[ARM] Reapply: Use __rt_div functions for divrem on Windows

[mstorsjo]

Summary

Reapplying r283383 after revert in r283442. The additional fix is a getting rid of a stray space in a function name, in the refactoring part of the commit.

This avoids falling back to calling out to the GCC rem functions (moddi3, umoddi3) when targeting Windows.

The rt_div functions have flipped the two arguments compared to the aeabi_divmod functions. To match MSVC, we emit a check for division by zero before actually calling the library function (even if the library function itself also might do the same check).

Not all calls to rt_div functions for division are currently merged with calls to the same function with the same parameters for the remainder. This is more wasteful than a div + mls as before, but avoids calls to moddi3.

This is reapplying D24076 with one additional typo fix.

[rovka]

Hi Martin,

I tested this with a config similar to the clang-native-arm-lnt bot and it seems to work fine. I think you can try to commit it again.

lib/Target/ARM/ARMISelLowering.cpp

if (Subtarget->isTargetWindows() && !Subtarget->hasDivide()) {
     setOperationAction(ISD::SDIV, MVT::i64, Custom);
     setOperationAction(ISD::UDIV, MVT::i64, Custom);
   }
 
   setOperationAction(ISD::SREM,  MVT::i32, Expand);
   setOperationAction(ISD::UREM,  MVT::i32, Expand);
   // Register based DivRem for AEABI (RTABI 4.2)
   if (Subtarget->isTargetAEABI() || Subtarget->isTargetAndroid() ||
-      Subtarget->isTargetGNUAEABI() || Subtarget->isTargetMuslAEABI()) {
+      Subtarget->isTargetGNUAEABI() || Subtarget->isTargetMuslAEABI() ||
+      Subtarget->isTargetWindows()) {
     setOperationAction(ISD::SREM, MVT::i64, Custom);
     setOperationAction(ISD::UREM, MVT::i64, Custom);
     HasStandaloneRem = false;
 
-    setLibcallName(RTLIB::SDIVREM_I8,  "__aeabi_idivmod");
-    setLibcallName(RTLIB::SDIVREM_I16, "__aeabi_idivmod");
-    setLibcallName(RTLIB::SDIVREM_I32, "__aeabi_idivmod");
-    setLibcallName(RTLIB::SDIVREM_I64, "__aeabi_ldivmod");
-    setLibcallName(RTLIB::UDIVREM_I8,  "__aeabi_uidivmod");
-    setLibcallName(RTLIB::UDIVREM_I16, "__aeabi_uidivmod");
-    setLibcallName(RTLIB::UDIVREM_I32, "__aeabi_uidivmod");
-    setLibcallName(RTLIB::UDIVREM_I64, "__aeabi_uldivmod");
+    for (const auto &LC :
+         {RTLIB::SDIVREM_I8, RTLIB::SDIVREM_I16, RTLIB::SDIVREM_I32})
+      setLibcallName(LC, Subtarget->isTargetWindows() ? "__rt_sdiv"
+                                                      : "__aeabi_idivmod");
+    setLibcallName(RTLIB::SDIVREM_I64, Subtarget->isTargetWindows()
+                                           ? "__rt_sdiv64"
+                                           : "__aeabi_ldivmod");
+    for (const auto &LC :
+         {RTLIB::UDIVREM_I8, RTLIB::UDIVREM_I16, RTLIB::UDIVREM_I32})
+      setLibcallName(LC, Subtarget->isTargetWindows() ? "__rt_udiv"
+                                                      : "__aeabi_uidivmod");
+    setLibcallName(RTLIB::UDIVREM_I64, Subtarget->isTargetWindows()
+                                           ? "__rt_udiv64"
+                                           : "__aeabi_uldivmod");
 
     setLibcallCallingConv(RTLIB::SDIVREM_I8, CallingConv::ARM_AAPCS);
     setLibcallCallingConv(RTLIB::SDIVREM_I16, CallingConv::ARM_AAPCS);
     setLibcallCallingConv(RTLIB::SDIVREM_I32, CallingConv::ARM_AAPCS);
     setLibcallCallingConv(RTLIB::SDIVREM_I64, CallingConv::ARM_AAPCS);
     setLibcallCallingConv(RTLIB::UDIVREM_I8, CallingConv::ARM_AAPCS);
     setLibcallCallingConv(RTLIB::UDIVREM_I16, CallingConv::ARM_AAPCS);
     setLibcallCallingConv(RTLIB::UDIVREM_I32, CallingConv::ARM_AAPCS);
SDValue ARMTargetLowering::LowerDIV_Windows(SDValue Op, SelectionDAG &DAG,
   SDLoc dl(Op);
 
   SDValue DBZCHK = DAG.getNode(ARMISD::WIN__DBZCHK, dl, MVT::Other,
                                DAG.getEntryNode(), Op.getOperand(1));
 
   return LowerWindowsDIVLibCall(Op, DAG, Signed, DBZCHK);
 }
 
+static SDValue WinDBZCheckDenominator(SelectionDAG &DAG, SDNode *N, SDValue InChain) {
+  SDLoc DL(N);
+  SDValue Op = N->getOperand(1);
+  if (N->getValueType(0) == MVT::i32)
+    return DAG.getNode(ARMISD::WIN__DBZCHK, DL, MVT::Other, InChain, Op);
+  SDValue Lo = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, MVT::i32, Op,
+                           DAG.getConstant(0, DL, MVT::i32));
+  SDValue Hi = DAG.getNode(ISD::EXTRACT_ELEMENT, DL, MVT::i32, Op,
+                           DAG.getConstant(1, DL, MVT::i32));
+  return DAG.getNode(ARMISD::WIN__DBZCHK, DL, MVT::Other, InChain,
+                     DAG.getNode(ISD::OR, DL, MVT::i32, Lo, Hi));
+}
+
 void ARMTargetLowering::ExpandDIV_Windows(
     SDValue Op, SelectionDAG &DAG, bool Signed,
     SmallVectorImpl<SDValue> &Results) const {
   const auto &DL = DAG.getDataLayout();
   const auto &TLI = DAG.getTargetLoweringInfo();
 
   assert(Op.getValueType() == MVT::i64 &&
          "unexpected type for custom lowering DIV");
   SDLoc dl(Op);
 
-  SDValue Lo = DAG.getNode(ISD::EXTRACT_ELEMENT, dl, MVT::i32, Op.getOperand(1),
-                           DAG.getConstant(0, dl, MVT::i32));
-  SDValue Hi = DAG.getNode(ISD::EXTRACT_ELEMENT, dl, MVT::i32, Op.getOperand(1),
-                           DAG.getConstant(1, dl, MVT::i32));
-  SDValue Or = DAG.getNode(ISD::OR, dl, MVT::i32, Lo, Hi);
-
-  SDValue DBZCHK =
-      DAG.getNode(ARMISD::WIN__DBZCHK, dl, MVT::Other, DAG.getEntryNode(), Or);
+  SDValue DBZCHK = WinDBZCheckDenominator(DAG, Op.getNode(), DAG.getEntryNode());
 
   SDValue Result = LowerWindowsDIVLibCall(Op, DAG, Signed, DBZCHK);
 
   SDValue Lower = DAG.getNode(ISD::TRUNCATE, dl, MVT::i32, Result);
   SDValue Upper = DAG.getNode(ISD::SRL, dl, MVT::i64, Result,
                               DAG.getConstant(32, dl, TLI.getPointerTy(DL)));
   Upper = DAG.getNode(ISD::TRUNCATE, dl, MVT::i32, Upper);
 
static RTLIB::Libcall getDivRemLibcall(
   case MVT::i16: LC = isSigned ? RTLIB::SDIVREM_I16 : RTLIB::UDIVREM_I16; break;
   case MVT::i32: LC = isSigned ? RTLIB::SDIVREM_I32 : RTLIB::UDIVREM_I32; break;
   case MVT::i64: LC = isSigned ? RTLIB::SDIVREM_I64 : RTLIB::UDIVREM_I64; break;
   }
   return LC;
 }
 
 static TargetLowering::ArgListTy getDivRemArgList(
-    const SDNode *N, LLVMContext *Context) {
+    const SDNode *N, LLVMContext *Context, const ARMSubtarget *Subtarget) {
   assert((N->getOpcode() == ISD::SDIVREM || N->getOpcode() == ISD::UDIVREM ||
           N->getOpcode() == ISD::SREM    || N->getOpcode() == ISD::UREM) &&
          "Unhandled Opcode in getDivRemArgList");
   bool isSigned = N->getOpcode() == ISD::SDIVREM ||
                   N->getOpcode() == ISD::SREM;
   TargetLowering::ArgListTy Args;
   TargetLowering::ArgListEntry Entry;
   for (unsigned i = 0, e = N->getNumOperands(); i != e; ++i) {
     EVT ArgVT = N->getOperand(i).getValueType();
     Type *ArgTy = ArgVT.getTypeForEVT(*Context);
     Entry.Node = N->getOperand(i);
     Entry.Ty = ArgTy;
     Entry.isSExt = isSigned;
     Entry.isZExt = !isSigned;
     Args.push_back(Entry);
   }
+  if (Subtarget->isTargetWindows() && Args.size() >= 2)
+    std::swap(Args[0], Args[1]);
   return Args;
 }
 
 SDValue ARMTargetLowering::LowerDivRem(SDValue Op, SelectionDAG &DAG) const {
   assert((Subtarget->isTargetAEABI() || Subtarget->isTargetAndroid() ||
-          Subtarget->isTargetGNUAEABI() || Subtarget->isTargetMuslAEABI()) &&
+          Subtarget->isTargetGNUAEABI() || Subtarget->isTargetMuslAEABI() ||
+          Subtarget->isTargetWindows()) &&
          "Register-based DivRem lowering only");
   unsigned Opcode = Op->getOpcode();
   assert((Opcode == ISD::SDIVREM || Opcode == ISD::UDIVREM) &&
          "Invalid opcode for Div/Rem lowering");
   bool isSigned = (Opcode == ISD::SDIVREM);
   EVT VT = Op->getValueType(0);
   Type *Ty = VT.getTypeForEVT(*DAG.getContext());
   SDLoc dl(Op);
if (Subtarget->hasDivide() && Op->getValueType(0).isSimple() &&
     return DAG.getNode(ISD::MERGE_VALUES, dl, DAG.getVTList(VT, VT), Values);
   }
 
   RTLIB::Libcall LC = getDivRemLibcall(Op.getNode(),
                                        VT.getSimpleVT().SimpleTy);
   SDValue InChain = DAG.getEntryNode();
 
   TargetLowering::ArgListTy Args = getDivRemArgList(Op.getNode(),
-                                                    DAG.getContext());
+                                                    DAG.getContext(),
+                                                    Subtarget);
 
   SDValue Callee = DAG.getExternalSymbol(getLibcallName(LC),
                                          getPointerTy(DAG.getDataLayout()));
 
   Type *RetTy = (Type*)StructType::get(Ty, Ty, nullptr);
 
+  if (Subtarget->isTargetWindows())
+    InChain = WinDBZCheckDenominator(DAG, Op.getNode(), InChain);
+
   TargetLowering::CallLoweringInfo CLI(DAG);
   CLI.setDebugLoc(dl).setChain(InChain)
     .setCallee(getLibcallCallingConv(LC), RetTy, Callee, std::move(Args))
     .setInRegister().setSExtResult(isSigned).setZExtResult(!isSigned);
 
   std::pair<SDValue, SDValue> CallInfo = LowerCallTo(CLI);
   return CallInfo.first;
 }
SDValue ARMTargetLowering::LowerREM(SDNode *N, SelectionDAG &DAG) const {
   RetTyParams.push_back(RetTyElement);
   RetTyParams.push_back(RetTyElement);
   ArrayRef<Type*> ret = ArrayRef<Type*>(RetTyParams);
   Type *RetTy = StructType::get(*DAG.getContext(), ret);
 
   RTLIB::Libcall LC = getDivRemLibcall(N, N->getValueType(0).getSimpleVT().
                                                              SimpleTy);
   SDValue InChain = DAG.getEntryNode();
-  TargetLowering::ArgListTy Args = getDivRemArgList(N, DAG.getContext());
+  TargetLowering::ArgListTy Args = getDivRemArgList(N, DAG.getContext(),
+                                                    Subtarget);
   bool isSigned = N->getOpcode() == ISD::SREM;
   SDValue Callee = DAG.getExternalSymbol(getLibcallName(LC),
                                          getPointerTy(DAG.getDataLayout()));
 
+  if (Subtarget->isTargetWindows())
+    InChain = WinDBZCheckDenominator(DAG, N, InChain);
+
   // Lower call
   CallLoweringInfo CLI(DAG);
   CLI.setChain(InChain)
      .setCallee(CallingConv::ARM_AAPCS, RetTy, Callee, std::move(Args))
      .setSExtResult(isSigned).setZExtResult(!isSigned).setDebugLoc(SDLoc(N));
   std::pair<SDValue, SDValue> CallResult = LowerCallTo(CLI);
 
   // Return second (rem) result operand (first contains div)

test/CodeGen/ARM/Windows/dbzchk.ll

 
 ; CHECK-CFG-ASM-LABEL: h:
 ; CHECK-CFG-ASM: cbz r{{[0-9]}}, .LBB2_2
 ; CHECK-CFG-ASM: b .LBB2_4
 ; CHECK-CFG-ASM-LABEL: .LBB2_2:
 ; CHECK-CFG-ASM-NEXT: udf.w #249
 ; CHECK-CFG-ASM-LABEL: .LBB2_4:
 ; CHECK-CFG-ASM: bl __rt_udiv
-; CHECK-CFG-ASM: pop.w {{{.*}}, r11, pc}
+; CHECK-CFG-ASM: pop.w {r11, pc}
 
 ; RUN: llc -O0 -mtriple thumbv7--windows-itanium -verify-machineinstrs -filetype asm -o - %s | FileCheck %s -check-prefix CHECK-WIN__DBZCHK
 
 ; long k(void);
 ; int l(void);
 ; int j(int i) {
 ;   if (l() == -1)
 ;     return 0;

test/CodeGen/ARM/divmod-eabi.ll

 ; EABI: mov [[div:r[0-9]+]], r0
 ; EABI: mov [[rem:r[0-9]+]], r1
 ; DARWIN: ___divsi3
 ; DARWIN: mov [[div:r[0-9]+]], r0
 ; DARWIN: __modsi3
 ; DARWIN-DEFAULT: add [[sum:r[0-9]+]], r0, [[div]]
 ; DARWIN-O0: mov [[rem:r[0-9]+]], r0
 ; WINDOWS: __rt_sdiv
-; WINDOWS-DEFAULT: mls [[rem:r[0-9]+]], r0,
-; WINDOWS-DEFAULT: adds [[sum:r[0-9]+]], [[rem]], r0
-; WINDOWS-O0: mov [[div:r[0-9]+]], r0
-; WINDOWS-O0: mls [[rem:r[0-9]+]], [[div]],
+; WINDOWS: __rt_sdiv
+; WINDOWS-DEFAULT: add [[sum:r[0-9]+]], r1
+; WINDOWS-O0: mov [[rem:r[0-9]+]], r1
   %rem8 = srem i32 %conv1, %conv
 ; EABI: __aeabi_idivmod
 ; DARWIN: __modsi3
 ; WINDOWS: __rt_sdiv
-; WINDOWS: mls [[rem1:r[0-9]+]], r0,
   %add = add nsw i32 %rem, %div
   %add13 = add nsw i32 %add, %rem8
   %conv14 = trunc i32 %add13 to i16
 ; EABI: add r0{{.*}}r1
 ; EABI: sxth r0, r0
 ; DARWIN-DEFAULT: add [[res:r[0-9]+]], [[sum]], r0
 ; DARWIN-O0: add [[sum:r[0-9]+]], [[rem]], [[div]]
 ; DARWIN-O0: add [[res:r[0-9]+]], [[sum]], r0
 ; DARWIN: sxth r0, [[res]]
-; WINDOWS-O0: adds [[sum:r[0-9]+]], [[rem]], [[div]]
-; WINDOWS: add [[rem1]], [[sum]]
-; WINDOWS: sxth [[res:r[0-9]+]], [[rem1]]
+; WINDOWS-DEFAULT: adds [[sum1:r[0-9]+]], [[sum]], r1
+; WINDOWS-O0: adds [[sum:r[0-9]+]], [[rem]],
+; WINDOWS-O0: add [[sum1:r[0-9]+]], r1
+; WINDOWS: sxth [[res:r[0-9]+]], [[sum1]]
   ret i16 %conv14
 }
 
 define i32 @f32(i32 %a, i32 %b) {
 ; EABI-LABEL: f32:
 ; DARWIN-LABEL: f32:
 ; WINDOWS-LABEL: f32:
 entry:
   %div = sdiv i32 %a, %b
   %rem = srem i32 %a, %b
 ; EABI: __aeabi_idivmod
 ; EABI: mov [[div:r[0-9]+]], r0
 ; EABI: mov [[rem:r[0-9]+]], r1
 ; DARWIN: ___divsi3
 ; DARWIN: mov [[div:r[0-9]+]], r0
 ; DARWIN: __modsi3
 ; DARWIN-DEFAULT: add [[sum:r[0-9]+]], r0, [[div]]
 ; DARWIN-O0: mov [[rem:r[0-9]+]], r0
 ; WINDOWS: __rt_sdiv
 ; WINDOWS: mov [[div:r[0-9]+]], r0
 ; WINDOWS: __rt_sdiv
-; WINDOWS: mls [[rem:r[0-9]+]], r0,
-; WINDOWS-DEFAULT: add [[div]], [[rem]]
+; WINDOWS-DEFAULT: add [[div]], r1
   %rem1 = srem i32 %b, %a
 ; EABI: __aeabi_idivmod
 ; DARWIN: __modsi3
 ; WINDOWS: __rt_sdiv
-; WINDOWS: mls [[rem1:r[0-9]+]], r0,
   %add = add nsw i32 %rem, %div
   %add2 = add nsw i32 %add, %rem1
 ; EABI: add r0{{.*}}r1
 ; DARWIN-DEFAULT: add r0, [[sum]], r0
 ; DARWIN-O0: add [[sum:r[0-9]+]], [[rem]], [[div]]
 ; DARWIN-O0: add [[res:r[0-9]+]], [[sum]], r0
-; WINDOWS-DEFAULT: add [[rem1]], [[div]]
+; WINDOWS-DEFAULT: adds r0, [[div]], r1
 ; WINDOWS-O0: adds [[sum:r[0-9]+]], [[rem]], [[div]]
-; WINDOWS-O0: add [[rem1]], [[sum]]
+; WINDOWS-O0: add [[sum]], r1
   ret i32 %add2
 }
 
 define i32 @uf(i32 %a, i32 %b) {
 ; EABI-LABEL: uf:
 ; DARWIN-LABEL: uf:
 ; WINDOWS-LABEL: uf:
 entry:
   %div = udiv i32 %a, %b
   %rem = urem i32 %a, %b
 ; EABI: __aeabi_uidivmod
 ; DARWIN: ___udivsi3
 ; DARWIN: mov [[div:r[0-9]+]], r0
 ; DARWIN: __umodsi3
 ; DARWIN-DEFAULT: add [[sum:r[0-9]+]], r0, [[div]]
 ; DARWIN-O0: mov [[rem:r[0-9]+]], r0
 ; WINDOWS: __rt_udiv
 ; WINDOWS: mov [[div:r[0-9]+]], r0
 ; WINDOWS: __rt_udiv
-; WINDOWS: mls [[rem:r[0-9]+]], r0,
-; WINDOWS-DEFAULT: add [[div]], [[rem]]
+; WINDOWS-DEFAULT: add [[div]], r1
   %rem1 = urem i32 %b, %a
 ; EABI: __aeabi_uidivmod
 ; DARWIN: __umodsi3
 ; WINDOWS: __rt_udiv
-; WINDOWS: mls [[rem1:r[0-9]+]], r0,
   %add = add nuw i32 %rem, %div
   %add2 = add nuw i32 %add, %rem1
 ; EABI: add r0{{.*}}r1
 ; DARWIN-DEFAULT: add r0, [[sum]], r0
 ; DARWIN-O0: add [[sum:r[0-9]+]], [[rem]], [[div]]
 ; DARWIN-O0: add [[res:r[0-9]+]], [[sum]], r0
-; WINDOWS-DEFAULT: add [[rem1]], [[div]]
-; WINDOWS-O0: adds [[sum:r[0-9]+]], [[rem]], [[div]]
-; WINDOWS-O0: add [[rem1]], [[sum]]
+; WINDOWS-DEFAULT: adds [[sum:r[0-9]+]], [[div]], r1
+; WINDOWS-O0: adds [[sum:r[0-9]+]],
+; WINDOWS-O0: add [[sum]], r1
   ret i32 %add2
 }
 
 define i64 @longf(i64 %a, i64 %b) {
 ; EABI-LABEL: longf:
 ; DARWIN-LABEL: longf:
 ; WINDOWS-LABEL: longf:
 entry:
   %div = sdiv i64 %a, %b
   %rem = srem i64 %a, %b
 ; EABI: __aeabi_ldivmod
 ; EABI-NEXT: adds r0
 ; EABI-NEXT: adc r1
 ; EABI-NOT: __aeabi_ldivmod
 ; DARWIN: ___divdi3
 ; DARWIN: mov [[div1:r[0-9]+]], r0
 ; DARWIN: mov [[div2:r[0-9]+]], r1
 ; DARWIN: __moddi3
 ; WINDOWS: __rt_sdiv64
-; WINDOWS: mov [[div1:r[0-9]+]], r0
-; WINDOWS: mov [[div2:r[0-9]+]], r1
-; WINDOWS: __moddi3
   %add = add nsw i64 %rem, %div
 ; DARWIN: adds r0{{.*}}[[div1]]
 ; DARWIN: adc r1{{.*}}[[div2]]
-; WINDOWS: adds.w r0, r0, [[div1]]
-; WINDOWS: adc.w r1, r1, [[div2]]
+; WINDOWS: adds r0, r0, r2
+; WINDOWS: adcs r1, r3
   ret i64 %add
 }
 
 define i16 @shortf(i16 %a, i16 %b) {
 ; EABI-LABEL: shortf:
 ; DARWIN-LABEL: shortf:
 ; WINDOWS-LABEL: shortf:
 entry:
   %div = sdiv i16 %a, %b
   %rem = srem i16 %a, %b
 ; EABI: __aeabi_idivmod
 ; DARWIN: ___divsi3
 ; DARWIN: mov [[div1:r[0-9]+]], r0
 ; DARWIN: __modsi3
 ; WINDOWS: __rt_sdiv
 ; WINDOWS: mov [[div:r[0-9]+]], r0
 ; WINDOWS: __rt_sdiv
-; WINDOWS: mls [[rem:r[0-9]+]], r0,
   %add = add nsw i16 %rem, %div
 ; EABI: add r0, r1
 ; DARWIN: add r0{{.*}}[[div1]]
-; WINDOWS: add [[rem]], [[div]]
+; WINDOWS: adds r0, r1, [[div]]
   ret i16 %add
 }
 
 define i32 @g1(i32 %a, i32 %b) {
 ; EABI-LABEL: g1:
 ; DARWIN-LABEL: g1:
 ; WINDOWS-LABEL: g1:
 entry:
   %div = sdiv i32 %a, %b
   %rem = srem i32 %a, %b
 ; EABI: __aeabi_idivmod
 ; DARWIN: ___divsi3
 ; DARWIN: mov [[sum:r[0-9]+]], r0
 ; DARWIN: __modsi3
 ; WINDOWS: __rt_sdiv
 ; WINDOWS: mov [[div:r[0-9]+]], r0
 ; WINDOWS: __rt_sdiv
-; WINDOWS: mls [[rem:r[0-9]+]], r0,
   %add = add nsw i32 %rem, %div
 ; EABI: add r0{{.*}}r1
 ; DARWIN: add r0{{.*}}[[sum]]
-; WINDOWS: add [[rem]], [[div]]
+; WINDOWS: adds r0, r1, [[div]]
   ret i32 %add
 }
 
 ; On both Darwin and Gnu, this is just a call to __modsi3
 define i32 @g2(i32 %a, i32 %b) {
 ; EABI-LABEL: g2:
 ; DARWIN-LABEL: g2:
 ; WINDOWS-LABEL: g2:
 entry:
   %rem = srem i32 %a, %b
 ; EABI: __aeabi_idivmod
 ; DARWIN: __modsi3
 ; WINDOWS: __rt_sdiv
   ret i32 %rem
 ; EABI: mov r0, r1
-; WINDOWS: mls r0, r0,
+; WINDOWS: mov  r0, r1
 }
 
 define i32 @g3(i32 %a, i32 %b) {
 ; EABI-LABEL: g3:
 ; DARWIN-LABEL: g3:
 ; WINDOWS-LABEL: g3:
 entry:
   %rem = srem i32 %a, %b
 ; EABI: __aeabi_idivmod
 ; EABI: mov [[mod:r[0-9]+]], r1
 ; DARWIN: __modsi3
 ; DARWIN: mov [[sum:r[0-9]+]], r0
 ; WINDOWS: __rt_sdiv
-; WINDOWS: mls [[rem:r[0-9]+]], r0,
+; WINDOWS: mov [[rem:r[0-9]+]], r1
   %rem1 = srem i32 %b, %rem
 ; EABI: __aeabi_idivmod
 ; DARWIN: __modsi3
 ; WINDOWS: __rt_sdiv
-; WINDOWS: mls [[rem1:r[0-9]+]], r0,
   %add = add nsw i32 %rem1, %rem
 ; EABI: add r0, r1, [[mod]]
 ; DARWIN: add r0{{.*}}[[sum]]
-; WINDOWS: add [[rem1]], [[rem]]
+; WINDOWS: adds r0, r1, [[rem]]
   ret i32 %add
 }
 
 define i32 @g4(i32 %a, i32 %b) {
 ; EABI-LABEL: g4:
 ; DARWIN-LABEL: g4:
 ; WINDOWS-LABEL: g4:
 entry:
   %div = sdiv i32 %a, %b
 ; EABI: __aeabi_idiv{{$}}
 ; EABI: mov [[div:r[0-9]+]], r0
 ; DARWIN: ___divsi3
 ; DARWIN: mov [[sum:r[0-9]+]], r0
 ; WINDOWS: __rt_sdiv
 ; WINDOWS: mov [[div:r[0-9]+]], r0
   %rem = srem i32 %b, %div
 ; EABI: __aeabi_idivmod
 ; DARWIN: __modsi3
 ; WINDOWS: __rt_sdiv
-; WINDOWS: mls [[rem:r[0-9]+]], r0,
   %add = add nsw i32 %rem, %div
 ; EABI: add r0, r1, [[div]]
 ; DARWIN: add r0{{.*}}[[sum]]
-; WINDOWS: add [[rem]], [[div]]
+; WINDOWS: adds r0, r1, [[div]]
   ret i32 %add
 }