diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst
--- a/llvm/docs/LangRef.rst
+++ b/llvm/docs/LangRef.rst
@@ -4822,7 +4822,7 @@
 - ``r``: A 32- or 64-bit general-purpose register (depending on the platform
   ``XLEN``).
 - ``vr``: A vector register. (requires V extension).
-- ``vm``: A vector mask register. (requires V extension).
+- ``vm``: A vector register for masking operand. (requires V extension).
 
 Sparc:
 
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
@@ -9310,8 +9310,8 @@
           return std::make_pair(0U, RC);
       }
     } else if (Constraint == "vm") {
-      if (TRI->isTypeLegalForClass(RISCV::VMRegClass, VT.SimpleTy))
-        return std::make_pair(0U, &RISCV::VMRegClass);
+      if (TRI->isTypeLegalForClass(RISCV::VMV0RegClass, VT.SimpleTy))
+        return std::make_pair(0U, &RISCV::VMV0RegClass);
     }
   }
 
@@ -9833,17 +9833,29 @@
     unsigned ValueVTBitSize = ValueVT.getSizeInBits().getKnownMinSize();
     unsigned PartVTBitSize = PartVT.getSizeInBits().getKnownMinSize();
     if (PartVTBitSize % ValueVTBitSize == 0) {
+      assert(PartVTBitSize >= ValueVTBitSize);
       // If the element types are different, bitcast to the same element type of
       // PartVT first.
+      // Give an example here, we want copy a <vscale x 1 x i8> value to
+      // <vscale x 4 x i16>.
+      // We need to convert <vscale x 1 x i8> to <vscale x 8 x i8> by insert
+      // subvector, then we can bitcast to <vscale x 4 x i16>.
       if (ValueEltVT != PartEltVT) {
-        unsigned Count = ValueVTBitSize / PartEltVT.getSizeInBits();
-        assert(Count != 0 && "The number of element should not be zero.");
-        EVT SameEltTypeVT =
-            EVT::getVectorVT(Context, PartEltVT, Count, /*IsScalable=*/true);
-        Val = DAG.getNode(ISD::BITCAST, DL, SameEltTypeVT, Val);
+        if (PartVTBitSize > ValueVTBitSize) {
+          unsigned Count = PartVTBitSize / ValueEltVT.getFixedSizeInBits();
+          assert(Count != 0 && "The number of element should not be zero.");
+          EVT SameEltTypeVT =
+              EVT::getVectorVT(Context, ValueEltVT, Count, /*IsScalable=*/true);
+          Val = DAG.getNode(ISD::INSERT_SUBVECTOR, DL, SameEltTypeVT,
+                            DAG.getUNDEF(SameEltTypeVT), Val,
+                            DAG.getVectorIdxConstant(0, DL));
+        }
+        Val = DAG.getNode(ISD::BITCAST, DL, PartVT, Val);
+      } else {
+        Val =
+            DAG.getNode(ISD::INSERT_SUBVECTOR, DL, PartVT, DAG.getUNDEF(PartVT),
+                        Val, DAG.getVectorIdxConstant(0, DL));
       }
-      Val = DAG.getNode(ISD::INSERT_SUBVECTOR, DL, PartVT, DAG.getUNDEF(PartVT),
-                        Val, DAG.getConstant(0, DL, Subtarget.getXLenVT()));
       Parts[0] = Val;
       return true;
     }
@@ -9873,19 +9885,23 @@
     unsigned ValueVTBitSize = ValueVT.getSizeInBits().getKnownMinSize();
     unsigned PartVTBitSize = PartVT.getSizeInBits().getKnownMinSize();
     if (PartVTBitSize % ValueVTBitSize == 0) {
+      assert(PartVTBitSize >= ValueVTBitSize);
       EVT SameEltTypeVT = ValueVT;
       // If the element types are different, convert it to the same element type
       // of PartVT.
+      // Give an example here, we want copy a <vscale x 1 x i8> value from
+      // <vscale x 4 x i16>.
+      // We need to convert <vscale x 4 x i16> to <vscale x 8 x i8> first,
+      // then we can extract <vscale x 1 x i8>.
       if (ValueEltVT != PartEltVT) {
-        unsigned Count = ValueVTBitSize / PartEltVT.getSizeInBits();
+        unsigned Count = PartVTBitSize / ValueEltVT.getFixedSizeInBits();
         assert(Count != 0 && "The number of element should not be zero.");
         SameEltTypeVT =
-            EVT::getVectorVT(Context, PartEltVT, Count, /*IsScalable=*/true);
+            EVT::getVectorVT(Context, ValueEltVT, Count, /*IsScalable=*/true);
+        Val = DAG.getNode(ISD::BITCAST, DL, SameEltTypeVT, Val);
       }
-      Val = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, SameEltTypeVT, Val,
-                        DAG.getConstant(0, DL, Subtarget.getXLenVT()));
-      if (ValueEltVT != PartEltVT)
-        Val = DAG.getNode(ISD::BITCAST, DL, ValueVT, Val);
+      Val = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, ValueVT, Val,
+                        DAG.getVectorIdxConstant(0, DL));
       return Val;
     }
   }
diff --git a/llvm/lib/Target/RISCV/RISCVRegisterInfo.td b/llvm/lib/Target/RISCV/RISCVRegisterInfo.td
--- a/llvm/lib/Target/RISCV/RISCVRegisterInfo.td
+++ b/llvm/lib/Target/RISCV/RISCVRegisterInfo.td
@@ -526,16 +526,15 @@
                      vfloat16m8_t, vfloat32m8_t, vfloat64m8_t],
              (add V8M8, V16M8, V24M8), 8>;
 
-defvar VMaskVTs = [vbool64_t, vbool32_t, vbool16_t, vbool8_t,
-                   vbool4_t, vbool2_t, vbool1_t];
+defvar VMaskVTs = [vbool1_t, vbool2_t, vbool4_t, vbool8_t, vbool16_t,
+                   vbool32_t, vbool64_t];
 
 def VMV0 : RegisterClass<"RISCV", VMaskVTs, 64, (add V0)> {
   let Size = 64;
 }
 
 // The register class is added for inline assembly for vector mask types.
-def VM : VReg<[vbool1_t, vbool2_t, vbool4_t, vbool8_t, vbool16_t,
-               vbool32_t, vbool64_t],
+def VM : VReg<VMaskVTs,
            (add (sequence "V%u", 8, 31),
                 (sequence "V%u", 0, 7)), 1>;
 
diff --git a/llvm/test/CodeGen/RISCV/rvv/inline-asm.ll b/llvm/test/CodeGen/RISCV/rvv/inline-asm.ll
--- a/llvm/test/CodeGen/RISCV/rvv/inline-asm.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/inline-asm.ll
@@ -10,7 +10,7 @@
 ; CHECK-NEXT:    #NO_APP
 ; CHECK-NEXT:    ret
 entry:
-  %0 = tail call <vscale x 1 x i1> asm "vmand.mm $0, $1, $2", "=^vm,^vm,^vm"(<vscale x 1 x i1> %in, <vscale x 1 x i1> %in2)
+  %0 = tail call <vscale x 1 x i1> asm "vmand.mm $0, $1, $2", "=^vr,^vr,^vr"(<vscale x 1 x i1> %in, <vscale x 1 x i1> %in2)
   ret <vscale x 1 x i1> %0
 }
 
@@ -22,7 +22,7 @@
 ; CHECK-NEXT:    #NO_APP
 ; CHECK-NEXT:    ret
 entry:
-  %0 = tail call <vscale x 2 x i1> asm "vmand.mm $0, $1, $2", "=^vm,^vm,^vm"(<vscale x 2 x i1> %in, <vscale x 2 x i1> %in2)
+  %0 = tail call <vscale x 2 x i1> asm "vmand.mm $0, $1, $2", "=^vr,^vr,^vr"(<vscale x 2 x i1> %in, <vscale x 2 x i1> %in2)
   ret <vscale x 2 x i1> %0
 }
 
@@ -34,7 +34,7 @@
 ; CHECK-NEXT:    #NO_APP
 ; CHECK-NEXT:    ret
 entry:
-  %0 = tail call <vscale x 4 x i1> asm "vmand.mm $0, $1, $2", "=^vm,^vm,^vm"(<vscale x 4 x i1> %in, <vscale x 4 x i1> %in2)
+  %0 = tail call <vscale x 4 x i1> asm "vmand.mm $0, $1, $2", "=^vr,^vr,^vr"(<vscale x 4 x i1> %in, <vscale x 4 x i1> %in2)
   ret <vscale x 4 x i1> %0
 }
 
@@ -46,7 +46,7 @@
 ; CHECK-NEXT:    #NO_APP
 ; CHECK-NEXT:    ret
 entry:
-  %0 = tail call <vscale x 8 x i1> asm "vmand.mm $0, $1, $2", "=^vm,^vm,^vm"(<vscale x 8 x i1> %in, <vscale x 8 x i1> %in2)
+  %0 = tail call <vscale x 8 x i1> asm "vmand.mm $0, $1, $2", "=^vr,^vr,^vr"(<vscale x 8 x i1> %in, <vscale x 8 x i1> %in2)
   ret <vscale x 8 x i1> %0
 }
 
@@ -58,7 +58,7 @@
 ; CHECK-NEXT:    #NO_APP
 ; CHECK-NEXT:    ret
 entry:
-  %0 = tail call <vscale x 16 x i1> asm "vmand.mm $0, $1, $2", "=^vm,^vm,^vm"(<vscale x 16 x i1> %in, <vscale x 16 x i1> %in2)
+  %0 = tail call <vscale x 16 x i1> asm "vmand.mm $0, $1, $2", "=^vr,^vr,^vr"(<vscale x 16 x i1> %in, <vscale x 16 x i1> %in2)
   ret <vscale x 16 x i1> %0
 }
 
@@ -70,7 +70,7 @@
 ; CHECK-NEXT:    #NO_APP
 ; CHECK-NEXT:    ret
 entry:
-  %0 = tail call <vscale x 32 x i1> asm "vmand.mm $0, $1, $2", "=^vm,^vm,^vm"(<vscale x 32 x i1> %in, <vscale x 32 x i1> %in2)
+  %0 = tail call <vscale x 32 x i1> asm "vmand.mm $0, $1, $2", "=^vr,^vr,^vr"(<vscale x 32 x i1> %in, <vscale x 32 x i1> %in2)
   ret <vscale x 32 x i1> %0
 }
 
@@ -82,7 +82,7 @@
 ; CHECK-NEXT:    #NO_APP
 ; CHECK-NEXT:    ret
 entry:
-  %0 = tail call <vscale x 64 x i1> asm "vmand.mm $0, $1, $2", "=^vm,^vm,^vm"(<vscale x 64 x i1> %in, <vscale x 64 x i1> %in2)
+  %0 = tail call <vscale x 64 x i1> asm "vmand.mm $0, $1, $2", "=^vr,^vr,^vr"(<vscale x 64 x i1> %in, <vscale x 64 x i1> %in2)
   ret <vscale x 64 x i1> %0
 }
 
@@ -350,6 +350,18 @@
   ret <vscale x 64 x i8> %0
 }
 
+define <vscale x 64 x i8> @test_64xi8_with_mask(<vscale x 64 x i8> %in, <vscale x 64 x i8> %in2, <vscale x 64 x i1> %mask) nounwind {
+; CHECK-LABEL: test_64xi8_with_mask:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    #APP
+; CHECK-NEXT:    vadd.vv v8, v8, v16, v0.t
+; CHECK-NEXT:    #NO_APP
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call <vscale x 64 x i8> asm "vadd.vv $0, $1, $2, $3.t", "=^vr,^vr,^vr,^vm"(<vscale x 64 x i8> %in, <vscale x 64 x i8> %in2, <vscale x 64 x i1> %mask)
+  ret <vscale x 64 x i8> %0
+}
+
 define <vscale x 4 x i8> @test_specify_reg_mf2(<vscale x 4 x i8> %in, <vscale x 4 x i8> %in2) nounwind {
 ; CHECK-LABEL: test_specify_reg_mf2:
 ; CHECK:       # %bb.0: # %entry