; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple aarch64-linux-gnu -mattr=+sve | FileCheck %s

target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
target triple = "aarch64-unknown-linux-gnu"

; Make sure callers set up the arguments correctly - tests AArch64ISelLowering::LowerCALL

define float @foo1(ptr %x0, ptr %x1, ptr %x2) nounwind {
; CHECK-LABEL: foo1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT:    addvl sp, sp, #-4
; CHECK-NEXT:    ptrue p0.b
; CHECK-NEXT:    fmov s0, #1.00000000
; CHECK-NEXT:    ld4d { z1.d - z4.d }, p0/z, [x0]
; CHECK-NEXT:    mov x0, sp
; CHECK-NEXT:    ld4d { z16.d - z19.d }, p0/z, [x1]
; CHECK-NEXT:    ld1d { z5.d }, p0/z, [x2]
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    st1d { z19.d }, p0, [sp, #3, mul vl]
; CHECK-NEXT:    st1d { z18.d }, p0, [sp, #2, mul vl]
; CHECK-NEXT:    st1d { z17.d }, p0, [sp, #1, mul vl]
; CHECK-NEXT:    st1d { z16.d }, p0, [sp]
; CHECK-NEXT:    bl callee1
; CHECK-NEXT:    addvl sp, sp, #4
; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT:    ret
entry:
  %0 = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
  %1 = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %0)
  %2 = call {<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>} @llvm.aarch64.sve.ld4.sret.nxv2f64(<vscale x 2 x i1> %1, ptr %x0)
  %3 = call {<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>} @llvm.aarch64.sve.ld4.sret.nxv2f64(<vscale x 2 x i1> %1, ptr %x1)
  %4 = call <vscale x 2 x double> @llvm.aarch64.sve.ld1.nxv2f64(<vscale x 2 x i1> %1, ptr %x2)
  %5 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  0
  %6 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  1
  %7 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  2
  %8 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  3
  %9 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> poison, <vscale x 2 x double> %5, i64 0)
  %10 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %9, <vscale x 2 x double> %6, i64 2)
  %11 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %10, <vscale x 2 x double> %7, i64 4)
  %12 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %11, <vscale x 2 x double> %8, i64 6)
  %13 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %3,  0
  %14 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %3,  1
  %15 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %3,  2
  %16 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %3,  3
  %17 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> undef, <vscale x 2 x double> %13, i64 0)
  %18 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %17, <vscale x 2 x double> %14, i64 2)
  %19 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %18, <vscale x 2 x double> %15, i64 4)
  %20 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %19, <vscale x 2 x double> %16, i64 6)
  %call = call float @callee1(float 1.000000e+00, <vscale x 8 x double> %12, <vscale x 8 x double> %20, <vscale x 2 x double> %4)
  ret float %call
}

define float @foo2(ptr %x0, ptr %x1) nounwind {
; CHECK-LABEL: foo2:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT:    sub sp, sp, #16
; CHECK-NEXT:    addvl sp, sp, #-4
; CHECK-NEXT:    ptrue p0.b
; CHECK-NEXT:    fmov s0, #1.00000000
; CHECK-NEXT:    add x8, sp, #16
; CHECK-NEXT:    add x9, sp, #16
; CHECK-NEXT:    mov w2, #2 // =0x2
; CHECK-NEXT:    mov w3, #3 // =0x3
; CHECK-NEXT:    mov w4, #4 // =0x4
; CHECK-NEXT:    mov w5, #5 // =0x5
; CHECK-NEXT:    mov w6, #6 // =0x6
; CHECK-NEXT:    mov w7, #7 // =0x7
; CHECK-NEXT:    ld4d { z1.d - z4.d }, p0/z, [x0]
; CHECK-NEXT:    mov w0, wzr
; CHECK-NEXT:    ld4d { z16.d - z19.d }, p0/z, [x1]
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    mov w1, #1 // =0x1
; CHECK-NEXT:    st1d { z19.d }, p0, [x8, #3, mul vl]
; CHECK-NEXT:    st1d { z18.d }, p0, [x8, #2, mul vl]
; CHECK-NEXT:    st1d { z17.d }, p0, [x8, #1, mul vl]
; CHECK-NEXT:    st1d { z16.d }, p0, [x9]
; CHECK-NEXT:    str x8, [sp]
; CHECK-NEXT:    bl callee2
; CHECK-NEXT:    addvl sp, sp, #4
; CHECK-NEXT:    add sp, sp, #16
; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT:    ret
entry:
  %0 = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
  %1 = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %0)
  %2 = call {<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>} @llvm.aarch64.sve.ld4.sret.nxv2f64(<vscale x 2 x i1> %1, ptr %x0)
  %3 = call {<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>} @llvm.aarch64.sve.ld4.sret.nxv2f64(<vscale x 2 x i1> %1, ptr %x1)
  %4 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  0
  %5 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  1
  %6 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  2
  %7 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  3
  %8 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> poison, <vscale x 2 x double> %4, i64 0)
  %9 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %8, <vscale x 2 x double> %5, i64 2)
  %10 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %9, <vscale x 2 x double> %6, i64 4)
  %11 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %10, <vscale x 2 x double> %7, i64 6)
  %12 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %3,  0
  %13 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %3,  1
  %14 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %3,  2
  %15 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %3,  3
  %16 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> poison, <vscale x 2 x double> %12, i64 0)
  %17 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %16, <vscale x 2 x double> %13, i64 2)
  %18 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %17, <vscale x 2 x double> %14, i64 4)
  %19 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %18, <vscale x 2 x double> %15, i64 6)
  %call = call float @callee2(i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, float 1.000000e+00, <vscale x 8 x double> %11, <vscale x 8 x double> %19)
  ret float %call
}

define float @foo3(ptr %x0, ptr %x1, ptr %x2) nounwind {
; CHECK-LABEL: foo3:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT:    addvl sp, sp, #-3
; CHECK-NEXT:    ptrue p0.b
; CHECK-NEXT:    fmov s0, #1.00000000
; CHECK-NEXT:    fmov s1, #2.00000000
; CHECK-NEXT:    ld4d { z2.d - z5.d }, p0/z, [x0]
; CHECK-NEXT:    mov x0, sp
; CHECK-NEXT:    ld3d { z16.d - z18.d }, p0/z, [x1]
; CHECK-NEXT:    ld1d { z6.d }, p0/z, [x2]
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    st1d { z18.d }, p0, [sp, #2, mul vl]
; CHECK-NEXT:    st1d { z17.d }, p0, [sp, #1, mul vl]
; CHECK-NEXT:    st1d { z16.d }, p0, [sp]
; CHECK-NEXT:    bl callee3
; CHECK-NEXT:    addvl sp, sp, #3
; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT:    ret
entry:
  %0 = call <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 31)
  %1 = call <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1> %0)
  %2 = call {<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>} @llvm.aarch64.sve.ld4.sret.nxv2f64(<vscale x 2 x i1> %1, ptr %x0)
  %3 = call {<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>} @llvm.aarch64.sve.ld3.sret.nxv2f64(<vscale x 2 x i1> %1, ptr %x1)
  %4 = call <vscale x 2 x double> @llvm.aarch64.sve.ld1.nxv2f64(<vscale x 2 x i1> %1, ptr %x2)
  %5 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  0
  %6 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  1
  %7 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  2
  %8 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %2,  3
  %9 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> poison, <vscale x 2 x double> %5, i64 0)
  %10 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %9, <vscale x 2 x double> %6, i64 2)
  %11 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %10, <vscale x 2 x double> %7, i64 4)
  %12 = call <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double> %11, <vscale x 2 x double> %8, i64 6)
  %13 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>} %3,  0
  %14 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %3,  1
  %15 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %3,  2
  %16 = call <vscale x 6 x double> @llvm.vector.insert.nxv6f64.nx2f64(<vscale x 6 x double> poison, <vscale x 2 x double> %13, i64 0)
  %17 = call <vscale x 6 x double> @llvm.vector.insert.nxv6f64.nx2f64(<vscale x 6 x double> %16 , <vscale x 2 x double> %14, i64 2)
  %18 = call <vscale x 6 x double> @llvm.vector.insert.nxv6f64.nx2f64(<vscale x 6 x double> %17 , <vscale x 2 x double> %15, i64 4)
  %call = call float @callee3(float 1.000000e+00, float 2.000000e+00, <vscale x 8 x double> %12, <vscale x 6 x double> %18, <vscale x 2 x double> %4)
  ret float %call
}

; Make sure callees read the arguments correctly - tests AArch64ISelLowering::LowerFormalArguments

define double @foo4(double %x0, ptr %ptr1, ptr %ptr2, ptr %ptr3, <vscale x 8 x double> %x1, <vscale x 8 x double> %x2, <vscale x 2 x double> %x3) nounwind {
; CHECK-LABEL: foo4:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1d { z6.d }, p0/z, [x3, #1, mul vl]
; CHECK-NEXT:    ld1d { z7.d }, p0/z, [x3]
; CHECK-NEXT:    ld1d { z24.d }, p0/z, [x3, #3, mul vl]
; CHECK-NEXT:    ld1d { z25.d }, p0/z, [x3, #2, mul vl]
; CHECK-NEXT:    st1d { z4.d }, p0, [x0, #3, mul vl]
; CHECK-NEXT:    st1d { z3.d }, p0, [x0, #2, mul vl]
; CHECK-NEXT:    st1d { z2.d }, p0, [x0, #1, mul vl]
; CHECK-NEXT:    st1d { z1.d }, p0, [x0]
; CHECK-NEXT:    st1d { z25.d }, p0, [x1, #2, mul vl]
; CHECK-NEXT:    st1d { z24.d }, p0, [x1, #3, mul vl]
; CHECK-NEXT:    st1d { z7.d }, p0, [x1]
; CHECK-NEXT:    st1d { z6.d }, p0, [x1, #1, mul vl]
; CHECK-NEXT:    st1d { z5.d }, p0, [x2]
; CHECK-NEXT:    ret
entry:
  store volatile <vscale x 8 x double> %x1, <vscale x 8 x double>* %ptr1
  store volatile <vscale x 8 x double> %x2, <vscale x 8 x double>* %ptr2
  store volatile <vscale x 2 x double> %x3, <vscale x 2 x double>* %ptr3
  ret double %x0
}

define double @foo5(i32 %i0, i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, ptr %ptr1, ptr %ptr2, double %x0, <vscale x 8 x double> %x1, <vscale x 8 x double> %x2) nounwind {
; CHECK-LABEL: foo5:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ldr x8, [sp]
; CHECK-NEXT:    ld1d { z5.d }, p0/z, [x8, #1, mul vl]
; CHECK-NEXT:    ld1d { z6.d }, p0/z, [x8]
; CHECK-NEXT:    ld1d { z7.d }, p0/z, [x8, #3, mul vl]
; CHECK-NEXT:    ld1d { z24.d }, p0/z, [x8, #2, mul vl]
; CHECK-NEXT:    st1d { z4.d }, p0, [x6, #3, mul vl]
; CHECK-NEXT:    st1d { z3.d }, p0, [x6, #2, mul vl]
; CHECK-NEXT:    st1d { z2.d }, p0, [x6, #1, mul vl]
; CHECK-NEXT:    st1d { z1.d }, p0, [x6]
; CHECK-NEXT:    st1d { z24.d }, p0, [x7, #2, mul vl]
; CHECK-NEXT:    st1d { z7.d }, p0, [x7, #3, mul vl]
; CHECK-NEXT:    st1d { z6.d }, p0, [x7]
; CHECK-NEXT:    st1d { z5.d }, p0, [x7, #1, mul vl]
; CHECK-NEXT:    ret
entry:
  store volatile <vscale x 8 x double> %x1, <vscale x 8 x double>* %ptr1
  store volatile <vscale x 8 x double> %x2, <vscale x 8 x double>* %ptr2
  ret double %x0
}

define double @foo6(double %x0, double %x1, ptr %ptr1, ptr %ptr2, <vscale x 8 x double> %x2, <vscale x 6 x double> %x3) nounwind {
; CHECK-LABEL: foo6:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.d
; CHECK-NEXT:    ld1d { z1.d }, p0/z, [x2]
; CHECK-NEXT:    ld1d { z6.d }, p0/z, [x2, #2, mul vl]
; CHECK-NEXT:    ld1d { z7.d }, p0/z, [x2, #1, mul vl]
; CHECK-NEXT:    st1d { z5.d }, p0, [x0, #3, mul vl]
; CHECK-NEXT:    st1d { z4.d }, p0, [x0, #2, mul vl]
; CHECK-NEXT:    st1d { z3.d }, p0, [x0, #1, mul vl]
; CHECK-NEXT:    st1d { z2.d }, p0, [x0]
; CHECK-NEXT:    st1d { z7.d }, p0, [x1, #1, mul vl]
; CHECK-NEXT:    st1d { z6.d }, p0, [x1, #2, mul vl]
; CHECK-NEXT:    st1d { z1.d }, p0, [x1]
; CHECK-NEXT:    ret
entry:
  store volatile <vscale x 8 x double> %x2, <vscale x 8 x double>* %ptr1
  store volatile <vscale x 6 x double> %x3, <vscale x 6 x double>* %ptr2
  ret double %x0
}

; Use AAVPCS, SVE register in z0 - z7 used

define void @aavpcs1(i32 %s0, i32 %s1, i32 %s2, i32 %s3, i32 %s4, i32 %s5, i32 %s6, <vscale x 4 x i32> %s7, <vscale x 4 x i32> %s8, <vscale x 4 x i32> %s9, <vscale x 4 x i32> %s10, <vscale x 4 x i32> %s11, <vscale x 4 x i32> %s12, <vscale x 4 x i32> %s13, <vscale x 4 x i32> %s14, <vscale x 4 x i32> %s15, <vscale x 4 x i32> %s16, ptr %ptr) nounwind {
; CHECK-LABEL: aavpcs1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ldp x8, x9, [sp]
; CHECK-NEXT:    ld1w { z3.s }, p0/z, [x8]
; CHECK-NEXT:    ld1w { z24.s }, p0/z, [x7]
; CHECK-NEXT:    st1w { z0.s }, p0, [x9]
; CHECK-NEXT:    st1w { z1.s }, p0, [x9]
; CHECK-NEXT:    st1w { z2.s }, p0, [x9]
; CHECK-NEXT:    st1w { z4.s }, p0, [x9]
; CHECK-NEXT:    st1w { z5.s }, p0, [x9]
; CHECK-NEXT:    st1w { z6.s }, p0, [x9]
; CHECK-NEXT:    st1w { z7.s }, p0, [x9]
; CHECK-NEXT:    st1w { z24.s }, p0, [x9]
; CHECK-NEXT:    st1w { z3.s }, p0, [x9]
; CHECK-NEXT:    ret
entry:
  store volatile <vscale x 4 x i32> %s7, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s8, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s9, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s11, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s12, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s13, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s14, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s15, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s16, <vscale x 4 x i32>* %ptr
  ret void
}

; Use AAVPCS, SVE register in z0 - z7 used

define void @aavpcs2(float %s0, float %s1, float %s2, float %s3, float %s4, float %s5, float %s6, <vscale x 4 x float> %s7, <vscale x 4 x float> %s8, <vscale x 4 x float> %s9, <vscale x 4 x float> %s10, <vscale x 4 x float> %s11, <vscale x 4 x float> %s12,<vscale x 4 x float> %s13,<vscale x 4 x float> %s14,<vscale x 4 x float> %s15,<vscale x 4 x float> %s16,ptr %ptr) nounwind {
; CHECK-LABEL: aavpcs2:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ldp x8, x9, [sp]
; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x8]
; CHECK-NEXT:    ld1w { z1.s }, p0/z, [x7]
; CHECK-NEXT:    ld1w { z2.s }, p0/z, [x0]
; CHECK-NEXT:    ld1w { z3.s }, p0/z, [x6]
; CHECK-NEXT:    ld1w { z4.s }, p0/z, [x5]
; CHECK-NEXT:    ld1w { z5.s }, p0/z, [x1]
; CHECK-NEXT:    ld1w { z6.s }, p0/z, [x4]
; CHECK-NEXT:    ld1w { z24.s }, p0/z, [x3]
; CHECK-NEXT:    st1w { z7.s }, p0, [x9]
; CHECK-NEXT:    st1w { z2.s }, p0, [x9]
; CHECK-NEXT:    st1w { z5.s }, p0, [x9]
; CHECK-NEXT:    st1w { z24.s }, p0, [x9]
; CHECK-NEXT:    st1w { z6.s }, p0, [x9]
; CHECK-NEXT:    st1w { z4.s }, p0, [x9]
; CHECK-NEXT:    st1w { z3.s }, p0, [x9]
; CHECK-NEXT:    st1w { z1.s }, p0, [x9]
; CHECK-NEXT:    st1w { z0.s }, p0, [x9]
; CHECK-NEXT:    ret
entry:
  store volatile <vscale x 4 x float> %s7, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s8, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s9, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s11, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s12, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s13, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s14, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s15, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s16, <vscale x 4 x float>* %ptr
  ret void
}

; Use AAVPCS, no SVE register in z0 - z7 used (floats occupy z0 - z7) but predicate arg is used

define void @aavpcs3(float %s0, float %s1, float %s2, float %s3, float %s4, float %s5, float %s6, float %s7, <vscale x 4 x float> %s8, <vscale x 4 x float> %s9, <vscale x 4 x float> %s10, <vscale x 4 x float> %s11, <vscale x 4 x float> %s12, <vscale x 4 x float> %s13, <vscale x 4 x float> %s14, <vscale x 4 x float> %s15, <vscale x 4 x float> %s16, <vscale x 4 x float> %s17, <vscale x 16 x i1> %p0, ptr %ptr) nounwind {
; CHECK-LABEL: aavpcs3:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ldr x8, [sp]
; CHECK-NEXT:    ldr x9, [sp, #16]
; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT:    ld1w { z1.s }, p0/z, [x8]
; CHECK-NEXT:    ld1w { z2.s }, p0/z, [x7]
; CHECK-NEXT:    ld1w { z3.s }, p0/z, [x1]
; CHECK-NEXT:    ld1w { z4.s }, p0/z, [x6]
; CHECK-NEXT:    ld1w { z5.s }, p0/z, [x5]
; CHECK-NEXT:    ld1w { z6.s }, p0/z, [x2]
; CHECK-NEXT:    ld1w { z7.s }, p0/z, [x4]
; CHECK-NEXT:    ld1w { z24.s }, p0/z, [x3]
; CHECK-NEXT:    st1w { z0.s }, p0, [x9]
; CHECK-NEXT:    st1w { z3.s }, p0, [x9]
; CHECK-NEXT:    st1w { z6.s }, p0, [x9]
; CHECK-NEXT:    st1w { z24.s }, p0, [x9]
; CHECK-NEXT:    st1w { z7.s }, p0, [x9]
; CHECK-NEXT:    st1w { z5.s }, p0, [x9]
; CHECK-NEXT:    st1w { z4.s }, p0, [x9]
; CHECK-NEXT:    st1w { z2.s }, p0, [x9]
; CHECK-NEXT:    st1w { z1.s }, p0, [x9]
; CHECK-NEXT:    ret
entry:
  store volatile <vscale x 4 x float> %s8, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s9, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s10, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s11, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s12, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s13, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s14, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s15, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s16, <vscale x 4 x float>* %ptr
  ret void
}

; use AAVPCS, SVE register in z0 - z7 used (i32s dont occupy z0 - z7)

define void @aavpcs4(i32 %s0, i32 %s1, i32 %s2, i32 %s3, i32 %s4, i32 %s5, i32 %s6, i32 %s7, <vscale x 4 x i32> %s8, <vscale x 4 x i32> %s9, <vscale x 4 x i32> %s10, <vscale x 4 x i32> %s11, <vscale x 4 x i32> %s12, <vscale x 4 x i32> %s13, <vscale x 4 x i32> %s14, <vscale x 4 x i32> %s15, <vscale x 4 x i32> %s16, <vscale x 4 x i32> %s17, ptr %ptr) nounwind {
; CHECK-LABEL: aavpcs4:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ldr x8, [sp]
; CHECK-NEXT:    ldr x9, [sp, #16]
; CHECK-NEXT:    ld1w { z24.s }, p0/z, [x8]
; CHECK-NEXT:    st1w { z0.s }, p0, [x9]
; CHECK-NEXT:    st1w { z1.s }, p0, [x9]
; CHECK-NEXT:    st1w { z2.s }, p0, [x9]
; CHECK-NEXT:    st1w { z3.s }, p0, [x9]
; CHECK-NEXT:    st1w { z4.s }, p0, [x9]
; CHECK-NEXT:    st1w { z5.s }, p0, [x9]
; CHECK-NEXT:    st1w { z6.s }, p0, [x9]
; CHECK-NEXT:    st1w { z7.s }, p0, [x9]
; CHECK-NEXT:    st1w { z24.s }, p0, [x9]
; CHECK-NEXT:    ret
entry:
  store volatile <vscale x 4 x i32> %s8, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s9, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s10, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s11, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s12, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s13, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s14, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s15, <vscale x 4 x i32>* %ptr
  store volatile <vscale x 4 x i32> %s16, <vscale x 4 x i32>* %ptr
  ret void
}

; Use AAVPCS, SVE register used in return

define <vscale x 4 x float> @aavpcs5(float %s0, float %s1, float %s2, float %s3, float %s4, float %s5, float %s6, float %s7, <vscale x 4 x float> %s8, <vscale x 4 x float> %s9, <vscale x 4 x float> %s10, <vscale x 4 x float> %s11, <vscale x 4 x float> %s12, <vscale x 4 x float> %s13, <vscale x 4 x float> %s14, <vscale x 4 x float> %s15, <vscale x 4 x float> %s16, <vscale x 4 x float> %s17, ptr %ptr) nounwind {
; CHECK-LABEL: aavpcs5:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ldr x8, [sp]
; CHECK-NEXT:    ldr x9, [sp, #16]
; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT:    ld1w { z1.s }, p0/z, [x8]
; CHECK-NEXT:    ld1w { z2.s }, p0/z, [x7]
; CHECK-NEXT:    ld1w { z3.s }, p0/z, [x1]
; CHECK-NEXT:    ld1w { z4.s }, p0/z, [x6]
; CHECK-NEXT:    ld1w { z5.s }, p0/z, [x5]
; CHECK-NEXT:    ld1w { z6.s }, p0/z, [x2]
; CHECK-NEXT:    ld1w { z7.s }, p0/z, [x4]
; CHECK-NEXT:    ld1w { z24.s }, p0/z, [x3]
; CHECK-NEXT:    st1w { z0.s }, p0, [x9]
; CHECK-NEXT:    st1w { z3.s }, p0, [x9]
; CHECK-NEXT:    st1w { z6.s }, p0, [x9]
; CHECK-NEXT:    st1w { z24.s }, p0, [x9]
; CHECK-NEXT:    st1w { z7.s }, p0, [x9]
; CHECK-NEXT:    st1w { z5.s }, p0, [x9]
; CHECK-NEXT:    st1w { z4.s }, p0, [x9]
; CHECK-NEXT:    st1w { z2.s }, p0, [x9]
; CHECK-NEXT:    st1w { z1.s }, p0, [x9]
; CHECK-NEXT:    ret
entry:
  store volatile <vscale x 4 x float> %s8, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s9, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s10, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s11, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s12, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s13, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s14, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s15, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s16, <vscale x 4 x float>* %ptr
  ret <vscale x 4 x float> %s8
}

define void @aapcs1(float %s0, float %s1, float %s2, float %s3, float %s4, float %s5, float %s6, float %s7, <vscale x 4 x float> %s8, <vscale x 4 x float> %s9, <vscale x 4 x float> %s10, <vscale x 4 x float> %s11, <vscale x 4 x float> %s12, <vscale x 4 x float> %s13, <vscale x 4 x float> %s14, <vscale x 4 x float> %s15, <vscale x 4 x float> %s16, <vscale x 4 x float> %s17, ptr %ptr) nounwind {
; CHECK-LABEL: aapcs1:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    ldr x8, [sp]
; CHECK-NEXT:    ldr x9, [sp, #16]
; CHECK-NEXT:    ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT:    ld1w { z1.s }, p0/z, [x8]
; CHECK-NEXT:    ld1w { z2.s }, p0/z, [x7]
; CHECK-NEXT:    ld1w { z3.s }, p0/z, [x1]
; CHECK-NEXT:    ld1w { z4.s }, p0/z, [x6]
; CHECK-NEXT:    ld1w { z5.s }, p0/z, [x5]
; CHECK-NEXT:    ld1w { z6.s }, p0/z, [x2]
; CHECK-NEXT:    ld1w { z7.s }, p0/z, [x4]
; CHECK-NEXT:    ld1w { z16.s }, p0/z, [x3]
; CHECK-NEXT:    st1w { z0.s }, p0, [x9]
; CHECK-NEXT:    st1w { z3.s }, p0, [x9]
; CHECK-NEXT:    st1w { z6.s }, p0, [x9]
; CHECK-NEXT:    st1w { z16.s }, p0, [x9]
; CHECK-NEXT:    st1w { z7.s }, p0, [x9]
; CHECK-NEXT:    st1w { z5.s }, p0, [x9]
; CHECK-NEXT:    st1w { z4.s }, p0, [x9]
; CHECK-NEXT:    st1w { z2.s }, p0, [x9]
; CHECK-NEXT:    st1w { z1.s }, p0, [x9]
; CHECK-NEXT:    ret
entry:
  store volatile <vscale x 4 x float> %s8, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s9, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s10, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s11, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s12, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s13, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s14, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s15, <vscale x 4 x float>* %ptr
  store volatile <vscale x 4 x float> %s16, <vscale x 4 x float>* %ptr
  ret void
}

declare void @non_sve_callee_high_range(float %f0, float %f1, float %f2, float %f3, float %f4, float %f5, float %f6, float %f7, <vscale x 4 x float> %v0, <vscale x 4 x float> %v1)

define void @non_sve_caller_non_sve_callee_high_range()  {
; CHECK-LABEL: non_sve_caller_non_sve_callee_high_range:
; CHECK:       // %bb.0:
; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT:    addvl sp, sp, #-2
; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
; CHECK-NEXT:    .cfi_offset w30, -8
; CHECK-NEXT:    .cfi_offset w29, -16
; CHECK-NEXT:    movi d0, #0000000000000000
; CHECK-NEXT:    fmov s1, #1.00000000
; CHECK-NEXT:    addvl x0, sp, #1
; CHECK-NEXT:    fmov s2, #2.00000000
; CHECK-NEXT:    fmov s3, #3.00000000
; CHECK-NEXT:    mov x1, sp
; CHECK-NEXT:    fmov s4, #4.00000000
; CHECK-NEXT:    fmov s5, #5.00000000
; CHECK-NEXT:    fmov s6, #6.00000000
; CHECK-NEXT:    fmov s7, #7.00000000
; CHECK-NEXT:    bl non_sve_callee_high_range
; CHECK-NEXT:    addvl sp, sp, #2
; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT:    ret
  call void @non_sve_callee_high_range(float 0.0, float 1.0, float 2.0, float 3.0, float 4.0, float 5.0, float 6.0, float 7.0, <vscale x 4 x float> undef, <vscale x 4 x float> undef)
  ret void
}

define void @non_sve_caller_high_range_non_sve_callee_high_range(float %f0, float %f1, float %f2, float %f3, float %f4, float %f5, float %f6, float %f7, <vscale x 4 x float> %v0, <vscale x 4 x float> %v1)  {
; CHECK-LABEL: non_sve_caller_high_range_non_sve_callee_high_range:
; CHECK:       // %bb.0:
; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT:    addvl sp, sp, #-2
; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x10, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 16 * VG
; CHECK-NEXT:    .cfi_offset w30, -8
; CHECK-NEXT:    .cfi_offset w29, -16
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    movi d0, #0000000000000000
; CHECK-NEXT:    fmov s1, #1.00000000
; CHECK-NEXT:    fmov s2, #2.00000000
; CHECK-NEXT:    fmov s3, #3.00000000
; CHECK-NEXT:    fmov s4, #4.00000000
; CHECK-NEXT:    fmov s5, #5.00000000
; CHECK-NEXT:    fmov s6, #6.00000000
; CHECK-NEXT:    fmov s7, #7.00000000
; CHECK-NEXT:    ld1w { z16.s }, p0/z, [x0]
; CHECK-NEXT:    ld1w { z17.s }, p0/z, [x1]
; CHECK-NEXT:    addvl x0, sp, #1
; CHECK-NEXT:    mov x1, sp
; CHECK-NEXT:    st1w { z17.s }, p0, [sp]
; CHECK-NEXT:    st1w { z16.s }, p0, [sp, #1, mul vl]
; CHECK-NEXT:    bl non_sve_callee_high_range
; CHECK-NEXT:    addvl sp, sp, #2
; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT:    ret
  call void @non_sve_callee_high_range(float 0.0, float 1.0, float 2.0, float 3.0, float 4.0, float 5.0, float 6.0, float 7.0, <vscale x 4 x float> %v0, <vscale x 4 x float> %v1)
  ret void
}

define <vscale x 4 x float> @sve_caller_non_sve_callee_high_range(<vscale x 4 x float> %v0, <vscale x 4 x float> %v1)  {
; CHECK-LABEL: sve_caller_non_sve_callee_high_range:
; CHECK:       // %bb.0:
; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT:    addvl sp, sp, #-18
; CHECK-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    addvl sp, sp, #-3
; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xa8, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 168 * VG
; CHECK-NEXT:    .cfi_offset w30, -8
; CHECK-NEXT:    .cfi_offset w29, -16
; CHECK-NEXT:    .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 16 - 32 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 16 - 40 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    mov z25.d, z0.d
; CHECK-NEXT:    str z0, [sp] // 16-byte Folded Spill
; CHECK-NEXT:    movi d0, #0000000000000000
; CHECK-NEXT:    mov z24.d, z1.d
; CHECK-NEXT:    addvl x0, sp, #2
; CHECK-NEXT:    fmov s1, #1.00000000
; CHECK-NEXT:    fmov s2, #2.00000000
; CHECK-NEXT:    addvl x1, sp, #1
; CHECK-NEXT:    fmov s3, #3.00000000
; CHECK-NEXT:    fmov s4, #4.00000000
; CHECK-NEXT:    fmov s5, #5.00000000
; CHECK-NEXT:    fmov s6, #6.00000000
; CHECK-NEXT:    fmov s7, #7.00000000
; CHECK-NEXT:    st1w { z24.s }, p0, [sp, #1, mul vl]
; CHECK-NEXT:    st1w { z25.s }, p0, [sp, #2, mul vl]
; CHECK-NEXT:    bl non_sve_callee_high_range
; CHECK-NEXT:    ldr z0, [sp] // 16-byte Folded Reload
; CHECK-NEXT:    addvl sp, sp, #3
; CHECK-NEXT:    ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    addvl sp, sp, #18
; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT:    ret
  call void @non_sve_callee_high_range(float 0.0, float 1.0, float 2.0, float 3.0, float 4.0, float 5.0, float 6.0, float 7.0, <vscale x 4 x float> %v0, <vscale x 4 x float> %v1)
  ret <vscale x 4 x float> %v0
}

define <vscale x 4 x float> @sve_ret_caller_non_sve_callee_high_range()  {
; CHECK-LABEL: sve_ret_caller_non_sve_callee_high_range:
; CHECK:       // %bb.0:
; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT:    addvl sp, sp, #-18
; CHECK-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
; CHECK-NEXT:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
; CHECK-NEXT:    addvl sp, sp, #-2
; CHECK-NEXT:    .cfi_escape 0x0f, 0x0d, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0xa0, 0x01, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 160 * VG
; CHECK-NEXT:    .cfi_offset w30, -8
; CHECK-NEXT:    .cfi_offset w29, -16
; CHECK-NEXT:    .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 16 - 8 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 16 - 16 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 16 - 24 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 16 - 32 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 16 - 40 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 16 - 48 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 16 - 56 * VG
; CHECK-NEXT:    .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x70, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 16 - 64 * VG
; CHECK-NEXT:    movi d0, #0000000000000000
; CHECK-NEXT:    fmov s1, #1.00000000
; CHECK-NEXT:    addvl x0, sp, #1
; CHECK-NEXT:    fmov s2, #2.00000000
; CHECK-NEXT:    fmov s3, #3.00000000
; CHECK-NEXT:    mov x1, sp
; CHECK-NEXT:    fmov s4, #4.00000000
; CHECK-NEXT:    fmov s5, #5.00000000
; CHECK-NEXT:    fmov s6, #6.00000000
; CHECK-NEXT:    fmov s7, #7.00000000
; CHECK-NEXT:    bl non_sve_callee_high_range
; CHECK-NEXT:    addvl sp, sp, #2
; CHECK-NEXT:    ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
; CHECK-NEXT:    ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
; CHECK-NEXT:    addvl sp, sp, #18
; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT:    ret
  call void @non_sve_callee_high_range(float 0.0, float 1.0, float 2.0, float 3.0, float 4.0, float 5.0, float 6.0, float 7.0, <vscale x 4 x float> undef, <vscale x 4 x float> undef)
  ret <vscale x 4 x float> undef
}

declare void @func_f8_and_v0_passed_via_memory(float %f0, float %f1, float %f2, float %f3, float %f4, float %f5, float %f6, float %f7, float %f8, <vscale x 4 x float> %v0)
define void @verify_all_operands_are_initialised() {
; CHECK-LABEL: verify_all_operands_are_initialised:
; CHECK:       // %bb.0:
; CHECK-NEXT:    stp x29, x30, [sp, #-16]! // 16-byte Folded Spill
; CHECK-NEXT:    sub sp, sp, #16
; CHECK-NEXT:    addvl sp, sp, #-1
; CHECK-NEXT:    .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x20, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 32 + 8 * VG
; CHECK-NEXT:    .cfi_offset w30, -8
; CHECK-NEXT:    .cfi_offset w29, -16
; CHECK-NEXT:    ptrue p0.s
; CHECK-NEXT:    movi d0, #0000000000000000
; CHECK-NEXT:    fmov s1, #1.00000000
; CHECK-NEXT:    fmov z16.s, #9.00000000
; CHECK-NEXT:    mov w8, #1090519040 // =0x41000000
; CHECK-NEXT:    add x0, sp, #16
; CHECK-NEXT:    fmov s2, #2.00000000
; CHECK-NEXT:    fmov s3, #3.00000000
; CHECK-NEXT:    add x9, sp, #16
; CHECK-NEXT:    fmov s4, #4.00000000
; CHECK-NEXT:    fmov s5, #5.00000000
; CHECK-NEXT:    fmov s6, #6.00000000
; CHECK-NEXT:    fmov s7, #7.00000000
; CHECK-NEXT:    st1w { z16.s }, p0, [x9]
; CHECK-NEXT:    str w8, [sp]
; CHECK-NEXT:    bl func_f8_and_v0_passed_via_memory
; CHECK-NEXT:    addvl sp, sp, #1
; CHECK-NEXT:    add sp, sp, #16
; CHECK-NEXT:    ldp x29, x30, [sp], #16 // 16-byte Folded Reload
; CHECK-NEXT:    ret
  call void @func_f8_and_v0_passed_via_memory(float 0.0, float 1.0, float 2.0, float 3.0, float 4.0, float 5.0, float 6.0, float 7.0, float 8.0, <vscale x 4 x float> shufflevector (<vscale x 4 x float> insertelement (<vscale x 4 x float> poison, float 9.000000e+00, i64 0), <vscale x 4 x float> poison, <vscale x 4 x i32> zeroinitializer))
  ret void
}

declare float @callee1(float, <vscale x 8 x double>, <vscale x 8 x double>, <vscale x 2 x double>)
declare float @callee2(i32, i32, i32, i32, i32, i32, i32, i32, float, <vscale x 8 x double>, <vscale x 8 x double>)
declare float @callee3(float, float, <vscale x 8 x double>, <vscale x 6 x double>, <vscale x 2 x double>)

declare <vscale x 16 x i1> @llvm.aarch64.sve.ptrue.nxv16i1(i32 immarg)
declare <vscale x 2 x i1> @llvm.aarch64.sve.convert.from.svbool.nxv2i1(<vscale x 16 x i1>)
declare {<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>} @llvm.aarch64.sve.ld4.sret.nxv2f64(<vscale x 2 x i1>, ptr)
declare {<vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>} @llvm.aarch64.sve.ld3.sret.nxv2f64(<vscale x 2 x i1>, ptr)
declare <vscale x 2 x double> @llvm.aarch64.sve.ld1.nxv2f64(<vscale x 2 x i1>, ptr)
declare double @llvm.aarch64.sve.faddv.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>)
declare <vscale x 8 x double> @llvm.vector.insert.nxv8f64.nx2f64(<vscale x 8 x double>, <vscale x 2 x double>, i64)
declare <vscale x 6 x double> @llvm.vector.insert.nxv6f64.nx2f64(<vscale x 6 x double>, <vscale x 2 x double>, i64)