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

define i1 @extractelt_nxv1i1(<vscale x 1 x i8>* %x, i64 %idx) nounwind {
; CHECK-LABEL: extractelt_nxv1i1:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a2, zero, e8, mf8, ta, ma
; CHECK-NEXT:    vle8.v v8, (a0)
; CHECK-NEXT:    vmseq.vi v0, v8, 0
; CHECK-NEXT:    vmv.v.i v8, 0
; CHECK-NEXT:    vmerge.vim v8, v8, 1, v0
; CHECK-NEXT:    vslidedown.vx v8, v8, a1
; CHECK-NEXT:    vmv.x.s a0, v8
; CHECK-NEXT:    ret
  %a = load <vscale x 1 x i8>, <vscale x 1 x i8>* %x
  %b = icmp eq <vscale x 1 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 1 x i1> %b, i64 %idx
  ret i1 %c
}

define i1 @extractelt_nxv2i1(<vscale x 2 x i8>* %x, i64 %idx) nounwind {
; CHECK-LABEL: extractelt_nxv2i1:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a2, zero, e8, mf4, ta, ma
; CHECK-NEXT:    vle8.v v8, (a0)
; CHECK-NEXT:    vmseq.vi v0, v8, 0
; CHECK-NEXT:    vmv.v.i v8, 0
; CHECK-NEXT:    vmerge.vim v8, v8, 1, v0
; CHECK-NEXT:    vslidedown.vx v8, v8, a1
; CHECK-NEXT:    vmv.x.s a0, v8
; CHECK-NEXT:    ret
  %a = load <vscale x 2 x i8>, <vscale x 2 x i8>* %x
  %b = icmp eq <vscale x 2 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 2 x i1> %b, i64 %idx
  ret i1 %c
}

define i1 @extractelt_nxv4i1(<vscale x 4 x i8>* %x, i64 %idx) nounwind {
; CHECK-LABEL: extractelt_nxv4i1:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a2, zero, e8, mf2, ta, ma
; CHECK-NEXT:    vle8.v v8, (a0)
; CHECK-NEXT:    vmseq.vi v0, v8, 0
; CHECK-NEXT:    vmv.v.i v8, 0
; CHECK-NEXT:    vmerge.vim v8, v8, 1, v0
; CHECK-NEXT:    vslidedown.vx v8, v8, a1
; CHECK-NEXT:    vmv.x.s a0, v8
; CHECK-NEXT:    ret
  %a = load <vscale x 4 x i8>, <vscale x 4 x i8>* %x
  %b = icmp eq <vscale x 4 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 4 x i1> %b, i64 %idx
  ret i1 %c
}

define i1 @extractelt_nxv8i1(<vscale x 8 x i8>* %x, i64 %idx) nounwind {
; CHECK-LABEL: extractelt_nxv8i1:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vl1r.v v8, (a0)
; CHECK-NEXT:    vsetvli a0, zero, e8, m1, ta, ma
; CHECK-NEXT:    vmseq.vi v0, v8, 0
; CHECK-NEXT:    vmv.v.i v8, 0
; CHECK-NEXT:    vmerge.vim v8, v8, 1, v0
; CHECK-NEXT:    vslidedown.vx v8, v8, a1
; CHECK-NEXT:    vmv.x.s a0, v8
; CHECK-NEXT:    ret
  %a = load <vscale x 8 x i8>, <vscale x 8 x i8>* %x
  %b = icmp eq <vscale x 8 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 8 x i1> %b, i64 %idx
  ret i1 %c
}

define i1 @extractelt_nxv16i1(<vscale x 16 x i8>* %x, i64 %idx) nounwind {
; CHECK-LABEL: extractelt_nxv16i1:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vl2r.v v8, (a0)
; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, ma
; CHECK-NEXT:    vmseq.vi v0, v8, 0
; CHECK-NEXT:    vmv.v.i v8, 0
; CHECK-NEXT:    vmerge.vim v8, v8, 1, v0
; CHECK-NEXT:    vsetivli zero, 1, e8, m2, ta, ma
; CHECK-NEXT:    vslidedown.vx v8, v8, a1
; CHECK-NEXT:    vmv.x.s a0, v8
; CHECK-NEXT:    ret
  %a = load <vscale x 16 x i8>, <vscale x 16 x i8>* %x
  %b = icmp eq <vscale x 16 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 16 x i1> %b, i64 %idx
  ret i1 %c
}

define i1 @extractelt_nxv32i1(<vscale x 32 x i8>* %x, i64 %idx) nounwind {
; CHECK-LABEL: extractelt_nxv32i1:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vl4r.v v8, (a0)
; CHECK-NEXT:    vsetvli a0, zero, e8, m4, ta, ma
; CHECK-NEXT:    vmseq.vi v0, v8, 0
; CHECK-NEXT:    vmv.v.i v8, 0
; CHECK-NEXT:    vmerge.vim v8, v8, 1, v0
; CHECK-NEXT:    vsetivli zero, 1, e8, m4, ta, ma
; CHECK-NEXT:    vslidedown.vx v8, v8, a1
; CHECK-NEXT:    vmv.x.s a0, v8
; CHECK-NEXT:    ret
  %a = load <vscale x 32 x i8>, <vscale x 32 x i8>* %x
  %b = icmp eq <vscale x 32 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 32 x i1> %b, i64 %idx
  ret i1 %c
}

define i1 @extractelt_nxv64i1(<vscale x 64 x i8>* %x, i64 %idx) nounwind {
; CHECK-LABEL: extractelt_nxv64i1:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vl8r.v v8, (a0)
; CHECK-NEXT:    vsetvli a0, zero, e8, m8, ta, ma
; CHECK-NEXT:    vmseq.vi v0, v8, 0
; CHECK-NEXT:    vmv.v.i v8, 0
; CHECK-NEXT:    vmerge.vim v8, v8, 1, v0
; CHECK-NEXT:    vsetivli zero, 1, e8, m8, ta, ma
; CHECK-NEXT:    vslidedown.vx v8, v8, a1
; CHECK-NEXT:    vmv.x.s a0, v8
; CHECK-NEXT:    ret
  %a = load <vscale x 64 x i8>, <vscale x 64 x i8>* %x
  %b = icmp eq <vscale x 64 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 64 x i1> %b, i64 %idx
  ret i1 %c
}

define i1 @extractelt_nxv128i1(<vscale x 128 x i8>* %x, i64 %idx) nounwind {
; RV32-LABEL: extractelt_nxv128i1:
; RV32:       # %bb.0:
; RV32-NEXT:    csrr a2, vlenb
; RV32-NEXT:    slli a3, a2, 4
; RV32-NEXT:    addi a3, a3, -1
; RV32-NEXT:    bltu a1, a3, .LBB7_2
; RV32-NEXT:  # %bb.1:
; RV32-NEXT:    mv a1, a3
; RV32-NEXT:  .LBB7_2:
; RV32-NEXT:    addi sp, sp, -80
; RV32-NEXT:    sw ra, 76(sp) # 4-byte Folded Spill
; RV32-NEXT:    sw s0, 72(sp) # 4-byte Folded Spill
; RV32-NEXT:    addi s0, sp, 80
; RV32-NEXT:    csrr a3, vlenb
; RV32-NEXT:    slli a3, a3, 4
; RV32-NEXT:    sub sp, sp, a3
; RV32-NEXT:    andi sp, sp, -64
; RV32-NEXT:    addi a3, sp, 64
; RV32-NEXT:    slli a2, a2, 3
; RV32-NEXT:    add a4, a0, a2
; RV32-NEXT:    vl8r.v v16, (a4)
; RV32-NEXT:    vl8r.v v24, (a0)
; RV32-NEXT:    add a1, a3, a1
; RV32-NEXT:    vsetvli a0, zero, e8, m8, ta, ma
; RV32-NEXT:    vmseq.vi v8, v16, 0
; RV32-NEXT:    vmseq.vi v0, v24, 0
; RV32-NEXT:    vmv.v.i v16, 0
; RV32-NEXT:    vmerge.vim v24, v16, 1, v0
; RV32-NEXT:    vs8r.v v24, (a3)
; RV32-NEXT:    add a2, a3, a2
; RV32-NEXT:    vmv1r.v v0, v8
; RV32-NEXT:    vmerge.vim v8, v16, 1, v0
; RV32-NEXT:    vs8r.v v8, (a2)
; RV32-NEXT:    lbu a0, 0(a1)
; RV32-NEXT:    addi sp, s0, -80
; RV32-NEXT:    lw ra, 76(sp) # 4-byte Folded Reload
; RV32-NEXT:    lw s0, 72(sp) # 4-byte Folded Reload
; RV32-NEXT:    addi sp, sp, 80
; RV32-NEXT:    ret
;
; RV64-LABEL: extractelt_nxv128i1:
; RV64:       # %bb.0:
; RV64-NEXT:    csrr a2, vlenb
; RV64-NEXT:    slli a3, a2, 4
; RV64-NEXT:    addi a3, a3, -1
; RV64-NEXT:    bltu a1, a3, .LBB7_2
; RV64-NEXT:  # %bb.1:
; RV64-NEXT:    mv a1, a3
; RV64-NEXT:  .LBB7_2:
; RV64-NEXT:    addi sp, sp, -80
; RV64-NEXT:    sd ra, 72(sp) # 8-byte Folded Spill
; RV64-NEXT:    sd s0, 64(sp) # 8-byte Folded Spill
; RV64-NEXT:    addi s0, sp, 80
; RV64-NEXT:    csrr a3, vlenb
; RV64-NEXT:    slli a3, a3, 4
; RV64-NEXT:    sub sp, sp, a3
; RV64-NEXT:    andi sp, sp, -64
; RV64-NEXT:    addi a3, sp, 64
; RV64-NEXT:    slli a2, a2, 3
; RV64-NEXT:    add a4, a0, a2
; RV64-NEXT:    vl8r.v v16, (a4)
; RV64-NEXT:    vl8r.v v24, (a0)
; RV64-NEXT:    add a1, a3, a1
; RV64-NEXT:    vsetvli a0, zero, e8, m8, ta, ma
; RV64-NEXT:    vmseq.vi v8, v16, 0
; RV64-NEXT:    vmseq.vi v0, v24, 0
; RV64-NEXT:    vmv.v.i v16, 0
; RV64-NEXT:    vmerge.vim v24, v16, 1, v0
; RV64-NEXT:    vs8r.v v24, (a3)
; RV64-NEXT:    add a2, a3, a2
; RV64-NEXT:    vmv1r.v v0, v8
; RV64-NEXT:    vmerge.vim v8, v16, 1, v0
; RV64-NEXT:    vs8r.v v8, (a2)
; RV64-NEXT:    lbu a0, 0(a1)
; RV64-NEXT:    addi sp, s0, -80
; RV64-NEXT:    ld ra, 72(sp) # 8-byte Folded Reload
; RV64-NEXT:    ld s0, 64(sp) # 8-byte Folded Reload
; RV64-NEXT:    addi sp, sp, 80
; RV64-NEXT:    ret
  %a = load <vscale x 128 x i8>, <vscale x 128 x i8>* %x
  %b = icmp eq <vscale x 128 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 128 x i1> %b, i64 %idx
  ret i1 %c
}

define i1 @extractelt_nxv1i1_idx0(<vscale x 1 x i8>* %x) nounwind {
; CHECK-LABEL: extractelt_nxv1i1_idx0:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, mf8, ta, ma
; CHECK-NEXT:    vle8.v v8, (a0)
; CHECK-NEXT:    vmseq.vi v8, v8, 0
; CHECK-NEXT:    vfirst.m a0, v8
; CHECK-NEXT:    seqz a0, a0
; CHECK-NEXT:    ret
  %a = load <vscale x 1 x i8>, <vscale x 1 x i8>* %x
  %b = icmp eq <vscale x 1 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 1 x i1> %b, i64 0
  ret i1 %c
}

define i1 @extractelt_nxv2i1_idx0(<vscale x 2 x i8>* %x) nounwind {
; CHECK-LABEL: extractelt_nxv2i1_idx0:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, mf4, ta, ma
; CHECK-NEXT:    vle8.v v8, (a0)
; CHECK-NEXT:    vmseq.vi v8, v8, 0
; CHECK-NEXT:    vfirst.m a0, v8
; CHECK-NEXT:    seqz a0, a0
; CHECK-NEXT:    ret
  %a = load <vscale x 2 x i8>, <vscale x 2 x i8>* %x
  %b = icmp eq <vscale x 2 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 2 x i1> %b, i64 0
  ret i1 %c
}

define i1 @extractelt_nxv4i1_idx0(<vscale x 4 x i8>* %x) nounwind {
; CHECK-LABEL: extractelt_nxv4i1_idx0:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, mf2, ta, ma
; CHECK-NEXT:    vle8.v v8, (a0)
; CHECK-NEXT:    vmseq.vi v8, v8, 0
; CHECK-NEXT:    vfirst.m a0, v8
; CHECK-NEXT:    seqz a0, a0
; CHECK-NEXT:    ret
  %a = load <vscale x 4 x i8>, <vscale x 4 x i8>* %x
  %b = icmp eq <vscale x 4 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 4 x i1> %b, i64 0
  ret i1 %c
}

define i1 @extractelt_nxv8i1_idx0(<vscale x 8 x i8>* %x) nounwind {
; CHECK-LABEL: extractelt_nxv8i1_idx0:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vl1r.v v8, (a0)
; CHECK-NEXT:    vsetvli a0, zero, e8, m1, ta, ma
; CHECK-NEXT:    vmseq.vi v8, v8, 0
; CHECK-NEXT:    vfirst.m a0, v8
; CHECK-NEXT:    seqz a0, a0
; CHECK-NEXT:    ret
  %a = load <vscale x 8 x i8>, <vscale x 8 x i8>* %x
  %b = icmp eq <vscale x 8 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 8 x i1> %b, i64 0
  ret i1 %c
}

define i1 @extractelt_nxv16i1_idx0(<vscale x 16 x i8>* %x) nounwind {
; CHECK-LABEL: extractelt_nxv16i1_idx0:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vl2r.v v8, (a0)
; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, ma
; CHECK-NEXT:    vmseq.vi v10, v8, 0
; CHECK-NEXT:    vfirst.m a0, v10
; CHECK-NEXT:    seqz a0, a0
; CHECK-NEXT:    ret
  %a = load <vscale x 16 x i8>, <vscale x 16 x i8>* %x
  %b = icmp eq <vscale x 16 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 16 x i1> %b, i64 0
  ret i1 %c
}

define i1 @extractelt_nxv32i1_idx0(<vscale x 32 x i8>* %x) nounwind {
; CHECK-LABEL: extractelt_nxv32i1_idx0:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vl4r.v v8, (a0)
; CHECK-NEXT:    vsetvli a0, zero, e8, m4, ta, ma
; CHECK-NEXT:    vmseq.vi v12, v8, 0
; CHECK-NEXT:    vfirst.m a0, v12
; CHECK-NEXT:    seqz a0, a0
; CHECK-NEXT:    ret
  %a = load <vscale x 32 x i8>, <vscale x 32 x i8>* %x
  %b = icmp eq <vscale x 32 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 32 x i1> %b, i64 0
  ret i1 %c
}

define i1 @extractelt_nxv64i1_idx0(<vscale x 64 x i8>* %x) nounwind {
; CHECK-LABEL: extractelt_nxv64i1_idx0:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vl8r.v v8, (a0)
; CHECK-NEXT:    vsetvli a0, zero, e8, m8, ta, ma
; CHECK-NEXT:    vmseq.vi v16, v8, 0
; CHECK-NEXT:    vfirst.m a0, v16
; CHECK-NEXT:    seqz a0, a0
; CHECK-NEXT:    ret
  %a = load <vscale x 64 x i8>, <vscale x 64 x i8>* %x
  %b = icmp eq <vscale x 64 x i8> %a, zeroinitializer
  %c = extractelement <vscale x 64 x i1> %b, i64 0
  ret i1 %c
}