[ARM] Lower UDIV+UREM to UDIV+MLS (and the same for SREM)

Summary:
This saves a library call to __aeabi_uidivmod. However, the
processor must feature hardware division in order to benefit from
the transformation.

Reviewers: scott-0, jmolloy, compnerd, rengolin

Subscribers: t.p.northover, compnerd, aemerson, rengolin, samparker, llvm-commits

Differential Revision: https://reviews.llvm.org/D24133

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@280808 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Target/ARM/ARMISelLowering.cpp

@@ -12098,6 +12098,24 @@ SDValue ARMTargetLowering::LowerDivRem(SDValue Op, SelectionDAG &DAG) const {
   bool isSigned = (Opcode == ISD::SDIVREM);
   EVT VT = Op->getValueType(0);
   Type *Ty = VT.getTypeForEVT(*DAG.getContext());
+  SDLoc dl(Op);
+
+  // If the target has hardware divide, use divide + multiply + subtract:
+  //     div = a / b
+  //     rem = a - b * div
+  //     return {div, rem}
+  // This should be lowered into UDIV/SDIV + MLS later on.
+  if (Subtarget->hasDivide()) {
+    unsigned DivOpcode = isSigned ? ISD::SDIV : ISD::UDIV;
+    const SDValue Dividend = Op->getOperand(0);
+    const SDValue Divisor = Op->getOperand(1);
+    SDValue Div = DAG.getNode(DivOpcode, dl, VT, Dividend, Divisor);
+    SDValue Mul = DAG.getNode(ISD::MUL, dl, VT, Div, Divisor);
+    SDValue Rem = DAG.getNode(ISD::SUB, dl, VT, Dividend, Mul);
+
+    SDValue Values[2] = {Div, Rem};
+    return DAG.getNode(ISD::MERGE_VALUES, dl, DAG.getVTList(VT, VT), Values);
+  }
 
   RTLIB::Libcall LC = getDivRemLibcall(Op.getNode(),
                                        VT.getSimpleVT().SimpleTy);
@@ -12111,7 +12129,6 @@ SDValue ARMTargetLowering::LowerDivRem(SDValue Op, SelectionDAG &DAG) const {
 
   Type *RetTy = (Type*)StructType::get(Ty, Ty, nullptr);
 
-  SDLoc dl(Op);
   TargetLowering::CallLoweringInfo CLI(DAG);
   CLI.setDebugLoc(dl).setChain(InChain)
     .setCallee(getLibcallCallingConv(LC), RetTy, Callee, std::move(Args))

test/CodeGen/ARM/urem-opt-size.ll

@@ -3,7 +3,12 @@
 ; expanded to a sequence of umull, lsrs, muls and sub instructions, but
 ; just a call to __aeabi_uidivmod.
 ;
+; When the processor features hardware division, UDIV + UREM can be turned
+; into UDIV + MLS. This prevents the library function __aeabi_uidivmod to be
+; pulled into the binary. The test uses ARMv7-M.
+;
 ; RUN: llc -mtriple=armv7a-eabi -mattr=-neon -verify-machineinstrs %s -o - | FileCheck %s
+; RUN: llc -mtriple=thumbv7m-eabi -verify-machineinstrs %s -o - | FileCheck %s -check-prefix=V7M
 
 target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-a:0:32-n32-S64"
 target triple = "thumbv7m-arm-none-eabi"
@@ -28,18 +33,56 @@ entry:
   ret i32 %div
 }
 
+; Test for unsigned remainder
 define i32 @foo3() local_unnamed_addr #0 {
 entry:
 ; CHECK-LABEL: foo3:
 ; CHECK: __aeabi_uidivmod
 ; CHECK-NOT: umull
+; V7M-LABEL: foo3:
+; V7M: udiv [[R2:r[0-9]+]], [[R0:r[0-9]+]], [[R1:r[0-9]+]]
+; V7M: mls {{r[0-9]+}}, [[R2]], [[R1]], [[R0]]
+; V7M-NOT: __aeabi_uidivmod
   %call = tail call i32 bitcast (i32 (...)* @GetValue to i32 ()*)()
   %rem = urem i32 %call, 1000000
   %cmp = icmp eq i32 %rem, 0
   %conv = zext i1 %cmp to i32
   ret i32 %conv
 }
 
+; Test for signed remainder
+define i32 @foo4() local_unnamed_addr #0 {
+entry:
+; CHECK-LABEL: foo4:
+; CHECK:__aeabi_idivmod
+; V7M-LABEL: foo4:
+; V7M: sdiv [[R2:r[0-9]+]], [[R0:r[0-9]+]], [[R1:r[0-9]+]]
+; V7M: mls {{r[0-9]+}}, [[R2]], [[R1]], [[R0]]
+; V7M-NOT: __aeabi_idivmod
+  %call = tail call i32 bitcast (i32 (...)* @GetValue to i32 ()*)()
+  %rem = srem i32 %call, 1000000
+  ret i32 %rem
+}
+
+; Check that doing a sdiv+srem has the same effect as only the srem,
+; as the division needs to be computed anyway in order to calculate
+; the remainder (i.e. make sure we don't end up with two divisions).
+define i32 @foo5() local_unnamed_addr #0 {
+entry:
+; CHECK-LABEL: foo5:
+; CHECK:__aeabi_idivmod
+; V7M-LABEL: foo5:
+; V7M: sdiv [[R2:r[0-9]+]], [[R0:r[0-9]+]], [[R1:r[0-9]+]]
+; V7M-NOT: sdiv
+; V7M: mls {{r[0-9]+}}, [[R2]], [[R1]], [[R0]]
+; V7M-NOT: __aeabi_idivmod
+  %call = tail call i32 bitcast (i32 (...)* @GetValue to i32 ()*)()
+  %div = sdiv i32 %call, 1000000
+  %rem = srem i32 %call, 1000000
+  %add = add i32 %div, %rem
+  ret i32 %add
+}
+
 declare i32 @GetValue(...) local_unnamed_addr
 
 attributes #0 = { minsize nounwind optsize }