diff options
author | Sanjay Patel <spatel@rotateright.com> | 2016-06-02 20:01:37 +0000 |
---|---|---|
committer | Sanjay Patel <spatel@rotateright.com> | 2016-06-02 20:01:37 +0000 |
commit | dba8b4c04d579b946572800d20419e70177b3194 (patch) | |
tree | e5e683c188b16a381030fc74d498b32cee96c050 /llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp | |
parent | 617409f0c0a990d2d4b62f1a3e02ca26bc41d67a (diff) | |
download | bcm5719-llvm-dba8b4c04d579b946572800d20419e70177b3194.tar.gz bcm5719-llvm-dba8b4c04d579b946572800d20419e70177b3194.zip |
transform obscured FP sign bit ops into a fabs/fneg using TLI hook
This is effectively a revert of:
http://reviews.llvm.org/rL249702 - [InstCombine] transform masking off of an FP sign bit into a fabs() intrinsic call (PR24886)
and:
http://reviews.llvm.org/rL249701 - [ValueTracking] teach computeKnownBits that a fabs() clears sign bits
and a reimplementation as a DAG combine for targets that have IEEE754-compliant fabs/fneg instructions.
This is intended to resolve the objections raised on the dev list:
http://lists.llvm.org/pipermail/llvm-dev/2016-April/098154.html
and:
https://llvm.org/bugs/show_bug.cgi?id=24886#c4
In the interest of patch minimalism, I've only partly enabled AArch64. PowerPC, MIPS, x86 and others can enable later.
Differential Revision: http://reviews.llvm.org/D19391
llvm-svn: 271573
Diffstat (limited to 'llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp')
-rw-r--r-- | llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp | 46 |
1 files changed, 46 insertions, 0 deletions
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp index d3378483499..e7ee596beec 100644 --- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp @@ -7351,6 +7351,49 @@ static unsigned getPPCf128HiElementSelector(const SelectionDAG &DAG) { return DAG.getDataLayout().isBigEndian() ? 1 : 0; } +static SDValue foldBitcastedFPLogic(SDNode *N, SelectionDAG &DAG, + const TargetLowering &TLI) { + // If this is not a bitcast to an FP type or if the target doesn't have + // IEEE754-compliant FP logic, we're done. + EVT VT = N->getValueType(0); + if (!VT.isFloatingPoint() || !TLI.hasBitPreservingFPLogic(VT)) + return SDValue(); + + // TODO: Use splat values for the constant-checking below and remove this + // restriction. + SDValue N0 = N->getOperand(0); + EVT SourceVT = N0.getValueType(); + if (SourceVT.isVector()) + return SDValue(); + + unsigned FPOpcode; + APInt SignMask; + switch (N0.getOpcode()) { + case ISD::AND: + FPOpcode = ISD::FABS; + SignMask = ~APInt::getSignBit(SourceVT.getSizeInBits()); + break; + case ISD::XOR: + FPOpcode = ISD::FNEG; + SignMask = APInt::getSignBit(SourceVT.getSizeInBits()); + break; + // TODO: ISD::OR --> ISD::FNABS? + default: + return SDValue(); + } + + // Fold (bitcast int (and (bitcast fp X to int), 0x7fff...) to fp) -> fabs X + // Fold (bitcast int (xor (bitcast fp X to int), 0x8000...) to fp) -> fneg X + SDValue LogicOp0 = N0.getOperand(0); + ConstantSDNode *LogicOp1 = dyn_cast<ConstantSDNode>(N0.getOperand(1)); + if (LogicOp1 && LogicOp1->getAPIntValue() == SignMask && + LogicOp0.getOpcode() == ISD::BITCAST && + LogicOp0->getOperand(0).getValueType() == VT) + return DAG.getNode(FPOpcode, SDLoc(N), VT, LogicOp0->getOperand(0)); + + return SDValue(); +} + SDValue DAGCombiner::visitBITCAST(SDNode *N) { SDValue N0 = N->getOperand(0); EVT VT = N->getValueType(0); @@ -7415,6 +7458,9 @@ SDValue DAGCombiner::visitBITCAST(SDNode *N) { } } + if (SDValue V = foldBitcastedFPLogic(N, DAG, TLI)) + return V; + // fold (bitconvert (fneg x)) -> (xor (bitconvert x), signbit) // fold (bitconvert (fabs x)) -> (and (bitconvert x), (not signbit)) // |