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

; Integers

define {<vscale x 16 x i1>, <vscale x 16 x i1>} @vector_deinterleave_load_nxv16i1_nxv32i1(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv16i1_nxv32i1:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m4, ta, ma
; CHECK-NEXT:    vlm.v v8, (a0)
; CHECK-NEXT:    csrr a0, vlenb
; CHECK-NEXT:    srli a0, a0, 2
; CHECK-NEXT:    vsetvli a1, zero, e8, mf2, ta, ma
; CHECK-NEXT:    vslidedown.vx v0, v8, a0
; CHECK-NEXT:    vsetvli a0, zero, e8, m2, ta, ma
; CHECK-NEXT:    vmv.v.i v12, 0
; CHECK-NEXT:    vmerge.vim v10, v12, 1, v0
; CHECK-NEXT:    vmv1r.v v0, v8
; CHECK-NEXT:    vmerge.vim v8, v12, 1, v0
; CHECK-NEXT:    vnsrl.wi v12, v8, 0
; CHECK-NEXT:    vnsrl.wi v14, v8, 8
; CHECK-NEXT:    vmsne.vi v0, v12, 0
; CHECK-NEXT:    vmsne.vi v8, v14, 0
; CHECK-NEXT:    ret
  %vec = load <vscale x 32 x i1>, ptr %p
  %deinterleaved.results = call {<vscale x 16 x i1>, <vscale x 16 x i1>} @llvm.vector.deinterleave2.nxv32i1(<vscale x 32 x i1> %vec)
  %t0 = extractvalue { <vscale x 16 x i1>, <vscale x 16 x i1> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 16 x i1>, <vscale x 16 x i1> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 16 x i1>, <vscale x 16 x i1> } poison, <vscale x 16 x i1> %t0, 0
  %res1 = insertvalue { <vscale x 16 x i1>, <vscale x 16 x i1> } %res0, <vscale x 16 x i1> %t1, 1
  ret {<vscale x 16 x i1>, <vscale x 16 x i1>} %res1
}

define {<vscale x 16 x i8>, <vscale x 16 x i8>} @vector_deinterleave_load_nxv16i8_nxv32i8(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv16i8_nxv32i8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m2, ta, ma
; CHECK-NEXT:    vlseg2e8.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 32 x i8>, ptr %p
  %deinterleaved.results = call {<vscale x 16 x i8>, <vscale x 16 x i8>} @llvm.vector.deinterleave2.nxv32i8(<vscale x 32 x i8> %vec)
  %t0 = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } poison, <vscale x 16 x i8> %t0, 0
  %res1 = insertvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } %res0, <vscale x 16 x i8> %t1, 1
  ret {<vscale x 16 x i8>, <vscale x 16 x i8>} %res1
}

define <vscale x 16 x i8> @vector_deinterleave_load_nxv16i8_nxv32i8_oneactive(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv16i8_nxv32i8_oneactive:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m2, ta, ma
; CHECK-NEXT:    vlseg2e8.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 32 x i8>, ptr %p
  %deinterleaved.results = call {<vscale x 16 x i8>, <vscale x 16 x i8>} @llvm.vector.deinterleave2.nxv32i8(<vscale x 32 x i8> %vec)
  %t0 = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } %deinterleaved.results, 0
  ret <vscale x 16 x i8> %t0
}

define <vscale x 16 x i8> @vector_deinterleave_load_nxv16i8_nxv32i8_oneactive2(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv16i8_nxv32i8_oneactive2:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m2, ta, ma
; CHECK-NEXT:    vlseg2e8.v v6, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 32 x i8>, ptr %p
  %deinterleaved.results = call {<vscale x 16 x i8>, <vscale x 16 x i8>} @llvm.vector.deinterleave2.nxv32i8(<vscale x 32 x i8> %vec)
  %t1 = extractvalue { <vscale x 16 x i8>, <vscale x 16 x i8> } %deinterleaved.results, 1
  ret <vscale x 16 x i8> %t1
}

; Shouldn't be lowered to vlseg because it's unaligned
define {<vscale x 8 x i16>, <vscale x 8 x i16>} @vector_deinterleave_load_nxv8i16_nxv16i16_align1(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv8i16_nxv16i16_align1:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vl4r.v v12, (a0)
; CHECK-NEXT:    vsetvli a0, zero, e16, m2, ta, ma
; CHECK-NEXT:    vnsrl.wi v8, v12, 0
; CHECK-NEXT:    vnsrl.wi v10, v12, 16
; CHECK-NEXT:    ret
  %vec = load <vscale x 16 x i16>, ptr %p, align 1
  %deinterleaved.results = call {<vscale x 8 x i16>, <vscale x 8 x i16>} @llvm.vector.deinterleave2.nxv16i16(<vscale x 16 x i16> %vec)
  %t0 = extractvalue { <vscale x 8 x i16>, <vscale x 8 x i16> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 8 x i16>, <vscale x 8 x i16> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 8 x i16>, <vscale x 8 x i16> } poison, <vscale x 8 x i16> %t0, 0
  %res1 = insertvalue { <vscale x 8 x i16>, <vscale x 8 x i16> } %res0, <vscale x 8 x i16> %t1, 1
  ret {<vscale x 8 x i16>, <vscale x 8 x i16>} %res1
}

define {<vscale x 8 x i16>, <vscale x 8 x i16>} @vector_deinterleave_load_nxv8i16_nxv16i16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv8i16_nxv16i16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e16, m2, ta, ma
; CHECK-NEXT:    vlseg2e16.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 16 x i16>, ptr %p
  %deinterleaved.results = call {<vscale x 8 x i16>, <vscale x 8 x i16>} @llvm.vector.deinterleave2.nxv16i16(<vscale x 16 x i16> %vec)
  %t0 = extractvalue { <vscale x 8 x i16>, <vscale x 8 x i16> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 8 x i16>, <vscale x 8 x i16> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 8 x i16>, <vscale x 8 x i16> } poison, <vscale x 8 x i16> %t0, 0
  %res1 = insertvalue { <vscale x 8 x i16>, <vscale x 8 x i16> } %res0, <vscale x 8 x i16> %t1, 1
  ret {<vscale x 8 x i16>, <vscale x 8 x i16>} %res1
}

define {<vscale x 4 x i32>, <vscale x 4 x i32>} @vector_deinterleave_load_nxv4i32_nxvv8i32(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv4i32_nxvv8i32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e32, m2, ta, ma
; CHECK-NEXT:    vlseg2e32.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 8 x i32>, ptr %p
  %deinterleaved.results = call {<vscale x 4 x i32>, <vscale x 4 x i32>} @llvm.vector.deinterleave2.nxv8i32(<vscale x 8 x i32> %vec)
  %t0 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } poison, <vscale x 4 x i32> %t0, 0
  %res1 = insertvalue { <vscale x 4 x i32>, <vscale x 4 x i32> } %res0, <vscale x 4 x i32> %t1, 1
  ret {<vscale x 4 x i32>, <vscale x 4 x i32>} %res1
}

define {<vscale x 2 x i64>, <vscale x 2 x i64>} @vector_deinterleave_load_nxv2i64_nxv4i64(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv2i64_nxv4i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e64, m2, ta, ma
; CHECK-NEXT:    vlseg2e64.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 4 x i64>, ptr %p
  %deinterleaved.results = call {<vscale x 2 x i64>, <vscale x 2 x i64>} @llvm.vector.deinterleave2.nxv4i64(<vscale x 4 x i64> %vec)
  %t0 = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } poison, <vscale x 2 x i64> %t0, 0
  %res1 = insertvalue { <vscale x 2 x i64>, <vscale x 2 x i64> } %res0, <vscale x 2 x i64> %t1, 1
  ret {<vscale x 2 x i64>, <vscale x 2 x i64>} %res1
}

define {<vscale x 4 x i64>, <vscale x 4 x i64>} @vector_deinterleave_load_nxv4i64_nxv8i64(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv4i64_nxv8i64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e64, m4, ta, ma
; CHECK-NEXT:    vlseg2e64.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 8 x i64>, ptr %p
  %deinterleaved.results = call {<vscale x 4 x i64>, <vscale x 4 x i64>} @llvm.vector.deinterleave2.nxv8i64(<vscale x 8 x i64> %vec)
  %t0 = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } poison, <vscale x 4 x i64> %t0, 0
  %res1 = insertvalue { <vscale x 4 x i64>, <vscale x 4 x i64> } %res0, <vscale x 4 x i64> %t1, 1
  ret {<vscale x 4 x i64>, <vscale x 4 x i64>} %res1
}

; This shouldn't be lowered to a vlseg because EMUL * NFIELDS >= 8
define {<vscale x 8 x i64>, <vscale x 8 x i64>} @vector_deinterleave_load_nxv8i64_nxv16i64(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv8i64_nxv16i64:
; 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, 4
; CHECK-NEXT:    sub sp, sp, a1
; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 16 * vlenb
; CHECK-NEXT:    li a1, 85
; CHECK-NEXT:    vsetvli a2, zero, e8, mf8, ta, ma
; CHECK-NEXT:    vmv.v.x v16, a1
; CHECK-NEXT:    csrr a1, vlenb
; CHECK-NEXT:    vl8re64.v v24, (a0)
; CHECK-NEXT:    slli a1, a1, 3
; CHECK-NEXT:    add a0, a0, a1
; CHECK-NEXT:    li a1, 170
; CHECK-NEXT:    vl8re64.v v0, (a0)
; CHECK-NEXT:    vmv.v.x v17, a1
; CHECK-NEXT:    vsetvli a0, zero, e64, m8, ta, ma
; CHECK-NEXT:    vcompress.vm v8, v24, v16
; CHECK-NEXT:    vmv1r.v v12, v16
; CHECK-NEXT:    vmv1r.v v13, v17
; CHECK-NEXT:    vcompress.vm v16, v24, v13
; CHECK-NEXT:    vcompress.vm v24, v0, v12
; CHECK-NEXT:    addi a0, sp, 16
; CHECK-NEXT:    vs8r.v v24, (a0) # vscale x 64-byte Folded Spill
; CHECK-NEXT:    vcompress.vm v24, v0, v13
; 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:    vs8r.v v24, (a0) # vscale x 64-byte Folded Spill
; CHECK-NEXT:    addi a0, sp, 16
; CHECK-NEXT:    vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
; CHECK-NEXT:    vmv4r.v v12, v24
; 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:    vl8r.v v24, (a0) # vscale x 64-byte Folded Reload
; CHECK-NEXT:    vmv4r.v v20, v24
; CHECK-NEXT:    csrr a0, vlenb
; CHECK-NEXT:    slli a0, a0, 4
; CHECK-NEXT:    add sp, sp, a0
; CHECK-NEXT:    .cfi_def_cfa sp, 16
; CHECK-NEXT:    addi sp, sp, 16
; CHECK-NEXT:    .cfi_def_cfa_offset 0
; CHECK-NEXT:    ret
  %vec = load <vscale x 16 x i64>, ptr %p
  %deinterleaved.results = call {<vscale x 8 x i64>, <vscale x 8 x i64>} @llvm.vector.deinterleave2.nxv16i64(<vscale x 16 x i64> %vec)
  %t0 = extractvalue { <vscale x 8 x i64>, <vscale x 8 x i64> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 8 x i64>, <vscale x 8 x i64> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 8 x i64>, <vscale x 8 x i64> } poison, <vscale x 8 x i64> %t0, 0
  %res1 = insertvalue { <vscale x 8 x i64>, <vscale x 8 x i64> } %res0, <vscale x 8 x i64> %t1, 1
  ret {<vscale x 8 x i64>, <vscale x 8 x i64>} %res1
}

; Floats

define {<vscale x 2 x bfloat>, <vscale x 2 x bfloat>} @vector_deinterleave_load_nxv2bf16_nxv4bf16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv2bf16_nxv4bf16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e16, mf2, ta, ma
; CHECK-NEXT:    vlseg2e16.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 4 x bfloat>, ptr %p
  %deinterleaved.results = call {<vscale x 2 x bfloat>, <vscale x 2 x bfloat>} @llvm.vector.deinterleave2.nxv4bf16(<vscale x 4 x bfloat> %vec)
  %t0 = extractvalue { <vscale x 2 x bfloat>, <vscale x 2 x bfloat> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 2 x bfloat>, <vscale x 2 x bfloat> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 2 x bfloat>, <vscale x 2 x bfloat> } poison, <vscale x 2 x bfloat> %t0, 0
  %res1 = insertvalue { <vscale x 2 x bfloat>, <vscale x 2 x bfloat> } %res0, <vscale x 2 x bfloat> %t1, 1
  ret {<vscale x 2 x bfloat>, <vscale x 2 x bfloat>} %res1
}

define {<vscale x 4 x bfloat>, <vscale x 4 x bfloat>} @vector_deinterleave_load_nxv4bf16_nxv8bf16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv4bf16_nxv8bf16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e16, m1, ta, ma
; CHECK-NEXT:    vlseg2e16.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 8 x bfloat>, ptr %p
  %deinterleaved.results = call {<vscale x 4 x bfloat>, <vscale x 4 x bfloat>} @llvm.vector.deinterleave2.nxv8bf16(<vscale x 8 x bfloat> %vec)
  %t0 = extractvalue { <vscale x 4 x bfloat>, <vscale x 4 x bfloat> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 4 x bfloat>, <vscale x 4 x bfloat> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 4 x bfloat>, <vscale x 4 x bfloat> } poison, <vscale x 4 x bfloat> %t0, 0
  %res1 = insertvalue { <vscale x 4 x bfloat>, <vscale x 4 x bfloat> } %res0, <vscale x 4 x bfloat> %t1, 1
  ret {<vscale x 4 x bfloat>, <vscale x 4 x bfloat>} %res1
}

define {<vscale x 2 x half>, <vscale x 2 x half>} @vector_deinterleave_load_nxv2f16_nxv4f16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv2f16_nxv4f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e16, mf2, ta, ma
; CHECK-NEXT:    vlseg2e16.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 4 x half>, ptr %p
  %deinterleaved.results = call {<vscale x 2 x half>, <vscale x 2 x half>} @llvm.vector.deinterleave2.nxv4f16(<vscale x 4 x half> %vec)
  %t0 = extractvalue { <vscale x 2 x half>, <vscale x 2 x half> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 2 x half>, <vscale x 2 x half> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 2 x half>, <vscale x 2 x half> } poison, <vscale x 2 x half> %t0, 0
  %res1 = insertvalue { <vscale x 2 x half>, <vscale x 2 x half> } %res0, <vscale x 2 x half> %t1, 1
  ret {<vscale x 2 x half>, <vscale x 2 x half>} %res1
}

define {<vscale x 4 x half>, <vscale x 4 x half>} @vector_deinterleave_load_nxv4f16_nxv8f16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv4f16_nxv8f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e16, m1, ta, ma
; CHECK-NEXT:    vlseg2e16.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 8 x half>, ptr %p
  %deinterleaved.results = call {<vscale x 4 x half>, <vscale x 4 x half>} @llvm.vector.deinterleave2.nxv8f16(<vscale x 8 x half> %vec)
  %t0 = extractvalue { <vscale x 4 x half>, <vscale x 4 x half> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 4 x half>, <vscale x 4 x half> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 4 x half>, <vscale x 4 x half> } poison, <vscale x 4 x half> %t0, 0
  %res1 = insertvalue { <vscale x 4 x half>, <vscale x 4 x half> } %res0, <vscale x 4 x half> %t1, 1
  ret {<vscale x 4 x half>, <vscale x 4 x half>} %res1
}

define {<vscale x 2 x float>, <vscale x 2 x float>} @vector_deinterleave_load_nxv2f32_nxv4f32(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv2f32_nxv4f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e32, m1, ta, ma
; CHECK-NEXT:    vlseg2e32.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 4 x float>, ptr %p
  %deinterleaved.results = call {<vscale x 2 x float>, <vscale x 2 x float>} @llvm.vector.deinterleave2.nxv4f32(<vscale x 4 x float> %vec)
  %t0 = extractvalue { <vscale x 2 x float>, <vscale x 2 x float> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 2 x float>, <vscale x 2 x float> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 2 x float>, <vscale x 2 x float> } poison, <vscale x 2 x float> %t0, 0
  %res1 = insertvalue { <vscale x 2 x float>, <vscale x 2 x float> } %res0, <vscale x 2 x float> %t1, 1
  ret {<vscale x 2 x float>, <vscale x 2 x float>} %res1
}

define {<vscale x 8 x bfloat>, <vscale x 8 x bfloat>} @vector_deinterleave_load_nxv8bf16_nxv16bf16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv8bf16_nxv16bf16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e16, m2, ta, ma
; CHECK-NEXT:    vlseg2e16.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 16 x bfloat>, ptr %p
  %deinterleaved.results = call {<vscale x 8 x bfloat>, <vscale x 8 x bfloat>} @llvm.vector.deinterleave2.nxv16bf16(<vscale x 16 x bfloat> %vec)
  %t0 = extractvalue { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } poison, <vscale x 8 x bfloat> %t0, 0
  %res1 = insertvalue { <vscale x 8 x bfloat>, <vscale x 8 x bfloat> } %res0, <vscale x 8 x bfloat> %t1, 1
  ret {<vscale x 8 x bfloat>, <vscale x 8 x bfloat>} %res1
}

define {<vscale x 8 x half>, <vscale x 8 x half>} @vector_deinterleave_load_nxv8f16_nxv16f16(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv8f16_nxv16f16:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e16, m2, ta, ma
; CHECK-NEXT:    vlseg2e16.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 16 x half>, ptr %p
  %deinterleaved.results = call {<vscale x 8 x half>, <vscale x 8 x half>} @llvm.vector.deinterleave2.nxv16f16(<vscale x 16 x half> %vec)
  %t0 = extractvalue { <vscale x 8 x half>, <vscale x 8 x half> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 8 x half>, <vscale x 8 x half> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 8 x half>, <vscale x 8 x half> } poison, <vscale x 8 x half> %t0, 0
  %res1 = insertvalue { <vscale x 8 x half>, <vscale x 8 x half> } %res0, <vscale x 8 x half> %t1, 1
  ret {<vscale x 8 x half>, <vscale x 8 x half>} %res1
}

define {<vscale x 4 x float>, <vscale x 4 x float>} @vector_deinterleave_load_nxv4f32_nxv8f32(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv4f32_nxv8f32:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e32, m2, ta, ma
; CHECK-NEXT:    vlseg2e32.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 8 x float>, ptr %p
  %deinterleaved.results = call {<vscale x 4 x float>, <vscale x 4 x float>} @llvm.vector.deinterleave2.nxv8f32(<vscale x 8 x float> %vec)
  %t0 = extractvalue { <vscale x 4 x float>, <vscale x 4 x float> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 4 x float>, <vscale x 4 x float> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 4 x float>, <vscale x 4 x float> } poison, <vscale x 4 x float> %t0, 0
  %res1 = insertvalue { <vscale x 4 x float>, <vscale x 4 x float> } %res0, <vscale x 4 x float> %t1, 1
  ret {<vscale x 4 x float>, <vscale x 4 x float>} %res1
}

define {<vscale x 2 x double>, <vscale x 2 x double>} @vector_deinterleave_load_nxv2f64_nxv4f64(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_nxv2f64_nxv4f64:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e64, m2, ta, ma
; CHECK-NEXT:    vlseg2e64.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 4 x double>, ptr %p
  %deinterleaved.results = call {<vscale x 2 x double>, <vscale x 2 x double>} @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %vec)
  %t0 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 2 x double>, <vscale x 2 x double> } poison, <vscale x 2 x double> %t0, 0
  %res1 = insertvalue { <vscale x 2 x double>, <vscale x 2 x double> } %res0, <vscale x 2 x double> %t1, 1
  ret {<vscale x 2 x double>, <vscale x 2 x double>} %res1
}

define {<vscale x 2 x ptr>, <vscale x 2 x ptr>} @vector_deinterleave_load_nxv2p0_nxv4p0(ptr %p) {
; RV32-LABEL: vector_deinterleave_load_nxv2p0_nxv4p0:
; RV32:       # %bb.0:
; RV32-NEXT:    vsetvli a1, zero, e32, m1, ta, ma
; RV32-NEXT:    vlseg2e32.v v8, (a0)
; RV32-NEXT:    ret
;
; RV64-LABEL: vector_deinterleave_load_nxv2p0_nxv4p0:
; RV64:       # %bb.0:
; RV64-NEXT:    vsetvli a1, zero, e64, m2, ta, ma
; RV64-NEXT:    vlseg2e64.v v8, (a0)
; RV64-NEXT:    ret
  %vec = load <vscale x 4 x ptr>, ptr %p
  %deinterleaved.results = call {<vscale x 2 x ptr>, <vscale x 2 x ptr>} @llvm.vector.deinterleave2.nxv4p0(<vscale x 4 x ptr> %vec)
  %t0 = extractvalue { <vscale x 2 x ptr>, <vscale x 2 x ptr> } %deinterleaved.results, 0
  %t1 = extractvalue { <vscale x 2 x ptr>, <vscale x 2 x ptr> } %deinterleaved.results, 1
  %res0 = insertvalue { <vscale x 2 x ptr>, <vscale x 2 x ptr> } poison, <vscale x 2 x ptr> %t0, 0
  %res1 = insertvalue { <vscale x 2 x ptr>, <vscale x 2 x ptr> } %res0, <vscale x 2 x ptr> %t1, 1
  ret {<vscale x 2 x ptr>, <vscale x 2 x ptr>} %res1
}

define { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @vector_deinterleave_load_factor3(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor3:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlseg3e8.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 24 x i8>, ptr %p
  %d0 = call {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} @llvm.vector.deinterleave3(<vscale x 24 x i8> %vec)
  %t0 = extractvalue {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} %d0, 0
  %t1 = extractvalue {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} %d0, 1
  %t2 = extractvalue {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} %d0, 2
  %res0 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } poison, <vscale x 8 x i8> %t0, 0
  %res1 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res0, <vscale x 8 x i8> %t1, 1
  %res2 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res1, <vscale x 8 x i8> %t2, 2
  ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res2
}

define { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @vector_deinterleave_load_factor4(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor4:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlseg4e8.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 32 x i8>, ptr %p
  %d0 = call { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @llvm.vector.deinterleave4(<vscale x 32 x i8> %vec)
  %t0 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 0
  %t1 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 1
  %t2 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 2
  %t3 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 3
  %res0 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } poison, <vscale x 8 x i8> %t0, 0
  %res1 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res0, <vscale x 8 x i8> %t1, 1
  %res2 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res1, <vscale x 8 x i8> %t2, 2
  %res3 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res2, <vscale x 8 x i8> %t3, 3
  ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res3
}

define <vscale x 8 x i8> @vector_deinterleave_load_factor4_oneactive(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor4_oneactive:
; CHECK:       # %bb.0:
; CHECK-NEXT:    li a1, 4
; CHECK-NEXT:    vsetvli a2, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlse8.v v8, (a0), a1
; CHECK-NEXT:    ret
  %vec = load <vscale x 32 x i8>, ptr %p
  %d0 = call { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @llvm.vector.deinterleave4(<vscale x 32 x i8> %vec)
  %t0 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 0
  ret <vscale x 8 x i8> %t0
}

define <vscale x 8 x i8> @vector_deinterleave_load_factor4_oneactive2(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor4_oneactive2:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi a0, a0, 3
; CHECK-NEXT:    li a1, 4
; CHECK-NEXT:    vsetvli a2, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlse8.v v8, (a0), a1
; CHECK-NEXT:    ret
  %vec = load <vscale x 32 x i8>, ptr %p
  %d0 = call { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @llvm.vector.deinterleave4(<vscale x 32 x i8> %vec)
  %t0 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 3
  ret <vscale x 8 x i8> %t0
}

define { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @vector_deinterleave_load_factor4_twoactive(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor4_twoactive:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlseg4e8.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 32 x i8>, ptr %p
  %d0 = call { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @llvm.vector.deinterleave4(<vscale x 32 x i8> %vec)
  %t0 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 0
  %t1 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 1
  %res0 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } poison, <vscale x 8 x i8> %t0, 0
  %res1 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res0, <vscale x 8 x i8> %t1, 1
  ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res1
}

define { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @vector_deinterleave_load_factor5(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor5:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlseg5e8.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 40 x i8>, ptr %p
  %d0 = call {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} @llvm.vector.deinterleave5(<vscale x 40 x i8> %vec)
  %t0 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 0
  %t1 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 1
  %t2 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 2
  %t3 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 3
  %t4 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 4
  %res0 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } poison, <vscale x 8 x i8> %t0, 0
  %res1 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res0, <vscale x 8 x i8> %t1, 1
  %res2 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res1, <vscale x 8 x i8> %t2, 2
  %res3 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res2, <vscale x 8 x i8> %t3, 3
  %res4 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res3, <vscale x 8 x i8> %t4, 4
  ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res4
}

define { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @vector_deinterleave_load_factor6(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor6:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlseg6e8.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 48 x i8>, ptr %p
  %d0 = call { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @llvm.vector.deinterleave6(<vscale x 48 x i8> %vec)
  %t0 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 0
  %t1 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 1
  %t2 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 2
  %t3 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 3
  %t4 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 4
  %t5 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 5
  %res0 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } poison, <vscale x 8 x i8> %t0, 0
  %res1 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res0, <vscale x 8 x i8> %t1, 1
  %res2 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res1, <vscale x 8 x i8> %t2, 2
  %res3 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res2, <vscale x 8 x i8> %t3, 3
  %res4 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res3, <vscale x 8 x i8> %t4, 4
  %res5 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res4, <vscale x 8 x i8> %t5, 5
  ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res5
}

define { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @vector_deinterleave_load_factor7(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor7:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlseg7e8.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 56 x i8>, ptr %p
  %d0 = call {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} @llvm.vector.deinterleave7(<vscale x 56 x i8> %vec)
  %t0 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 0
  %t1 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 1
  %t2 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 2
  %t3 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 3
  %t4 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 4
  %t5 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 5
  %t6 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 6
  %res0 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } poison, <vscale x 8 x i8> %t0, 0
  %res1 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res0, <vscale x 8 x i8> %t1, 1
  %res2 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res1, <vscale x 8 x i8> %t2, 2
  %res3 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res2, <vscale x 8 x i8> %t3, 3
  %res4 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res3, <vscale x 8 x i8> %t4, 4
  %res5 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res4, <vscale x 8 x i8> %t5, 5
  %res6 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res5, <vscale x 8 x i8> %t6, 6
  ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res6
}

define { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @vector_deinterleave_load_factor8(ptr %p) {
; CHECK-LABEL: vector_deinterleave_load_factor8:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlseg8e8.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = load <vscale x 64 x i8>, ptr %p
  %d0 = call { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } @llvm.vector.deinterleave8(<vscale x 64 x i8> %vec)
  %t0 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 0
  %t1 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 1
  %t2 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 2
  %t3 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 3
  %t4 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 4
  %t5 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 5
  %t6 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 6
  %t7 = extractvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %d0, 7
  %res0 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } poison, <vscale x 8 x i8> %t0, 0
  %res1 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res0, <vscale x 8 x i8> %t1, 1
  %res2 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res1, <vscale x 8 x i8> %t2, 2
  %res3 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res2, <vscale x 8 x i8> %t3, 3
  %res4 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res3, <vscale x 8 x i8> %t4, 4
  %res5 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res4, <vscale x 8 x i8> %t5, 5
  %res6 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res5, <vscale x 8 x i8> %t6, 6
  %res7 = insertvalue { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res6, <vscale x 8 x i8> %t7, 7
  ret { <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8> } %res7
}

define {<vscale x 16 x i8>, <vscale x 16 x i8>} @masked_load_factor2(ptr %p) {
; CHECK-LABEL: masked_load_factor2:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m2, ta, ma
; CHECK-NEXT:    vlseg2e8.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = call <vscale x 32 x i8> @llvm.masked.load(ptr %p, i32 4, <vscale x 32 x i1> splat (i1 true), <vscale x 32 x i8> poison)
  %deinterleaved.results = call {<vscale x 16 x i8>, <vscale x 16 x i8>} @llvm.vector.deinterleave2.nxv32i8(<vscale x 32 x i8> %vec)
  ret {<vscale x 16 x i8>, <vscale x 16 x i8>} %deinterleaved.results
}

define {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} @masked_load_factor4(ptr %p) {
; CHECK-LABEL: masked_load_factor4:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlseg4e8.v v8, (a0)
; CHECK-NEXT:    ret
  %vec = call <vscale x 32 x i8> @llvm.masked.load(ptr %p, i32 4, <vscale x 32 x i1> splat (i1 true), <vscale x 32 x i8> poison)
  %deinterleaved.results = call {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} @llvm.vector.deinterleave4.nxv32i8(<vscale x 32 x i8> %vec)
  ret {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} %deinterleaved.results
}

define {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} @masked_load_factor4_mask(ptr %p, <vscale x 8 x i1> %mask) {
; CHECK-LABEL: masked_load_factor4_mask:
; CHECK:       # %bb.0:
; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlseg4e8.v v8, (a0), v0.t
; CHECK-NEXT:    ret
  %interleaved.mask = tail call <vscale x 32 x i1> @llvm.vector.interleave4.nxv32i1(<vscale x 8 x i1> %mask, <vscale x 8 x i1> %mask, <vscale x 8 x i1> %mask, <vscale x 8 x i1> %mask)
  %vec = call <vscale x 32 x i8> @llvm.masked.load(ptr %p, i32 4, <vscale x 32 x i1> %interleaved.mask, <vscale x 32 x i8> poison)
  %deinterleaved.results = call {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} @llvm.vector.deinterleave4.nxv32i8(<vscale x 32 x i8> %vec)
  ret {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} %deinterleaved.results
}

; Negative test - some of the deinterleaved elements might come from the
; passthru not the load
define {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} @masked_load_factor4_passthru(ptr %p, <vscale x 8 x i1> %mask, <vscale x 32 x i8> %passthru) {
; CHECK-LABEL: masked_load_factor4_passthru:
; 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:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
; CHECK-NEXT:    vmv.v.i v12, 0
; CHECK-NEXT:    addi a1, sp, 16
; CHECK-NEXT:    csrr a2, vlenb
; CHECK-NEXT:    vmerge.vim v12, v12, 1, v0
; CHECK-NEXT:    add a3, a1, a2
; CHECK-NEXT:    vmv.v.v v13, v12
; CHECK-NEXT:    srli a4, a2, 2
; CHECK-NEXT:    vmv.v.v v14, v12
; CHECK-NEXT:    srli a5, a2, 3
; CHECK-NEXT:    vmv.v.v v15, v12
; CHECK-NEXT:    vsseg4e8.v v12, (a1)
; CHECK-NEXT:    vl1r.v v12, (a1)
; CHECK-NEXT:    add a1, a4, a5
; CHECK-NEXT:    vl1r.v v13, (a3)
; CHECK-NEXT:    add a3, a3, a2
; CHECK-NEXT:    add a2, a3, a2
; CHECK-NEXT:    vl1r.v v14, (a3)
; CHECK-NEXT:    vl1r.v v15, (a2)
; CHECK-NEXT:    vmsne.vi v13, v13, 0
; CHECK-NEXT:    vmsne.vi v0, v12, 0
; CHECK-NEXT:    vmsne.vi v12, v14, 0
; CHECK-NEXT:    vmsne.vi v14, v15, 0
; CHECK-NEXT:    vsetvli zero, a4, e8, mf2, tu, ma
; CHECK-NEXT:    vslideup.vx v0, v13, a5
; CHECK-NEXT:    vsetvli zero, a1, e8, mf2, tu, ma
; CHECK-NEXT:    vslideup.vx v0, v12, a4
; CHECK-NEXT:    vsetvli a2, zero, e8, mf2, ta, ma
; CHECK-NEXT:    vslideup.vx v0, v14, a1
; CHECK-NEXT:    vsetvli a1, zero, e8, m4, ta, mu
; CHECK-NEXT:    vle8.v v8, (a0), v0.t
; CHECK-NEXT:    csrr a0, vlenb
; CHECK-NEXT:    slli a0, a0, 2
; CHECK-NEXT:    add a0, sp, a0
; CHECK-NEXT:    addi a0, a0, 16
; CHECK-NEXT:    vs4r.v v8, (a0)
; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
; CHECK-NEXT:    vlseg4e8.v v8, (a0)
; CHECK-NEXT:    csrr a0, vlenb
; CHECK-NEXT:    slli a0, a0, 3
; CHECK-NEXT:    add sp, sp, a0
; CHECK-NEXT:    .cfi_def_cfa sp, 16
; CHECK-NEXT:    addi sp, sp, 16
; CHECK-NEXT:    .cfi_def_cfa_offset 0
; CHECK-NEXT:    ret
  %interleaved.mask = tail call <vscale x 32 x i1> @llvm.vector.interleave4.nxv32i1(<vscale x 8 x i1> %mask, <vscale x 8 x i1> %mask, <vscale x 8 x i1> %mask, <vscale x 8 x i1> %mask)
  %vec = call <vscale x 32 x i8> @llvm.masked.load(ptr %p, i32 4, <vscale x 32 x i1> %interleaved.mask, <vscale x 32 x i8> %passthru)
  %deinterleaved.results = call {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} @llvm.vector.deinterleave4.nxv32i8(<vscale x 32 x i8> %vec)
  ret {<vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>, <vscale x 8 x i8>} %deinterleaved.results
}

define { <8 x float>, <8 x float> } @deinterleave_unrelated(<16 x float> %arg) {
; CHECK-LABEL: deinterleave_unrelated:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    vsetivli zero, 16, e32, m4, ta, ma
; CHECK-NEXT:    vfabs.v v12, v8
; CHECK-NEXT:    li a0, 32
; CHECK-NEXT:    vsetivli zero, 8, e32, m2, ta, ma
; CHECK-NEXT:    vnsrl.wx v10, v12, a0
; CHECK-NEXT:    vnsrl.wi v8, v12, 0
; CHECK-NEXT:    ret
entry:
  %abs = call <16 x float> @llvm.fabs(<16 x float> %arg)
  %res = call { <8 x float>, <8 x float> } @llvm.vector.deinterleave2.v16f32(<16 x float> %abs)
  ret { <8 x float>, <8 x float> } %res
}