diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
--- a/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
@@ -983,6 +983,7 @@
     SplitVecRes_Gather(cast<MemSDNode>(N), Lo, Hi, /*SplitSETCC*/ true);
     break;
   case ISD::SETCC:
+  case ISD::VP_SETCC:
     SplitVecRes_SETCC(N, Lo, Hi);
     break;
   case ISD::VECTOR_REVERSE:
@@ -2108,8 +2109,24 @@
   else
     std::tie(RL, RH) = DAG.SplitVectorOperand(N, 1);
 
-  Lo = DAG.getNode(N->getOpcode(), DL, LoVT, LL, RL, N->getOperand(2));
-  Hi = DAG.getNode(N->getOpcode(), DL, HiVT, LH, RH, N->getOperand(2));
+  if (N->getOpcode() != ISD::VP_SETCC) {
+    Lo = DAG.getNode(N->getOpcode(), DL, LoVT, LL, RL, N->getOperand(2));
+    Hi = DAG.getNode(N->getOpcode(), DL, HiVT, LH, RH, N->getOperand(2));
+    return;
+  }
+
+  assert(N->getNumOperands() == 5 && "Unexpected number of operands!");
+  assert(N->getOpcode() == ISD::VP_SETCC && "Expected VP_SETCC opcode");
+
+  SDValue MaskLo, MaskHi, EVLLo, EVLHi;
+  std::tie(MaskLo, MaskHi) = SplitMask(N->getOperand(3));
+  std::tie(EVLLo, EVLHi) =
+      DAG.SplitEVL(N->getOperand(4), N->getValueType(0), DL);
+
+  Lo = DAG.getNode(N->getOpcode(), DL, LoVT, LL, RL, N->getOperand(2), MaskLo,
+                   EVLLo);
+  Hi = DAG.getNode(N->getOpcode(), DL, HiVT, LH, RH, N->getOperand(2), MaskHi,
+                   EVLHi);
 }
 
 void DAGTypeLegalizer::SplitVecRes_UnaryOp(SDNode *N, SDValue &Lo,
@@ -2644,6 +2661,7 @@
     report_fatal_error("Do not know how to split this operator's "
                        "operand!\n");
 
+  case ISD::VP_SETCC:
   case ISD::SETCC:             Res = SplitVecOp_VSETCC(N); break;
   case ISD::BITCAST:           Res = SplitVecOp_BITCAST(N); break;
   case ISD::EXTRACT_SUBVECTOR: Res = SplitVecOp_EXTRACT_SUBVECTOR(N); break;
@@ -3478,8 +3496,21 @@
   EVT PartResVT = EVT::getVectorVT(Context, MVT::i1, PartEltCnt);
   EVT WideResVT = EVT::getVectorVT(Context, MVT::i1, PartEltCnt*2);
 
-  LoRes = DAG.getNode(ISD::SETCC, DL, PartResVT, Lo0, Lo1, N->getOperand(2));
-  HiRes = DAG.getNode(ISD::SETCC, DL, PartResVT, Hi0, Hi1, N->getOperand(2));
+  if (N->getOpcode() == ISD::SETCC) {
+    LoRes = DAG.getNode(ISD::SETCC, DL, PartResVT, Lo0, Lo1, N->getOperand(2));
+    HiRes = DAG.getNode(ISD::SETCC, DL, PartResVT, Hi0, Hi1, N->getOperand(2));
+  }
+
+  if (N->getOpcode() == ISD::VP_SETCC) {
+    SDValue MaskLo, MaskHi, EVLLo, EVLHi;
+    std::tie(MaskLo, MaskHi) = SplitMask(N->getOperand(3));
+    std::tie(EVLLo, EVLHi) =
+        DAG.SplitEVL(N->getOperand(4), N->getValueType(0), DL);
+    LoRes = DAG.getNode(ISD::VP_SETCC, DL, PartResVT, Lo0, Lo1,
+                        N->getOperand(2), MaskLo, EVLLo);
+    HiRes = DAG.getNode(ISD::VP_SETCC, DL, PartResVT, Hi0, Hi1,
+                        N->getOperand(2), MaskHi, EVLHi);
+  }
   SDValue Con = DAG.getNode(ISD::CONCAT_VECTORS, DL, WideResVT, LoRes, HiRes);
 
   EVT OpVT = N->getOperand(0).getValueType();
@@ -3585,6 +3616,7 @@
     Res = WidenVecRes_Select(N);
     break;
   case ISD::SELECT_CC:         Res = WidenVecRes_SELECT_CC(N); break;
+  case ISD::VP_SETCC:
   case ISD::SETCC:             Res = WidenVecRes_SETCC(N); break;
   case ISD::UNDEF:             Res = WidenVecRes_UNDEF(N); break;
   case ISD::VECTOR_SHUFFLE:
@@ -5248,8 +5280,17 @@
          InOp2.getValueType() == WidenInVT &&
          "Input not widened to expected type!");
   (void)WidenInVT;
-  return DAG.getNode(ISD::SETCC, SDLoc(N),
-                     WidenVT, InOp1, InOp2, N->getOperand(2));
+  if (N->getNumOperands() == 3)
+    return DAG.getNode(ISD::SETCC, SDLoc(N), WidenVT, InOp1, InOp2,
+                       N->getOperand(2));
+
+  assert(N->getNumOperands() == 5 && "Unexpected number of operands!");
+  assert(N->getOpcode() == ISD::VP_SETCC && "Expected VP_SETCC opcode");
+
+  SDValue Mask =
+      GetWidenedMask(N->getOperand(3), WidenVT.getVectorElementCount());
+  return DAG.getNode(ISD::VP_SETCC, SDLoc(N), WidenVT, InOp1, InOp2,
+                     N->getOperand(2), Mask, N->getOperand(4));
 }
 
 SDValue DAGTypeLegalizer::WidenVecRes_STRICT_FSETCC(SDNode *N) {
diff --git a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-setcc-int-vp.ll b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-setcc-int-vp.ll
--- a/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-setcc-int-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/fixed-vectors-setcc-int-vp.ll
@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=riscv32 -mattr=+v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s \
+; RUN: llc -mtriple=riscv32 -mattr=+v,+m -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s \
 ; RUN:   | FileCheck %s --check-prefixes=CHECK,RV32
-; RUN: llc -mtriple=riscv64 -mattr=+v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s \
+; RUN: llc -mtriple=riscv64 -mattr=+v,+m -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s \
 ; RUN:   | FileCheck %s --check-prefixes=CHECK,RV64
 
 ; FIXME: We're missing canonicalizations of ISD::VP_SETCC equivalent to those
@@ -57,6 +57,42 @@
   ret <8 x i1> %v
 }
 
+declare <5 x i1> @llvm.vp.icmp.v5i8(<5 x i8>, <5 x i8>, metadata, <5 x i1>, i32)
+
+define <5 x i1> @icmp_eq_vv_v5i8(<5 x i8> %va, <5 x i8> %vb, <5 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vv_v5i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vmseq.vv v0, v8, v9, v0.t
+; CHECK-NEXT:    ret
+  %v = call <5 x i1> @llvm.vp.icmp.v5i8(<5 x i8> %va, <5 x i8> %vb, metadata !"eq", <5 x i1> %m, i32 %evl)
+  ret <5 x i1> %v
+}
+
+define <5 x i1> @icmp_eq_vx_v5i8(<5 x i8> %va, i8 %b, <5 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_v5i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, ma
+; CHECK-NEXT:    vmseq.vx v0, v8, a0, v0.t
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <5 x i8> poison, i8 %b, i32 0
+  %vb = shufflevector <5 x i8> %elt.head, <5 x i8> poison, <5 x i32> zeroinitializer
+  %v = call <5 x i1> @llvm.vp.icmp.v5i8(<5 x i8> %va, <5 x i8> %vb, metadata !"eq", <5 x i1> %m, i32 %evl)
+  ret <5 x i1> %v
+}
+
+define <5 x i1> @icmp_eq_vx_swap_v5i8(<5 x i8> %va, i8 %b, <5 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_swap_v5i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, ma
+; CHECK-NEXT:    vmseq.vx v0, v8, a0, v0.t
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <5 x i8> poison, i8 %b, i32 0
+  %vb = shufflevector <5 x i8> %elt.head, <5 x i8> poison, <5 x i32> zeroinitializer
+  %v = call <5 x i1> @llvm.vp.icmp.v5i8(<5 x i8> %vb, <5 x i8> %va, metadata !"eq", <5 x i1> %m, i32 %evl)
+  ret <5 x i1> %v
+}
+
 declare <8 x i1> @llvm.vp.icmp.v8i8(<8 x i8>, <8 x i8>, metadata, <8 x i1>, i32)
 
 define <8 x i1> @icmp_eq_vv_v8i8(<8 x i8> %va, <8 x i8> %vb, <8 x i1> %m, i32 zeroext %evl) {
@@ -587,6 +623,138 @@
   ret <8 x i1> %v
 }
 
+declare <256 x i1> @llvm.vp.icmp.v256i8(<256 x i8>, <256 x i8>, metadata, <256 x i1>, i32)
+
+define <256 x i1> @icmp_eq_vv_v256i8(<256 x i8> %va, <256 x i8> %vb, <256 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vv_v256i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    li a4, 24
+; CHECK-NEXT:    mul a1, a1, a4
+; CHECK-NEXT:    sub sp, sp, a1
+; CHECK-NEXT:    li a4, 128
+; CHECK-NEXT:    vsetvli zero, a4, e8, m8, ta, mu
+; CHECK-NEXT:    vle8.v v24, (a0)
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    slli a1, a1, 3
+; CHECK-NEXT:    add a1, sp, a1
+; CHECK-NEXT:    addi a1, a1, 16
+; CHECK-NEXT:    vs8r.v v24, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    slli a1, a1, 4
+; CHECK-NEXT:    add a1, sp, a1
+; CHECK-NEXT:    addi a1, a1, 16
+; CHECK-NEXT:    vs8r.v v16, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    addi a0, a0, 128
+; CHECK-NEXT:    mv a1, a3
+; CHECK-NEXT:    bltu a3, a4, .LBB51_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    li a1, 128
+; CHECK-NEXT:  .LBB51_2:
+; CHECK-NEXT:    li a4, 0
+; CHECK-NEXT:    vlm.v v24, (a2)
+; CHECK-NEXT:    vle8.v v16, (a0)
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vs8r.v v16, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, ma
+; CHECK-NEXT:    addi a0, a3, -128
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    slli a1, a1, 3
+; CHECK-NEXT:    add a1, sp, a1
+; CHECK-NEXT:    addi a1, a1, 16
+; CHECK-NEXT:    vl8re8.v v16, (a1) # Unknown-size Folded Reload
+; CHECK-NEXT:    vmseq.vv v1, v8, v16, v0.t
+; CHECK-NEXT:    bltu a3, a0, .LBB51_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    mv a4, a0
+; CHECK-NEXT:  .LBB51_4:
+; CHECK-NEXT:    vsetvli zero, a4, e8, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    vl8re8.v v16, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vmseq.vv v8, v16, v24, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    li a1, 24
+; CHECK-NEXT:    mul a0, a0, a1
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %v = call <256 x i1> @llvm.vp.icmp.v256i8(<256 x i8> %va, <256 x i8> %vb, metadata !"eq", <256 x i1> %m, i32 %evl)
+  ret <256 x i1> %v
+}
+
+define <256 x i1> @icmp_eq_vx_v256i8(<256 x i8> %va, i8 %b, <256 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_v256i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a3, 128
+; CHECK-NEXT:    vsetvli zero, a3, e8, m8, ta, mu
+; CHECK-NEXT:    vlm.v v25, (a1)
+; CHECK-NEXT:    addi a4, a2, -128
+; CHECK-NEXT:    vmv1r.v v24, v0
+; CHECK-NEXT:    li a1, 0
+; CHECK-NEXT:    bltu a2, a4, .LBB52_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a1, a4
+; CHECK-NEXT:  .LBB52_2:
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v25
+; CHECK-NEXT:    vmseq.vx v25, v16, a0, v0.t
+; CHECK-NEXT:    bltu a2, a3, .LBB52_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    li a2, 128
+; CHECK-NEXT:  .LBB52_4:
+; CHECK-NEXT:    vsetvli zero, a2, e8, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmseq.vx v16, v8, a0, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    vmv1r.v v8, v25
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <256 x i8> poison, i8 %b, i32 0
+  %vb = shufflevector <256 x i8> %elt.head, <256 x i8> poison, <256 x i32> zeroinitializer
+  %v = call <256 x i1> @llvm.vp.icmp.v256i8(<256 x i8> %va, <256 x i8> %vb, metadata !"eq", <256 x i1> %m, i32 %evl)
+  ret <256 x i1> %v
+}
+
+define <256 x i1> @icmp_eq_vx_swap_v256i8(<256 x i8> %va, i8 %b, <256 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_swap_v256i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    li a3, 128
+; CHECK-NEXT:    vsetvli zero, a3, e8, m8, ta, mu
+; CHECK-NEXT:    vlm.v v25, (a1)
+; CHECK-NEXT:    addi a4, a2, -128
+; CHECK-NEXT:    vmv1r.v v24, v0
+; CHECK-NEXT:    li a1, 0
+; CHECK-NEXT:    bltu a2, a4, .LBB53_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a1, a4
+; CHECK-NEXT:  .LBB53_2:
+; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v25
+; CHECK-NEXT:    vmseq.vx v25, v16, a0, v0.t
+; CHECK-NEXT:    bltu a2, a3, .LBB53_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    li a2, 128
+; CHECK-NEXT:  .LBB53_4:
+; CHECK-NEXT:    vsetvli zero, a2, e8, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmseq.vx v16, v8, a0, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    vmv1r.v v8, v25
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <256 x i8> poison, i8 %b, i32 0
+  %vb = shufflevector <256 x i8> %elt.head, <256 x i8> poison, <256 x i32> zeroinitializer
+  %v = call <256 x i1> @llvm.vp.icmp.v256i8(<256 x i8> %vb, <256 x i8> %va, metadata !"eq", <256 x i1> %m, i32 %evl)
+  ret <256 x i1> %v
+}
+
 declare <8 x i1> @llvm.vp.icmp.v8i32(<8 x i32>, <8 x i32>, metadata, <8 x i1>, i32)
 
 define <8 x i1> @icmp_eq_vv_v8i32(<8 x i32> %va, <8 x i32> %vb, <8 x i1> %m, i32 zeroext %evl) {
@@ -1162,6 +1330,120 @@
   ret <8 x i1> %v
 }
 
+declare <64 x i1> @llvm.vp.icmp.v64i32(<64 x i32>, <64 x i32>, metadata, <64 x i1>, i32)
+
+define <64 x i1> @icmp_eq_vv_v64i32(<64 x i32> %va, <64 x i32> %vb, <64 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vv_v64i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    slli a1, a1, 3
+; CHECK-NEXT:    sub sp, sp, a1
+; CHECK-NEXT:    vmv1r.v v1, v0
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    li a3, 0
+; CHECK-NEXT:    li a1, 32
+; CHECK-NEXT:    addi a4, a0, 128
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; CHECK-NEXT:    vle32.v v24, (a4)
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf2, ta, mu
+; CHECK-NEXT:    addi a4, a2, -32
+; CHECK-NEXT:    vslidedown.vi v0, v0, 4
+; CHECK-NEXT:    bltu a2, a4, .LBB99_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a3, a4
+; CHECK-NEXT:  .LBB99_2:
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, mu
+; CHECK-NEXT:    vle32.v v8, (a0)
+; CHECK-NEXT:    vsetvli zero, a3, e32, m8, ta, ma
+; CHECK-NEXT:    vmseq.vv v2, v16, v24, v0.t
+; CHECK-NEXT:    bltu a2, a1, .LBB99_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    li a2, 32
+; CHECK-NEXT:  .LBB99_4:
+; CHECK-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vmseq.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, tu, mu
+; CHECK-NEXT:    vslideup.vi v16, v2, 4
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %v = call <64 x i1> @llvm.vp.icmp.v64i32(<64 x i32> %va, <64 x i32> %vb, metadata !"eq", <64 x i1> %m, i32 %evl)
+  ret <64 x i1> %v
+}
+
+define <64 x i1> @icmp_eq_vx_v64i32(<64 x i32> %va, i32 %b, <64 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_v64i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmv1r.v v24, v0
+; CHECK-NEXT:    li a2, 0
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf2, ta, mu
+; CHECK-NEXT:    addi a3, a1, -32
+; CHECK-NEXT:    vslidedown.vi v0, v0, 4
+; CHECK-NEXT:    bltu a1, a3, .LBB100_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a2, a3
+; CHECK-NEXT:  .LBB100_2:
+; CHECK-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; CHECK-NEXT:    li a2, 32
+; CHECK-NEXT:    vmseq.vx v25, v16, a0, v0.t
+; CHECK-NEXT:    bltu a1, a2, .LBB100_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    li a1, 32
+; CHECK-NEXT:  .LBB100_4:
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmseq.vx v16, v8, a0, v0.t
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, tu, mu
+; CHECK-NEXT:    vslideup.vi v16, v25, 4
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <64 x i32> poison, i32 %b, i32 0
+  %vb = shufflevector <64 x i32> %elt.head, <64 x i32> poison, <64 x i32> zeroinitializer
+  %v = call <64 x i1> @llvm.vp.icmp.v64i32(<64 x i32> %va, <64 x i32> %vb, metadata !"eq", <64 x i1> %m, i32 %evl)
+  ret <64 x i1> %v
+}
+
+define <64 x i1> @icmp_eq_vx_swap_v64i32(<64 x i32> %va, i32 %b, <64 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_swap_v64i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmv1r.v v24, v0
+; CHECK-NEXT:    li a2, 0
+; CHECK-NEXT:    vsetivli zero, 4, e8, mf2, ta, mu
+; CHECK-NEXT:    addi a3, a1, -32
+; CHECK-NEXT:    vslidedown.vi v0, v0, 4
+; CHECK-NEXT:    bltu a1, a3, .LBB101_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a2, a3
+; CHECK-NEXT:  .LBB101_2:
+; CHECK-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; CHECK-NEXT:    li a2, 32
+; CHECK-NEXT:    vmseq.vx v25, v16, a0, v0.t
+; CHECK-NEXT:    bltu a1, a2, .LBB101_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    li a1, 32
+; CHECK-NEXT:  .LBB101_4:
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmseq.vx v16, v8, a0, v0.t
+; CHECK-NEXT:    vsetivli zero, 8, e8, mf2, tu, mu
+; CHECK-NEXT:    vslideup.vi v16, v25, 4
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <64 x i32> poison, i32 %b, i32 0
+  %vb = shufflevector <64 x i32> %elt.head, <64 x i32> poison, <64 x i32> zeroinitializer
+  %v = call <64 x i1> @llvm.vp.icmp.v64i32(<64 x i32> %vb, <64 x i32> %va, metadata !"eq", <64 x i1> %m, i32 %evl)
+  ret <64 x i1> %v
+}
+
 declare <8 x i1> @llvm.vp.icmp.v8i64(<8 x i64>, <8 x i64>, metadata, <8 x i1>, i32)
 
 define <8 x i1> @icmp_eq_vv_v8i64(<8 x i64> %va, <8 x i64> %vb, <8 x i1> %m, i32 zeroext %evl) {
diff --git a/llvm/test/CodeGen/RISCV/rvv/setcc-int-vp.ll b/llvm/test/CodeGen/RISCV/rvv/setcc-int-vp.ll
--- a/llvm/test/CodeGen/RISCV/rvv/setcc-int-vp.ll
+++ b/llvm/test/CodeGen/RISCV/rvv/setcc-int-vp.ll
@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=riscv32 -mattr=+v -verify-machineinstrs < %s \
+; RUN: llc -mtriple=riscv32 -mattr=+v,+m -verify-machineinstrs < %s \
 ; RUN:   | FileCheck %s --check-prefixes=CHECK,RV32
-; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs < %s \
+; RUN: llc -mtriple=riscv64 -mattr=+v,+m -verify-machineinstrs < %s \
 ; RUN:   | FileCheck %s --check-prefixes=CHECK,RV64
 
 ; FIXME: We're missing canonicalizations of ISD::VP_SETCC equivalent to those
@@ -537,6 +537,42 @@
   ret <vscale x 1 x i1> %v
 }
 
+declare <vscale x 3 x i1> @llvm.vp.icmp.nxv3i8(<vscale x 3 x i8>, <vscale x 3 x i8>, metadata, <vscale x 3 x i1>, i32)
+
+define <vscale x 3 x i1> @icmp_eq_vv_nxv3i8(<vscale x 3 x i8> %va, <vscale x 3 x i8> %vb, <vscale x 3 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vv_nxv3i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, ma
+; CHECK-NEXT:    vmseq.vv v0, v8, v9, v0.t
+; CHECK-NEXT:    ret
+  %v = call <vscale x 3 x i1> @llvm.vp.icmp.nxv3i8(<vscale x 3 x i8> %va, <vscale x 3 x i8> %vb, metadata !"eq", <vscale x 3 x i1> %m, i32 %evl)
+  ret <vscale x 3 x i1> %v
+}
+
+define <vscale x 3 x i1> @icmp_eq_vx_nxv3i8(<vscale x 3 x i8> %va, i8 %b, <vscale x 3 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_nxv3i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, ma
+; CHECK-NEXT:    vmseq.vx v0, v8, a0, v0.t
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <vscale x 3 x i8> poison, i8 %b, i32 0
+  %vb = shufflevector <vscale x 3 x i8> %elt.head, <vscale x 3 x i8> poison, <vscale x 3 x i32> zeroinitializer
+  %v = call <vscale x 3 x i1> @llvm.vp.icmp.nxv3i8(<vscale x 3 x i8> %va, <vscale x 3 x i8> %vb, metadata !"eq", <vscale x 3 x i1> %m, i32 %evl)
+  ret <vscale x 3 x i1> %v
+}
+
+define <vscale x 3 x i1> @icmp_eq_vx_swap_nxv3i8(<vscale x 3 x i8> %va, i8 %b, <vscale x 3 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_swap_nxv3i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, ma
+; CHECK-NEXT:    vmseq.vx v0, v8, a0, v0.t
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <vscale x 3 x i8> poison, i8 %b, i32 0
+  %vb = shufflevector <vscale x 3 x i8> %elt.head, <vscale x 3 x i8> poison, <vscale x 3 x i32> zeroinitializer
+  %v = call <vscale x 3 x i1> @llvm.vp.icmp.nxv3i8(<vscale x 3 x i8> %vb, <vscale x 3 x i8> %va, metadata !"eq", <vscale x 3 x i1> %m, i32 %evl)
+  ret <vscale x 3 x i1> %v
+}
+
 declare <vscale x 8 x i1> @llvm.vp.icmp.nxv8i7(<vscale x 8 x i7>, <vscale x 8 x i7>, metadata, <vscale x 8 x i1>, i32)
 
 define <vscale x 8 x i1> @icmp_eq_vv_nxv8i7(<vscale x 8 x i7> %va, <vscale x 8 x i7> %vb, <vscale x 8 x i1> %m, i32 zeroext %evl) {
@@ -1117,6 +1153,139 @@
   ret <vscale x 8 x i1> %v
 }
 
+declare <vscale x 128 x i1> @llvm.vp.icmp.nxv128i8(<vscale x 128 x i8>, <vscale x 128 x i8>, metadata, <vscale x 128 x i1>, i32)
+
+define <vscale x 128 x i1> @icmp_eq_vv_nxv128i8(<vscale x 128 x i8> %va, <vscale x 128 x i8> %vb, <vscale x 128 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vv_nxv128i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    li a4, 24
+; CHECK-NEXT:    mul a1, a1, a4
+; CHECK-NEXT:    sub sp, sp, a1
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    slli a1, a1, 3
+; CHECK-NEXT:    add a4, a0, a1
+; CHECK-NEXT:    vl8r.v v24, (a4)
+; CHECK-NEXT:    csrr a4, vlenb
+; CHECK-NEXT:    slli a4, a4, 3
+; CHECK-NEXT:    add a4, sp, a4
+; CHECK-NEXT:    addi a4, a4, 16
+; CHECK-NEXT:    vs8r.v v24, (a4) # Unknown-size Folded Spill
+; CHECK-NEXT:    vsetvli a4, zero, e8, m8, ta, mu
+; CHECK-NEXT:    vlm.v v25, (a2)
+; CHECK-NEXT:    sub a4, a3, a1
+; CHECK-NEXT:    vmv1r.v v24, v0
+; CHECK-NEXT:    csrr a2, vlenb
+; CHECK-NEXT:    slli a2, a2, 4
+; CHECK-NEXT:    add a2, sp, a2
+; CHECK-NEXT:    addi a2, a2, 16
+; CHECK-NEXT:    vs8r.v v8, (a2) # Unknown-size Folded Spill
+; CHECK-NEXT:    li a2, 0
+; CHECK-NEXT:    bltu a3, a4, .LBB96_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a2, a4
+; CHECK-NEXT:  .LBB96_2:
+; CHECK-NEXT:    vl8r.v v8, (a0)
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vs8r.v v8, (a0) # Unknown-size Folded Spill
+; CHECK-NEXT:    vsetvli zero, a2, e8, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v25
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vmseq.vv v1, v16, v8, v0.t
+; CHECK-NEXT:    bltu a3, a1, .LBB96_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    mv a3, a1
+; CHECK-NEXT:  .LBB96_4:
+; CHECK-NEXT:    vsetvli zero, a3, e8, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 4
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    addi a0, a0, 16
+; CHECK-NEXT:    vl8re8.v v8, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vmseq.vv v16, v8, v24, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    vmv1r.v v8, v1
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    li a1, 24
+; CHECK-NEXT:    mul a0, a0, a1
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 128 x i1> @llvm.vp.icmp.nxv128i8(<vscale x 128 x i8> %va, <vscale x 128 x i8> %vb, metadata !"eq", <vscale x 128 x i1> %m, i32 %evl)
+  ret <vscale x 128 x i1> %v
+}
+
+define <vscale x 128 x i1> @icmp_eq_vx_nxv128i8(<vscale x 128 x i8> %va, i8 %b, <vscale x 128 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_nxv128i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    slli a3, a3, 3
+; CHECK-NEXT:    mv a4, a2
+; CHECK-NEXT:    bltu a2, a3, .LBB97_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a4, a3
+; CHECK-NEXT:  .LBB97_2:
+; CHECK-NEXT:    li a5, 0
+; CHECK-NEXT:    vsetvli a6, zero, e8, m8, ta, mu
+; CHECK-NEXT:    vlm.v v24, (a1)
+; CHECK-NEXT:    vsetvli zero, a4, e8, m8, ta, ma
+; CHECK-NEXT:    sub a1, a2, a3
+; CHECK-NEXT:    vmseq.vx v25, v8, a0, v0.t
+; CHECK-NEXT:    bltu a2, a1, .LBB97_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    mv a5, a1
+; CHECK-NEXT:  .LBB97_4:
+; CHECK-NEXT:    vsetvli zero, a5, e8, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmseq.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v25
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <vscale x 128 x i8> poison, i8 %b, i8 0
+  %vb = shufflevector <vscale x 128 x i8> %elt.head, <vscale x 128 x i8> poison, <vscale x 128 x i32> zeroinitializer
+  %v = call <vscale x 128 x i1> @llvm.vp.icmp.nxv128i8(<vscale x 128 x i8> %va, <vscale x 128 x i8> %vb, metadata !"eq", <vscale x 128 x i1> %m, i32 %evl)
+  ret <vscale x 128 x i1> %v
+}
+
+define <vscale x 128 x i1> @icmp_eq_vx_swap_nxv128i8(<vscale x 128 x i8> %va, i8 %b, <vscale x 128 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_swap_nxv128i8:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    slli a3, a3, 3
+; CHECK-NEXT:    mv a4, a2
+; CHECK-NEXT:    bltu a2, a3, .LBB98_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a4, a3
+; CHECK-NEXT:  .LBB98_2:
+; CHECK-NEXT:    li a5, 0
+; CHECK-NEXT:    vsetvli a6, zero, e8, m8, ta, mu
+; CHECK-NEXT:    vlm.v v24, (a1)
+; CHECK-NEXT:    vsetvli zero, a4, e8, m8, ta, ma
+; CHECK-NEXT:    sub a1, a2, a3
+; CHECK-NEXT:    vmseq.vx v25, v8, a0, v0.t
+; CHECK-NEXT:    bltu a2, a1, .LBB98_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    mv a5, a1
+; CHECK-NEXT:  .LBB98_4:
+; CHECK-NEXT:    vsetvli zero, a5, e8, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmseq.vx v8, v16, a0, v0.t
+; CHECK-NEXT:    vmv1r.v v0, v25
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <vscale x 128 x i8> poison, i8 %b, i8 0
+  %vb = shufflevector <vscale x 128 x i8> %elt.head, <vscale x 128 x i8> poison, <vscale x 128 x i32> zeroinitializer
+  %v = call <vscale x 128 x i1> @llvm.vp.icmp.nxv128i8(<vscale x 128 x i8> %vb, <vscale x 128 x i8> %va, metadata !"eq", <vscale x 128 x i1> %m, i32 %evl)
+  ret <vscale x 128 x i1> %v
+}
+
 declare <vscale x 1 x i1> @llvm.vp.icmp.nxv1i32(<vscale x 1 x i32>, <vscale x 1 x i32>, metadata, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x i1> @icmp_eq_vv_nxv1i32(<vscale x 1 x i32> %va, <vscale x 1 x i32> %vb, <vscale x 1 x i1> %m, i32 zeroext %evl) {
@@ -2222,6 +2391,128 @@
   ret <vscale x 8 x i1> %v
 }
 
+declare <vscale x 32 x i1> @llvm.vp.icmp.nxv32i32(<vscale x 32 x i32>, <vscale x 32 x i32>, metadata, <vscale x 32 x i1>, i32)
+
+define <vscale x 32 x i1> @icmp_eq_vv_nxv32i32(<vscale x 32 x i32> %va, <vscale x 32 x i32> %vb, <vscale x 32 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vv_nxv32i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -16
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    slli a1, a1, 3
+; CHECK-NEXT:    sub sp, sp, a1
+; CHECK-NEXT:    vmv1r.v v1, v0
+; CHECK-NEXT:    addi a1, sp, 16
+; CHECK-NEXT:    vs8r.v v8, (a1) # Unknown-size Folded Spill
+; CHECK-NEXT:    li a4, 0
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    srli a1, a3, 2
+; CHECK-NEXT:    vsetvli a5, zero, e8, mf2, ta, mu
+; CHECK-NEXT:    slli a5, a3, 3
+; CHECK-NEXT:    add a5, a0, a5
+; CHECK-NEXT:    vl8re32.v v24, (a5)
+; CHECK-NEXT:    slli a3, a3, 1
+; CHECK-NEXT:    sub a5, a2, a3
+; CHECK-NEXT:    vslidedown.vx v0, v0, a1
+; CHECK-NEXT:    bltu a2, a5, .LBB189_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a4, a5
+; CHECK-NEXT:  .LBB189_2:
+; CHECK-NEXT:    vl8re32.v v8, (a0)
+; CHECK-NEXT:    vsetvli zero, a4, e32, m8, ta, ma
+; CHECK-NEXT:    vmseq.vv v2, v16, v24, v0.t
+; CHECK-NEXT:    bltu a2, a3, .LBB189_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    mv a2, a3
+; CHECK-NEXT:  .LBB189_4:
+; CHECK-NEXT:    vsetvli zero, a2, e32, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v1
+; CHECK-NEXT:    addi a0, sp, 16
+; CHECK-NEXT:    vl8re8.v v24, (a0) # Unknown-size Folded Reload
+; CHECK-NEXT:    vmseq.vv v16, v24, v8, v0.t
+; CHECK-NEXT:    add a0, a1, a1
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, tu, mu
+; CHECK-NEXT:    vslideup.vx v16, v2, a1
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    slli a0, a0, 3
+; CHECK-NEXT:    add sp, sp, a0
+; CHECK-NEXT:    addi sp, sp, 16
+; CHECK-NEXT:    ret
+  %v = call <vscale x 32 x i1> @llvm.vp.icmp.nxv32i32(<vscale x 32 x i32> %va, <vscale x 32 x i32> %vb, metadata !"eq", <vscale x 32 x i1> %m, i32 %evl)
+  ret <vscale x 32 x i1> %v
+}
+
+define <vscale x 32 x i1> @icmp_eq_vx_nxv32i32(<vscale x 32 x i32> %va, i32 %b, <vscale x 32 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_nxv32i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmv1r.v v24, v0
+; CHECK-NEXT:    li a4, 0
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    srli a2, a3, 2
+; CHECK-NEXT:    vsetvli a5, zero, e8, mf2, ta, mu
+; CHECK-NEXT:    slli a3, a3, 1
+; CHECK-NEXT:    sub a5, a1, a3
+; CHECK-NEXT:    vslidedown.vx v0, v0, a2
+; CHECK-NEXT:    bltu a1, a5, .LBB190_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a4, a5
+; CHECK-NEXT:  .LBB190_2:
+; CHECK-NEXT:    vsetvli zero, a4, e32, m8, ta, ma
+; CHECK-NEXT:    vmseq.vx v25, v16, a0, v0.t
+; CHECK-NEXT:    bltu a1, a3, .LBB190_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    mv a1, a3
+; CHECK-NEXT:  .LBB190_4:
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmseq.vx v16, v8, a0, v0.t
+; CHECK-NEXT:    add a0, a2, a2
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, tu, mu
+; CHECK-NEXT:    vslideup.vx v16, v25, a2
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <vscale x 32 x i32> poison, i32 %b, i32 0
+  %vb = shufflevector <vscale x 32 x i32> %elt.head, <vscale x 32 x i32> poison, <vscale x 32 x i32> zeroinitializer
+  %v = call <vscale x 32 x i1> @llvm.vp.icmp.nxv32i32(<vscale x 32 x i32> %va, <vscale x 32 x i32> %vb, metadata !"eq", <vscale x 32 x i1> %m, i32 %evl)
+  ret <vscale x 32 x i1> %v
+}
+
+define <vscale x 32 x i1> @icmp_eq_vx_swap_nxv32i32(<vscale x 32 x i32> %va, i32 %b, <vscale x 32 x i1> %m, i32 zeroext %evl) {
+; CHECK-LABEL: icmp_eq_vx_swap_nxv32i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vmv1r.v v24, v0
+; CHECK-NEXT:    li a4, 0
+; CHECK-NEXT:    csrr a3, vlenb
+; CHECK-NEXT:    srli a2, a3, 2
+; CHECK-NEXT:    vsetvli a5, zero, e8, mf2, ta, mu
+; CHECK-NEXT:    slli a3, a3, 1
+; CHECK-NEXT:    sub a5, a1, a3
+; CHECK-NEXT:    vslidedown.vx v0, v0, a2
+; CHECK-NEXT:    bltu a1, a5, .LBB191_2
+; CHECK-NEXT:  # %bb.1:
+; CHECK-NEXT:    mv a4, a5
+; CHECK-NEXT:  .LBB191_2:
+; CHECK-NEXT:    vsetvli zero, a4, e32, m8, ta, ma
+; CHECK-NEXT:    vmseq.vx v25, v16, a0, v0.t
+; CHECK-NEXT:    bltu a1, a3, .LBB191_4
+; CHECK-NEXT:  # %bb.3:
+; CHECK-NEXT:    mv a1, a3
+; CHECK-NEXT:  .LBB191_4:
+; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, ma
+; CHECK-NEXT:    vmv1r.v v0, v24
+; CHECK-NEXT:    vmseq.vx v16, v8, a0, v0.t
+; CHECK-NEXT:    add a0, a2, a2
+; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, tu, mu
+; CHECK-NEXT:    vslideup.vx v16, v25, a2
+; CHECK-NEXT:    vmv1r.v v0, v16
+; CHECK-NEXT:    ret
+  %elt.head = insertelement <vscale x 32 x i32> poison, i32 %b, i32 0
+  %vb = shufflevector <vscale x 32 x i32> %elt.head, <vscale x 32 x i32> poison, <vscale x 32 x i32> zeroinitializer
+  %v = call <vscale x 32 x i1> @llvm.vp.icmp.nxv32i32(<vscale x 32 x i32> %vb, <vscale x 32 x i32> %va, metadata !"eq", <vscale x 32 x i1> %m, i32 %evl)
+  ret <vscale x 32 x i1> %v
+}
+
 declare <vscale x 1 x i1> @llvm.vp.icmp.nxv1i64(<vscale x 1 x i64>, <vscale x 1 x i64>, metadata, <vscale x 1 x i1>, i32)
 
 define <vscale x 1 x i1> @icmp_eq_vv_nxv1i64(<vscale x 1 x i64> %va, <vscale x 1 x i64> %vb, <vscale x 1 x i1> %m, i32 zeroext %evl) {