diff options
Diffstat (limited to 'llvm/lib')
| -rw-r--r-- | llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp | 29 | ||||
| -rw-r--r-- | llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp | 5 | ||||
| -rw-r--r-- | llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp | 1 | ||||
| -rw-r--r-- | llvm/lib/CodeGen/TargetLoweringBase.cpp | 1 |
4 files changed, 35 insertions, 1 deletions
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp index 20e749ba569..4ef16cb7186 100644 --- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp @@ -11571,6 +11571,34 @@ SDValue DAGCombiner::visitFPOW(SDNode *N) { if (!ExponentC) return SDValue(); + // Try to convert x ** (1/3) into cube root. + // TODO: Handle the various flavors of long double. + // TODO: Since we're approximating, we don't need an exact 1/3 exponent. + // Some range near 1/3 should be fine. + EVT VT = N->getValueType(0); + if ((VT == MVT::f32 && ExponentC->getValueAPF().isExactlyValue(1.0f/3.0f)) || + (VT == MVT::f64 && ExponentC->getValueAPF().isExactlyValue(1.0/3.0))) { + // pow(-0.0, 1/3) = +0.0; cbrt(-0.0) = -0.0. + // pow(-inf, 1/3) = +inf; cbrt(-inf) = -inf. + // pow(-val, 1/3) = nan; cbrt(-val) = -num. + // For regular numbers, rounding may cause the results to differ. + // Therefore, we require { nsz ninf nnan afn } for this transform. + // TODO: We could select out the special cases if we don't have nsz/ninf. + SDNodeFlags Flags = N->getFlags(); + if (!Flags.hasNoSignedZeros() || !Flags.hasNoInfs() || !Flags.hasNoNaNs() || + !Flags.hasApproximateFuncs()) + return SDValue(); + + // Do not create a cbrt() libcall if the target does not have it, and do not + // turn a pow that has lowering support into a cbrt() libcall. + if (!DAG.getLibInfo().has(LibFunc_cbrt) || + (!DAG.getTargetLoweringInfo().isOperationExpand(ISD::FPOW, VT) && + DAG.getTargetLoweringInfo().isOperationExpand(ISD::FCBRT, VT))) + return SDValue(); + + return DAG.getNode(ISD::FCBRT, SDLoc(N), VT, N->getOperand(0), Flags); + } + // Try to convert x ** (1/4) into square roots. // x ** (1/2) is canonicalized to sqrt, so we do not bother with that case. // TODO: This could be extended (using a target hook) to handle smaller @@ -11587,7 +11615,6 @@ SDValue DAGCombiner::visitFPOW(SDNode *N) { return SDValue(); // Don't double the number of libcalls. We are trying to inline fast code. - EVT VT = N->getValueType(0); if (!DAG.getTargetLoweringInfo().isOperationLegalOrCustom(ISD::FSQRT, VT)) return SDValue(); diff --git a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp index 13d412cd7de..b6bd8541ac7 100644 --- a/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp @@ -4047,6 +4047,11 @@ void SelectionDAGLegalize::ConvertNodeToLibcall(SDNode *Node) { RTLIB::SQRT_F80, RTLIB::SQRT_F128, RTLIB::SQRT_PPCF128)); break; + case ISD::FCBRT: + Results.push_back(ExpandFPLibCall(Node, RTLIB::CBRT_F32, RTLIB::CBRT_F64, + RTLIB::CBRT_F80, RTLIB::CBRT_F128, + RTLIB::CBRT_PPCF128)); + break; case ISD::FSIN: case ISD::STRICT_FSIN: Results.push_back(ExpandFPLibCall(Node, RTLIB::SIN_F32, RTLIB::SIN_F64, diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp index 7289579502d..594a587e412 100644 --- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGDumper.cpp @@ -181,6 +181,7 @@ std::string SDNode::getOperationName(const SelectionDAG *G) const { case ISD::FNEG: return "fneg"; case ISD::FSQRT: return "fsqrt"; case ISD::STRICT_FSQRT: return "strict_fsqrt"; + case ISD::FCBRT: return "fcbrt"; case ISD::FSIN: return "fsin"; case ISD::STRICT_FSIN: return "strict_fsin"; case ISD::FCOS: return "fcos"; diff --git a/llvm/lib/CodeGen/TargetLoweringBase.cpp b/llvm/lib/CodeGen/TargetLoweringBase.cpp index aeb321f4a42..b9cdbeabdb3 100644 --- a/llvm/lib/CodeGen/TargetLoweringBase.cpp +++ b/llvm/lib/CodeGen/TargetLoweringBase.cpp @@ -666,6 +666,7 @@ void TargetLoweringBase::initActions() { // These library functions default to expand. for (MVT VT : {MVT::f32, MVT::f64, MVT::f128}) { + setOperationAction(ISD::FCBRT, VT, Expand); setOperationAction(ISD::FLOG , VT, Expand); setOperationAction(ISD::FLOG2, VT, Expand); setOperationAction(ISD::FLOG10, VT, Expand); |
