Mask, mti.Mask, mti.Mask,
+                      mti.Log2SEW, VR, VR>;
 }
 
 multiclass VPatBinaryW_VV<string intrinsic, string instruction,
@@ -3334,6 +3435,9 @@
     def : VPatTiedBinaryNoMask<intrinsic, instruction # "_WV_" # Vti.LMul.MX,
                                Wti.Vector, Vti.Vector,
                                Vti.Log2SEW, Wti.RegClass, Vti.RegClass>;
+    def : VPatTiedBinaryNoMaskTU<intrinsic, instruction # "_WV_" # Vti.LMul.MX,
+                                 Wti.Vector, Vti.Vector,
+                                 Vti.Log2SEW, Wti.RegClass, Vti.RegClass>;
     let AddedComplexity = 1 in
     def : VPatTiedBinaryMask<intrinsic, instruction # "_WV_" # Vti.LMul.MX,
                              Wti.Vector, Vti.Vector, Vti.Mask,
@@ -3455,10 +3559,10 @@
 multiclass VPatBinaryM_VV<string intrinsic, string instruction,
                           list<VTypeInfo> vtilist> {
   foreach vti = vtilist in
-    defm : VPatBinary<intrinsic, instruction # "_VV_" # vti.LMul.MX,
-                      vti.Mask, vti.Vector, vti.Vector, vti.Mask,
-                      vti.Log2SEW, VR,
-                      vti.RegClass, vti.RegClass>;
+    defm : VPatBinaryM<intrinsic, instruction # "_VV_" # vti.LMul.MX,
+                       vti.Mask, vti.Vector, vti.Vector, vti.Mask,
+                       vti.Log2SEW, VR,
+                       vti.RegClass, vti.RegClass>;
 }
 
 multiclass VPatBinarySwappedM_VV<string intrinsic, string instruction,
@@ -3474,20 +3578,20 @@
                           list<VTypeInfo> vtilist> {
   foreach vti = vtilist in {
     defvar kind = "V"#vti.ScalarSuffix;
-    defm : VPatBinary<intrinsic, instruction#"_"#kind#"_"#vti.LMul.MX,
-                      vti.Mask, vti.Vector, vti.Scalar, vti.Mask,
-                      vti.Log2SEW, VR,
-                      vti.RegClass, vti.ScalarRegClass>;
+    defm : VPatBinaryM<intrinsic, instruction#"_"#kind#"_"#vti.LMul.MX,
+                       vti.Mask, vti.Vector, vti.Scalar, vti.Mask,
+                       vti.Log2SEW, VR,
+                       vti.RegClass, vti.ScalarRegClass>;
   }
 }
 
 multiclass VPatBinaryM_VI<string intrinsic, string instruction,
                           list<VTypeInfo> vtilist> {
   foreach vti = vtilist in
-    defm : VPatBinary<intrinsic, instruction # "_VI_" # vti.LMul.MX,
-                      vti.Mask, vti.Vector, XLenVT, vti.Mask,
-                      vti.Log2SEW, VR,
-                      vti.RegClass, simm5>;
+    defm : VPatBinaryM<intrinsic, instruction # "_VI_" # vti.LMul.MX,
+                       vti.Mask, vti.Vector, XLenVT, vti.Mask,
+                       vti.Log2SEW, VR,
+                       vti.RegClass, simm5>;
 }
 
 multiclass VPatBinaryV_VV_VX_VI<string intrinsic, string instruction,
@@ -4000,7 +4104,8 @@
   // Occurs when legalizing vrsub.vx intrinsics for i64 on RV32 since we need
   // to use a more complex splat sequence. Add the pattern for all VTs for
   // consistency.
-  def : Pat<(vti.Vector (int_riscv_vrsub (vti.Vector vti.RegClass:$rs2),
+  def : Pat<(vti.Vector (int_riscv_vrsub (vti.Vector (undef)),
+                                         (vti.Vector vti.RegClass:$rs2),
                                          (vti.Vector vti.RegClass:$rs1),
                                          VLOpFrag)),
             (!cast<Instruction>("PseudoVSUB_VV_"#vti.LMul.MX) vti.RegClass:$rs1,
@@ -4023,7 +4128,8 @@
                                                       (XLenVT timm:$policy))>;
 
   // Match VSUB with a small immediate to vadd.vi by negating the immediate.
-  def : Pat<(vti.Vector (int_riscv_vsub (vti.Vector vti.RegClass:$rs1),
+  def : Pat<(vti.Vector (int_riscv_vsub (vti.Vector (undef)),
+                                        (vti.Vector vti.RegClass:$rs1),
                                         (vti.Scalar simm5_plus1:$rs2),
                                         VLOpFrag)),
             (!cast<Instruction>("PseudoVADD_VI_"#vti.LMul.MX) vti.RegClass:$rs1,
@@ -4609,7 +4715,8 @@
 
 foreach vti = AllIntegerVectors in {
   // Emit shift by 1 as an add since it might be faster.
-  def : Pat<(vti.Vector (int_riscv_vsll (vti.Vector vti.RegClass:$rs1),
+  def : Pat<(vti.Vector (int_riscv_vsll (vti.Vector undef),
+                                        (vti.Vector vti.RegClass:$rs1),
                                         (XLenVT 1), VLOpFrag)),
             (!cast<Instruction>("PseudoVADD_VV_"#vti.LMul.MX) vti.RegClass:$rs1,
                                                               vti.RegClass:$rs1,
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoVVLPatterns.td b/llvm/lib/Target/RISCV/RISCVInstrInfoVVLPatterns.td
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoVVLPatterns.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoVVLPatterns.td
@@ -1581,9 +1581,10 @@
   SDTCisVec<0>, SDTCisSameAs<1, 0>, SDTCisSameAs<2, 0>, SDTCisVT<3, XLenVT>,
   SDTCVecEltisVT<4, i1>, SDTCisSameNumEltsAs<0, 4>, SDTCisVT<5, XLenVT>
 ]>;
-def SDTRVVSlide1 : SDTypeProfile<1, 4, [
-  SDTCisVec<0>, SDTCisSameAs<1, 0>, SDTCisInt<0>, SDTCisVT<2, XLenVT>,
-  SDTCVecEltisVT<3, i1>, SDTCisSameNumEltsAs<0, 3>, SDTCisVT<4, XLenVT>
+def SDTRVVSlide1 : SDTypeProfile<1, 5, [
+  SDTCisVec<0>, SDTCisSameAs<1, 0>, SDTCisSameAs<2, 0>, SDTCisInt<0>,
+  SDTCisVT<3, XLenVT>, SDTCVecEltisVT<4, i1>, SDTCisSameNumEltsAs<0, 4>,
+  SDTCisVT<5, XLenVT>
 ]>;
 
 def riscv_slideup_vl   : SDNode<"RISCVISD::VSLIDEUP_VL", SDTRVVSlide, []>;
@@ -1598,16 +1599,30 @@
                                       VLOpFrag)),
             (!cast<Instruction>("PseudoVID_V_"#vti.LMul.MX) GPR:$vl, vti.Log2SEW)>;
 
-  def : Pat<(vti.Vector (riscv_slide1up_vl (vti.Vector vti.RegClass:$rs1),
+  def : Pat<(vti.Vector (riscv_slide1up_vl (vti.Vector undef),
+                                           (vti.Vector vti.RegClass:$rs1),
                                            GPR:$rs2, (vti.Mask true_mask),
                                            VLOpFrag)),
             (!cast<Instruction>("PseudoVSLIDE1UP_VX_"#vti.LMul.MX)
                 vti.RegClass:$rs1, GPR:$rs2, GPR:$vl, vti.Log2SEW)>;
-  def : Pat<(vti.Vector (riscv_slide1down_vl (vti.Vector vti.RegClass:$rs1),
+  def : Pat<(vti.Vector (riscv_slide1up_vl (vti.Vector vti.RegClass:$rd),
+                                           (vti.Vector vti.RegClass:$rs1),
                                            GPR:$rs2, (vti.Mask true_mask),
                                            VLOpFrag)),
+            (!cast<Instruction>("PseudoVSLIDE1UP_VX_"#vti.LMul.MX#"_TU")
+                vti.RegClass:$rd, vti.RegClass:$rs1, GPR:$rs2, GPR:$vl, vti.Log2SEW)>;
+  def : Pat<(vti.Vector (riscv_slide1down_vl (vti.Vector undef),
+                                             (vti.Vector vti.RegClass:$rs1),
+                                             GPR:$rs2, (vti.Mask true_mask),
+                                             VLOpFrag)),
             (!cast<Instruction>("PseudoVSLIDE1DOWN_VX_"#vti.LMul.MX)
                 vti.RegClass:$rs1, GPR:$rs2, GPR:$vl, vti.Log2SEW)>;
+  def : Pat<(vti.Vector (riscv_slide1down_vl (vti.Vector vti.RegClass:$rd),
+                                             (vti.Vector vti.RegClass:$rs1),
+                                             GPR:$rs2, (vti.Mask true_mask),
+                                             VLOpFrag)),
+            (!cast<Instruction>("PseudoVSLIDE1DOWN_VX_"#vti.LMul.MX#"_TU")
+                vti.RegClass:$rd, vti.RegClass:$rs1, GPR:$rs2, GPR:$vl, vti.Log2SEW)>;
 }
 
 foreach vti = !listconcat(AllIntegerVectors, AllFloatVectors) in {
diff --git a/llvm/test/CodeGen/RISCV/rvv/unmasked-tu.ll b/llvm/test/CodeGen/RISCV/rvv/unmasked-tu.ll
--- a/llvm/test/CodeGen/RISCV/rvv/unmasked-tu.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/unmasked-tu.ll
@@ -118,3 +118,90 @@
 
   ret <vscale x 1 x i8> %a
 }
+
+declare <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.nxv1i8(
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen);
+
+define <vscale x 1 x i8> @intrinsic_vadd_vv_nxv1i8_nxv1i8_nxv1i8(<vscale x 1 x i8> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, iXLen %3) nounwind {
+; RV32-LABEL: intrinsic_vadd_vv_nxv1i8_nxv1i8_nxv1i8:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    vsetvli zero, a0, e8, mf8, tu, mu
+; RV32-NEXT:    vadd.vv v8, v9, v10
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vadd_vv_nxv1i8_nxv1i8_nxv1i8:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a0, e8, mf8, tu, mu
+; RV64-NEXT:    vadd.vv v8, v9, v10
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i8> @llvm.riscv.vadd.nxv1i8.nxv1i8(
+    <vscale x 1 x i8> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    iXLen %3)
+
+  ret <vscale x 1 x i8> %a
+}
+
+declare <vscale x 1 x i16> @llvm.riscv.vwadd.nxv1i16.nxv1i8.nxv1i8(
+  <vscale x 1 x i16>,
+  <vscale x 1 x i8>,
+  <vscale x 1 x i8>,
+  iXLen);
+
+define <vscale x 1 x i16> @intrinsic_vwadd_vv_nxv1i16_nxv1i8_nxv1i8(<vscale x 1 x i16> %0, <vscale x 1 x i8> %1, <vscale x 1 x i8> %2, iXLen %3) nounwind {
+; RV32-LABEL: intrinsic_vwadd_vv_nxv1i16_nxv1i8_nxv1i8:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    vsetvli zero, a0, e8, mf8, tu, mu
+; RV32-NEXT:    vwadd.vv v8, v9, v10
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vwadd_vv_nxv1i16_nxv1i8_nxv1i8:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a0, e8, mf8, tu, mu
+; RV64-NEXT:    vwadd.vv v8, v9, v10
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i16> @llvm.riscv.vwadd.nxv1i16.nxv1i8.nxv1i8(
+    <vscale x 1 x i16> %0,
+    <vscale x 1 x i8> %1,
+    <vscale x 1 x i8> %2,
+    iXLen %3)
+
+  ret <vscale x 1 x i16> %a
+}
+
+declare <vscale x 1 x i64> @llvm.riscv.vslide1down.nxv1i64(
+  <vscale x 1 x i64>,
+  <vscale x 1 x i64>,
+  i64,
+  iXLen);
+
+define <vscale x 1 x i64> @intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64(<vscale x 1 x i64> %0, <vscale x 1 x i64> %1, i64 %2, iXLen %3) nounwind {
+; RV32-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    slli a2, a2, 1
+; RV32-NEXT:    vsetvli zero, a2, e32, m1, tu, mu
+; RV32-NEXT:    vmv1r.v v10, v8
+; RV32-NEXT:    vslide1down.vx v10, v9, a0
+; RV32-NEXT:    vslide1down.vx v8, v10, a1
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: intrinsic_vslide1down_vx_nxv1i64_nxv1i64_i64:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    vsetvli zero, a1, e64, m1, tu, mu
+; RV64-NEXT:    vslide1down.vx v8, v9, a0
+; RV64-NEXT:    ret
+entry:
+  %a = call <vscale x 1 x i64> @llvm.riscv.vslide1down.nxv1i64(
+    <vscale x 1 x i64> %0,
+    <vscale x 1 x i64> %1,
+    i64 %2,
+    iXLen %3)
+
+  ret <vscale x 1 x i64> %a
+}
diff --git a/llvm/test/CodeGen/RISCV/rvv/vslide1up-rv32.ll b/llvm/test/CodeGen/RISCV/rvv/vslide1up-rv32.ll
--- a/llvm/test/CodeGen/RISCV/rvv/vslide1up-rv32.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/vslide1up-rv32.ll
@@ -2,6 +2,7 @@
 ; RUN: llc -mtriple=riscv32 -mattr=+v,+f -verify-machineinstrs \
 ; RUN:   < %s | FileCheck %s
 declare <vscale x 1 x i8> @llvm.riscv.vslide1up.nxv1i8.i8(
+  <vscale x 1 x i8>,
   <vscale x 1 x i8>,
   i8,
   i32);
@@ -15,6 +16,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 1 x i8> @llvm.riscv.vslide1up.nxv1i8.i8(
+    <vscale x 1 x i8> undef,
     <vscale x 1 x i8> %0,
     i8 %1,
     i32 %2)
@@ -48,6 +50,7 @@
 }
 
 declare <vscale x 2 x i8> @llvm.riscv.vslide1up.nxv2i8.i8(
+  <vscale x 2 x i8>,
   <vscale x 2 x i8>,
   i8,
   i32);
@@ -61,6 +64,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 2 x i8> @llvm.riscv.vslide1up.nxv2i8.i8(
+    <vscale x 2 x i8> undef,
     <vscale x 2 x i8> %0,
     i8 %1,
     i32 %2)
@@ -94,6 +98,7 @@
 }
 
 declare <vscale x 4 x i8> @llvm.riscv.vslide1up.nxv4i8.i8(
+  <vscale x 4 x i8>,
   <vscale x 4 x i8>,
   i8,
   i32);
@@ -107,6 +112,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 4 x i8> @llvm.riscv.vslide1up.nxv4i8.i8(
+    <vscale x 4 x i8> undef,
     <vscale x 4 x i8> %0,
     i8 %1,
     i32 %2)
@@ -140,6 +146,7 @@
 }
 
 declare <vscale x 8 x i8> @llvm.riscv.vslide1up.nxv8i8.i8(
+  <vscale x 8 x i8>,
   <vscale x 8 x i8>,
   i8,
   i32);
@@ -153,6 +160,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 8 x i8> @llvm.riscv.vslide1up.nxv8i8.i8(
+    <vscale x 8 x i8> undef,
     <vscale x 8 x i8> %0,
     i8 %1,
     i32 %2)
@@ -186,6 +194,7 @@
 }
 
 declare <vscale x 16 x i8> @llvm.riscv.vslide1up.nxv16i8.i8(
+  <vscale x 16 x i8>,
   <vscale x 16 x i8>,
   i8,
   i32);
@@ -199,6 +208,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 16 x i8> @llvm.riscv.vslide1up.nxv16i8.i8(
+    <vscale x 16 x i8> undef,
     <vscale x 16 x i8> %0,
     i8 %1,
     i32 %2)
@@ -232,6 +242,7 @@
 }
 
 declare <vscale x 32 x i8> @llvm.riscv.vslide1up.nxv32i8.i8(
+  <vscale x 32 x i8>,
   <vscale x 32 x i8>,
   i8,
   i32);
@@ -245,6 +256,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 32 x i8> @llvm.riscv.vslide1up.nxv32i8.i8(
+    <vscale x 32 x i8> undef,
     <vscale x 32 x i8> %0,
     i8 %1,
     i32 %2)
@@ -278,6 +290,7 @@
 }
 
 declare <vscale x 64 x i8> @llvm.riscv.vslide1up.nxv64i8.i8(
+  <vscale x 64 x i8>,
   <vscale x 64 x i8>,
   i8,
   i32);
@@ -291,6 +304,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 64 x i8> @llvm.riscv.vslide1up.nxv64i8.i8(
+    <vscale x 64 x i8> undef,
     <vscale x 64 x i8> %0,
     i8 %1,
     i32 %2)
@@ -324,6 +338,7 @@
 }
 
 declare <vscale x 1 x i16> @llvm.riscv.vslide1up.nxv1i16.i16(
+  <vscale x 1 x i16>,
   <vscale x 1 x i16>,
   i16,
   i32);
@@ -337,6 +352,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 1 x i16> @llvm.riscv.vslide1up.nxv1i16.i16(
+    <vscale x 1 x i16> undef,
     <vscale x 1 x i16> %0,
     i16 %1,
     i32 %2)
@@ -370,6 +386,7 @@
 }
 
 declare <vscale x 2 x i16> @llvm.riscv.vslide1up.nxv2i16.i16(
+  <vscale x 2 x i16>,
   <vscale x 2 x i16>,
   i16,
   i32);
@@ -383,6 +400,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 2 x i16> @llvm.riscv.vslide1up.nxv2i16.i16(
+    <vscale x 2 x i16> undef,
     <vscale x 2 x i16> %0,
     i16 %1,
     i32 %2)
@@ -416,6 +434,7 @@
 }
 
 declare <vscale x 4 x i16> @llvm.riscv.vslide1up.nxv4i16.i16(
+  <vscale x 4 x i16>,
   <vscale x 4 x i16>,
   i16,
   i32);
@@ -429,6 +448,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 4 x i16> @llvm.riscv.vslide1up.nxv4i16.i16(
+    <vscale x 4 x i16> undef,
     <vscale x 4 x i16> %0,
     i16 %1,
     i32 %2)
@@ -462,6 +482,7 @@
 }
 
 declare <vscale x 8 x i16> @llvm.riscv.vslide1up.nxv8i16.i16(
+  <vscale x 8 x i16>,
   <vscale x 8 x i16>,
   i16,
   i32);
@@ -475,6 +496,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 8 x i16> @llvm.riscv.vslide1up.nxv8i16.i16(
+    <vscale x 8 x i16> undef,
     <vscale x 8 x i16> %0,
     i16 %1,
     i32 %2)
@@ -508,6 +530,7 @@
 }
 
 declare <vscale x 16 x i16> @llvm.riscv.vslide1up.nxv16i16.i16(
+  <vscale x 16 x i16>,
   <vscale x 16 x i16>,
   i16,
   i32);
@@ -521,6 +544,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 16 x i16> @llvm.riscv.vslide1up.nxv16i16.i16(
+    <vscale x 16 x i16> undef,
     <vscale x 16 x i16> %0,
     i16 %1,
     i32 %2)
@@ -554,6 +578,7 @@
 }
 
 declare <vscale x 32 x i16> @llvm.riscv.vslide1up.nxv32i16.i16(
+  <vscale x 32 x i16>,
   <vscale x 32 x i16>,
   i16,
   i32);
@@ -567,6 +592,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 32 x i16> @llvm.riscv.vslide1up.nxv32i16.i16(
+    <vscale x 32 x i16> undef,
     <vscale x 32 x i16> %0,
     i16 %1,
     i32 %2)
@@ -600,6 +626,7 @@
 }
 
 declare <vscale x 1 x i32> @llvm.riscv.vslide1up.nxv1i32.i32(
+  <vscale x 1 x i32>,
   <vscale x 1 x i32>,
   i32,
   i32);
@@ -613,6 +640,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 1 x i32> @llvm.riscv.vslide1up.nxv1i32.i32(
+    <vscale x 1 x i32> undef,
     <vscale x 1 x i32> %0,
     i32 %1,
     i32 %2)
@@ -646,6 +674,7 @@
 }
 
 declare <vscale x 2 x i32> @llvm.riscv.vslide1up.nxv2i32.i32(
+  <vscale x 2 x i32>,
   <vscale x 2 x i32>,
   i32,
   i32);
@@ -659,6 +688,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 2 x i32> @llvm.riscv.vslide1up.nxv2i32.i32(
+    <vscale x 2 x i32> undef,
     <vscale x 2 x i32> %0,
     i32 %1,
     i32 %2)
@@ -692,6 +722,7 @@
 }
 
 declare <vscale x 4 x i32> @llvm.riscv.vslide1up.nxv4i32.i32(
+  <vscale x 4 x i32>,
   <vscale x 4 x i32>,
   i32,
   i32);
@@ -705,6 +736,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 4 x i32> @llvm.riscv.vslide1up.nxv4i32.i32(
+    <vscale x 4 x i32> undef,
     <vscale x 4 x i32> %0,
     i32 %1,
     i32 %2)
@@ -738,6 +770,7 @@
 }
 
 declare <vscale x 8 x i32> @llvm.riscv.vslide1up.nxv8i32.i32(
+  <vscale x 8 x i32>,
   <vscale x 8 x i32>,
   i32,
   i32);
@@ -751,6 +784,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 8 x i32> @llvm.riscv.vslide1up.nxv8i32.i32(
+    <vscale x 8 x i32> undef,
     <vscale x 8 x i32> %0,
     i32 %1,
     i32 %2)
@@ -784,6 +818,7 @@
 }
 
 declare <vscale x 16 x i32> @llvm.riscv.vslide1up.nxv16i32.i32(
+  <vscale x 16 x i32>,
   <vscale x 16 x i32>,
   i32,
   i32);
@@ -797,6 +832,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 16 x i32> @llvm.riscv.vslide1up.nxv16i32.i32(
+    <vscale x 16 x i32> undef,
     <vscale x 16 x i32> %0,
     i32 %1,
     i32 %2)
@@ -830,6 +866,7 @@
 }
 
 declare <vscale x 1 x i64> @llvm.riscv.vslide1up.nxv1i64.i64(
+  <vscale x 1 x i64>,
   <vscale x 1 x i64>,
   i64,
   i32);
@@ -844,6 +881,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 1 x i64> @llvm.riscv.vslide1up.nxv1i64.i64(
+    <vscale x 1 x i64> undef,
     <vscale x 1 x i64> %0,
     i64 %1,
     i32 %2)
@@ -881,6 +919,7 @@
 }
 
 declare <vscale x 2 x i64> @llvm.riscv.vslide1up.nxv2i64.i64(
+  <vscale x 2 x i64>,
   <vscale x 2 x i64>,
   i64,
   i32);
@@ -895,6 +934,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 2 x i64> @llvm.riscv.vslide1up.nxv2i64.i64(
+    <vscale x 2 x i64> undef,
     <vscale x 2 x i64> %0,
     i64 %1,
     i32 %2)
@@ -932,6 +972,7 @@
 }
 
 declare <vscale x 4 x i64> @llvm.riscv.vslide1up.nxv4i64.i64(
+  <vscale x 4 x i64>,
   <vscale x 4 x i64>,
   i64,
   i32);
@@ -946,6 +987,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 4 x i64> @llvm.riscv.vslide1up.nxv4i64.i64(
+    <vscale x 4 x i64> undef,
     <vscale x 4 x i64> %0,
     i64 %1,
     i32 %2)
@@ -983,6 +1025,7 @@
 }
 
 declare <vscale x 8 x i64> @llvm.riscv.vslide1up.nxv8i64.i64(
+  <vscale x 8 x i64>,
   <vscale x 8 x i64>,
   i64,
   i32);
@@ -997,6 +1040,7 @@
 ; CHECK-NEXT:    ret
 entry:
   %a = call <vscale x 8 x i64> @llvm.riscv.vslide1up.nxv8i64.i64(
+    <vscale x 8 x i64> undef,
     <vscale x 8 x i64> %0,
     i64 %1,
     i32 %2)