; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple riscv64 < %s -o - | FileCheck %s

%"buff" = type { [4096 x i64] }

declare void @bar()

define i1 @foo() nounwind "probe-stack"="inline-asm" "target-features"="+v" {
; CHECK-LABEL: foo:
; CHECK:       # %bb.0:
; CHECK-NEXT:    addi sp, sp, -2032
; CHECK-NEXT:    sd ra, 2024(sp) # 8-byte Folded Spill
; CHECK-NEXT:    sd s0, 2016(sp) # 8-byte Folded Spill
; CHECK-NEXT:    sd s1, 2008(sp) # 8-byte Folded Spill
; CHECK-NEXT:    sd s2, 2000(sp) # 8-byte Folded Spill
; CHECK-NEXT:    sd s3, 1992(sp) # 8-byte Folded Spill
; CHECK-NEXT:    lui a0, 7
; CHECK-NEXT:    sub t1, sp, a0
; CHECK-NEXT:    lui t2, 1
; CHECK-NEXT:  .LBB0_1: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    sub sp, sp, t2
; CHECK-NEXT:    sd zero, 0(sp)
; CHECK-NEXT:    bne sp, t1, .LBB0_1
; CHECK-NEXT:  # %bb.2:
; CHECK-NEXT:    addi sp, sp, -2048
; CHECK-NEXT:    addi sp, sp, -96
; CHECK-NEXT:    csrr t1, vlenb
; CHECK-NEXT:    lui t2, 1
; CHECK-NEXT:  .LBB0_3: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT:    sub sp, sp, t2
; CHECK-NEXT:    sd zero, 0(sp)
; CHECK-NEXT:    sub t1, t1, t2
; CHECK-NEXT:    bge t1, t2, .LBB0_3
; CHECK-NEXT:  # %bb.4:
; CHECK-NEXT:    sub sp, sp, t1
; CHECK-NEXT:    li a0, 86
; CHECK-NEXT:    addi s0, sp, 48
; CHECK-NEXT:    addi s1, sp, 32
; CHECK-NEXT:    addi s2, sp, 16
; CHECK-NEXT:    lui a1, 353637
; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT:    vmv.v.x v8, a0
; CHECK-NEXT:    lui a0, 8
; CHECK-NEXT:    addi a0, a0, 32
; CHECK-NEXT:    add a0, sp, a0
; CHECK-NEXT:    vs1r.v v8, (a0) # vscale x 8-byte Folded Spill
; CHECK-NEXT:    addi a0, a1, 1622
; CHECK-NEXT:    vse8.v v8, (s0)
; CHECK-NEXT:    vse8.v v8, (s1)
; CHECK-NEXT:    vse8.v v8, (s2)
; CHECK-NEXT:    slli a1, a0, 32
; CHECK-NEXT:    add s3, a0, a1
; CHECK-NEXT:    sd s3, 64(sp)
; CHECK-NEXT:    call bar
; CHECK-NEXT:    lui a0, 8
; CHECK-NEXT:    addi a0, a0, 32
; CHECK-NEXT:    add a0, sp, a0
; CHECK-NEXT:    vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
; CHECK-NEXT:    vse8.v v8, (s0)
; CHECK-NEXT:    vse8.v v8, (s1)
; CHECK-NEXT:    vse8.v v8, (s2)
; CHECK-NEXT:    sd s3, 64(sp)
; CHECK-NEXT:    li a0, 0
; CHECK-NEXT:    csrr a1, vlenb
; CHECK-NEXT:    add sp, sp, a1
; CHECK-NEXT:    lui a1, 8
; CHECK-NEXT:    addi a1, a1, -1952
; CHECK-NEXT:    add sp, sp, a1
; CHECK-NEXT:    ld ra, 2024(sp) # 8-byte Folded Reload
; CHECK-NEXT:    ld s0, 2016(sp) # 8-byte Folded Reload
; CHECK-NEXT:    ld s1, 2008(sp) # 8-byte Folded Reload
; CHECK-NEXT:    ld s2, 2000(sp) # 8-byte Folded Reload
; CHECK-NEXT:    ld s3, 1992(sp) # 8-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 2032
; CHECK-NEXT:    ret
  %1 = alloca %"buff", align 8
  call void @llvm.memset.p0.i64(ptr %1, i8 86, i64 56, i1 false)
  call void @bar()
  call void @llvm.memset.p0.i64(ptr %1, i8 86, i64 56, i1 false)
  ret i1 false
}