[DAG][X86] Convert isNegatibleForFree/GetNegatedExpression to a target hook (PR42863)

This patch converts the DAGCombine isNegatibleForFree/GetNegatedExpression into overridable TLI hooks and includes a demonstration X86 implementation.

The intention is to let us extend existing FNEG combines to work more generally with negatible float ops, allowing it work with target specific combines and opcodes (e.g. X86's FMA variants).

Unlike the SimplifyDemandedBits, we can't just handle target nodes through a Target callback, we need to do this as an override to allow targets to handle generic opcodes as well. This does mean that the target implementations has to duplicate some checks (recursion depth etc.).

I've only begun to replace X86's FNEG handling here, handling FMADDSUB/FMSUBADD negation and some low impact codegen changes (some FMA negatation propagation). We can build on this in future patches.

Differential Revision: https://reviews.llvm.org/D67557

llvm-svn: 372333

1 files changed, 240 insertions, 0 deletions

diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index fbe4e8cca8e..0b6f8ba4257 100644
--- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -5331,6 +5331,246 @@ verifyReturnAddressArgumentIsConstant(SDValue Op, SelectionDAG &DAG) const {
   return false;
 }
 
+char TargetLowering::isNegatibleForFree(SDValue Op, SelectionDAG &DAG,
+                                        bool LegalOperations, bool ForCodeSize,
+                                        unsigned Depth) const {
+  // fneg is removable even if it has multiple uses.
+  if (Op.getOpcode() == ISD::FNEG)
+    return 2;
+
+  // Don't allow anything with multiple uses unless we know it is free.
+  EVT VT = Op.getValueType();
+  const SDNodeFlags Flags = Op->getFlags();
+  const TargetOptions &Options = DAG.getTarget().Options;
+  if (!Op.hasOneUse() && !(Op.getOpcode() == ISD::FP_EXTEND &&
+                           isFPExtFree(VT, Op.getOperand(0).getValueType())))
+    return 0;
+
+  // Don't recurse exponentially.
+  if (Depth > SelectionDAG::MaxRecursionDepth)
+    return 0;
+
+  switch (Op.getOpcode()) {
+  case ISD::ConstantFP: {
+    if (!LegalOperations)
+      return 1;
+
+    // Don't invert constant FP values after legalization unless the target says
+    // the negated constant is legal.
+    return isOperationLegal(ISD::ConstantFP, VT) ||
+           isFPImmLegal(neg(cast<ConstantFPSDNode>(Op)->getValueAPF()), VT,
+                        ForCodeSize);
+  }
+  case ISD::BUILD_VECTOR: {
+    // Only permit BUILD_VECTOR of constants.
+    if (llvm::any_of(Op->op_values(), [&](SDValue N) {
+          return !N.isUndef() && !isa<ConstantFPSDNode>(N);
+        }))
+      return 0;
+    if (!LegalOperations)
+      return 1;
+    if (isOperationLegal(ISD::ConstantFP, VT) &&
+        isOperationLegal(ISD::BUILD_VECTOR, VT))
+      return 1;
+    return llvm::all_of(Op->op_values(), [&](SDValue N) {
+      return N.isUndef() ||
+             isFPImmLegal(neg(cast<ConstantFPSDNode>(N)->getValueAPF()), VT,
+                          ForCodeSize);
+    });
+  }
+  case ISD::FADD:
+    if (!Options.NoSignedZerosFPMath && !Flags.hasNoSignedZeros())
+      return 0;
+
+    // After operation legalization, it might not be legal to create new FSUBs.
+    if (LegalOperations && !isOperationLegalOrCustom(ISD::FSUB, VT))
+      return 0;
+
+    // fold (fneg (fadd A, B)) -> (fsub (fneg A), B)
+    if (char V = isNegatibleForFree(Op.getOperand(0), DAG, LegalOperations,
+                                    ForCodeSize, Depth + 1))
+      return V;
+    // fold (fneg (fadd A, B)) -> (fsub (fneg B), A)
+    return isNegatibleForFree(Op.getOperand(1), DAG, LegalOperations,
+                              ForCodeSize, Depth + 1);
+  case ISD::FSUB:
+    // We can't turn -(A-B) into B-A when we honor signed zeros.
+    if (!Options.NoSignedZerosFPMath && !Flags.hasNoSignedZeros())
+      return 0;
+
+    // fold (fneg (fsub A, B)) -> (fsub B, A)
+    return 1;
+
+  case ISD::FMUL:
+  case ISD::FDIV:
+    // fold (fneg (fmul X, Y)) -> (fmul (fneg X), Y) or (fmul X, (fneg Y))
+    if (char V = isNegatibleForFree(Op.getOperand(0), DAG, LegalOperations,
+                                    ForCodeSize, Depth + 1))
+      return V;
+
+    // Ignore X * 2.0 because that is expected to be canonicalized to X + X.
+    if (auto *C = isConstOrConstSplatFP(Op.getOperand(1)))
+      if (C->isExactlyValue(2.0) && Op.getOpcode() == ISD::FMUL)
+        return 0;
+
+    return isNegatibleForFree(Op.getOperand(1), DAG, LegalOperations,
+                              ForCodeSize, Depth + 1);
+
+  case ISD::FMA:
+  case ISD::FMAD: {
+    if (!Options.NoSignedZerosFPMath && !Flags.hasNoSignedZeros())
+      return 0;
+
+    // fold (fneg (fma X, Y, Z)) -> (fma (fneg X), Y, (fneg Z))
+    // fold (fneg (fma X, Y, Z)) -> (fma X, (fneg Y), (fneg Z))
+    char V2 = isNegatibleForFree(Op.getOperand(2), DAG, LegalOperations,
+                                 ForCodeSize, Depth + 1);
+    if (!V2)
+      return 0;
+
+    // One of Op0/Op1 must be cheaply negatible, then select the cheapest.
+    char V0 = isNegatibleForFree(Op.getOperand(0), DAG, LegalOperations,
+                                 ForCodeSize, Depth + 1);
+    char V1 = isNegatibleForFree(Op.getOperand(1), DAG, LegalOperations,
+                                 ForCodeSize, Depth + 1);
+    char V01 = std::max(V0, V1);
+    return V01 ? std::max(V01, V2) : 0;
+  }
+
+  case ISD::FP_EXTEND:
+  case ISD::FP_ROUND:
+  case ISD::FSIN:
+    return isNegatibleForFree(Op.getOperand(0), DAG, LegalOperations,
+                              ForCodeSize, Depth + 1);
+  }
+
+  return 0;
+}
+
+SDValue TargetLowering::getNegatedExpression(SDValue Op, SelectionDAG &DAG,
+                                             bool LegalOperations,
+                                             bool ForCodeSize,
+                                             unsigned Depth) const {
+  // fneg is removable even if it has multiple uses.
+  if (Op.getOpcode() == ISD::FNEG)
+    return Op.getOperand(0);
+
+  assert(Depth <= SelectionDAG::MaxRecursionDepth &&
+         "getNegatedExpression doesn't match isNegatibleForFree");
+  const SDNodeFlags Flags = Op->getFlags();
+
+  switch (Op.getOpcode()) {
+  case ISD::ConstantFP: {
+    APFloat V = cast<ConstantFPSDNode>(Op)->getValueAPF();
+    V.changeSign();
+    return DAG.getConstantFP(V, SDLoc(Op), Op.getValueType());
+  }
+  case ISD::BUILD_VECTOR: {
+    SmallVector<SDValue, 4> Ops;
+    for (SDValue C : Op->op_values()) {
+      if (C.isUndef()) {
+        Ops.push_back(C);
+        continue;
+      }
+      APFloat V = cast<ConstantFPSDNode>(C)->getValueAPF();
+      V.changeSign();
+      Ops.push_back(DAG.getConstantFP(V, SDLoc(Op), C.getValueType()));
+    }
+    return DAG.getBuildVector(Op.getValueType(), SDLoc(Op), Ops);
+  }
+  case ISD::FADD:
+    assert((DAG.getTarget().Options.NoSignedZerosFPMath ||
+            Flags.hasNoSignedZeros()) &&
+           "Expected NSZ fp-flag");
+
+    // fold (fneg (fadd A, B)) -> (fsub (fneg A), B)
+    if (isNegatibleForFree(Op.getOperand(0), DAG, LegalOperations, ForCodeSize,
+                           Depth + 1))
+      return DAG.getNode(ISD::FSUB, SDLoc(Op), Op.getValueType(),
+                         getNegatedExpression(Op.getOperand(0), DAG,
+                                              LegalOperations, ForCodeSize,
+                                              Depth + 1),
+                         Op.getOperand(1), Flags);
+    // fold (fneg (fadd A, B)) -> (fsub (fneg B), A)
+    return DAG.getNode(ISD::FSUB, SDLoc(Op), Op.getValueType(),
+                       getNegatedExpression(Op.getOperand(1), DAG,
+                                            LegalOperations, ForCodeSize,
+                                            Depth + 1),
+                       Op.getOperand(0), Flags);
+  case ISD::FSUB:
+    // fold (fneg (fsub 0, B)) -> B
+    if (ConstantFPSDNode *N0CFP =
+            isConstOrConstSplatFP(Op.getOperand(0), /*AllowUndefs*/ true))
+      if (N0CFP->isZero())
+        return Op.getOperand(1);
+
+    // fold (fneg (fsub A, B)) -> (fsub B, A)
+    return DAG.getNode(ISD::FSUB, SDLoc(Op), Op.getValueType(),
+                       Op.getOperand(1), Op.getOperand(0), Flags);
+
+  case ISD::FMUL:
+  case ISD::FDIV:
+    // fold (fneg (fmul X, Y)) -> (fmul (fneg X), Y)
+    if (isNegatibleForFree(Op.getOperand(0), DAG, LegalOperations, ForCodeSize,
+                           Depth + 1))
+      return DAG.getNode(Op.getOpcode(), SDLoc(Op), Op.getValueType(),
+                         getNegatedExpression(Op.getOperand(0), DAG,
+                                              LegalOperations, ForCodeSize,
+                                              Depth + 1),
+                         Op.getOperand(1), Flags);
+
+    // fold (fneg (fmul X, Y)) -> (fmul X, (fneg Y))
+    return DAG.getNode(
+        Op.getOpcode(), SDLoc(Op), Op.getValueType(), Op.getOperand(0),
+        getNegatedExpression(Op.getOperand(1), DAG, LegalOperations,
+                             ForCodeSize, Depth + 1),
+        Flags);
+
+  case ISD::FMA:
+  case ISD::FMAD: {
+    assert((DAG.getTarget().Options.NoSignedZerosFPMath ||
+            Flags.hasNoSignedZeros()) &&
+           "Expected NSZ fp-flag");
+
+    SDValue Neg2 = getNegatedExpression(Op.getOperand(2), DAG, LegalOperations,
+                                        ForCodeSize, Depth + 1);
+
+    char V0 = isNegatibleForFree(Op.getOperand(0), DAG, LegalOperations,
+                                 ForCodeSize, Depth + 1);
+    char V1 = isNegatibleForFree(Op.getOperand(1), DAG, LegalOperations,
+                                 ForCodeSize, Depth + 1);
+    if (V0 >= V1) {
+      // fold (fneg (fma X, Y, Z)) -> (fma (fneg X), Y, (fneg Z))
+      SDValue Neg0 = getNegatedExpression(
+          Op.getOperand(0), DAG, LegalOperations, ForCodeSize, Depth + 1);
+      return DAG.getNode(Op.getOpcode(), SDLoc(Op), Op.getValueType(), Neg0,
+                         Op.getOperand(1), Neg2, Flags);
+    }
+
+    // fold (fneg (fma X, Y, Z)) -> (fma X, (fneg Y), (fneg Z))
+    SDValue Neg1 = getNegatedExpression(Op.getOperand(1), DAG, LegalOperations,
+                                        ForCodeSize, Depth + 1);
+    return DAG.getNode(Op.getOpcode(), SDLoc(Op), Op.getValueType(),
+                       Op.getOperand(0), Neg1, Neg2, Flags);
+  }
+
+  case ISD::FP_EXTEND:
+  case ISD::FSIN:
+    return DAG.getNode(Op.getOpcode(), SDLoc(Op), Op.getValueType(),
+                       getNegatedExpression(Op.getOperand(0), DAG,
+                                            LegalOperations, ForCodeSize,
+                                            Depth + 1));
+  case ISD::FP_ROUND:
+    return DAG.getNode(ISD::FP_ROUND, SDLoc(Op), Op.getValueType(),
+                       getNegatedExpression(Op.getOperand(0), DAG,
+                                            LegalOperations, ForCodeSize,
+                                            Depth + 1),
+                       Op.getOperand(1));
+  }
+
+  llvm_unreachable("Unknown code");
+}
+
 //===----------------------------------------------------------------------===//
 // Legalization Utilities
 //===----------------------------------------------------------------------===//