; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=riscv64 -mattr=+m,+d,+v -verify-machineinstrs \
; RUN:   -M no-aliases < %s | FileCheck %s

target triple = "riscv64-unknown-unknown-elf"

define target("riscv.vector.tuple", <vscale x 8 x i8>, 5) @load_store_m1x5(target("riscv.vector.tuple", <vscale x 8 x i8>, 5) %tuple) {
; CHECK-LABEL: load_store_m1x5:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -16
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    csrrs a0, vlenb, zero
; CHECK-NEXT:    slli a0, a0, 3
; CHECK-NEXT:    sub sp, sp, a0
; 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:    addi a0, sp, 16
; CHECK-NEXT:    csrrs a1, vlenb, zero
; CHECK-NEXT:    vs1r.v v8, (a0)
; CHECK-NEXT:    add a2, a0, a1
; CHECK-NEXT:    vs1r.v v9, (a2)
; CHECK-NEXT:    add a3, a2, a1
; CHECK-NEXT:    vs1r.v v10, (a3)
; CHECK-NEXT:    add a4, a3, a1
; CHECK-NEXT:    vs1r.v v11, (a4)
; CHECK-NEXT:    add a1, a4, a1
; CHECK-NEXT:    vs1r.v v12, (a1)
; CHECK-NEXT:    #APP
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    vl1re8.v v8, (a0)
; CHECK-NEXT:    vl1re8.v v9, (a2)
; CHECK-NEXT:    vl1re8.v v10, (a3)
; CHECK-NEXT:    vl1re8.v v11, (a4)
; CHECK-NEXT:    vl1re8.v v12, (a1)
; CHECK-NEXT:    csrrs a0, vlenb, zero
; 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:    jalr zero, 0(ra)
entry:
  %tuple.addr = alloca target("riscv.vector.tuple", <vscale x 8 x i8>, 5), align 1
  store target("riscv.vector.tuple", <vscale x 8 x i8>, 5) %tuple, ptr %tuple.addr, align 1
  call void asm sideeffect "",
  "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
  %0 = load target("riscv.vector.tuple", <vscale x 8 x i8>, 5), ptr %tuple.addr, align 1
  ret target("riscv.vector.tuple", <vscale x 8 x i8>, 5) %0
}

define target("riscv.vector.tuple", <vscale x 16 x i8>, 2) @load_store_m2x2(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %tuple) {
; CHECK-LABEL: load_store_m2x2:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -16
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    csrrs a0, vlenb, zero
; CHECK-NEXT:    slli a0, a0, 2
; CHECK-NEXT:    sub sp, sp, a0
; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x04, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 4 * vlenb
; CHECK-NEXT:    addi a0, sp, 16
; CHECK-NEXT:    csrrs a1, vlenb, zero
; CHECK-NEXT:    vs2r.v v8, (a0)
; CHECK-NEXT:    slli a1, a1, 1
; CHECK-NEXT:    add a1, a0, a1
; CHECK-NEXT:    vs2r.v v10, (a1)
; CHECK-NEXT:    #APP
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    vl2re8.v v8, (a0)
; CHECK-NEXT:    vl2re8.v v10, (a1)
; CHECK-NEXT:    csrrs a0, vlenb, zero
; CHECK-NEXT:    slli a0, a0, 2
; 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:    jalr zero, 0(ra)
entry:
  %tuple.addr = alloca target("riscv.vector.tuple", <vscale x 16 x i8>, 2), align 1
  store target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %tuple, ptr %tuple.addr, align 1
  call void asm sideeffect "",
  "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
  %0 = load target("riscv.vector.tuple", <vscale x 16 x i8>, 2), ptr %tuple.addr, align 1
  ret target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %0
}

define target("riscv.vector.tuple", <vscale x 32 x i8>, 2) @load_store_m4x2(target("riscv.vector.tuple", <vscale x 32 x i8>, 2) %tuple) {
; CHECK-LABEL: load_store_m4x2:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -16
; CHECK-NEXT:    .cfi_def_cfa_offset 16
; CHECK-NEXT:    csrrs a0, vlenb, zero
; CHECK-NEXT:    slli a0, a0, 3
; CHECK-NEXT:    sub sp, sp, a0
; 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:    addi a0, sp, 16
; CHECK-NEXT:    csrrs a1, vlenb, zero
; CHECK-NEXT:    vs4r.v v8, (a0)
; CHECK-NEXT:    slli a1, a1, 2
; CHECK-NEXT:    add a1, a0, a1
; CHECK-NEXT:    vs4r.v v12, (a1)
; CHECK-NEXT:    #APP
; CHECK-NEXT:    #NO_APP
; CHECK-NEXT:    vl4re8.v v8, (a0)
; CHECK-NEXT:    vl4re8.v v12, (a1)
; CHECK-NEXT:    csrrs a0, vlenb, zero
; 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:    jalr zero, 0(ra)
entry:
  %tuple.addr = alloca target("riscv.vector.tuple", <vscale x 32 x i8>, 2), align 1
  store target("riscv.vector.tuple", <vscale x 32 x i8>, 2) %tuple, ptr %tuple.addr, align 1
  call void asm sideeffect "",
  "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"()
  %0 = load target("riscv.vector.tuple", <vscale x 32 x i8>, 2), ptr %tuple.addr, align 1
  ret target("riscv.vector.tuple", <vscale x 32 x i8>, 2) %0
}