; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes='default<O2>' -S | FileCheck %s

target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.12.0"

define {i8*, i32} @f(i8* %buffer, i32* %array) {
; CHECK-LABEL: @f(
; CHECK-NEXT:  PostSpill:
; CHECK-NEXT:    [[ARRAY_SPILL_ADDR:%.*]] = bitcast i8* [[BUFFER:%.*]] to i32**
; CHECK-NEXT:    store i32* [[ARRAY:%.*]], i32** [[ARRAY_SPILL_ADDR]], align 8
; CHECK-NEXT:    [[LOAD:%.*]] = load i32, i32* [[ARRAY]], align 4
; CHECK-NEXT:    [[LOAD_POS:%.*]] = icmp sgt i32 [[LOAD]], 0
; CHECK-NEXT:    [[TMP0:%.*]] = tail call i32 @llvm.smax.i32(i32 [[LOAD]], i32 0)
; CHECK-NEXT:    [[TMP1:%.*]] = select i1 [[LOAD_POS]], i8* bitcast (void (i8*, i1)* @f.resume.0 to i8*), i8* bitcast (void (i8*, i1)* @f.resume.1 to i8*)
; CHECK-NEXT:    [[TMP2:%.*]] = insertvalue { i8*, i32 } undef, i8* [[TMP1]], 0
; CHECK-NEXT:    [[TMP3:%.*]] = insertvalue { i8*, i32 } [[TMP2]], i32 [[TMP0]], 1
; CHECK-NEXT:    ret { i8*, i32 } [[TMP3]]
;
entry:
  %id = call token @llvm.coro.id.retcon.once(i32 8, i32 8, i8* %buffer, i8* bitcast (void (i8*, i1)* @prototype to i8*), i8* bitcast (i8* (i32)* @allocate to i8*), i8* bitcast (void (i8*)* @deallocate to i8*))
  %hdl = call i8* @llvm.coro.begin(token %id, i8* null)
  %load = load i32, i32* %array
  %load.pos = icmp sgt i32 %load, 0
  br i1 %load.pos, label %pos, label %neg

pos:
  %unwind0 = call i1 (...) @llvm.coro.suspend.retcon.i1(i32 %load)
  br i1 %unwind0, label %cleanup, label %pos.cont

pos.cont:
  store i32 0, i32* %array, align 4
  br label %cleanup

neg:
  %unwind1 = call i1 (...) @llvm.coro.suspend.retcon.i1(i32 0)
  br i1 %unwind1, label %cleanup, label %neg.cont

neg.cont:
  store i32 10, i32* %array, align 4
  br label %cleanup

cleanup:
  call i1 @llvm.coro.end(i8* %hdl, i1 0)
  unreachable
}

define void @test(i32* %array) {
; CHECK-LABEL: @test(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[TMP0:%.*]] = alloca i32*, align 8
; CHECK-NEXT:    [[DOTSUB:%.*]] = bitcast i32** [[TMP0]] to i8*
; CHECK-NEXT:    store i32* [[ARRAY:%.*]], i32** [[TMP0]], align 8
; CHECK-NEXT:    [[LOAD_I:%.*]] = load i32, i32* [[ARRAY]], align 4
; CHECK-NEXT:    [[LOAD_POS_I:%.*]] = icmp sgt i32 [[LOAD_I]], 0
; CHECK-NEXT:    [[TMP1:%.*]] = tail call i32 @llvm.smax.i32(i32 [[LOAD_I]], i32 0)
; CHECK-NEXT:    tail call void @print(i32 [[TMP1]])
; CHECK-NEXT:    [[CONT_CAST:%.*]] = select i1 [[LOAD_POS_I]], void (i8*, i1)* @f.resume.0, void (i8*, i1)* @f.resume.1
; CHECK-NEXT:    call void [[CONT_CAST]](i8* nonnull [[DOTSUB]], i1 zeroext false)
; CHECK-NEXT:    ret void
;
entry:
  %0 = alloca [8 x i8], align 8
  %buffer = bitcast [8 x i8]* %0 to i8*
  %prepare = call i8* @llvm.coro.prepare.retcon(i8* bitcast ({i8*, i32} (i8*, i32*)* @f to i8*))
  %f = bitcast i8* %prepare to {i8*, i32} (i8*, i32*)*
  %result = call {i8*, i32} %f(i8* %buffer, i32* %array)
  %value = extractvalue {i8*, i32} %result, 1
  call void @print(i32 %value)
  %cont = extractvalue {i8*, i32} %result, 0
  %cont.cast = bitcast i8* %cont to void (i8*, i1)*
  call void %cont.cast(i8* %buffer, i1 zeroext 0)
  ret void
}

;   Unfortunately, we don't seem to fully optimize this right now due
;   to some sort of phase-ordering thing.

declare token @llvm.coro.id.retcon.once(i32, i32, i8*, i8*, i8*, i8*)
declare i8* @llvm.coro.begin(token, i8*)
declare i1 @llvm.coro.suspend.retcon.i1(...)
declare i1 @llvm.coro.end(i8*, i1)
declare i8* @llvm.coro.prepare.retcon(i8*)

declare void @prototype(i8*, i1 zeroext)

declare noalias i8* @allocate(i32 %size)
declare void @deallocate(i8* %ptr)

declare void @print(i32)