; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=m68k-linux -verify-machineinstrs | FileCheck %s

define zeroext i8 @smul_i8(i8 signext %a, i8 signext %b) nounwind ssp {
; CHECK-LABEL: smul_i8:
; CHECK:       ; %bb.0: ; %entry
; CHECK-NEXT:    move.b (11,%sp), %d0
; CHECK-NEXT:    and.l #255, %d0
; CHECK-NEXT:    move.b (7,%sp), %d1
; CHECK-NEXT:    and.l #255, %d1
; CHECK-NEXT:    muls %d0, %d1
; CHECK-NEXT:    move.l %d1, %d0
; CHECK-NEXT:    and.l #65535, %d0
; CHECK-NEXT:    and.l #255, %d0
; CHECK-NEXT:    rts
entry:
  %smul = tail call { i8, i1 } @llvm.smul.with.overflow.i8(i8 %a, i8 %b)
  %cmp = extractvalue { i8, i1 } %smul, 1
  %smul.result = extractvalue { i8, i1 } %smul, 0
  %X = select i1 %cmp, i8 42, i8 %smul.result
  ret i8 %X
}

define zeroext i8 @smul_i8_no_ovf(i8 signext %a, i8 signext %b) nounwind ssp {
; CHECK-LABEL: smul_i8_no_ovf:
; CHECK:       ; %bb.0: ; %entry
; CHECK-NEXT:    move.l #42, %d0
; CHECK-NEXT:    rts
entry:
  %smul = tail call { i8, i1 } @llvm.smul.with.overflow.i8(i8 %a, i8 %b)
  %cmp = extractvalue { i8, i1 } %smul, 1
  %smul.result = extractvalue { i8, i1 } %smul, 0
  %X = select i1 %cmp, i8 %smul.result, i8 42
  ret i8 %X
}

declare { i8, i1 } @llvm.smul.with.overflow.i8(i8, i8) nounwind readnone

define zeroext i16 @smul_i16(i16 signext %a, i16 signext %b) nounwind ssp {
; CHECK-LABEL: smul_i16:
; CHECK:       ; %bb.0: ; %entry
; CHECK-NEXT:    move.w (6,%sp), %d0
; CHECK-NEXT:    move.w (10,%sp), %d1
; CHECK-NEXT:    muls %d1, %d0
; CHECK-NEXT:    and.l #65535, %d0
; CHECK-NEXT:    rts
entry:
  %smul = tail call { i16, i1 } @llvm.smul.with.overflow.i16(i16 %a, i16 %b)
  %cmp = extractvalue { i16, i1 } %smul, 1
  %smul.result = extractvalue { i16, i1 } %smul, 0
  %X = select i1 %cmp, i16 42, i16 %smul.result
  ret i16 %X
}

declare { i16, i1 } @llvm.smul.with.overflow.i16(i16, i16) nounwind readnone

declare i32 @printf(i8*, ...) nounwind
declare {i32, i1} @llvm.smul.with.overflow.i32(i32, i32)

@ok = internal constant [4 x i8] c"%d\0A\00"
@no = internal constant [4 x i8] c"no\0A\00"

define fastcc i1 @test1(i32 %v1, i32 %v2) nounwind {
; CHECK-LABEL: test1:
; CHECK:       ; %bb.0: ; %entry
; CHECK-NEXT:    suba.l #12, %sp
; CHECK-NEXT:    muls.l %d1, %d0
; CHECK-NEXT:    bvc .LBB3_1
; CHECK-NEXT:  ; %bb.2: ; %overflow
; CHECK-NEXT:    lea (no,%pc), %a0
; CHECK-NEXT:    move.l %a0, (%sp)
; CHECK-NEXT:    jsr printf@PLT
; CHECK-NEXT:    move.b #0, %d0
; CHECK-NEXT:    adda.l #12, %sp
; CHECK-NEXT:    rts
; CHECK-NEXT:  .LBB3_1: ; %normal
; CHECK-NEXT:    move.l %d0, (4,%sp)
; CHECK-NEXT:    lea (ok,%pc), %a0
; CHECK-NEXT:    move.l %a0, (%sp)
; CHECK-NEXT:    jsr printf@PLT
; CHECK-NEXT:    move.b #1, %d0
; CHECK-NEXT:    adda.l #12, %sp
; CHECK-NEXT:    rts
entry:
  %t = call {i32, i1} @llvm.smul.with.overflow.i32(i32 %v1, i32 %v2)
  %sum = extractvalue {i32, i1} %t, 0
  %obit = extractvalue {i32, i1} %t, 1
  br i1 %obit, label %overflow, label %normal

normal:
  %t1 = tail call i32 (i8*, ...) @printf( i8* getelementptr ([4 x i8], [4 x i8]* @ok, i32 0, i32 0), i32 %sum ) nounwind
  ret i1 true

overflow:
  %t2 = tail call i32 (i8*, ...) @printf( i8* getelementptr ([4 x i8], [4 x i8]* @no, i32 0, i32 0) ) nounwind
  ret i1 false
}

define fastcc i1 @test2(i32 %v1, i32 %v2) nounwind {
; CHECK-LABEL: test2:
; CHECK:       ; %bb.0: ; %entry
; CHECK-NEXT:    suba.l #12, %sp
; CHECK-NEXT:    muls.l %d1, %d0
; CHECK-NEXT:    svs %d1
; CHECK-NEXT:    sub.b #1, %d1
; CHECK-NEXT:    bne .LBB4_2
; CHECK-NEXT:  ; %bb.1: ; %overflow
; CHECK-NEXT:    lea (no,%pc), %a0
; CHECK-NEXT:    move.l %a0, (%sp)
; CHECK-NEXT:    jsr printf@PLT
; CHECK-NEXT:    move.b #0, %d0
; CHECK-NEXT:    adda.l #12, %sp
; CHECK-NEXT:    rts
; CHECK-NEXT:  .LBB4_2: ; %normal
; CHECK-NEXT:    move.l %d0, (4,%sp)
; CHECK-NEXT:    lea (ok,%pc), %a0
; CHECK-NEXT:    move.l %a0, (%sp)
; CHECK-NEXT:    jsr printf@PLT
; CHECK-NEXT:    move.b #1, %d0
; CHECK-NEXT:    adda.l #12, %sp
; CHECK-NEXT:    rts
entry:
  %t = call {i32, i1} @llvm.smul.with.overflow.i32(i32 %v1, i32 %v2)
  %sum = extractvalue {i32, i1} %t, 0
  %obit = extractvalue {i32, i1} %t, 1
  br i1 %obit, label %overflow, label %normal

overflow:
  %t2 = tail call i32 (i8*, ...) @printf( i8* getelementptr ([4 x i8], [4 x i8]* @no, i32 0, i32 0) ) nounwind
  ret i1 false

normal:
  %t1 = tail call i32 (i8*, ...) @printf( i8* getelementptr ([4 x i8], [4 x i8]* @ok, i32 0, i32 0), i32 %sum ) nounwind
  ret i1 true
}

define i32 @test3(i32 %a, i32 %b) nounwind readnone {
; CHECK-LABEL: test3:
; CHECK:       ; %bb.0: ; %entry
; CHECK-NEXT:    move.l (8,%sp), %d0
; CHECK-NEXT:    add.l (4,%sp), %d0
; CHECK-NEXT:    add.l %d0, %d0
; CHECK-NEXT:    rts
entry:
	%tmp0 = add i32 %b, %a
	%tmp1 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 %tmp0, i32 2)
	%tmp2 = extractvalue { i32, i1 } %tmp1, 0
	ret i32 %tmp2
}

; Same as umul-with-overflow, we shouldn't fallback to
; builtin here
define i32 @test4(i32 %a, i32 %b) nounwind readnone {
; CHECK-LABEL: test4:
; CHECK:       ; %bb.0: ; %entry
; CHECK-NEXT:    move.l (8,%sp), %d0
; CHECK-NEXT:    add.l (4,%sp), %d0
; CHECK-NEXT:    move.l #4, %d1
; CHECK-NEXT:    muls.l %d1, %d0
; CHECK-NEXT:    rts
entry:
	%tmp0 = add i32 %b, %a
	%tmp1 = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 %tmp0, i32 4)
	%tmp2 = extractvalue { i32, i1 } %tmp1, 0
	ret i32 %tmp2
}