[SelectionDAG] Handle unary SelectPatternFlavor for ABS case in SelectionDAGBuilder::visitSelect

These changes are related to PR37743 and include:

    SelectionDAGBuilder::visitSelect handles the unary SelectPatternFlavor::SPF_ABS case to build ABS node.

    Delete the redundant recognizer of the integer ABS pattern from the DAGCombiner.

    Add promoting the integer ABS node in the LegalizeIntegerType.

    Expand-based legalization of integer result for the ABS nodes.

    Expand-based legalization of ABS vector operations.

    Add some integer abs testcases for different typesizes for Thumb arch

    Add the custom ABS expanding and change the SAD pattern recognizer for X86 arch: The i64 result of the ABS is expanded to:
        tmp = (SRA, Hi, 31)
        Lo = (UADDO tmp, Lo)
        Hi = (XOR tmp, (ADDCARRY tmp, hi, Lo:1))
        Lo = (XOR tmp, Lo)

    The "detectZextAbsDiff" function is changed for the recognition of pattern with the ABS node. Given a ABS node, detect the following pattern:
        (ABS (SUB (ZERO_EXTEND a), (ZERO_EXTEND b))).

    Change integer abs testcases for codegen with the ABS node support for AArch64.
        Indicate that the ABS is legal for the i64 type when the NEON is supported.
        Change the integer abs testcases to show changing of codegen.

    Add combine and legalization of ABS nodes for Thumb arch.

    Extend 'matchSelectPattern' to recognize the ABS patterns with ICMP_SGE condition.

For discussion, see https://bugs.llvm.org/show_bug.cgi?id=37743

Patch by: @ikulagin (Ivan Kulagin)

Differential Revision: https://reviews.llvm.org/D49837

llvm-svn: 356468

1 files changed, 54 insertions, 0 deletions

diff --git a/llvm/lib/Target/ARM/ARMISelLowering.cpp b/llvm/lib/Target/ARM/ARMISelLowering.cpp
index 9748e204a5d..c1482822bc6 100644
--- a/llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ b/llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -1207,6 +1207,9 @@ ARMTargetLowering::ARMTargetLowering(const TargetMachine &TM,
   setPrefLoopAlignment(Subtarget->getPrefLoopAlignment());
 
   setMinFunctionAlignment(Subtarget->isThumb() ? 1 : 2);
+
+  if (Subtarget->isThumb() || Subtarget->isThumb2())
+    setTargetDAGCombine(ISD::ABS);
 }
 
 bool ARMTargetLowering::useSoftFloat() const {
@@ -8180,6 +8183,10 @@ void ARMTargetLowering::ReplaceNodeResults(SDNode *N,
     return;
   case ISD::INTRINSIC_WO_CHAIN:
     return ReplaceLongIntrinsic(N, Results, DAG);
+  case ISD::ABS:
+     lowerABS(N, Results, DAG);
+     return ;
+
   }
   if (Res.getNode())
     Results.push_back(Res);
@@ -10377,6 +10384,19 @@ static SDValue PerformAddeSubeCombine(SDNode *N,
   return SDValue();
 }
 
+static SDValue PerformABSCombine(SDNode *N,
+                                  TargetLowering::DAGCombinerInfo &DCI,
+                                  const ARMSubtarget *Subtarget) {
+  SDValue res;
+  SelectionDAG &DAG = DCI.DAG;
+  const TargetLowering &TLI = DAG.getTargetLoweringInfo();
+
+  if (!TLI.expandABS(N, res, DAG))
+    return SDValue();
+
+  return res;
+}
+
 /// PerformADDECombine - Target-specific dag combine transform from
 /// ARMISD::ADDC, ARMISD::ADDE, and ISD::MUL_LOHI to MLAL or
 /// ARMISD::ADDC, ARMISD::ADDE and ARMISD::UMLAL to ARMISD::UMAAL
@@ -12884,6 +12904,7 @@ SDValue ARMTargetLowering::PerformDAGCombine(SDNode *N,
                                              DAGCombinerInfo &DCI) const {
   switch (N->getOpcode()) {
   default: break;
+  case ISD::ABS:        return PerformABSCombine(N, DCI, Subtarget);
   case ARMISD::ADDE:    return PerformADDECombine(N, DCI, Subtarget);
   case ARMISD::UMLAL:   return PerformUMLALCombine(N, DCI.DAG, Subtarget);
   case ISD::ADD:        return PerformADDCombine(N, DCI, Subtarget);
@@ -14395,6 +14416,39 @@ SDValue ARMTargetLowering::LowerFP_ROUND(SDValue Op, SelectionDAG &DAG) const {
                      SDLoc(Op)).first;
 }
 
+void ARMTargetLowering::lowerABS(SDNode *N, SmallVectorImpl<SDValue> &Results,
+                                 SelectionDAG &DAG) const {
+  EVT VT = N->getValueType(0);
+  assert(VT == MVT::i64 && "Unexpected type (!= i64) on ABS.");
+  MVT HalfT = MVT::i32;
+  SDLoc dl(N);
+  SDValue Hi, Lo, Tmp;
+
+  if (!isOperationLegalOrCustom(ISD::ADDCARRY, HalfT) ||
+      !isOperationLegalOrCustom(ISD::UADDO, HalfT))
+    return ;
+
+  unsigned OpTypeBits = HalfT.getScalarSizeInBits();
+  SDVTList VTList = DAG.getVTList(HalfT, MVT::i1);
+
+  Lo = DAG.getNode(ISD::EXTRACT_ELEMENT, dl, HalfT, N->getOperand(0),
+                   DAG.getConstant(0, dl, HalfT));
+  Hi = DAG.getNode(ISD::EXTRACT_ELEMENT, dl, HalfT, N->getOperand(0),
+                   DAG.getConstant(1, dl, HalfT));
+
+  Tmp = DAG.getNode(ISD::SRA, dl, HalfT, Hi,
+                    DAG.getConstant(OpTypeBits - 1, dl,
+                    getShiftAmountTy(HalfT, DAG.getDataLayout())));
+  Lo = DAG.getNode(ISD::UADDO, dl, VTList, Tmp, Lo);
+  Hi = DAG.getNode(ISD::ADDCARRY, dl, VTList, Tmp, Hi,
+                   SDValue(Lo.getNode(), 1));
+  Hi = DAG.getNode(ISD::XOR, dl, HalfT, Tmp, Hi);
+  Lo = DAG.getNode(ISD::XOR, dl, HalfT, Tmp, Lo);
+
+  Results.push_back(Lo);
+  Results.push_back(Hi);
+}
+
 bool
 ARMTargetLowering::isOffsetFoldingLegal(const GlobalAddressSDNode *GA) const {
   // The ARM target isn't yet aware of offsets.