diff options
Diffstat (limited to 'llvm/lib')
-rw-r--r-- | llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp | 41 | ||||
-rw-r--r-- | llvm/lib/Target/X86/X86ISelLowering.cpp | 6 | ||||
-rw-r--r-- | llvm/lib/Target/X86/X86ISelLowering.h | 3 |
3 files changed, 39 insertions, 11 deletions
diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp index ff00e6c2590..82d86204d80 100644 --- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp +++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp @@ -4200,20 +4200,39 @@ bool TargetLowering::expandFP_TO_UINT(SDNode *Node, SDValue &Result, return true; } - // Expand based on maximum range of FP_TO_SINT: - // True = fp_to_sint(Src) - // False = 0x8000000000000000 + fp_to_sint(Src - 0x8000000000000000) - // Result = select (Src < 0x8000000000000000), True, False SDValue Cst = DAG.getConstantFP(APF, dl, SrcVT); SDValue Sel = DAG.getSetCC(dl, SetCCVT, Src, Cst, ISD::SETLT); - SDValue True = DAG.getNode(ISD::FP_TO_SINT, dl, DstVT, Src); - // TODO: Should any fast-math-flags be set for the FSUB? - SDValue False = DAG.getNode(ISD::FP_TO_SINT, dl, DstVT, - DAG.getNode(ISD::FSUB, dl, SrcVT, Src, Cst)); - False = DAG.getNode(ISD::XOR, dl, DstVT, False, - DAG.getConstant(SignMask, dl, DstVT)); - Result = DAG.getSelect(dl, DstVT, Sel, True, False); + bool Strict = shouldUseStrictFP_TO_INT(SrcVT, DstVT, /*IsSigned*/ false); + if (Strict) { + // Expand based on maximum range of FP_TO_SINT, if the value exceeds the + // signmask then offset (the result of which should be fully representable). + // Sel = Src < 0x8000000000000000 + // Val = select Sel, Src, Src - 0x8000000000000000 + // Ofs = select Sel, 0, 0x8000000000000000 + // Result = fp_to_sint(Val) ^ Ofs + + // TODO: Should any fast-math-flags be set for the FSUB? + SDValue Val = DAG.getSelect(dl, SrcVT, Sel, Src, + DAG.getNode(ISD::FSUB, dl, SrcVT, Src, Cst)); + SDValue Ofs = DAG.getSelect(dl, DstVT, Sel, DAG.getConstant(0, dl, DstVT), + DAG.getConstant(SignMask, dl, DstVT)); + Result = DAG.getNode(ISD::XOR, dl, DstVT, + DAG.getNode(ISD::FP_TO_SINT, dl, DstVT, Val), Ofs); + } else { + // Expand based on maximum range of FP_TO_SINT: + // True = fp_to_sint(Src) + // False = 0x8000000000000000 + fp_to_sint(Src - 0x8000000000000000) + // Result = select (Src < 0x8000000000000000), True, False + + SDValue True = DAG.getNode(ISD::FP_TO_SINT, dl, DstVT, Src); + // TODO: Should any fast-math-flags be set for the FSUB? + SDValue False = DAG.getNode(ISD::FP_TO_SINT, dl, DstVT, + DAG.getNode(ISD::FSUB, dl, SrcVT, Src, Cst)); + False = DAG.getNode(ISD::XOR, dl, DstVT, False, + DAG.getConstant(SignMask, dl, DstVT)); + Result = DAG.getSelect(dl, DstVT, Sel, True, False); + } return true; } diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp index f8102002b72..809c5a149a0 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.cpp +++ b/llvm/lib/Target/X86/X86ISelLowering.cpp @@ -4812,6 +4812,12 @@ bool X86TargetLowering::decomposeMulByConstant(EVT VT, SDValue C) const { (1 - MulC).isPowerOf2() || (-(MulC + 1)).isPowerOf2(); } +bool X86TargetLowering::shouldUseStrictFP_TO_INT(EVT FpVT, EVT IntVT, + bool IsSigned) const { + // f80 UINT_TO_FP is more efficient using Strict code if FCMOV is available. + return !IsSigned && FpVT == MVT::f80 && Subtarget.hasCMov(); +} + bool X86TargetLowering::isExtractSubvectorCheap(EVT ResVT, EVT SrcVT, unsigned Index) const { if (!isOperationLegalOrCustom(ISD::EXTRACT_SUBVECTOR, ResVT)) diff --git a/llvm/lib/Target/X86/X86ISelLowering.h b/llvm/lib/Target/X86/X86ISelLowering.h index fe151d89dd2..a3441694452 100644 --- a/llvm/lib/Target/X86/X86ISelLowering.h +++ b/llvm/lib/Target/X86/X86ISelLowering.h @@ -1047,6 +1047,9 @@ namespace llvm { bool decomposeMulByConstant(EVT VT, SDValue C) const override; + bool shouldUseStrictFP_TO_INT(EVT FpVT, EVT IntVT, + bool IsSigned) const override; + /// Return true if EXTRACT_SUBVECTOR is cheap for this result type /// with this index. bool isExtractSubvectorCheap(EVT ResVT, EVT SrcVT, |