Index: llvm/include/llvm/CodeGen/SelectionDAG.h =================================================================== --- llvm/include/llvm/CodeGen/SelectionDAG.h +++ llvm/include/llvm/CodeGen/SelectionDAG.h @@ -935,7 +935,7 @@ SDValue getNode(unsigned Opcode, const SDLoc &DL, ArrayRef ResultTys, ArrayRef Ops); SDValue getNode(unsigned Opcode, const SDLoc &DL, SDVTList VTList, - ArrayRef Ops); + ArrayRef Ops, const SDNodeFlags Flags = SDNodeFlags()); // Specialize based on number of operands. SDValue getNode(unsigned Opcode, const SDLoc &DL, EVT VT); Index: llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp =================================================================== --- llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp +++ llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp @@ -7435,7 +7435,7 @@ } SDValue SelectionDAG::getNode(unsigned Opcode, const SDLoc &DL, SDVTList VTList, - ArrayRef Ops) { + ArrayRef Ops, const SDNodeFlags Flags) { if (VTList.NumVTs == 1) return getNode(Opcode, DL, VTList.VTs[0], Ops); @@ -7504,6 +7504,7 @@ return SDValue(E, 0); N = newSDNode(Opcode, DL.getIROrder(), DL.getDebugLoc(), VTList); + N->setFlags(Flags); createOperands(N, Ops); CSEMap.InsertNode(N, IP); } else { Index: llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp =================================================================== --- llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp +++ llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp @@ -1113,29 +1113,23 @@ visit(I.getOpcode(), I); if (auto *FPMO = dyn_cast(&I)) { - // Propagate the fast-math-flags of this IR instruction to the DAG node that - // maps to this instruction. - // TODO: We could handle all flags (nsw, etc) here. - // TODO: If an IR instruction maps to >1 node, only the final node will have - // flags set. - if (SDNode *Node = getNodeForIRValue(&I)) { - SDNodeFlags IncomingFlags; - IncomingFlags.copyFMF(*FPMO); - if (!Node->getFlags().isDefined()) - Node->setFlags(IncomingFlags); - else - Node->intersectFlagsWith(IncomingFlags); - } - } - // Constrained FP intrinsics with fpexcept.ignore should also get - // the NoFPExcept flag. - if (auto *FPI = dyn_cast(&I)) - if (FPI->getExceptionBehavior() == fp::ExceptionBehavior::ebIgnore) + // ContrainedFPIntrinsics handle their own FMF. + if (!isa(&I)) { + // Propagate the fast-math-flags of this IR instruction to the DAG node that + // maps to this instruction. + // TODO: We could handle all flags (nsw, etc) here. + // TODO: If an IR instruction maps to >1 node, only the final node will have + // flags set. if (SDNode *Node = getNodeForIRValue(&I)) { - SDNodeFlags Flags = Node->getFlags(); - Flags.setNoFPExcept(true); - Node->setFlags(Flags); + SDNodeFlags IncomingFlags; + IncomingFlags.copyFMF(*FPMO); + if (!Node->getFlags().isDefined()) + Node->setFlags(IncomingFlags); + else + Node->intersectFlagsWith(IncomingFlags); } + } + } if (!I.isTerminator() && !HasTailCall && !isStatepoint(&I)) // statepoints handle their exports internally @@ -7080,6 +7074,13 @@ SDVTList VTs = DAG.getVTList(ValueVTs); fp::ExceptionBehavior EB = FPI.getExceptionBehavior().getValue(); + SDNodeFlags Flags; + if (EB == fp::ExceptionBehavior::ebIgnore) + Flags.setNoFPExcept(true); + + if (auto *FPOp = dyn_cast(&FPI)) + Flags.copyFMF(*FPOp); + unsigned Opcode; switch (FPI.getIntrinsicID()) { default: llvm_unreachable("Impossible intrinsic"); // Can't reach here. @@ -7095,7 +7096,7 @@ !TLI.isFMAFasterThanFMulAndFAdd(DAG.getMachineFunction(), ValueVTs[0])) { Opers.pop_back(); - SDValue Mul = DAG.getNode(ISD::STRICT_FMUL, sdl, VTs, Opers); + SDValue Mul = DAG.getNode(ISD::STRICT_FMUL, sdl, VTs, Opers, Flags); pushOutChain(Mul, EB); Opcode = ISD::STRICT_FADD; Opers.clear(); @@ -7123,7 +7124,7 @@ } } - SDValue Result = DAG.getNode(Opcode, sdl, VTs, Opers); + SDValue Result = DAG.getNode(Opcode, sdl, VTs, Opers, Flags); pushOutChain(Result, EB); SDValue FPResult = Result.getValue(0); Index: llvm/test/CodeGen/X86/fp-intrinsics-flags.ll =================================================================== --- llvm/test/CodeGen/X86/fp-intrinsics-flags.ll +++ llvm/test/CodeGen/X86/fp-intrinsics-flags.ll @@ -108,7 +108,7 @@ ; CHECK: [[MOV32rm:%[0-9]+]]:gr32 = MOV32rm %fixed-stack.0, 1, $noreg, 0, $noreg :: (load 4 from %fixed-stack.0) ; CHECK: [[MOV32rm1:%[0-9]+]]:gr32 = MOV32rm %fixed-stack.1, 1, $noreg, 0, $noreg :: (load 4 from %fixed-stack.1, align 16) ; CHECK: [[MOVSDrm_alt:%[0-9]+]]:fr64 = MOVSDrm_alt %fixed-stack.3, 1, $noreg, 0, $noreg :: (load 8 from %fixed-stack.3, align 16) -; CHECK: %3:fr64 = nofpexcept DIVSDrm [[MOVSDrm_alt]], %fixed-stack.2, 1, $noreg, 0, $noreg, implicit $mxcsr :: (load 8 from %fixed-stack.2) +; CHECK: %3:fr64 = DIVSDrm [[MOVSDrm_alt]], %fixed-stack.2, 1, $noreg, 0, $noreg, implicit $mxcsr :: (load 8 from %fixed-stack.2) ; CHECK: MOVSDmr killed [[MOV32rm1]], 1, $noreg, 0, $noreg, %3 :: (store 8 into %ir.x, align 4) ; CHECK: MOVSDmr killed [[MOV32rm]], 1, $noreg, 0, $noreg, %3 :: (store 8 into %ir.y, align 4) ; CHECK: RET 0 @@ -126,7 +126,7 @@ ; CHECK-LABEL: name: sitofp_cse ; CHECK: [[MOV32rm:%[0-9]+]]:gr32 = MOV32rm %fixed-stack.0, 1, $noreg, 0, $noreg :: (load 4 from %fixed-stack.0, align 8) ; CHECK: [[MOV32rm1:%[0-9]+]]:gr32 = MOV32rm %fixed-stack.1, 1, $noreg, 0, $noreg :: (load 4 from %fixed-stack.1) -; CHECK: %2:fr64 = nofpexcept CVTSI2SDrm %fixed-stack.2, 1, $noreg, 0, $noreg :: (load 4 from %fixed-stack.2, align 16) +; CHECK: %2:fr64 = CVTSI2SDrm %fixed-stack.2, 1, $noreg, 0, $noreg :: (load 4 from %fixed-stack.2, align 16) ; CHECK: MOVSDmr killed [[MOV32rm1]], 1, $noreg, 0, $noreg, %2 :: (store 8 into %ir.x, align 4) ; CHECK: MOVSDmr killed [[MOV32rm]], 1, $noreg, 0, $noreg, %2 :: (store 8 into %ir.y, align 4) ; CHECK: RET 0