; 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 -riscv-v-fixed-length-vector-lmul-max=4 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,LMULMAX4
; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -riscv-v-fixed-length-vector-lmul-max=4 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,LMULMAX4
; RUN: llc -mtriple=riscv32 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -riscv-v-fixed-length-vector-lmul-max=1 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,LMULMAX1
; RUN: llc -mtriple=riscv64 -mattr=+experimental-v -riscv-v-vector-bits-min=128 -riscv-v-fixed-length-vector-lmul-max=1 -verify-machineinstrs < %s | FileCheck %s --check-prefixes=CHECK,LMULMAX1

define void @gather_const_v16i8(<16 x i8>* %x) {
; CHECK-LABEL: gather_const_v16i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, 12
; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
; CHECK-NEXT:    vlse8.v v8, (a1), zero
; CHECK-NEXT:    vse8.v v8, (a0)
; CHECK-NEXT:    ret
  %a = load <16 x i8>, <16 x i8>* %x
  %b = extractelement <16 x i8> %a, i32 12
  %c = insertelement <16 x i8> undef, i8 %b, i32 0
  %d = shufflevector <16 x i8> %c, <16 x i8> undef, <16 x i32> zeroinitializer
  store <16 x i8> %d, <16 x i8>* %x
  ret void
}

define void @gather_const_v8i16(<8 x i16>* %x) {
; CHECK-LABEL: gather_const_v8i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, 10
; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
; CHECK-NEXT:    vlse16.v v8, (a1), zero
; CHECK-NEXT:    vse16.v v8, (a0)
; CHECK-NEXT:    ret
  %a = load <8 x i16>, <8 x i16>* %x
  %b = extractelement <8 x i16> %a, i32 5
  %c = insertelement <8 x i16> undef, i16 %b, i32 0
  %d = shufflevector <8 x i16> %c, <8 x i16> undef, <8 x i32> zeroinitializer
  store <8 x i16> %d, <8 x i16>* %x
  ret void
}

define void @gather_const_v4i32(<4 x i32>* %x) {
; CHECK-LABEL: gather_const_v4i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, 12
; CHECK-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
; CHECK-NEXT:    vlse32.v v8, (a1), zero
; CHECK-NEXT:    vse32.v v8, (a0)
; CHECK-NEXT:    ret
  %a = load <4 x i32>, <4 x i32>* %x
  %b = extractelement <4 x i32> %a, i32 3
  %c = insertelement <4 x i32> undef, i32 %b, i32 0
  %d = shufflevector <4 x i32> %c, <4 x i32> undef, <4 x i32> zeroinitializer
  store <4 x i32> %d, <4 x i32>* %x
  ret void
}

define void @gather_const_v2i64(<2 x i64>* %x) {
; CHECK-LABEL: gather_const_v2i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a1, a0, 8
; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
; CHECK-NEXT:    vlse64.v v8, (a1), zero
; CHECK-NEXT:    vse64.v v8, (a0)
; CHECK-NEXT:    ret
  %a = load <2 x i64>, <2 x i64>* %x
  %b = extractelement <2 x i64> %a, i32 1
  %c = insertelement <2 x i64> undef, i64 %b, i32 0
  %d = shufflevector <2 x i64> %c, <2 x i64> undef, <2 x i32> zeroinitializer
  store <2 x i64> %d, <2 x i64>* %x
  ret void
}

define void @gather_const_v64i8(<64 x i8>* %x) {
; LMULMAX4-LABEL: gather_const_v64i8:
; LMULMAX4:       # %bb.0:
; LMULMAX4-NEXT:    addi a1, a0, 32
; LMULMAX4-NEXT:    li a2, 64
; LMULMAX4-NEXT:    vsetvli zero, a2, e8, m4, ta, mu
; LMULMAX4-NEXT:    vlse8.v v8, (a1), zero
; LMULMAX4-NEXT:    vse8.v v8, (a0)
; LMULMAX4-NEXT:    ret
;
; LMULMAX1-LABEL: gather_const_v64i8:
; LMULMAX1:       # %bb.0:
; LMULMAX1-NEXT:    addi a1, a0, 32
; LMULMAX1-NEXT:    vsetivli zero, 16, e8, m1, ta, mu
; LMULMAX1-NEXT:    vlse8.v v8, (a1), zero
; LMULMAX1-NEXT:    addi a2, a0, 16
; LMULMAX1-NEXT:    addi a3, a0, 48
; LMULMAX1-NEXT:    vse8.v v8, (a1)
; LMULMAX1-NEXT:    vse8.v v8, (a3)
; LMULMAX1-NEXT:    vse8.v v8, (a0)
; LMULMAX1-NEXT:    vse8.v v8, (a2)
; LMULMAX1-NEXT:    ret
  %a = load <64 x i8>, <64 x i8>* %x
  %b = extractelement <64 x i8> %a, i32 32
  %c = insertelement <64 x i8> undef, i8 %b, i32 0
  %d = shufflevector <64 x i8> %c, <64 x i8> undef, <64 x i32> zeroinitializer
  store <64 x i8> %d, <64 x i8>* %x
  ret void
}

define void @gather_const_v16i16(<32 x i16>* %x) {
; LMULMAX4-LABEL: gather_const_v16i16:
; LMULMAX4:       # %bb.0:
; LMULMAX4-NEXT:    addi a1, a0, 50
; LMULMAX4-NEXT:    li a2, 32
; LMULMAX4-NEXT:    vsetvli zero, a2, e16, m4, ta, mu
; LMULMAX4-NEXT:    vlse16.v v8, (a1), zero
; LMULMAX4-NEXT:    vse16.v v8, (a0)
; LMULMAX4-NEXT:    ret
;
; LMULMAX1-LABEL: gather_const_v16i16:
; LMULMAX1:       # %bb.0:
; LMULMAX1-NEXT:    addi a1, a0, 50
; LMULMAX1-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
; LMULMAX1-NEXT:    vlse16.v v8, (a1), zero
; LMULMAX1-NEXT:    addi a1, a0, 16
; LMULMAX1-NEXT:    addi a2, a0, 48
; LMULMAX1-NEXT:    addi a3, a0, 32
; LMULMAX1-NEXT:    vse16.v v8, (a3)
; LMULMAX1-NEXT:    vse16.v v8, (a2)
; LMULMAX1-NEXT:    vse16.v v8, (a0)
; LMULMAX1-NEXT:    vse16.v v8, (a1)
; LMULMAX1-NEXT:    ret
  %a = load <32 x i16>, <32 x i16>* %x
  %b = extractelement <32 x i16> %a, i32 25
  %c = insertelement <32 x i16> undef, i16 %b, i32 0
  %d = shufflevector <32 x i16> %c, <32 x i16> undef, <32 x i32> zeroinitializer
  store <32 x i16> %d, <32 x i16>* %x
  ret void
}

define void @gather_const_v16i32(<16 x i32>* %x) {
; LMULMAX4-LABEL: gather_const_v16i32:
; LMULMAX4:       # %bb.0:
; LMULMAX4-NEXT:    addi a1, a0, 36
; LMULMAX4-NEXT:    vsetivli zero, 16, e32, m4, ta, mu
; LMULMAX4-NEXT:    vlse32.v v8, (a1), zero
; LMULMAX4-NEXT:    vse32.v v8, (a0)
; LMULMAX4-NEXT:    ret
;
; LMULMAX1-LABEL: gather_const_v16i32:
; LMULMAX1:       # %bb.0:
; LMULMAX1-NEXT:    addi a1, a0, 36
; LMULMAX1-NEXT:    vsetivli zero, 4, e32, m1, ta, mu
; LMULMAX1-NEXT:    vlse32.v v8, (a1), zero
; LMULMAX1-NEXT:    addi a1, a0, 16
; LMULMAX1-NEXT:    addi a2, a0, 48
; LMULMAX1-NEXT:    addi a3, a0, 32
; LMULMAX1-NEXT:    vse32.v v8, (a3)
; LMULMAX1-NEXT:    vse32.v v8, (a2)
; LMULMAX1-NEXT:    vse32.v v8, (a0)
; LMULMAX1-NEXT:    vse32.v v8, (a1)
; LMULMAX1-NEXT:    ret
  %a = load <16 x i32>, <16 x i32>* %x
  %b = extractelement <16 x i32> %a, i32 9
  %c = insertelement <16 x i32> undef, i32 %b, i32 0
  %d = shufflevector <16 x i32> %c, <16 x i32> undef, <16 x i32> zeroinitializer
  store <16 x i32> %d, <16 x i32>* %x
  ret void
}

define void @gather_const_v8i64(<8 x i64>* %x) {
; LMULMAX4-LABEL: gather_const_v8i64:
; LMULMAX4:       # %bb.0:
; LMULMAX4-NEXT:    addi a1, a0, 24
; LMULMAX4-NEXT:    vsetivli zero, 8, e64, m4, ta, mu
; LMULMAX4-NEXT:    vlse64.v v8, (a1), zero
; LMULMAX4-NEXT:    vse64.v v8, (a0)
; LMULMAX4-NEXT:    ret
;
; LMULMAX1-LABEL: gather_const_v8i64:
; LMULMAX1:       # %bb.0:
; LMULMAX1-NEXT:    addi a1, a0, 24
; LMULMAX1-NEXT:    vsetivli zero, 2, e64, m1, ta, mu
; LMULMAX1-NEXT:    vlse64.v v8, (a1), zero
; LMULMAX1-NEXT:    addi a1, a0, 16
; LMULMAX1-NEXT:    addi a2, a0, 48
; LMULMAX1-NEXT:    addi a3, a0, 32
; LMULMAX1-NEXT:    vse64.v v8, (a3)
; LMULMAX1-NEXT:    vse64.v v8, (a2)
; LMULMAX1-NEXT:    vse64.v v8, (a0)
; LMULMAX1-NEXT:    vse64.v v8, (a1)
; LMULMAX1-NEXT:    ret
  %a = load <8 x i64>, <8 x i64>* %x
  %b = extractelement <8 x i64> %a, i32 3
  %c = insertelement <8 x i64> undef, i64 %b, i32 0
  %d = shufflevector <8 x i64> %c, <8 x i64> undef, <8 x i32> zeroinitializer
  store <8 x i64> %d, <8 x i64>* %x
  ret void
}

define void @splat_concat_low(<4 x i16>* %x, <4 x i16>* %y, <8 x i16>* %z) {
; CHECK-LABEL: splat_concat_low:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a0, a0, 2
; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
; CHECK-NEXT:    vlse16.v v8, (a0), zero
; CHECK-NEXT:    vse16.v v8, (a2)
; CHECK-NEXT:    ret
  %a = load <4 x i16>, <4 x i16>* %x
  %b = load <4 x i16>, <4 x i16>* %y
  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  %d = shufflevector <8 x i16> %c, <8 x i16> undef, <8 x i32> <i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
  store <8 x i16> %d, <8 x i16>* %z
  ret void
}

define void @splat_concat_high(<4 x i16>* %x, <4 x i16>* %y, <8 x i16>* %z) {
; CHECK-LABEL: splat_concat_high:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a0, a1, 2
; CHECK-NEXT:    vsetivli zero, 8, e16, m1, ta, mu
; CHECK-NEXT:    vlse16.v v8, (a0), zero
; CHECK-NEXT:    vse16.v v8, (a2)
; CHECK-NEXT:    ret
  %a = load <4 x i16>, <4 x i16>* %x
  %b = load <4 x i16>, <4 x i16>* %y
  %c = shufflevector <4 x i16> %a, <4 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
  %d = shufflevector <8 x i16> %c, <8 x i16> undef, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
  store <8 x i16> %d, <8 x i16>* %z
  ret void
}