llvm/test/CodeGen/RISCV/rvv/fixed-vectors-vadd-vp.ll

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s \
; RUN:   | FileCheck %s --check-prefixes=CHECK,RV32
; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s \
; RUN:   | FileCheck %s --check-prefixes=CHECK,RV64

declare <8 x i7> @llvm.vp.add.v8i7(<8 x i7>, <8 x i7>, <8 x i1>, i32)

define <8 x i7> @vadd_vv_v8i7(<8 x i7> %va, <8 x i7> %b, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v8i7:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <8 x i7> @llvm.vp.add.v8i7(<8 x i7> %va, <8 x i7> %b, <8 x i1> %m, i32 %evl)
  ret <8 x i7> %v
}

declare <2 x i8> @llvm.vp.add.v2i8(<2 x i8>, <2 x i8>, <2 x i1>, i32)

define <2 x i8> @vadd_vv_v2i8(<2 x i8> %va, <2 x i8> %b, <2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v2i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> %va, <2 x i8> %b, <2 x i1> %m, i32 %evl)
  ret <2 x i8> %v
}

define <2 x i8> @vadd_vv_v2i8_unmasked(<2 x i8> %va, <2 x i8> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v2i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> %va, <2 x i8> %b, <2 x i1> %m, i32 %evl)
  ret <2 x i8> %v
}

define <2 x i8> @vadd_vx_v2i8(<2 x i8> %va, i8 %b, <2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v2i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i8> undef, i8 %b, i32 0
  %vb = shufflevector <2 x i8> %elt.head, <2 x i8> undef, <2 x i32> zeroinitializer
  %v = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> %va, <2 x i8> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i8> %v
}

define <2 x i8> @vadd_vx_v2i8_unmasked(<2 x i8> %va, i8 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v2i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf8, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i8> undef, i8 %b, i32 0
  %vb = shufflevector <2 x i8> %elt.head, <2 x i8> undef, <2 x i32> zeroinitializer
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> %va, <2 x i8> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i8> %v
}

define <2 x i8> @vadd_vi_v2i8(<2 x i8> %va, <2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v2i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <2 x i8> %elt.head, <2 x i8> undef, <2 x i32> zeroinitializer
  %v = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> %va, <2 x i8> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i8> %v
}

define <2 x i8> @vadd_vi_v2i8_unmasked(<2 x i8> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v2i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf8, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <2 x i8> %elt.head, <2 x i8> undef, <2 x i32> zeroinitializer
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> %va, <2 x i8> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i8> %v
}

declare <4 x i8> @llvm.vp.add.v4i8(<4 x i8>, <4 x i8>, <4 x i1>, i32)

define <4 x i8> @vadd_vv_v4i8(<4 x i8> %va, <4 x i8> %b, <4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v4i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> %va, <4 x i8> %b, <4 x i1> %m, i32 %evl)
  ret <4 x i8> %v
}

define <4 x i8> @vadd_vv_v4i8_unmasked(<4 x i8> %va, <4 x i8> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v4i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> %va, <4 x i8> %b, <4 x i1> %m, i32 %evl)
  ret <4 x i8> %v
}

define <4 x i8> @vadd_vx_v4i8(<4 x i8> %va, i8 %b, <4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v4i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i8> undef, i8 %b, i32 0
  %vb = shufflevector <4 x i8> %elt.head, <4 x i8> undef, <4 x i32> zeroinitializer
  %v = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> %va, <4 x i8> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i8> %v
}

define <4 x i8> @vadd_vx_v4i8_unmasked(<4 x i8> %va, i8 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v4i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf4, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i8> undef, i8 %b, i32 0
  %vb = shufflevector <4 x i8> %elt.head, <4 x i8> undef, <4 x i32> zeroinitializer
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> %va, <4 x i8> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i8> %v
}

define <4 x i8> @vadd_vi_v4i8(<4 x i8> %va, <4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v4i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <4 x i8> %elt.head, <4 x i8> undef, <4 x i32> zeroinitializer
  %v = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> %va, <4 x i8> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i8> %v
}

define <4 x i8> @vadd_vi_v4i8_unmasked(<4 x i8> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v4i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf4, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <4 x i8> %elt.head, <4 x i8> undef, <4 x i32> zeroinitializer
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> %va, <4 x i8> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i8> %v
}

declare <5 x i8> @llvm.vp.add.v5i8(<5 x i8>, <5 x i8>, <5 x i1>, i32)

define <5 x i8> @vadd_vv_v5i8(<5 x i8> %va, <5 x i8> %b, <5 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v5i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <5 x i8> @llvm.vp.add.v5i8(<5 x i8> %va, <5 x i8> %b, <5 x i1> %m, i32 %evl)
  ret <5 x i8> %v
}

define <5 x i8> @vadd_vv_v5i8_unmasked(<5 x i8> %va, <5 x i8> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v5i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <5 x i1> undef, i1 true, i32 0
  %m = shufflevector <5 x i1> %head, <5 x i1> undef, <5 x i32> zeroinitializer
  %v = call <5 x i8> @llvm.vp.add.v5i8(<5 x i8> %va, <5 x i8> %b, <5 x i1> %m, i32 %evl)
  ret <5 x i8> %v
}

define <5 x i8> @vadd_vx_v5i8(<5 x i8> %va, i8 %b, <5 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v5i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <5 x i8> undef, i8 %b, i32 0
  %vb = shufflevector <5 x i8> %elt.head, <5 x i8> undef, <5 x i32> zeroinitializer
  %v = call <5 x i8> @llvm.vp.add.v5i8(<5 x i8> %va, <5 x i8> %vb, <5 x i1> %m, i32 %evl)
  ret <5 x i8> %v
}

define <5 x i8> @vadd_vx_v5i8_unmasked(<5 x i8> %va, i8 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v5i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <5 x i8> undef, i8 %b, i32 0
  %vb = shufflevector <5 x i8> %elt.head, <5 x i8> undef, <5 x i32> zeroinitializer
  %head = insertelement <5 x i1> undef, i1 true, i32 0
  %m = shufflevector <5 x i1> %head, <5 x i1> undef, <5 x i32> zeroinitializer
  %v = call <5 x i8> @llvm.vp.add.v5i8(<5 x i8> %va, <5 x i8> %vb, <5 x i1> %m, i32 %evl)
  ret <5 x i8> %v
}

define <5 x i8> @vadd_vi_v5i8(<5 x i8> %va, <5 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v5i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <5 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <5 x i8> %elt.head, <5 x i8> undef, <5 x i32> zeroinitializer
  %v = call <5 x i8> @llvm.vp.add.v5i8(<5 x i8> %va, <5 x i8> %vb, <5 x i1> %m, i32 %evl)
  ret <5 x i8> %v
}

define <5 x i8> @vadd_vi_v5i8_unmasked(<5 x i8> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v5i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <5 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <5 x i8> %elt.head, <5 x i8> undef, <5 x i32> zeroinitializer
  %head = insertelement <5 x i1> undef, i1 true, i32 0
  %m = shufflevector <5 x i1> %head, <5 x i1> undef, <5 x i32> zeroinitializer
  %v = call <5 x i8> @llvm.vp.add.v5i8(<5 x i8> %va, <5 x i8> %vb, <5 x i1> %m, i32 %evl)
  ret <5 x i8> %v
}

declare <8 x i8> @llvm.vp.add.v8i8(<8 x i8>, <8 x i8>, <8 x i1>, i32)

define <8 x i8> @vadd_vv_v8i8(<8 x i8> %va, <8 x i8> %b, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v8i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> %va, <8 x i8> %b, <8 x i1> %m, i32 %evl)
  ret <8 x i8> %v
}

define <8 x i8> @vadd_vv_v8i8_unmasked(<8 x i8> %va, <8 x i8> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v8i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> %va, <8 x i8> %b, <8 x i1> %m, i32 %evl)
  ret <8 x i8> %v
}

define <8 x i8> @vadd_vx_v8i8(<8 x i8> %va, i8 %b, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v8i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i8> undef, i8 %b, i32 0
  %vb = shufflevector <8 x i8> %elt.head, <8 x i8> undef, <8 x i32> zeroinitializer
  %v = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> %va, <8 x i8> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i8> %v
}

define <8 x i8> @vadd_vx_v8i8_unmasked(<8 x i8> %va, i8 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v8i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i8> undef, i8 %b, i32 0
  %vb = shufflevector <8 x i8> %elt.head, <8 x i8> undef, <8 x i32> zeroinitializer
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> %va, <8 x i8> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i8> %v
}

define <8 x i8> @vadd_vi_v8i8(<8 x i8> %va, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v8i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <8 x i8> %elt.head, <8 x i8> undef, <8 x i32> zeroinitializer
  %v = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> %va, <8 x i8> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i8> %v
}

define <8 x i8> @vadd_vi_v8i8_unmasked(<8 x i8> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v8i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, mf2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <8 x i8> %elt.head, <8 x i8> undef, <8 x i32> zeroinitializer
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> %va, <8 x i8> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i8> %v
}

declare <16 x i8> @llvm.vp.add.v16i8(<16 x i8>, <16 x i8>, <16 x i1>, i32)

define <16 x i8> @vadd_vv_v16i8(<16 x i8> %va, <16 x i8> %b, <16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v16i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> %va, <16 x i8> %b, <16 x i1> %m, i32 %evl)
  ret <16 x i8> %v
}

define <16 x i8> @vadd_vv_v16i8_unmasked(<16 x i8> %va, <16 x i8> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v16i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> %va, <16 x i8> %b, <16 x i1> %m, i32 %evl)
  ret <16 x i8> %v
}

define <16 x i8> @vadd_vx_v16i8(<16 x i8> %va, i8 %b, <16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v16i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i8> undef, i8 %b, i32 0
  %vb = shufflevector <16 x i8> %elt.head, <16 x i8> undef, <16 x i32> zeroinitializer
  %v = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> %va, <16 x i8> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i8> %v
}

define <16 x i8> @vadd_vx_v16i8_unmasked(<16 x i8> %va, i8 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v16i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e8, m1, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i8> undef, i8 %b, i32 0
  %vb = shufflevector <16 x i8> %elt.head, <16 x i8> undef, <16 x i32> zeroinitializer
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> %va, <16 x i8> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i8> %v
}

define <16 x i8> @vadd_vi_v16i8(<16 x i8> %va, <16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v16i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <16 x i8> %elt.head, <16 x i8> undef, <16 x i32> zeroinitializer
  %v = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> %va, <16 x i8> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i8> %v
}

define <16 x i8> @vadd_vi_v16i8_unmasked(<16 x i8> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v16i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e8, m1, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <16 x i8> %elt.head, <16 x i8> undef, <16 x i32> zeroinitializer
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> %va, <16 x i8> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i8> %v
}

declare <256 x i8> @llvm.vp.add.v258i8(<256 x i8>, <256 x i8>, <256 x i1>, i32)

define <256 x i8> @vadd_vi_v258i8(<256 x i8> %va, <256 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v258i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    li a2, 128
; CHECK-NEXT:    vsetvli zero, a2, e8, m8, ta, mu
; CHECK-NEXT:    vlm.v v25, (a0)
; CHECK-NEXT:    addi a3, a1, -128
; CHECK-NEXT:    vmv1r.v v24, v0
; CHECK-NEXT:    li a0, 0
; CHECK-NEXT:    bltu a1, a3, .LBB31_2
; CHECK-NEXT:  # %bb.1:
; CHECK-NEXT:    mv a0, a3
; CHECK-NEXT:  .LBB31_2:
; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
; CHECK-NEXT:    vmv1r.v v0, v25
; CHECK-NEXT:    vadd.vi v16, v16, -1, v0.t
; CHECK-NEXT:    bltu a1, a2, .LBB31_4
; CHECK-NEXT:  # %bb.3:
; CHECK-NEXT:    li a1, 128
; CHECK-NEXT:  .LBB31_4:
; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, mu
; CHECK-NEXT:    vmv1r.v v0, v24
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <256 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <256 x i8> %elt.head, <256 x i8> undef, <256 x i32> zeroinitializer
  %v = call <256 x i8> @llvm.vp.add.v258i8(<256 x i8> %va, <256 x i8> %vb, <256 x i1> %m, i32 %evl)
  ret <256 x i8> %v
}

define <256 x i8> @vadd_vi_v258i8_unmasked(<256 x i8> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v258i8_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, -128
; CHECK-NEXT:    li a2, 0
; CHECK-NEXT:    bltu a0, a1, .LBB32_2
; CHECK-NEXT:  # %bb.1:
; CHECK-NEXT:    mv a2, a1
; CHECK-NEXT:  .LBB32_2:
; CHECK-NEXT:    vsetvli zero, a2, e8, m8, ta, mu
; CHECK-NEXT:    li a1, 128
; CHECK-NEXT:    vadd.vi v16, v16, -1
; CHECK-NEXT:    bltu a0, a1, .LBB32_4
; CHECK-NEXT:  # %bb.3:
; CHECK-NEXT:    li a0, 128
; CHECK-NEXT:  .LBB32_4:
; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <256 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <256 x i8> %elt.head, <256 x i8> undef, <256 x i32> zeroinitializer
  %head = insertelement <256 x i1> undef, i1 true, i32 0
  %m = shufflevector <256 x i1> %head, <256 x i1> undef, <256 x i32> zeroinitializer
  %v = call <256 x i8> @llvm.vp.add.v258i8(<256 x i8> %va, <256 x i8> %vb, <256 x i1> %m, i32 %evl)
  ret <256 x i8> %v
}

; Test splitting when the %evl is a known constant.

define <256 x i8> @vadd_vi_v258i8_evl129(<256 x i8> %va, <256 x i1> %m) {
; CHECK-LABEL: vadd_vi_v258i8_evl129:
; CHECK:       # %bb.0:
; CHECK-NEXT:    li a1, 128
; CHECK-NEXT:    vsetvli zero, a1, e8, m8, ta, mu
; CHECK-NEXT:    vlm.v v24, (a0)
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    vsetivli zero, 1, e8, m8, ta, mu
; CHECK-NEXT:    vmv1r.v v0, v24
; CHECK-NEXT:    vadd.vi v16, v16, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <256 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <256 x i8> %elt.head, <256 x i8> undef, <256 x i32> zeroinitializer
  %v = call <256 x i8> @llvm.vp.add.v258i8(<256 x i8> %va, <256 x i8> %vb, <256 x i1> %m, i32 129)
  ret <256 x i8> %v
}

; FIXME: The upper half is doing nothing.

define <256 x i8> @vadd_vi_v258i8_evl128(<256 x i8> %va, <256 x i1> %m) {
; CHECK-LABEL: vadd_vi_v258i8_evl128:
; CHECK:       # %bb.0:
; CHECK-NEXT:    li a0, 128
; CHECK-NEXT:    vsetvli zero, a0, e8, m8, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <256 x i8> undef, i8 -1, i32 0
  %vb = shufflevector <256 x i8> %elt.head, <256 x i8> undef, <256 x i32> zeroinitializer
  %v = call <256 x i8> @llvm.vp.add.v258i8(<256 x i8> %va, <256 x i8> %vb, <256 x i1> %m, i32 128)
  ret <256 x i8> %v
}

declare <2 x i16> @llvm.vp.add.v2i16(<2 x i16>, <2 x i16>, <2 x i1>, i32)

define <2 x i16> @vadd_vv_v2i16(<2 x i16> %va, <2 x i16> %b, <2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v2i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <2 x i16> @llvm.vp.add.v2i16(<2 x i16> %va, <2 x i16> %b, <2 x i1> %m, i32 %evl)
  ret <2 x i16> %v
}

define <2 x i16> @vadd_vv_v2i16_unmasked(<2 x i16> %va, <2 x i16> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v2i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i16> @llvm.vp.add.v2i16(<2 x i16> %va, <2 x i16> %b, <2 x i1> %m, i32 %evl)
  ret <2 x i16> %v
}

define <2 x i16> @vadd_vx_v2i16(<2 x i16> %va, i16 %b, <2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v2i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i16> undef, i16 %b, i32 0
  %vb = shufflevector <2 x i16> %elt.head, <2 x i16> undef, <2 x i32> zeroinitializer
  %v = call <2 x i16> @llvm.vp.add.v2i16(<2 x i16> %va, <2 x i16> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i16> %v
}

define <2 x i16> @vadd_vx_v2i16_unmasked(<2 x i16> %va, i16 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v2i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf4, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i16> undef, i16 %b, i32 0
  %vb = shufflevector <2 x i16> %elt.head, <2 x i16> undef, <2 x i32> zeroinitializer
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i16> @llvm.vp.add.v2i16(<2 x i16> %va, <2 x i16> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i16> %v
}

define <2 x i16> @vadd_vi_v2i16(<2 x i16> %va, <2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v2i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i16> undef, i16 -1, i32 0
  %vb = shufflevector <2 x i16> %elt.head, <2 x i16> undef, <2 x i32> zeroinitializer
  %v = call <2 x i16> @llvm.vp.add.v2i16(<2 x i16> %va, <2 x i16> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i16> %v
}

define <2 x i16> @vadd_vi_v2i16_unmasked(<2 x i16> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v2i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf4, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i16> undef, i16 -1, i32 0
  %vb = shufflevector <2 x i16> %elt.head, <2 x i16> undef, <2 x i32> zeroinitializer
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i16> @llvm.vp.add.v2i16(<2 x i16> %va, <2 x i16> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i16> %v
}

declare <4 x i16> @llvm.vp.add.v4i16(<4 x i16>, <4 x i16>, <4 x i1>, i32)

define <4 x i16> @vadd_vv_v4i16(<4 x i16> %va, <4 x i16> %b, <4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v4i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <4 x i16> @llvm.vp.add.v4i16(<4 x i16> %va, <4 x i16> %b, <4 x i1> %m, i32 %evl)
  ret <4 x i16> %v
}

define <4 x i16> @vadd_vv_v4i16_unmasked(<4 x i16> %va, <4 x i16> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v4i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i16> @llvm.vp.add.v4i16(<4 x i16> %va, <4 x i16> %b, <4 x i1> %m, i32 %evl)
  ret <4 x i16> %v
}

define <4 x i16> @vadd_vx_v4i16(<4 x i16> %va, i16 %b, <4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v4i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i16> undef, i16 %b, i32 0
  %vb = shufflevector <4 x i16> %elt.head, <4 x i16> undef, <4 x i32> zeroinitializer
  %v = call <4 x i16> @llvm.vp.add.v4i16(<4 x i16> %va, <4 x i16> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i16> %v
}

define <4 x i16> @vadd_vx_v4i16_unmasked(<4 x i16> %va, i16 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v4i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, mf2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i16> undef, i16 %b, i32 0
  %vb = shufflevector <4 x i16> %elt.head, <4 x i16> undef, <4 x i32> zeroinitializer
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i16> @llvm.vp.add.v4i16(<4 x i16> %va, <4 x i16> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i16> %v
}

define <4 x i16> @vadd_vi_v4i16(<4 x i16> %va, <4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v4i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i16> undef, i16 -1, i32 0
  %vb = shufflevector <4 x i16> %elt.head, <4 x i16> undef, <4 x i32> zeroinitializer
  %v = call <4 x i16> @llvm.vp.add.v4i16(<4 x i16> %va, <4 x i16> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i16> %v
}

define <4 x i16> @vadd_vi_v4i16_unmasked(<4 x i16> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v4i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, mf2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i16> undef, i16 -1, i32 0
  %vb = shufflevector <4 x i16> %elt.head, <4 x i16> undef, <4 x i32> zeroinitializer
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i16> @llvm.vp.add.v4i16(<4 x i16> %va, <4 x i16> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i16> %v
}

declare <8 x i16> @llvm.vp.add.v8i16(<8 x i16>, <8 x i16>, <8 x i1>, i32)

define <8 x i16> @vadd_vv_v8i16(<8 x i16> %va, <8 x i16> %b, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v8i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <8 x i16> @llvm.vp.add.v8i16(<8 x i16> %va, <8 x i16> %b, <8 x i1> %m, i32 %evl)
  ret <8 x i16> %v
}

define <8 x i16> @vadd_vv_v8i16_unmasked(<8 x i16> %va, <8 x i16> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v8i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i16> @llvm.vp.add.v8i16(<8 x i16> %va, <8 x i16> %b, <8 x i1> %m, i32 %evl)
  ret <8 x i16> %v
}

define <8 x i16> @vadd_vx_v8i16(<8 x i16> %va, i16 %b, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v8i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i16> undef, i16 %b, i32 0
  %vb = shufflevector <8 x i16> %elt.head, <8 x i16> undef, <8 x i32> zeroinitializer
  %v = call <8 x i16> @llvm.vp.add.v8i16(<8 x i16> %va, <8 x i16> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i16> %v
}

define <8 x i16> @vadd_vx_v8i16_unmasked(<8 x i16> %va, i16 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v8i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m1, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i16> undef, i16 %b, i32 0
  %vb = shufflevector <8 x i16> %elt.head, <8 x i16> undef, <8 x i32> zeroinitializer
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i16> @llvm.vp.add.v8i16(<8 x i16> %va, <8 x i16> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i16> %v
}

define <8 x i16> @vadd_vi_v8i16(<8 x i16> %va, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v8i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i16> undef, i16 -1, i32 0
  %vb = shufflevector <8 x i16> %elt.head, <8 x i16> undef, <8 x i32> zeroinitializer
  %v = call <8 x i16> @llvm.vp.add.v8i16(<8 x i16> %va, <8 x i16> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i16> %v
}

define <8 x i16> @vadd_vi_v8i16_unmasked(<8 x i16> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v8i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m1, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i16> undef, i16 -1, i32 0
  %vb = shufflevector <8 x i16> %elt.head, <8 x i16> undef, <8 x i32> zeroinitializer
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i16> @llvm.vp.add.v8i16(<8 x i16> %va, <8 x i16> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i16> %v
}

declare <16 x i16> @llvm.vp.add.v16i16(<16 x i16>, <16 x i16>, <16 x i1>, i32)

define <16 x i16> @vadd_vv_v16i16(<16 x i16> %va, <16 x i16> %b, <16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v16i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v10, v0.t
; CHECK-NEXT:    ret
  %v = call <16 x i16> @llvm.vp.add.v16i16(<16 x i16> %va, <16 x i16> %b, <16 x i1> %m, i32 %evl)
  ret <16 x i16> %v
}

define <16 x i16> @vadd_vv_v16i16_unmasked(<16 x i16> %va, <16 x i16> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v16i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v10
; CHECK-NEXT:    ret
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i16> @llvm.vp.add.v16i16(<16 x i16> %va, <16 x i16> %b, <16 x i1> %m, i32 %evl)
  ret <16 x i16> %v
}

define <16 x i16> @vadd_vx_v16i16(<16 x i16> %va, i16 %b, <16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v16i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i16> undef, i16 %b, i32 0
  %vb = shufflevector <16 x i16> %elt.head, <16 x i16> undef, <16 x i32> zeroinitializer
  %v = call <16 x i16> @llvm.vp.add.v16i16(<16 x i16> %va, <16 x i16> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i16> %v
}

define <16 x i16> @vadd_vx_v16i16_unmasked(<16 x i16> %va, i16 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v16i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e16, m2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i16> undef, i16 %b, i32 0
  %vb = shufflevector <16 x i16> %elt.head, <16 x i16> undef, <16 x i32> zeroinitializer
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i16> @llvm.vp.add.v16i16(<16 x i16> %va, <16 x i16> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i16> %v
}

define <16 x i16> @vadd_vi_v16i16(<16 x i16> %va, <16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v16i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i16> undef, i16 -1, i32 0
  %vb = shufflevector <16 x i16> %elt.head, <16 x i16> undef, <16 x i32> zeroinitializer
  %v = call <16 x i16> @llvm.vp.add.v16i16(<16 x i16> %va, <16 x i16> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i16> %v
}

define <16 x i16> @vadd_vi_v16i16_unmasked(<16 x i16> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v16i16_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e16, m2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i16> undef, i16 -1, i32 0
  %vb = shufflevector <16 x i16> %elt.head, <16 x i16> undef, <16 x i32> zeroinitializer
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i16> @llvm.vp.add.v16i16(<16 x i16> %va, <16 x i16> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i16> %v
}

declare <2 x i32> @llvm.vp.add.v2i32(<2 x i32>, <2 x i32>, <2 x i1>, i32)

define <2 x i32> @vadd_vv_v2i32(<2 x i32> %va, <2 x i32> %b, <2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v2i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> %va, <2 x i32> %b, <2 x i1> %m, i32 %evl)
  ret <2 x i32> %v
}

define <2 x i32> @vadd_vv_v2i32_unmasked(<2 x i32> %va, <2 x i32> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v2i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> %va, <2 x i32> %b, <2 x i1> %m, i32 %evl)
  ret <2 x i32> %v
}

define <2 x i32> @vadd_vx_v2i32(<2 x i32> %va, i32 %b, <2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v2i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i32> undef, i32 %b, i32 0
  %vb = shufflevector <2 x i32> %elt.head, <2 x i32> undef, <2 x i32> zeroinitializer
  %v = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> %va, <2 x i32> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i32> %v
}

define <2 x i32> @vadd_vx_v2i32_unmasked(<2 x i32> %va, i32 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v2i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, mf2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i32> undef, i32 %b, i32 0
  %vb = shufflevector <2 x i32> %elt.head, <2 x i32> undef, <2 x i32> zeroinitializer
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> %va, <2 x i32> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i32> %v
}

define <2 x i32> @vadd_vi_v2i32(<2 x i32> %va, <2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v2i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i32> undef, i32 -1, i32 0
  %vb = shufflevector <2 x i32> %elt.head, <2 x i32> undef, <2 x i32> zeroinitializer
  %v = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> %va, <2 x i32> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i32> %v
}

define <2 x i32> @vadd_vi_v2i32_unmasked(<2 x i32> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v2i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, mf2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i32> undef, i32 -1, i32 0
  %vb = shufflevector <2 x i32> %elt.head, <2 x i32> undef, <2 x i32> zeroinitializer
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> %va, <2 x i32> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i32> %v
}

declare <4 x i32> @llvm.vp.add.v4i32(<4 x i32>, <4 x i32>, <4 x i1>, i32)

define <4 x i32> @vadd_vv_v4i32(<4 x i32> %va, <4 x i32> %b, <4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v4i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> %va, <4 x i32> %b, <4 x i1> %m, i32 %evl)
  ret <4 x i32> %v
}

define <4 x i32> @vadd_vv_v4i32_unmasked(<4 x i32> %va, <4 x i32> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v4i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> %va, <4 x i32> %b, <4 x i1> %m, i32 %evl)
  ret <4 x i32> %v
}

define <4 x i32> @vadd_vx_v4i32(<4 x i32> %va, i32 %b, <4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v4i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i32> undef, i32 %b, i32 0
  %vb = shufflevector <4 x i32> %elt.head, <4 x i32> undef, <4 x i32> zeroinitializer
  %v = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> %va, <4 x i32> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i32> %v
}

define <4 x i32> @vadd_vx_v4i32_unmasked(<4 x i32> %va, i32 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v4i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m1, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i32> undef, i32 %b, i32 0
  %vb = shufflevector <4 x i32> %elt.head, <4 x i32> undef, <4 x i32> zeroinitializer
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> %va, <4 x i32> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i32> %v
}

define <4 x i32> @vadd_vi_v4i32(<4 x i32> %va, <4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v4i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i32> undef, i32 -1, i32 0
  %vb = shufflevector <4 x i32> %elt.head, <4 x i32> undef, <4 x i32> zeroinitializer
  %v = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> %va, <4 x i32> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i32> %v
}

define <4 x i32> @vadd_vi_v4i32_unmasked(<4 x i32> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v4i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m1, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i32> undef, i32 -1, i32 0
  %vb = shufflevector <4 x i32> %elt.head, <4 x i32> undef, <4 x i32> zeroinitializer
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> %va, <4 x i32> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i32> %v
}

declare <8 x i32> @llvm.vp.add.v8i32(<8 x i32>, <8 x i32>, <8 x i1>, i32)

define <8 x i32> @vadd_vv_v8i32(<8 x i32> %va, <8 x i32> %b, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v8i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v10, v0.t
; CHECK-NEXT:    ret
  %v = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %va, <8 x i32> %b, <8 x i1> %m, i32 %evl)
  ret <8 x i32> %v
}

define <8 x i32> @vadd_vv_v8i32_unmasked(<8 x i32> %va, <8 x i32> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v8i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v10
; CHECK-NEXT:    ret
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %va, <8 x i32> %b, <8 x i1> %m, i32 %evl)
  ret <8 x i32> %v
}

define <8 x i32> @vadd_vx_v8i32(<8 x i32> %va, i32 %b, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v8i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i32> undef, i32 %b, i32 0
  %vb = shufflevector <8 x i32> %elt.head, <8 x i32> undef, <8 x i32> zeroinitializer
  %v = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %va, <8 x i32> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i32> %v
}

define <8 x i32> @vadd_vx_v8i32_unmasked(<8 x i32> %va, i32 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v8i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m2, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i32> undef, i32 %b, i32 0
  %vb = shufflevector <8 x i32> %elt.head, <8 x i32> undef, <8 x i32> zeroinitializer
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %va, <8 x i32> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i32> %v
}

define <8 x i32> @vadd_vi_v8i32(<8 x i32> %va, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v8i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i32> undef, i32 -1, i32 0
  %vb = shufflevector <8 x i32> %elt.head, <8 x i32> undef, <8 x i32> zeroinitializer
  %v = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %va, <8 x i32> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i32> %v
}

define <8 x i32> @vadd_vi_v8i32_unmasked(<8 x i32> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v8i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i32> undef, i32 -1, i32 0
  %vb = shufflevector <8 x i32> %elt.head, <8 x i32> undef, <8 x i32> zeroinitializer
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> %va, <8 x i32> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i32> %v
}

declare <16 x i32> @llvm.vp.add.v16i32(<16 x i32>, <16 x i32>, <16 x i1>, i32)

define <16 x i32> @vadd_vv_v16i32(<16 x i32> %va, <16 x i32> %b, <16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v16i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v12, v0.t
; CHECK-NEXT:    ret
  %v = call <16 x i32> @llvm.vp.add.v16i32(<16 x i32> %va, <16 x i32> %b, <16 x i1> %m, i32 %evl)
  ret <16 x i32> %v
}

define <16 x i32> @vadd_vv_v16i32_unmasked(<16 x i32> %va, <16 x i32> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v16i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v12
; CHECK-NEXT:    ret
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i32> @llvm.vp.add.v16i32(<16 x i32> %va, <16 x i32> %b, <16 x i1> %m, i32 %evl)
  ret <16 x i32> %v
}

define <16 x i32> @vadd_vx_v16i32(<16 x i32> %va, i32 %b, <16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v16i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i32> undef, i32 %b, i32 0
  %vb = shufflevector <16 x i32> %elt.head, <16 x i32> undef, <16 x i32> zeroinitializer
  %v = call <16 x i32> @llvm.vp.add.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i32> %v
}

define <16 x i32> @vadd_vx_v16i32_unmasked(<16 x i32> %va, i32 %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vx_v16i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a1, e32, m4, ta, mu
; CHECK-NEXT:    vadd.vx v8, v8, a0
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i32> undef, i32 %b, i32 0
  %vb = shufflevector <16 x i32> %elt.head, <16 x i32> undef, <16 x i32> zeroinitializer
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i32> @llvm.vp.add.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i32> %v
}

define <16 x i32> @vadd_vi_v16i32(<16 x i32> %va, <16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v16i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i32> undef, i32 -1, i32 0
  %vb = shufflevector <16 x i32> %elt.head, <16 x i32> undef, <16 x i32> zeroinitializer
  %v = call <16 x i32> @llvm.vp.add.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i32> %v
}

define <16 x i32> @vadd_vi_v16i32_unmasked(<16 x i32> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v16i32_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e32, m4, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i32> undef, i32 -1, i32 0
  %vb = shufflevector <16 x i32> %elt.head, <16 x i32> undef, <16 x i32> zeroinitializer
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i32> @llvm.vp.add.v16i32(<16 x i32> %va, <16 x i32> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i32> %v
}

declare <2 x i64> @llvm.vp.add.v2i64(<2 x i64>, <2 x i64>, <2 x i1>, i32)

define <2 x i64> @vadd_vv_v2i64(<2 x i64> %va, <2 x i64> %b, <2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v2i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9, v0.t
; CHECK-NEXT:    ret
  %v = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> %va, <2 x i64> %b, <2 x i1> %m, i32 %evl)
  ret <2 x i64> %v
}

define <2 x i64> @vadd_vv_v2i64_unmasked(<2 x i64> %va, <2 x i64> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v2i64_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v9
; CHECK-NEXT:    ret
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> %va, <2 x i64> %b, <2 x i1> %m, i32 %evl)
  ret <2 x i64> %v
}

define <2 x i64> @vadd_vx_v2i64(<2 x i64> %va, i64 %b, <2 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vadd_vx_v2i64:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    .cfi_def_cfa_offset 16
; RV32-NEXT:    sw a1, 12(sp)
; RV32-NEXT:    sw a0, 8(sp)
; RV32-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
; RV32-NEXT:    addi a0, sp, 8
; RV32-NEXT:    vlse64.v v9, (a0), zero
; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, mu
; RV32-NEXT:    vadd.vv v8, v8, v9, v0.t
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vx_v2i64:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
; RV64-NEXT:    vadd.vx v8, v8, a0, v0.t
; RV64-NEXT:    ret
  %elt.head = insertelement <2 x i64> undef, i64 %b, i32 0
  %vb = shufflevector <2 x i64> %elt.head, <2 x i64> undef, <2 x i32> zeroinitializer
  %v = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> %va, <2 x i64> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i64> %v
}

define <2 x i64> @vadd_vx_v2i64_unmasked(<2 x i64> %va, i64 %b, i32 zeroext %evl) {
; RV32-LABEL: vadd_vx_v2i64_unmasked:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    .cfi_def_cfa_offset 16
; RV32-NEXT:    sw a1, 12(sp)
; RV32-NEXT:    sw a0, 8(sp)
; RV32-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
; RV32-NEXT:    addi a0, sp, 8
; RV32-NEXT:    vlse64.v v9, (a0), zero
; RV32-NEXT:    vsetvli zero, a2, e64, m1, ta, mu
; RV32-NEXT:    vadd.vv v8, v8, v9
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vx_v2i64_unmasked:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetvli zero, a1, e64, m1, ta, mu
; RV64-NEXT:    vadd.vx v8, v8, a0
; RV64-NEXT:    ret
  %elt.head = insertelement <2 x i64> undef, i64 %b, i32 0
  %vb = shufflevector <2 x i64> %elt.head, <2 x i64> undef, <2 x i32> zeroinitializer
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> %va, <2 x i64> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i64> %v
}

define <2 x i64> @vadd_vi_v2i64(<2 x i64> %va, <2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v2i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <2 x i64> %elt.head, <2 x i64> undef, <2 x i32> zeroinitializer
  %v = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> %va, <2 x i64> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i64> %v
}

define <2 x i64> @vadd_vi_v2i64_unmasked(<2 x i64> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v2i64_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m1, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <2 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <2 x i64> %elt.head, <2 x i64> undef, <2 x i32> zeroinitializer
  %head = insertelement <2 x i1> undef, i1 true, i32 0
  %m = shufflevector <2 x i1> %head, <2 x i1> undef, <2 x i32> zeroinitializer
  %v = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> %va, <2 x i64> %vb, <2 x i1> %m, i32 %evl)
  ret <2 x i64> %v
}

declare <4 x i64> @llvm.vp.add.v4i64(<4 x i64>, <4 x i64>, <4 x i1>, i32)

define <4 x i64> @vadd_vv_v4i64(<4 x i64> %va, <4 x i64> %b, <4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v4i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v10, v0.t
; CHECK-NEXT:    ret
  %v = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> %va, <4 x i64> %b, <4 x i1> %m, i32 %evl)
  ret <4 x i64> %v
}

define <4 x i64> @vadd_vv_v4i64_unmasked(<4 x i64> %va, <4 x i64> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v4i64_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v10
; CHECK-NEXT:    ret
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> %va, <4 x i64> %b, <4 x i1> %m, i32 %evl)
  ret <4 x i64> %v
}

define <4 x i64> @vadd_vx_v4i64(<4 x i64> %va, i64 %b, <4 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vadd_vx_v4i64:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    .cfi_def_cfa_offset 16
; RV32-NEXT:    sw a1, 12(sp)
; RV32-NEXT:    sw a0, 8(sp)
; RV32-NEXT:    vsetivli zero, 4, e64, m2, ta, mu
; RV32-NEXT:    addi a0, sp, 8
; RV32-NEXT:    vlse64.v v10, (a0), zero
; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, mu
; RV32-NEXT:    vadd.vv v8, v8, v10, v0.t
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vx_v4i64:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, mu
; RV64-NEXT:    vadd.vx v8, v8, a0, v0.t
; RV64-NEXT:    ret
  %elt.head = insertelement <4 x i64> undef, i64 %b, i32 0
  %vb = shufflevector <4 x i64> %elt.head, <4 x i64> undef, <4 x i32> zeroinitializer
  %v = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> %va, <4 x i64> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i64> %v
}

define <4 x i64> @vadd_vx_v4i64_unmasked(<4 x i64> %va, i64 %b, i32 zeroext %evl) {
; RV32-LABEL: vadd_vx_v4i64_unmasked:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    .cfi_def_cfa_offset 16
; RV32-NEXT:    sw a1, 12(sp)
; RV32-NEXT:    sw a0, 8(sp)
; RV32-NEXT:    vsetivli zero, 4, e64, m2, ta, mu
; RV32-NEXT:    addi a0, sp, 8
; RV32-NEXT:    vlse64.v v10, (a0), zero
; RV32-NEXT:    vsetvli zero, a2, e64, m2, ta, mu
; RV32-NEXT:    vadd.vv v8, v8, v10
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vx_v4i64_unmasked:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetvli zero, a1, e64, m2, ta, mu
; RV64-NEXT:    vadd.vx v8, v8, a0
; RV64-NEXT:    ret
  %elt.head = insertelement <4 x i64> undef, i64 %b, i32 0
  %vb = shufflevector <4 x i64> %elt.head, <4 x i64> undef, <4 x i32> zeroinitializer
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> %va, <4 x i64> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i64> %v
}

define <4 x i64> @vadd_vi_v4i64(<4 x i64> %va, <4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v4i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <4 x i64> %elt.head, <4 x i64> undef, <4 x i32> zeroinitializer
  %v = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> %va, <4 x i64> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i64> %v
}

define <4 x i64> @vadd_vi_v4i64_unmasked(<4 x i64> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v4i64_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m2, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <4 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <4 x i64> %elt.head, <4 x i64> undef, <4 x i32> zeroinitializer
  %head = insertelement <4 x i1> undef, i1 true, i32 0
  %m = shufflevector <4 x i1> %head, <4 x i1> undef, <4 x i32> zeroinitializer
  %v = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> %va, <4 x i64> %vb, <4 x i1> %m, i32 %evl)
  ret <4 x i64> %v
}

declare <8 x i64> @llvm.vp.add.v8i64(<8 x i64>, <8 x i64>, <8 x i1>, i32)

define <8 x i64> @vadd_vv_v8i64(<8 x i64> %va, <8 x i64> %b, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v8i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v12, v0.t
; CHECK-NEXT:    ret
  %v = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> %va, <8 x i64> %b, <8 x i1> %m, i32 %evl)
  ret <8 x i64> %v
}

define <8 x i64> @vadd_vv_v8i64_unmasked(<8 x i64> %va, <8 x i64> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v8i64_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v12
; CHECK-NEXT:    ret
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> %va, <8 x i64> %b, <8 x i1> %m, i32 %evl)
  ret <8 x i64> %v
}

define <8 x i64> @vadd_vx_v8i64(<8 x i64> %va, i64 %b, <8 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vadd_vx_v8i64:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    .cfi_def_cfa_offset 16
; RV32-NEXT:    sw a1, 12(sp)
; RV32-NEXT:    sw a0, 8(sp)
; RV32-NEXT:    vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT:    addi a0, sp, 8
; RV32-NEXT:    vlse64.v v12, (a0), zero
; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, mu
; RV32-NEXT:    vadd.vv v8, v8, v12, v0.t
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vx_v8i64:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT:    vadd.vx v8, v8, a0, v0.t
; RV64-NEXT:    ret
  %elt.head = insertelement <8 x i64> undef, i64 %b, i32 0
  %vb = shufflevector <8 x i64> %elt.head, <8 x i64> undef, <8 x i32> zeroinitializer
  %v = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> %va, <8 x i64> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i64> %v
}

define <8 x i64> @vadd_vx_v8i64_unmasked(<8 x i64> %va, i64 %b, i32 zeroext %evl) {
; RV32-LABEL: vadd_vx_v8i64_unmasked:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    .cfi_def_cfa_offset 16
; RV32-NEXT:    sw a1, 12(sp)
; RV32-NEXT:    sw a0, 8(sp)
; RV32-NEXT:    vsetivli zero, 8, e64, m4, ta, mu
; RV32-NEXT:    addi a0, sp, 8
; RV32-NEXT:    vlse64.v v12, (a0), zero
; RV32-NEXT:    vsetvli zero, a2, e64, m4, ta, mu
; RV32-NEXT:    vadd.vv v8, v8, v12
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vx_v8i64_unmasked:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetvli zero, a1, e64, m4, ta, mu
; RV64-NEXT:    vadd.vx v8, v8, a0
; RV64-NEXT:    ret
  %elt.head = insertelement <8 x i64> undef, i64 %b, i32 0
  %vb = shufflevector <8 x i64> %elt.head, <8 x i64> undef, <8 x i32> zeroinitializer
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> %va, <8 x i64> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i64> %v
}

define <8 x i64> @vadd_vi_v8i64(<8 x i64> %va, <8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v8i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <8 x i64> %elt.head, <8 x i64> undef, <8 x i32> zeroinitializer
  %v = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> %va, <8 x i64> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i64> %v
}

define <8 x i64> @vadd_vi_v8i64_unmasked(<8 x i64> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v8i64_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m4, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <8 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <8 x i64> %elt.head, <8 x i64> undef, <8 x i32> zeroinitializer
  %head = insertelement <8 x i1> undef, i1 true, i32 0
  %m = shufflevector <8 x i1> %head, <8 x i1> undef, <8 x i32> zeroinitializer
  %v = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> %va, <8 x i64> %vb, <8 x i1> %m, i32 %evl)
  ret <8 x i64> %v
}

declare <16 x i64> @llvm.vp.add.v16i64(<16 x i64>, <16 x i64>, <16 x i1>, i32)

define <16 x i64> @vadd_vv_v16i64(<16 x i64> %va, <16 x i64> %b, <16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v16i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v16, v0.t
; CHECK-NEXT:    ret
  %v = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> %va, <16 x i64> %b, <16 x i1> %m, i32 %evl)
  ret <16 x i64> %v
}

define <16 x i64> @vadd_vv_v16i64_unmasked(<16 x i64> %va, <16 x i64> %b, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vv_v16i64_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
; CHECK-NEXT:    vadd.vv v8, v8, v16
; CHECK-NEXT:    ret
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> %va, <16 x i64> %b, <16 x i1> %m, i32 %evl)
  ret <16 x i64> %v
}

define <16 x i64> @vadd_vx_v16i64(<16 x i64> %va, i64 %b, <16 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vadd_vx_v16i64:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    .cfi_def_cfa_offset 16
; RV32-NEXT:    sw a1, 12(sp)
; RV32-NEXT:    sw a0, 8(sp)
; RV32-NEXT:    vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT:    addi a0, sp, 8
; RV32-NEXT:    vlse64.v v16, (a0), zero
; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT:    vadd.vv v8, v8, v16, v0.t
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vx_v16i64:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT:    vadd.vx v8, v8, a0, v0.t
; RV64-NEXT:    ret
  %elt.head = insertelement <16 x i64> undef, i64 %b, i32 0
  %vb = shufflevector <16 x i64> %elt.head, <16 x i64> undef, <16 x i32> zeroinitializer
  %v = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> %va, <16 x i64> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i64> %v
}

define <16 x i64> @vadd_vx_v16i64_unmasked(<16 x i64> %va, i64 %b, i32 zeroext %evl) {
; RV32-LABEL: vadd_vx_v16i64_unmasked:
; RV32:       # %bb.0:
; RV32-NEXT:    addi sp, sp, -16
; RV32-NEXT:    .cfi_def_cfa_offset 16
; RV32-NEXT:    sw a1, 12(sp)
; RV32-NEXT:    sw a0, 8(sp)
; RV32-NEXT:    vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT:    addi a0, sp, 8
; RV32-NEXT:    vlse64.v v16, (a0), zero
; RV32-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
; RV32-NEXT:    vadd.vv v8, v8, v16
; RV32-NEXT:    addi sp, sp, 16
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vx_v16i64_unmasked:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT:    vadd.vx v8, v8, a0
; RV64-NEXT:    ret
  %elt.head = insertelement <16 x i64> undef, i64 %b, i32 0
  %vb = shufflevector <16 x i64> %elt.head, <16 x i64> undef, <16 x i32> zeroinitializer
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> %va, <16 x i64> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i64> %v
}

define <16 x i64> @vadd_vi_v16i64(<16 x i64> %va, <16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v16i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1, v0.t
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <16 x i64> %elt.head, <16 x i64> undef, <16 x i32> zeroinitializer
  %v = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> %va, <16 x i64> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i64> %v
}

define <16 x i64> @vadd_vi_v16i64_unmasked(<16 x i64> %va, i32 zeroext %evl) {
; CHECK-LABEL: vadd_vi_v16i64_unmasked:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
; CHECK-NEXT:    vadd.vi v8, v8, -1
; CHECK-NEXT:    ret
  %elt.head = insertelement <16 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <16 x i64> %elt.head, <16 x i64> undef, <16 x i32> zeroinitializer
  %head = insertelement <16 x i1> undef, i1 true, i32 0
  %m = shufflevector <16 x i1> %head, <16 x i1> undef, <16 x i32> zeroinitializer
  %v = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> %va, <16 x i64> %vb, <16 x i1> %m, i32 %evl)
  ret <16 x i64> %v
}

; Test that split-legalization works as expected.

declare <32 x i64> @llvm.vp.add.v32i64(<32 x i64>, <32 x i64>, <32 x i1>, i32)

define <32 x i64> @vadd_vx_v32i64(<32 x i64> %va, <32 x i1> %m, i32 zeroext %evl) {
; RV32-LABEL: vadd_vx_v32i64:
; RV32:       # %bb.0:
; RV32-NEXT:    vmv1r.v v1, v0
; RV32-NEXT:    li a1, 0
; RV32-NEXT:    vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT:    vslidedown.vi v0, v0, 2
; RV32-NEXT:    li a2, 32
; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, mu
; RV32-NEXT:    addi a2, a0, -16
; RV32-NEXT:    vmv.v.i v24, -1
; RV32-NEXT:    bltu a0, a2, .LBB107_2
; RV32-NEXT:  # %bb.1:
; RV32-NEXT:    mv a1, a2
; RV32-NEXT:  .LBB107_2:
; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
; RV32-NEXT:    li a1, 16
; RV32-NEXT:    vadd.vv v16, v16, v24, v0.t
; RV32-NEXT:    bltu a0, a1, .LBB107_4
; RV32-NEXT:  # %bb.3:
; RV32-NEXT:    li a0, 16
; RV32-NEXT:  .LBB107_4:
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
; RV32-NEXT:    vmv1r.v v0, v1
; RV32-NEXT:    vadd.vv v8, v8, v24, v0.t
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vx_v32i64:
; RV64:       # %bb.0:
; RV64-NEXT:    vmv1r.v v24, v0
; RV64-NEXT:    li a1, 0
; RV64-NEXT:    vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT:    addi a2, a0, -16
; RV64-NEXT:    vslidedown.vi v0, v0, 2
; RV64-NEXT:    bltu a0, a2, .LBB107_2
; RV64-NEXT:  # %bb.1:
; RV64-NEXT:    mv a1, a2
; RV64-NEXT:  .LBB107_2:
; RV64-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
; RV64-NEXT:    li a1, 16
; RV64-NEXT:    vadd.vi v16, v16, -1, v0.t
; RV64-NEXT:    bltu a0, a1, .LBB107_4
; RV64-NEXT:  # %bb.3:
; RV64-NEXT:    li a0, 16
; RV64-NEXT:  .LBB107_4:
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
; RV64-NEXT:    vmv1r.v v0, v24
; RV64-NEXT:    vadd.vi v8, v8, -1, v0.t
; RV64-NEXT:    ret
  %elt.head = insertelement <32 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <32 x i64> %elt.head, <32 x i64> undef, <32 x i32> zeroinitializer
  %v = call <32 x i64> @llvm.vp.add.v32i64(<32 x i64> %va, <32 x i64> %vb, <32 x i1> %m, i32 %evl)
  ret <32 x i64> %v
}

define <32 x i64> @vadd_vi_v32i64_unmasked(<32 x i64> %va, i32 zeroext %evl) {
; RV32-LABEL: vadd_vi_v32i64_unmasked:
; RV32:       # %bb.0:
; RV32-NEXT:    li a1, 0
; RV32-NEXT:    li a2, 32
; RV32-NEXT:    vsetvli zero, a2, e32, m8, ta, mu
; RV32-NEXT:    addi a2, a0, -16
; RV32-NEXT:    vmv.v.i v24, -1
; RV32-NEXT:    bltu a0, a2, .LBB108_2
; RV32-NEXT:  # %bb.1:
; RV32-NEXT:    mv a1, a2
; RV32-NEXT:  .LBB108_2:
; RV32-NEXT:    vsetvli zero, a1, e64, m8, ta, mu
; RV32-NEXT:    li a1, 16
; RV32-NEXT:    vadd.vv v16, v16, v24
; RV32-NEXT:    bltu a0, a1, .LBB108_4
; RV32-NEXT:  # %bb.3:
; RV32-NEXT:    li a0, 16
; RV32-NEXT:  .LBB108_4:
; RV32-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
; RV32-NEXT:    vadd.vv v8, v8, v24
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vi_v32i64_unmasked:
; RV64:       # %bb.0:
; RV64-NEXT:    addi a1, a0, -16
; RV64-NEXT:    li a2, 0
; RV64-NEXT:    bltu a0, a1, .LBB108_2
; RV64-NEXT:  # %bb.1:
; RV64-NEXT:    mv a2, a1
; RV64-NEXT:  .LBB108_2:
; RV64-NEXT:    vsetvli zero, a2, e64, m8, ta, mu
; RV64-NEXT:    li a1, 16
; RV64-NEXT:    vadd.vi v16, v16, -1
; RV64-NEXT:    bltu a0, a1, .LBB108_4
; RV64-NEXT:  # %bb.3:
; RV64-NEXT:    li a0, 16
; RV64-NEXT:  .LBB108_4:
; RV64-NEXT:    vsetvli zero, a0, e64, m8, ta, mu
; RV64-NEXT:    vadd.vi v8, v8, -1
; RV64-NEXT:    ret
  %elt.head = insertelement <32 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <32 x i64> %elt.head, <32 x i64> undef, <32 x i32> zeroinitializer
  %head = insertelement <32 x i1> undef, i1 true, i32 0
  %m = shufflevector <32 x i1> %head, <32 x i1> undef, <32 x i32> zeroinitializer
  %v = call <32 x i64> @llvm.vp.add.v32i64(<32 x i64> %va, <32 x i64> %vb, <32 x i1> %m, i32 %evl)
  ret <32 x i64> %v
}

; FIXME: We don't match vadd.vi on RV32.

define <32 x i64> @vadd_vx_v32i64_evl12(<32 x i64> %va, <32 x i1> %m) {
; RV32-LABEL: vadd_vx_v32i64_evl12:
; RV32:       # %bb.0:
; RV32-NEXT:    li a0, 32
; RV32-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
; RV32-NEXT:    vmv.v.i v16, -1
; RV32-NEXT:    vsetivli zero, 12, e64, m8, ta, mu
; RV32-NEXT:    vadd.vv v8, v8, v16, v0.t
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vx_v32i64_evl12:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetivli zero, 12, e64, m8, ta, mu
; RV64-NEXT:    vadd.vi v8, v8, -1, v0.t
; RV64-NEXT:    ret
  %elt.head = insertelement <32 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <32 x i64> %elt.head, <32 x i64> undef, <32 x i32> zeroinitializer
  %v = call <32 x i64> @llvm.vp.add.v32i64(<32 x i64> %va, <32 x i64> %vb, <32 x i1> %m, i32 12)
  ret <32 x i64> %v
}

define <32 x i64> @vadd_vx_v32i64_evl27(<32 x i64> %va, <32 x i1> %m) {
; RV32-LABEL: vadd_vx_v32i64_evl27:
; RV32:       # %bb.0:
; RV32-NEXT:    vsetivli zero, 2, e8, mf4, ta, mu
; RV32-NEXT:    vslidedown.vi v1, v0, 2
; RV32-NEXT:    li a0, 32
; RV32-NEXT:    vsetvli zero, a0, e32, m8, ta, mu
; RV32-NEXT:    vmv.v.i v24, -1
; RV32-NEXT:    vsetivli zero, 16, e64, m8, ta, mu
; RV32-NEXT:    vadd.vv v8, v8, v24, v0.t
; RV32-NEXT:    vsetivli zero, 11, e64, m8, ta, mu
; RV32-NEXT:    vmv1r.v v0, v1
; RV32-NEXT:    vadd.vv v16, v16, v24, v0.t
; RV32-NEXT:    ret
;
; RV64-LABEL: vadd_vx_v32i64_evl27:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetivli zero, 2, e8, mf4, ta, mu
; RV64-NEXT:    vslidedown.vi v24, v0, 2
; RV64-NEXT:    vsetivli zero, 16, e64, m8, ta, mu
; RV64-NEXT:    vadd.vi v8, v8, -1, v0.t
; RV64-NEXT:    vsetivli zero, 11, e64, m8, ta, mu
; RV64-NEXT:    vmv1r.v v0, v24
; RV64-NEXT:    vadd.vi v16, v16, -1, v0.t
; RV64-NEXT:    ret
  %elt.head = insertelement <32 x i64> undef, i64 -1, i32 0
  %vb = shufflevector <32 x i64> %elt.head, <32 x i64> undef, <32 x i32> zeroinitializer
  %v = call <32 x i64> @llvm.vp.add.v32i64(<32 x i64> %va, <32 x i64> %vb, <32 x i1> %m, i32 27)
  ret <32 x i64> %v
}