search for: allowfpopfus

...(LegalOperations && TLI.isOperationLegal(ISD::FMAD, VT)); static bool isContractable(SDNode *N) { SDNodeFlags F = N->getFlags(); return F.hasAllowContract() || F.hasAllowReassociation(); } bool CanFuse = Options.UnsafeFPMath || isContractable(N); bool AllowFusionGlobally = (Options.AllowFPOpFusion == FPOpFusion::Fast || CanFuse || HasFMAD); // If the addition is not contractable, do not combine. if (!AllowFusionGlobally && !isContractable(N)) return SDValue(); Specifically the AllowFusionGlobally, I would have expected something more like: bool AllowFusionGlobally = (Options...

...> > static bool isContractable(SDNode *N) { >   SDNodeFlags F = N->getFlags(); >   return F.hasAllowContract() || F.hasAllowReassociation(); > } > > bool CanFuse = Options.UnsafeFPMath || isContractable(N); > bool AllowFusionGlobally = (Options.AllowFPOpFusion == > FPOpFusion::Fast || CanFuse || HasFMAD); > // If the addition is not contractable, do not combine. > if (!AllowFusionGlobally && !isContractable(N)) >     return SDValue(); > > Specifically the AllowFusionGlobally, I would have expected >...

...e %add } $ llc -mattr=+fma fma.ll -fp-contract=off -o - | grep vfmadd vfmadd213sd %xmm2, %xmm1, %xmm0 # xmm0 = (xmm1 * xmm0) + xmm2 It still generates an fma due to the logic in DAGCombiner: bool CanFuse = Options.UnsafeFPMath || isContractable(N); bool AllowFusionGlobally = (Options.AllowFPOpFusion == FPOpFusion::Fast || CanFuse || HasFMAD); In this case, UnsafeFPMath is false but isContractable() is true since the FADD node is tagged as 'fast'. A simple fix would just be to check for -fp-contract=off, however, I also found there is disagreement in...

...>        SDNodeFlags F = N->getFlags(); > >        return F.hasAllowContract() || F.hasAllowReassociation(); > >     } > > > >     bool CanFuse = Options.UnsafeFPMath || isContractable(N); > >     bool AllowFusionGlobally = (Options.AllowFPOpFusion == > >     FPOpFusion::Fast || CanFuse || HasFMAD); > >     // If the addition is not contractable, do not combine. > >     if (!AllowFusionGlobally && !isContractable(N)) > >          return SDValue(); > > > >     Specifi...

...few conditions that contribute to the decision of whether > or not to make the fmuladd -> fma translation. The relevant code is in > CodeGen/SelectionDAG/SelectionDAGBuilder.cpp: > > case Intrinsic::fmuladd: { > EVT VT = TLI.getValueType(I.getType()); > if (TM.Options.AllowFPOpFusion != FPOpFusion::Strict && > TLI.isOperationLegal(ISD::FMA, VT) && > TLI.isFMAFasterThanMulAndAdd(VT)){ > > [ use FMA ] > } else { > [ use MUL + ADD ] > } We've written a few TableGen patterns here locally to match FMA...

...>      >        return F.hasAllowContract() || > F.hasAllowReassociation(); > >      >     } > >      > > >      >     bool CanFuse = Options.UnsafeFPMath || isContractable(N); > >      >     bool AllowFusionGlobally = (Options.AllowFPOpFusion == > >      >     FPOpFusion::Fast || CanFuse || HasFMAD); > >      >     // If the addition is not contractable, do not combine. > >      >     if (!AllowFusionGlobally && !isContractable(N)) > >      >          return SDValue(); &...

...; } > > There are a few conditions that contribute to the decision of whether or not to make the fmuladd -> fma translation. The relevant code is in CodeGen/SelectionDAG/SelectionDAGBuilder.cpp: case Intrinsic::fmuladd: { EVT VT = TLI.getValueType(I.getType()); if (TM.Options.AllowFPOpFusion != FPOpFusion::Strict && TLI.isOperationLegal(ISD::FMA, VT) && TLI.isFMAFasterThanMulAndAdd(VT)){ [ use FMA ] } else { [ use MUL + ADD ] } -Hal > > > Hope that helps, > Cameron > > > ______________________________...

...getFlags(); >>> > return F.hasAllowContract() || F.hasAllowReassociation(); >>> > } >>> > >>> > bool CanFuse = Options.UnsafeFPMath || isContractable(N); >>> > bool AllowFusionGlobally = (Options.AllowFPOpFusion == >>> > FPOpFusion::Fast || CanFuse || HasFMAD); >>> > // If the addition is not contractable, do not combine. >>> > if (!AllowFusionGlobally && !isContractable(N)) >>> > return SDValue(); >>&...

Nicolai, Can you do without the use of -fp-contract=fast (Options.AllowFPOpFusion == FPOpFusion::Fast ) and without Unsafe? As I SPIR-V’s usage of NoContraction flies in the face of both. If so, you should be able to get what you want, as then you are down to just IR flags. You will need a model to generate the correct behavior though in your SPIR-V implementation wrt IR fl...

...td::string mcjit_error; engineBuilder.setMCPU(llvm::sys::getHostCPUName()); engineBuilder.setEngineKind(llvm::EngineKind::JIT); engineBuilder.setOptLevel(llvm::CodeGenOpt::Aggressive); engineBuilder.setErrorStr(&mcjit_error); llvm::TargetOptions targetOptions; targetOptions.AllowFPOpFusion = llvm::FPOpFusion::Fast; engineBuilder.setTargetOptions( targetOptions ); TargetMachine *targetMachine = engineBuilder.selectTarget(); assert(targetMachine && "failed to create target machine"); std::cout << targetMachine->createDataLayout().getStringR...

On Fri, Jan 11, 2013 at 1:08 PM, Andrew Booker <andrew.booker at arm.com>wrote: > The fmuladd intrinsic is described as saying that a multiply and > addition sequence can be fused into an fma instruction "if the code > generator determines that the fused expression would be legal and > efficient". (http://llvm.org/docs/LangRef.html#llvm-fma-intrinsic) > >

...>> > return F.hasAllowContract() || F.hasAllowReassociation(); >>>> > } >>>> > >>>> > bool CanFuse = Options.UnsafeFPMath || isContractable(N); >>>> > bool AllowFusionGlobally = (Options.AllowFPOpFusion == >>>> > FPOpFusion::Fast || CanFuse || HasFMAD); >>>> > // If the addition is not contractable, do not combine. >>>> > if (!AllowFusionGlobally && !isContractable(N)) >>>> > return SDVa...

...t; return F.hasAllowContract() || F.hasAllowReassociation(); >>>>> > } >>>>> > >>>>> > bool CanFuse = Options.UnsafeFPMath || isContractable(N); >>>>> > bool AllowFusionGlobally = (Options.AllowFPOpFusion == >>>>> > FPOpFusion::Fast || CanFuse || HasFMAD); >>>>> > // If the addition is not contractable, do not combine. >>>>> > if (!AllowFusionGlobally && !isContractable(N)) >>>>> >...

On Fri, Sep 18, 2015 at 10:34 PM, Tim Northover <t.p.northover at gmail.com> wrote: > AArch64's fmadd instruction is fused, which means it can produce a > different result to the two operations executed separately. The C and > C++ standards do not allow such changes. Sorry, sloppy language on my part. I was aware of fmadd, but I was really asking about turning sequences like:

...sys::getHostCPUName()); >> >> engineBuilder.setEngineKind(llvm::EngineKind::JIT); >> engineBuilder.setOptLevel(llvm::CodeGenOpt::Aggressive); >> engineBuilder.setErrorStr(&mcjit_error); >> >> llvm::TargetOptions targetOptions; >> targetOptions.AllowFPOpFusion = llvm::FPOpFusion::Fast; >> engineBuilder.setTargetOptions( targetOptions ); >> >> TargetMachine *targetMachine = engineBuilder.selectTarget(); >> >> assert(targetMachine && "failed to create target machine"); >> >> std::cout &...

...std::unique_ptr<llvm::Module>(Mod))); engineBuilder.setMCPU(llvm::sys::getHostCPUName()); engineBuilder.setEngineKind(llvm::EngineKind::JIT); engineBuilder.setOptLevel(llvm::CodeGenOpt::Aggressive); engineBuilder.setErrorStr(&mcjit_error); llvm::TargetOptions targetOptions; targetOptions.AllowFPOpFusion = llvm::FPOpFusion::Fast; engineBuilder.setTargetOptions( targetOptions ); TheExecutionEngine = engineBuilder.create(); targetMachine = engineBuilder.selectTarget(); Mod->setDataLayout( targetMachine->createDataLayout() ); TheExecutionEngine->finalizeObject(); // MCJIT fptr_mainFunc...

...eBuilder.setMCPU(llvm::sys::getHostCPUName()); > engineBuilder.setEngineKind(llvm::EngineKind::JIT); > engineBuilder.setOptLevel(llvm::CodeGenOpt::Aggressive); > engineBuilder.setErrorStr(&mcjit_error); > > llvm::TargetOptions targetOptions; > targetOptions.AllowFPOpFusion = llvm::FPOpFusion::Fast; > engineBuilder.setTargetOptions( targetOptions ); > > TheExecutionEngine = engineBuilder.create(); > > targetMachine = engineBuilder.selectTarget(); > Mod->setDataLayout( targetMachine->createDataLayout() ); > > TheExec...

> On Dec 6, 2017, at 02:28, Haidl, Michael <michael.haidl at uni-muenster.de> wrote: > > The IR goes through a backend agnostic preparation phase that brings it into SSA from and changes the AS from 0 to 1. This sounds possibly problematic to me. The IR should be created with the correct address space to begin with. Changing this in the middle sounds suspect. > After this

...FMF in > metadata) was discussed here: > https://llvm.org/bugs/show_bug.cgi?id=13118 > 3. The backend needs a thread of its own. We have at least these > mechanisms to handle FMA codegen: > a. TargetOptions for LessPreciseFPMADOption, UnsafeFPMath, > NoInfsFPMath, NoNaNsFPMath, AllowFPOpFusion (Fast, Standard, Strict) > b. SDNodeFlags for UnsafeAlgebra, NoNaNs, NoInfs, NoSignedZeros (but > nothing for FMA since IR FMF has nothing for FMA) > c. SelectionDAGTargetInfo::generateFMAsInMachineCombiner() > d. TargetLoweringBase::isFMAFasterThanFMulAndFAdd() > e. TargetLow...

...few conditions that contribute to the decision of whether or > not to make the fmuladd -> fma translation. The relevant code is in > CodeGen/SelectionDAG/SelectionDAGBuilder.cpp: > > case Intrinsic::fmuladd: { > EVT VT = TLI.getValueType(I.getType()); > if (TM.Options.AllowFPOpFusion != FPOpFusion::Strict && > TLI.isOperationLegal(ISD::FMA, VT) && > TLI.isFMAFasterThanMulAndAdd(VT)){ > > [ use FMA ] > } else { > [ use MUL + ADD ] > } > > -Hal > > > > > > > Hope that helps,...