[AArch64] Lower sdiv x, pow2 using add + select + shift.

The target-independent DAGcombiner will generate:
asr w1, X, #31 w1 = splat sign bit.
add X, X, w1, lsr #28 X = X + 0 or pow2-1
asr w0, X, asr #4 w0 = X/pow2

However, the add + shifts is expensive, so generate:
add w0, X, 15 w0 = X + pow2-1
cmp X, wzr X - 0
csel X, w0, X, lt X = (X < 0) ? X + pow2-1 : X;
asr w0, X, asr 4 w0 = X/pow2

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213758 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/Target/TargetLowering.h

@@ -2545,6 +2545,11 @@ public:
   SDValue BuildUDIV(SDNode *N, const APInt &Divisor, SelectionDAG &DAG,
                     bool IsAfterLegalization,
                     std::vector<SDNode *> *Created) const;
+  virtual SDValue BuildSDIVPow2(SDNode *N, const APInt &Divisor,
+                                SelectionDAG &DAG,
+                                std::vector<SDNode *> *Created) const {
+    return SDValue();
+  }
 
   //===--------------------------------------------------------------------===//
   // Legalization utility functions

lib/CodeGen/SelectionDAG/DAGCombiner.cpp

@@ -304,6 +304,7 @@ namespace {
     SDValue CombineConsecutiveLoads(SDNode *N, EVT VT);
     SDValue ConstantFoldBITCASTofBUILD_VECTOR(SDNode *, EVT);
     SDValue BuildSDIV(SDNode *N);
+    SDValue BuildSDIVPow2(SDNode *N);
     SDValue BuildUDIV(SDNode *N);
     SDValue MatchBSwapHWordLow(SDNode *N, SDValue N0, SDValue N1,
                                bool DemandHighBits = true);
@@ -2033,6 +2034,11 @@ SDValue DAGCombiner::visitSDIV(SDNode *N) {
     if (TLI.isPow2DivCheap())
       return SDValue();
 
+    // Target-specific implementation of sdiv x, pow2.
+    SDValue Res = BuildSDIVPow2(N);
+    if (Res.getNode())
+      return Res;
+
     unsigned lg2 = N1C->getAPIntValue().countTrailingZeros();
 
     // Splat the sign bit into the register
@@ -11482,9 +11488,9 @@ SDValue DAGCombiner::SimplifySetCC(EVT VT, SDValue N0,
   return TLI.SimplifySetCC(VT, N0, N1, Cond, foldBooleans, DagCombineInfo, DL);
 }
 
-/// BuildSDIVSequence - Given an ISD::SDIV node expressing a divide by constant,
-/// return a DAG expression to select that will generate the same value by
-/// multiplying by a magic number.  See:
+/// BuildSDIV - Given an ISD::SDIV node expressing a divide by constant, return
+/// a DAG expression to select that will generate the same value by multiplying
+/// by a magic number.  See:
 /// <http://the.wall.riscom.net/books/proc/ppc/cwg/code2.html>
 SDValue DAGCombiner::BuildSDIV(SDNode *N) {
   ConstantSDNode *C = isConstOrConstSplat(N->getOperand(1));
@@ -11504,6 +11510,26 @@ SDValue DAGCombiner::BuildSDIV(SDNode *N) {
   return S;
 }
 
+/// BuildSDIVPow2 - Given an ISD::SDIV node expressing a divide by constant
+/// power of 2, return a DAG expression to select that will generate the same
+/// value by right shifting.
+SDValue DAGCombiner::BuildSDIVPow2(SDNode *N) {
+  ConstantSDNode *C = isConstOrConstSplat(N->getOperand(1));
+  if (!C)
+    return SDValue();
+
+  // Avoid division by zero.
+  if (!C->getAPIntValue())
+    return SDValue();
+
+  std::vector<SDNode *> Built;
+  SDValue S = TLI.BuildSDIVPow2(N, C->getAPIntValue(), DAG, &Built);
+
+  for (SDNode *N : Built)
+    AddToWorklist(N);
+  return S;
+}
+
 /// BuildUDIV - Given an ISD::UDIV node expressing a divide by constant,
 /// return a DAG expression to select that will generate the same value by
 /// multiplying by a magic number.  See:

lib/Target/AArch64/AArch64ISelLowering.cpp

@@ -6382,6 +6382,48 @@ static SDValue performXorCombine(SDNode *N, SelectionDAG &DAG,
   return performIntegerAbsCombine(N, DAG);
 }
 
+SDValue
+AArch64TargetLowering::BuildSDIVPow2(SDNode *N, const APInt &Divisor,
+                                     SelectionDAG &DAG,
+                                     std::vector<SDNode *> *Created) const {
+  // fold (sdiv X, pow2)
+  EVT VT = N->getValueType(0);
+  if ((VT != MVT::i32 && VT != MVT::i64) ||
+      !(Divisor.isPowerOf2() || (-Divisor).isPowerOf2()))
+    return SDValue();
+
+  SDLoc DL(N);
+  SDValue N0 = N->getOperand(0);
+  unsigned Lg2 = Divisor.countTrailingZeros();
+  SDValue Zero = DAG.getConstant(0, VT);
+  SDValue Pow2MinusOne = DAG.getConstant((1 << Lg2) - 1, VT);
+
+  // Add (N0 < 0) ? Pow2 - 1 : 0;
+  SDValue CCVal;
+  SDValue Cmp = getAArch64Cmp(N0, Zero, ISD::SETLT, CCVal, DAG, DL);
+  SDValue Add = DAG.getNode(ISD::ADD, DL, VT, N0, Pow2MinusOne);
+  SDValue CSel = DAG.getNode(AArch64ISD::CSEL, DL, VT, Add, N0, CCVal, Cmp);
+
+  if (Created) {
+    Created->push_back(Cmp.getNode());
+    Created->push_back(Add.getNode());
+    Created->push_back(CSel.getNode());
+  }
+
+  // Divide by pow2.
+  SDValue SRA =
+      DAG.getNode(ISD::SRA, DL, VT, CSel, DAG.getConstant(Lg2, MVT::i64));
+
+  // If we're dividing by a positive value, we're done.  Otherwise, we must
+  // negate the result.
+  if (Divisor.isNonNegative())
+    return SRA;
+
+  if (Created)
+    Created->push_back(SRA.getNode());
+  return DAG.getNode(ISD::SUB, DL, VT, DAG.getConstant(0, VT), SRA);
+}
+
 static SDValue performMulCombine(SDNode *N, SelectionDAG &DAG,
                                  TargetLowering::DAGCombinerInfo &DCI,
                                  const AArch64Subtarget *Subtarget) {

lib/Target/AArch64/AArch64ISelLowering.h

@@ -424,6 +424,9 @@ private:
   SDValue LowerCONCAT_VECTORS(SDValue Op, SelectionDAG &DAG) const;
   SDValue LowerFSINCOS(SDValue Op, SelectionDAG &DAG) const;
 
+  SDValue BuildSDIVPow2(SDNode *N, const APInt &Divisor, SelectionDAG &DAG,
+                        std::vector<SDNode *> *Created) const;
+
   ConstraintType
   getConstraintType(const std::string &Constraint) const override;
   unsigned getRegisterByName(const char* RegName, EVT VT) const override;

test/CodeGen/AArch64/sdivpow2.ll

@@ -0,0 +1,61 @@
+; RUN: llc -mtriple=arm64-linux-gnu -o - %s | FileCheck %s
+
+define i32 @test1(i32 %x) {
+; CHECK-LABEL: test1
+; CHECK: add w8, w0, #7
+; CHECK: cmp w0, #0
+; CHECK: csel w8, w8, w0, lt
+; CHECK: asr w0, w8, #3
+  %div = sdiv i32 %x, 8
+  ret i32 %div
+}
+
+define i32 @test2(i32 %x) {
+; CHECK-LABEL: test2
+; CHECK: add w8, w0, #7
+; CHECK: cmp w0, #0
+; CHECK: csel w8, w8, w0, lt
+; CHECK: neg w0, w8, asr #3
+  %div = sdiv i32 %x, -8
+  ret i32 %div
+}
+
+define i32 @test3(i32 %x) {
+; CHECK-LABEL: test3
+; CHECK: add w8, w0, #31
+; CHECK: cmp w0, #0
+; CHECK: csel w8, w8, w0, lt
+; CHECK: asr w0, w8, #5
+  %div = sdiv i32 %x, 32
+  ret i32 %div
+}
+
+define i64 @test4(i64 %x) {
+; CHECK-LABEL: test4
+; CHECK: add x8, x0, #7
+; CHECK: cmp x0, #0
+; CHECK: csel x8, x8, x0, lt
+; CHECK: asr x0, x8, #3
+  %div = sdiv i64 %x, 8
+  ret i64 %div
+}
+
+define i64 @test5(i64 %x) {
+; CHECK-LABEL: test5
+; CHECK: add x8, x0, #7
+; CHECK: cmp x0, #0
+; CHECK: csel x8, x8, x0, lt
+; CHECK: neg x0, x8, asr #3
+  %div = sdiv i64 %x, -8
+  ret i64 %div
+}
+
+define i64 @test6(i64 %x) {
+; CHECK-LABEL: test6
+; CHECK: add x8, x0, #63
+; CHECK: cmp x0, #0
+; CHECK: csel x8, x8, x0, lt
+; CHECK: asr x0, x8, #6
+  %div = sdiv i64 %x, 64
+  ret i64 %div
+}