; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv64 -mattr=+v -verify-machineinstrs \
; RUN:   < %s | FileCheck %s

define dso_local void @lots_args(i32 signext %x0, i32 signext %x1, <vscale x 16 x i32> %v0, i32 signext %x2, i32 signext %x3, i32 signext %x4, i32 signext %x5, i32 signext %x6, i32 %x7, i32 %x8, i32 %x9) #0 {
; CHECK-LABEL: lots_args:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -64
; CHECK-NEXT:    sd ra, 56(sp) # 8-byte Folded Spill
; CHECK-NEXT:    sd s0, 48(sp) # 8-byte Folded Spill
; CHECK-NEXT:    addi s0, sp, 64
; CHECK-NEXT:    csrr t0, vlenb
; CHECK-NEXT:    slli t0, t0, 3
; CHECK-NEXT:    sub sp, sp, t0
; CHECK-NEXT:    ld t0, 8(s0)
; CHECK-NEXT:    ld t1, 0(s0)
; CHECK-NEXT:    sw a0, -28(s0)
; CHECK-NEXT:    sw a1, -32(s0)
; CHECK-NEXT:    csrr a0, vlenb
; CHECK-NEXT:    slli a0, a0, 3
; CHECK-NEXT:    sub a0, s0, a0
; CHECK-NEXT:    addi a0, a0, -64
; CHECK-NEXT:    vs8r.v v8, (a0)
; CHECK-NEXT:    sw a2, -36(s0)
; CHECK-NEXT:    sw a3, -40(s0)
; CHECK-NEXT:    sw a4, -44(s0)
; CHECK-NEXT:    sw a5, -48(s0)
; CHECK-NEXT:    sw a6, -52(s0)
; CHECK-NEXT:    sw a7, -56(s0)
; CHECK-NEXT:    sw t1, -60(s0)
; CHECK-NEXT:    sw t0, -64(s0)
; CHECK-NEXT:    addi sp, s0, -64
; CHECK-NEXT:    ld ra, 56(sp) # 8-byte Folded Reload
; CHECK-NEXT:    ld s0, 48(sp) # 8-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 64
; CHECK-NEXT:    ret
entry:
  %x0.addr = alloca i32, align 4
  %x1.addr = alloca i32, align 4
  %v0.addr = alloca <vscale x 16 x i32>, align 4
  %x2.addr = alloca i32, align 4
  %x3.addr = alloca i32, align 4
  %x4.addr = alloca i32, align 4
  %x5.addr = alloca i32, align 4
  %x6.addr = alloca i32, align 4
  %x7.addr = alloca i32, align 4
  %x8.addr = alloca i32, align 4
  %x9.addr = alloca i32, align 4
  store i32 %x0, ptr %x0.addr, align 4
  store i32 %x1, ptr %x1.addr, align 4
  store <vscale x 16 x i32> %v0, <vscale x 16 x i32>* %v0.addr, align 4
  store i32 %x2, ptr %x2.addr, align 4
  store i32 %x3, ptr %x3.addr, align 4
  store i32 %x4, ptr %x4.addr, align 4
  store i32 %x5, ptr %x5.addr, align 4
  store i32 %x6, ptr %x6.addr, align 4
  store i32 %x7, ptr %x7.addr, align 4
  store i32 %x8, ptr %x8.addr, align 4
  store i32 %x9, ptr %x9.addr, align 4
  ret void
}

define dso_local signext i32 @main() #0 {
; CHECK-LABEL: main:
; CHECK:       # %bb.0: # %entry
; CHECK-NEXT:    addi sp, sp, -112
; CHECK-NEXT:    sd ra, 104(sp) # 8-byte Folded Spill
; CHECK-NEXT:    sd s0, 96(sp) # 8-byte Folded Spill
; CHECK-NEXT:    sd s1, 88(sp) # 8-byte Folded Spill
; CHECK-NEXT:    addi s0, sp, 112
; CHECK-NEXT:    csrr a0, vlenb
; CHECK-NEXT:    slli a0, a0, 3
; CHECK-NEXT:    sub sp, sp, a0
; CHECK-NEXT:    sw zero, -36(s0)
; CHECK-NEXT:    vsetivli zero, 2, e64, m1, ta, ma
; CHECK-NEXT:    vmv.v.i v8, 0
; CHECK-NEXT:    addi a0, s0, -64
; CHECK-NEXT:    vse64.v v8, (a0)
; CHECK-NEXT:    vsetivli a1, 4, e32, m8, ta, ma
; CHECK-NEXT:    sd a1, -72(s0)
; CHECK-NEXT:    ld a1, -72(s0)
; CHECK-NEXT:    vsetvli zero, a1, e32, m8, ta, ma
; CHECK-NEXT:    vle32.v v8, (a0)
; CHECK-NEXT:    csrr s1, vlenb
; CHECK-NEXT:    slli s1, s1, 3
; CHECK-NEXT:    sub s1, s0, s1
; CHECK-NEXT:    addi s1, s1, -112
; CHECK-NEXT:    vs8r.v v8, (s1)
; CHECK-NEXT:    li a0, 1
; CHECK-NEXT:    sw a0, -76(s0)
; CHECK-NEXT:    sw a0, -80(s0)
; CHECK-NEXT:    sw a0, -84(s0)
; CHECK-NEXT:    sw a0, -88(s0)
; CHECK-NEXT:    sw a0, -92(s0)
; CHECK-NEXT:    sw a0, -96(s0)
; CHECK-NEXT:    sw a0, -100(s0)
; CHECK-NEXT:    sw a0, -104(s0)
; CHECK-NEXT:    sw a0, -108(s0)
; CHECK-NEXT:    sw a0, -112(s0)
; CHECK-NEXT:    lw a0, -76(s0)
; CHECK-NEXT:    lw a1, -80(s0)
; CHECK-NEXT:    vl8re32.v v8, (s1)
; CHECK-NEXT:    lw a2, -84(s0)
; CHECK-NEXT:    lw a3, -88(s0)
; CHECK-NEXT:    lw a4, -92(s0)
; CHECK-NEXT:    lw a5, -96(s0)
; CHECK-NEXT:    lw a6, -100(s0)
; CHECK-NEXT:    lw a7, -104(s0)
; CHECK-NEXT:    lw t0, -108(s0)
; CHECK-NEXT:    lw t1, -112(s0)
; CHECK-NEXT:    addi sp, sp, -16
; CHECK-NEXT:    sd t1, 8(sp)
; CHECK-NEXT:    sd t0, 0(sp)
; CHECK-NEXT:    call lots_args
; CHECK-NEXT:    addi sp, sp, 16
; CHECK-NEXT:    lw a0, -76(s0)
; CHECK-NEXT:    lw a1, -80(s0)
; CHECK-NEXT:    vl8re32.v v8, (s1)
; CHECK-NEXT:    lw a2, -84(s0)
; CHECK-NEXT:    lw a3, -88(s0)
; CHECK-NEXT:    lw a4, -92(s0)
; CHECK-NEXT:    lw a5, -96(s0)
; CHECK-NEXT:    lw a6, -100(s0)
; CHECK-NEXT:    lw a7, -104(s0)
; CHECK-NEXT:    lw t0, -108(s0)
; CHECK-NEXT:    lw t1, -112(s0)
; CHECK-NEXT:    addi sp, sp, -16
; CHECK-NEXT:    sd t1, 8(sp)
; CHECK-NEXT:    sd t0, 0(sp)
; CHECK-NEXT:    call lots_args
; CHECK-NEXT:    addi sp, sp, 16
; CHECK-NEXT:    li a0, 0
; CHECK-NEXT:    addi sp, s0, -112
; CHECK-NEXT:    ld ra, 104(sp) # 8-byte Folded Reload
; CHECK-NEXT:    ld s0, 96(sp) # 8-byte Folded Reload
; CHECK-NEXT:    ld s1, 88(sp) # 8-byte Folded Reload
; CHECK-NEXT:    addi sp, sp, 112
; CHECK-NEXT:    ret
entry:
  %retval = alloca i32, align 4
  %input = alloca [4 x i32], align 4
  %vl = alloca i64, align 8
  %v0 = alloca <vscale x 16 x i32>, align 4
  %x0 = alloca i32, align 4
  %x1 = alloca i32, align 4
  %x2 = alloca i32, align 4
  %x3 = alloca i32, align 4
  %x4 = alloca i32, align 4
  %x5 = alloca i32, align 4
  %x6 = alloca i32, align 4
  %x7 = alloca i32, align 4
  %x8 = alloca i32, align 4
  %x9 = alloca i32, align 4
  store i32 0, ptr %retval, align 4
  call void @llvm.memset.p0.i64(ptr align 4 %input, i8 0, i64 16, i1 false)
  %0 = call i64 @llvm.riscv.vsetvli.i64(i64 4, i64 2, i64 3)
  store i64 %0, ptr %vl, align 8
  %1 = load i64, ptr %vl, align 8
  %2 = call <vscale x 16 x i32> @llvm.riscv.vle.nxv16i32.i64(<vscale x 16 x i32> undef, <vscale x 16 x i32>* %input, i64 %1)
  store <vscale x 16 x i32> %2, <vscale x 16 x i32>* %v0, align 4
  store i32 1, ptr %x0, align 4
  store i32 1, ptr %x1, align 4
  store i32 1, ptr %x2, align 4
  store i32 1, ptr %x3, align 4
  store i32 1, ptr %x4, align 4
  store i32 1, ptr %x5, align 4
  store i32 1, ptr %x6, align 4
  store i32 1, ptr %x7, align 4
  store i32 1, ptr %x8, align 4
  store i32 1, ptr %x9, align 4
  %3 = load i32, ptr %x0, align 4
  %4 = load i32, ptr %x1, align 4
  %5 = load <vscale x 16 x i32>, <vscale x 16 x i32>* %v0, align 4
  %6 = load i32, ptr %x2, align 4
  %7 = load i32, ptr %x3, align 4
  %8 = load i32, ptr %x4, align 4
  %9 = load i32, ptr %x5, align 4
  %10 = load i32, ptr %x6, align 4
  %11 = load i32, ptr %x7, align 4
  %12 = load i32, ptr %x8, align 4
  %13 = load i32, ptr %x9, align 4
  call void @lots_args(i32 signext %3, i32 signext %4, <vscale x 16 x i32> %5, i32 signext %6, i32 signext %7, i32 signext %8, i32 signext %9, i32 signext %10, i32 %11, i32 %12, i32 %13)
  %14 = load i32, ptr %x0, align 4
  %15 = load i32, ptr %x1, align 4
  %16 = load <vscale x 16 x i32>, <vscale x 16 x i32>* %v0, align 4
  %17 = load i32, ptr %x2, align 4
  %18 = load i32, ptr %x3, align 4
  %19 = load i32, ptr %x4, align 4
  %20 = load i32, ptr %x5, align 4
  %21 = load i32, ptr %x6, align 4
  %22 = load i32, ptr %x7, align 4
  %23 = load i32, ptr %x8, align 4
  %24 = load i32, ptr %x9, align 4
  call void @lots_args(i32 signext %14, i32 signext %15, <vscale x 16 x i32> %16, i32 signext %17, i32 signext %18, i32 signext %19, i32 signext %20, i32 signext %21, i32 %22, i32 %23, i32 %24)
  ret i32 0
}

declare void @llvm.memset.p0.i64(ptr nocapture writeonly, i8, i64, i1 immarg)

declare i64 @llvm.riscv.vsetvli.i64(i64, i64 immarg, i64 immarg)

declare <vscale x 16 x i32> @llvm.riscv.vle.nxv16i32.i64(<vscale x 16 x i32>, <vscale x 16 x i32>* nocapture, i64)

attributes #0 = { noinline nounwind optnone "frame-pointer"="all" }