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

; This test makes sure we are extracting the found similarity sections
; correctly at the call site.

define void @extract1() {
; CHECK-LABEL: @extract1(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[C:%.*]] = alloca i32, align 4
; CHECK-NEXT:    call void @outlined_ir_func_1(ptr [[A]], ptr [[B]], ptr [[C]])
; CHECK-NEXT:    ret void
;
entry:
  %a = alloca i32, align 4
  %b = alloca i32, align 4
  %c = alloca i32, align 4
  store i32 2, ptr %a, align 4
  store i32 3, ptr %b, align 4
  store i32 4, ptr %c, align 4
  %al = load i32, ptr %a
  %bl = load i32, ptr %b
  %cl = load i32, ptr %c
  ret void
}

define void @extract2() {
; CHECK-LABEL: @extract2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[C:%.*]] = alloca i32, align 4
; CHECK-NEXT:    call void @outlined_ir_func_1(ptr [[A]], ptr [[B]], ptr [[C]])
; CHECK-NEXT:    ret void
;
entry:
  %a = alloca i32, align 4
  %b = alloca i32, align 4
  %c = alloca i32, align 4
  store i32 2, ptr %a, align 4
  store i32 3, ptr %b, align 4
  store i32 4, ptr %c, align 4
  %al = load i32, ptr %a
  %bl = load i32, ptr %b
  %cl = load i32, ptr %c
  ret void
}

; There are potential ouptuts in this sections, but we do not extract sections
; with outputs right now, since they cannot be consolidated.
define void @extract_outs1() #0 {
; CHECK-LABEL: @extract_outs1(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[DOTLOC:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[ADD_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[OUTPUT:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[RESULT:%.*]] = alloca i32, align 4
; CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 -1, ptr [[ADD_LOC]])
; CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 -1, ptr [[DOTLOC]])
; CHECK-NEXT:    call void @outlined_ir_func_0(ptr [[A]], ptr [[B]], ptr [[OUTPUT]], ptr [[ADD_LOC]], ptr [[DOTLOC]])
; CHECK-NEXT:    [[ADD_RELOAD:%.*]] = load i32, ptr [[ADD_LOC]], align 4
; CHECK-NEXT:    [[DOTRELOAD:%.*]] = load i32, ptr [[DOTLOC]], align 4
; CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 -1, ptr [[ADD_LOC]])
; CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 -1, ptr [[DOTLOC]])
; CHECK-NEXT:    [[TMP0:%.*]] = load i32, ptr [[OUTPUT]], align 4
; CHECK-NEXT:    call void @outlined_ir_func_2(i32 [[DOTRELOAD]], i32 [[ADD_RELOAD]], ptr [[RESULT]])
; CHECK-NEXT:    ret void
;
entry:
  %a = alloca i32, align 4
  %b = alloca i32, align 4
  %output = alloca i32, align 4
  %result = alloca i32, align 4
  store i32 2, ptr %a, align 4
  store i32 3, ptr %b, align 4
  %0 = load i32, ptr %a, align 4
  %1 = load i32, ptr %b, align 4
  %add = add i32 %0, %1
  store i32 %add, ptr %output, align 4
  %2 = load i32, ptr %output, align 4
  %3 = load i32, ptr %output, align 4
  %mul = mul i32 %2, %add
  store i32 %mul, ptr %result, align 4
  ret void
}

; There are potential ouptuts in this sections, but we do not extract sections
; with outputs right now, since they cannot be consolidated.
define void @extract_outs2() #0 {
; CHECK-LABEL: @extract_outs2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[DOTLOC:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[ADD_LOC:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[A:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[B:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[OUTPUT:%.*]] = alloca i32, align 4
; CHECK-NEXT:    [[RESULT:%.*]] = alloca i32, align 4
; CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 -1, ptr [[ADD_LOC]])
; CHECK-NEXT:    call void @llvm.lifetime.start.p0(i64 -1, ptr [[DOTLOC]])
; CHECK-NEXT:    call void @outlined_ir_func_0(ptr [[A]], ptr [[B]], ptr [[OUTPUT]], ptr [[ADD_LOC]], ptr [[DOTLOC]])
; CHECK-NEXT:    [[ADD_RELOAD:%.*]] = load i32, ptr [[ADD_LOC]], align 4
; CHECK-NEXT:    [[DOTRELOAD:%.*]] = load i32, ptr [[DOTLOC]], align 4
; CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 -1, ptr [[ADD_LOC]])
; CHECK-NEXT:    call void @llvm.lifetime.end.p0(i64 -1, ptr [[DOTLOC]])
; CHECK-NEXT:    call void @outlined_ir_func_2(i32 [[DOTRELOAD]], i32 [[ADD_RELOAD]], ptr [[RESULT]])
; CHECK-NEXT:    ret void
;
entry:
  %a = alloca i32, align 4
  %b = alloca i32, align 4
  %output = alloca i32, align 4
  %result = alloca i32, align 4
  store i32 2, ptr %a, align 4
  store i32 3, ptr %b, align 4
  %0 = load i32, ptr %a, align 4
  %1 = load i32, ptr %b, align 4
  %add = add i32 %0, %1
  store i32 %add, ptr %output, align 4
  %2 = load i32, ptr %output, align 4
  %mul = mul i32 %2, %add
  store i32 %mul, ptr %result, align 4
  ret void
}