[llvm-commits] [llvm] r166049 - in /llvm/trunk: lib/CodeGen/SelectionDAG/DAGCombiner.cpp test/CodeGen/X86/trunc-fp2int.ll

[Michael Liao]

Sure, I am looking into it now. - Michael

On Wed, 2012-10-17 at 13:57 -0700, Daniel Dunbar wrote:
> Hi Michael,
> 
> Are you sure about this transformation? It breaks
> SingleSource/UnitTests/FloatPrecision.c on ARMv7/O0/-g.
> 
> Can you take a look? The expected output of the test is:
> --
> 2147483648000.000000
> 0
> --
> but with your patch the executable built with Clang at -O0 generates:
> --
> 2147483648000.000000
> ffffffff
> --
> 
> Thanks,
>  - Daniel
> 
> On Tue, Oct 16, 2012 at 12:38 PM, Michael Liao <michael.liao at intel.com> wrote:
> > Author: hliao
> > Date: Tue Oct 16 14:38:35 2012
> > New Revision: 166049
> >
> > URL: http://llvm.org/viewvc/llvm-project?rev=166049&view=rev
> > Log:
> > Teach DAG combine to fold (trunc (fptoXi x)) to (fptoXi x)
> >
> >
> > Added:
> >     llvm/trunk/test/CodeGen/X86/trunc-fp2int.ll
> > Modified:
> >     llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
> >
> > Modified: llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
> > URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp?rev=166049&r1=166048&r2=166049&view=diff
> > ==============================================================================
> > --- llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp (original)
> > +++ llvm/trunk/lib/CodeGen/SelectionDAG/DAGCombiner.cpp Tue Oct 16 14:38:35 2012
> > @@ -5308,6 +5308,52 @@
> >      if (Reduced.getNode())
> >        return Reduced;
> >    }
> > +  // fold (trunc (fptoXi x)) -> (smaller fptoXi x)
> > +  if ((N0.getOpcode() == ISD::FP_TO_UINT ||
> > +       N0.getOpcode() == ISD::FP_TO_SINT) && !LegalTypes)
> > +    return DAG.getNode(N0.getOpcode(), N->getDebugLoc(), VT, N0.getOperand(0));
> > +  // fold (trunc (concat ... x ...)) -> (concat ..., (trunc x), ...)),
> > +  // where ... are all 'undef'.
> > +  if (N0.getOpcode() == ISD::CONCAT_VECTORS && !LegalTypes) {
> > +    SmallVector<EVT, 8> VTs;
> > +    SDValue V;
> > +    unsigned Idx = 0;
> > +    unsigned NumDefs = 0;
> > +
> > +    for (unsigned i = 0, e = N0.getNumOperands(); i != e; ++i) {
> > +      SDValue X = N0.getOperand(i);
> > +      if (X.getOpcode() != ISD::UNDEF) {
> > +        V = X;
> > +        Idx = i;
> > +        NumDefs++;
> > +      }
> > +      // Stop if more than one members are non-undef.
> > +      if (NumDefs > 1)
> > +        break;
> > +      VTs.push_back(EVT::getVectorVT(*DAG.getContext(),
> > +                                     VT.getVectorElementType(),
> > +                                     X.getValueType().getVectorNumElements()));
> > +    }
> > +
> > +    if (NumDefs == 0)
> > +      return DAG.getUNDEF(VT);
> > +
> > +    if (NumDefs == 1) {
> > +      assert(V.getNode() && "The single defined operand is empty!");
> > +      SmallVector<SDValue, 8> Opnds;
> > +      for (unsigned i = 0, e = VTs.size(); i != e; ++i) {
> > +        if (i != Idx) {
> > +          Opnds.push_back(DAG.getUNDEF(VTs[i]));
> > +          continue;
> > +        }
> > +        SDValue NV = DAG.getNode(ISD::TRUNCATE, V.getDebugLoc(), VTs[i], V);
> > +        AddToWorkList(NV.getNode());
> > +        Opnds.push_back(NV);
> > +      }
> > +      return DAG.getNode(ISD::CONCAT_VECTORS, N->getDebugLoc(), VT,
> > +                         &Opnds[0], Opnds.size());
> > +    }
> > +  }
> >
> >    // Simplify the operands using demanded-bits information.
> >    if (!VT.isVector() &&
> >
> > Added: llvm/trunk/test/CodeGen/X86/trunc-fp2int.ll
> > URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/trunc-fp2int.ll?rev=166049&view=auto
> > ==============================================================================
> > --- llvm/trunk/test/CodeGen/X86/trunc-fp2int.ll (added)
> > +++ llvm/trunk/test/CodeGen/X86/trunc-fp2int.ll Tue Oct 16 14:38:35 2012
> > @@ -0,0 +1,18 @@
> > +; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=corei7 | FileCheck %s
> > +
> > +define <4 x i8> @bar(<4 x float> %in) nounwind readnone alwaysinline {
> > +  %1 = fptoui <4 x float> %in to <4 x i8>
> > +  ret <4 x i8> %1
> > +; CHECK: bar
> > +; CHECK: cvttps2dq
> > +}
> > +define <4 x i8> @foo(<4 x float> %in) nounwind readnone alwaysinline {
> > +  %1 = fptoui <4 x float> %in to <4 x i32>
> > +  %2 = trunc <4 x i32> %1 to <4 x i16>
> > +  %3 = shufflevector <4 x i16> %2, <4 x i16> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
> > +  %4 = trunc <8 x i16> %3 to <8 x i8>
> > +  %5 = shufflevector <8 x i8> %4, <8 x i8> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
> > +  ret <4 x i8> %5
> > +; CHECK: foo
> > +; CHECK: cvttps2dq
> > +}
> >
> >
> > _______________________________________________
> > llvm-commits mailing list
> > llvm-commits at cs.uiuc.edu
> > http://lists.cs.uiuc.edu/mailman/listinfo/llvm-commits