; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-linux-gnu -aarch64-streaming-hazard-size=0 -mattr=+sve -mattr=+sme -start-after=simplifycfg -enable-tail-merge=false -verify-machineinstrs < %s | FileCheck %s

declare void @normal_callee();
declare void @streaming_callee() "aarch64_pstate_sm_enabled";
declare void @streaming_compatible_callee() "aarch64_pstate_sm_compatible";

define float @sm_body_sm_compatible_simple() "aarch64_pstate_sm_compatible" "aarch64_pstate_sm_body" nounwind {
; CHECK-LABEL: sm_body_sm_compatible_simple:
; CHECK:       // %bb.0:
; CHECK-NEXT:    stp d15, d14, [sp, #-96]! // 16-byte Folded Spill
; CHECK-NEXT:    rdsvl x9, #1
; CHECK-NEXT:    stp d13, d12, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT:    lsr x9, x9, #3
; CHECK-NEXT:    stp d11, d10, [sp, #32] // 16-byte Folded Spill
; CHECK-NEXT:    stp d9, d8, [sp, #48] // 16-byte Folded Spill
; CHECK-NEXT:    stp x30, x9, [sp, #64] // 16-byte Folded Spill
; CHECK-NEXT:    cntd x9
; CHECK-NEXT:    str x9, [sp, #80] // 8-byte Folded Spill
; CHECK-NEXT:    bl __arm_sme_state
; CHECK-NEXT:    and x8, x0, #0x1
; CHECK-NEXT:    tbnz w8, #0, .LBB0_2
; CHECK-NEXT:  // %bb.1:
; CHECK-NEXT:    smstart sm
; CHECK-NEXT:  .LBB0_2:
; CHECK-NEXT:    tbnz w8, #0, .LBB0_4
; CHECK-NEXT:  // %bb.3:
; CHECK-NEXT:    smstop sm
; CHECK-NEXT:  .LBB0_4:
; CHECK-NEXT:    ldp d9, d8, [sp, #48] // 16-byte Folded Reload
; CHECK-NEXT:    fmov s0, wzr
; CHECK-NEXT:    ldp d11, d10, [sp, #32] // 16-byte Folded Reload
; CHECK-NEXT:    ldr x30, [sp, #64] // 8-byte Folded Reload
; CHECK-NEXT:    ldp d13, d12, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT:    ldp d15, d14, [sp], #96 // 16-byte Folded Reload
; CHECK-NEXT:    ret
  ret float zeroinitializer
}

define void @sm_body_caller_sm_compatible_caller_normal_callee() "aarch64_pstate_sm_compatible" "aarch64_pstate_sm_body" nounwind {
; CHECK-LABEL: sm_body_caller_sm_compatible_caller_normal_callee:
; CHECK:       // %bb.0:
; CHECK-NEXT:    stp d15, d14, [sp, #-96]! // 16-byte Folded Spill
; CHECK-NEXT:    rdsvl x9, #1
; CHECK-NEXT:    stp d13, d12, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT:    lsr x9, x9, #3
; CHECK-NEXT:    stp d11, d10, [sp, #32] // 16-byte Folded Spill
; CHECK-NEXT:    stp d9, d8, [sp, #48] // 16-byte Folded Spill
; CHECK-NEXT:    stp x30, x9, [sp, #64] // 16-byte Folded Spill
; CHECK-NEXT:    cntd x9
; CHECK-NEXT:    stp x9, x19, [sp, #80] // 16-byte Folded Spill
; CHECK-NEXT:    bl __arm_sme_state
; CHECK-NEXT:    and x19, x0, #0x1
; CHECK-NEXT:    tbnz w19, #0, .LBB1_2
; CHECK-NEXT:  // %bb.1:
; CHECK-NEXT:    smstart sm
; CHECK-NEXT:  .LBB1_2:
; CHECK-NEXT:    smstop sm
; CHECK-NEXT:    bl normal_callee
; CHECK-NEXT:    smstart sm
; CHECK-NEXT:    tbnz w19, #0, .LBB1_4
; CHECK-NEXT:  // %bb.3:
; CHECK-NEXT:    smstop sm
; CHECK-NEXT:  .LBB1_4:
; CHECK-NEXT:    ldp d9, d8, [sp, #48] // 16-byte Folded Reload
; CHECK-NEXT:    ldr x19, [sp, #88] // 8-byte Folded Reload
; CHECK-NEXT:    ldp d11, d10, [sp, #32] // 16-byte Folded Reload
; CHECK-NEXT:    ldr x30, [sp, #64] // 8-byte Folded Reload
; CHECK-NEXT:    ldp d13, d12, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT:    ldp d15, d14, [sp], #96 // 16-byte Folded Reload
; CHECK-NEXT:    ret
  call void @normal_callee()
  ret void
}

; Function Attrs: nounwind uwtable vscale_range(1,16)
define void @streaming_body_and_streaming_compatible_interface_multi_basic_block(i32 noundef %x) "aarch64_pstate_sm_compatible" "aarch64_pstate_sm_body" nounwind {
; CHECK-LABEL: streaming_body_and_streaming_compatible_interface_multi_basic_block:
; CHECK:       // %bb.0: // %entry
; CHECK-NEXT:    stp d15, d14, [sp, #-96]! // 16-byte Folded Spill
; CHECK-NEXT:    rdsvl x9, #1
; CHECK-NEXT:    stp d13, d12, [sp, #16] // 16-byte Folded Spill
; CHECK-NEXT:    mov w8, w0
; CHECK-NEXT:    lsr x9, x9, #3
; CHECK-NEXT:    stp d11, d10, [sp, #32] // 16-byte Folded Spill
; CHECK-NEXT:    stp d9, d8, [sp, #48] // 16-byte Folded Spill
; CHECK-NEXT:    stp x30, x9, [sp, #64] // 16-byte Folded Spill
; CHECK-NEXT:    cntd x9
; CHECK-NEXT:    stp x9, x19, [sp, #80] // 16-byte Folded Spill
; CHECK-NEXT:    bl __arm_sme_state
; CHECK-NEXT:    and x19, x0, #0x1
; CHECK-NEXT:    tbnz w19, #0, .LBB2_2
; CHECK-NEXT:  // %bb.1: // %entry
; CHECK-NEXT:    smstart sm
; CHECK-NEXT:  .LBB2_2: // %entry
; CHECK-NEXT:    cbz w8, .LBB2_6
; CHECK-NEXT:  // %bb.3: // %if.else
; CHECK-NEXT:    bl streaming_compatible_callee
; CHECK-NEXT:    tbnz w19, #0, .LBB2_5
; CHECK-NEXT:  // %bb.4: // %if.else
; CHECK-NEXT:    smstop sm
; CHECK-NEXT:  .LBB2_5: // %if.else
; CHECK-NEXT:    ldp d9, d8, [sp, #48] // 16-byte Folded Reload
; CHECK-NEXT:    ldr x19, [sp, #88] // 8-byte Folded Reload
; CHECK-NEXT:    ldp d11, d10, [sp, #32] // 16-byte Folded Reload
; CHECK-NEXT:    ldr x30, [sp, #64] // 8-byte Folded Reload
; CHECK-NEXT:    ldp d13, d12, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT:    ldp d15, d14, [sp], #96 // 16-byte Folded Reload
; CHECK-NEXT:    ret
; CHECK-NEXT:  .LBB2_6: // %if.then
; CHECK-NEXT:    smstop sm
; CHECK-NEXT:    bl normal_callee
; CHECK-NEXT:    smstart sm
; CHECK-NEXT:    tbnz w19, #0, .LBB2_8
; CHECK-NEXT:  // %bb.7: // %if.then
; CHECK-NEXT:    smstop sm
; CHECK-NEXT:  .LBB2_8: // %if.then
; CHECK-NEXT:    ldp d9, d8, [sp, #48] // 16-byte Folded Reload
; CHECK-NEXT:    ldr x19, [sp, #88] // 8-byte Folded Reload
; CHECK-NEXT:    ldp d11, d10, [sp, #32] // 16-byte Folded Reload
; CHECK-NEXT:    ldr x30, [sp, #64] // 8-byte Folded Reload
; CHECK-NEXT:    ldp d13, d12, [sp, #16] // 16-byte Folded Reload
; CHECK-NEXT:    ldp d15, d14, [sp], #96 // 16-byte Folded Reload
; CHECK-NEXT:    ret
entry:
  %cmp = icmp eq i32 %x, 0
  br i1 %cmp, label %if.then, label %if.else

if.then:                                          ; preds = %entry
  tail call void @normal_callee()
  br label %return

if.else:                                          ; preds = %entry
  tail call void @streaming_compatible_callee()
  br label %return

return:                                           ; preds = %if.else, %if.then
  ret void
}