; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --include-generated-funcs
; RUN: opt -S -passes=verify,iroutliner -ir-outlining-no-cost < %s | FileCheck %s

; Here we have multiple exits, but the different sources, same outputs are
; needed, this checks that they are compressed, and moved into the appropriate
; output blocks.

define void @outline_outputs1() #0 {
entry:
  %output = alloca i32, align 4
  %result = alloca i32, align 4
  %output2 = alloca i32, align 4
  %result2 = alloca i32, align 4
  %a = alloca i32, align 4
  %b = alloca i32, align 4
  br label %block_2
block_1:
  %a2 = alloca i32, align 4
  %b2 = alloca i32, align 4
  br label %block_2
block_2:
  %a2val = load i32, ptr %a
  %b2val = load i32, ptr %b
  %add2 = add i32 2, %a2val
  %mul2 = mul i32 2, %b2val
  br label %block_5
block_3:
  %aval = load i32, ptr %a
  %bval = load i32, ptr %b
  %add = add i32 2, %aval
  %mul = mul i32 2, %bval
  br label %block_4
block_4:
  store i32 %add, ptr %output, align 4
  store i32 %mul, ptr %result, align 4
  br label %block_6
block_5:
  store i32 %add2, ptr %output, align 4
  store i32 %mul2, ptr %result, align 4
  br label %block_6
dummy:
  ret void
block_6:
  %diff = phi i32 [%aval, %block_4], [%a2val, %block_5]
  ret void
}

define void @outline_outputs2() #0 {
entry:
  %output = alloca i32, align 4
  %result = alloca i32, align 4
  %output2 = alloca i32, align 4
  %result2 = alloca i32, align 4
  %a = alloca i32, align 4
  %b = alloca i32, align 4
  br label %block_2
block_1:
  %a2 = alloca i32, align 4
  %b2 = alloca i32, align 4
  br label %block_2
block_2:
  %a2val = load i32, ptr %a
  %b2val = load i32, ptr %b
  %add2 = add i32 2, %a2val
  %mul2 = mul i32 2, %b2val
  br label %block_5
block_3:
  %aval = load i32, ptr %a
  %bval = load i32, ptr %b
  %add = add i32 2, %aval
  %mul = mul i32 2, %bval
  br label %block_4
block_4:
  store i32 %add, ptr %output, align 4
  store i32 %mul, ptr %result, align 4
  br label %block_6
block_5:
  store i32 %add2, ptr %output, align 4
  store i32 %mul2, ptr %result, align 4
  br label %block_6
dummy:
  ret void
block_6:
  %diff = phi i32 [%aval, %block_4], [%a2val, %block_5]
  ret void
}

; CHECK-LABEL: @outline_outputs1(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[DIFF_CE_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[OUTPUT:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[RESULT:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[OUTPUT2:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[RESULT2:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT:    br label [[BLOCK_2:%.*]]
; CHECK:       block_1:
; CHECK-NEXT:    [[A2:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[B2:%.*]] = alloca i32, align 4
; CHECK-NEXT:    br label [[BLOCK_2]]
; CHECK:       block_2:
; CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 -1, ptr [[DIFF_CE_LOC]])
; CHECK-NEXT:    call void @outlined_ir_func_0(ptr [[A]], ptr [[B]], ptr [[OUTPUT]], ptr [[RESULT]], ptr [[DIFF_CE_LOC]])
; CHECK-NEXT:    [[DIFF_CE_RELOAD:%.*]] = load i32, ptr [[DIFF_CE_LOC]], align 4
; CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 -1, ptr [[DIFF_CE_LOC]])
; CHECK-NEXT:    br label [[BLOCK_6:%.*]]
; CHECK: dummy:
; CHECK-NEXT:  ret void
; CHECK:       block_6:
; CHECK-NEXT:    [[DIFF:%.*]] = phi i32 [ [[DIFF_CE_RELOAD]], [[BLOCK_2]] ]
; CHECK-NEXT:    ret void
;
;
; CHECK-LABEL: @outline_outputs2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[DIFF_CE_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[OUTPUT:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[RESULT:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[OUTPUT2:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[RESULT2:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT:    br label [[BLOCK_2:%.*]]
; CHECK:       block_1:
; CHECK-NEXT:    [[A2:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[B2:%.*]] = alloca i32, align 4
; CHECK-NEXT:    br label [[BLOCK_2]]
; CHECK:       block_2:
; CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 -1, ptr [[DIFF_CE_LOC]])
; CHECK-NEXT:    call void @outlined_ir_func_0(ptr [[A]], ptr [[B]], ptr [[OUTPUT]], ptr [[RESULT]], ptr [[DIFF_CE_LOC]])
; CHECK-NEXT:    [[DIFF_CE_RELOAD:%.*]] = load i32, ptr [[DIFF_CE_LOC]], align 4
; CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 -1, ptr [[DIFF_CE_LOC]])
; CHECK-NEXT:    br label [[BLOCK_6:%.*]]
; CHECK: dummy:
; CHECK-NEXT:  ret void
; CHECK:       block_6:
; CHECK-NEXT:    [[DIFF:%.*]] = phi i32 [ [[DIFF_CE_RELOAD]], [[BLOCK_2]] ]
; CHECK-NEXT:    ret void
;
;
; CHECK:  define internal void @outlined_ir_func_0(
; CHECK-NEXT:  newFuncRoot:
; CHECK-NEXT:    br label [[BLOCK_2_TO_OUTLINE:%.*]]
; CHECK:       block_2_to_outline:
; CHECK-NEXT:    [[A2VAL:%.*]] = load i32, ptr [[TMP0:%.*]], align 4
; CHECK-NEXT:    [[B2VAL:%.*]] = load i32, ptr [[TMP1:%.*]], align 4
; CHECK-NEXT:    [[ADD2:%.*]] = add i32 2, [[A2VAL]]
; CHECK-NEXT:    [[MUL2:%.*]] = mul i32 2, [[B2VAL]]
; CHECK-NEXT:    br label [[BLOCK_5:%.*]]
; CHECK:       block_3:
; CHECK-NEXT:    [[AVAL:%.*]] = load i32, ptr [[TMP0]], align 4
; CHECK-NEXT:    [[BVAL:%.*]] = load i32, ptr [[TMP1]], align 4
; CHECK-NEXT:    [[ADD:%.*]] = add i32 2, [[AVAL]]
; CHECK-NEXT:    [[MUL:%.*]] = mul i32 2, [[BVAL]]
; CHECK-NEXT:    br label [[BLOCK_4:%.*]]
; CHECK:       block_4:
; CHECK-NEXT:    store i32 [[ADD]], ptr [[TMP2:%.*]], align 4
; CHECK-NEXT:    store i32 [[MUL]], ptr [[TMP3:%.*]], align 4
; CHECK-NEXT:    br label [[BLOCK_6_SPLIT:%.*]]
; CHECK:       block_5:
; CHECK-NEXT:    store i32 [[ADD2]], ptr [[TMP2]], align 4
; CHECK-NEXT:    store i32 [[MUL2]], ptr [[TMP3]], align 4
; CHECK-NEXT:    br label [[BLOCK_6_SPLIT]]
; CHECK:       block_6.split:
; CHECK-NEXT:    [[DIFF_CE:%.*]] = phi i32 [ [[AVAL]], [[BLOCK_4]] ], [ [[A2VAL]], [[BLOCK_5]] ]
; CHECK-NEXT:    br label [[BLOCK_6_EXITSTUB:%.*]]
; CHECK:       block_6.exitStub:
; CHECK-NEXT:    store i32 [[DIFF_CE]], ptr [[TMP4:%.*]], align 4
; CHECK-NEXT:    ret void
;