diff options
| author | Matt Arsenault <Matthew.Arsenault@amd.com> | 2019-10-28 11:00:12 -0700 |
|---|---|---|
| committer | Matt Arsenault <arsenm2@gmail.com> | 2019-10-31 07:51:38 -0700 |
| commit | 1725f2884175ca618d29b06e35f5c6ebd618053d (patch) | |
| tree | cdb06decf1ce6352e3da55ff9233279e448ac3fd /llvm/lib/Target/AMDGPU/SIISelLowering.h | |
| parent | bc56166281ae025fcbe701bdb3a02b488bcedc09 (diff) | |
| download | bcm5719-llvm-1725f2884175ca618d29b06e35f5c6ebd618053d.tar.gz bcm5719-llvm-1725f2884175ca618d29b06e35f5c6ebd618053d.zip | |
DAG: Add new control for ISD::FMAD formation
For AMDGPU this depends on whether denormals are enabled in the
default FP mode for the function. Currently this is treated as a
subtarget feature, so FMAD is selectively legal based on that. I want
to move this out of the subtarget features so this can be controlled
with a denormal mode attribute. Additionally, this will allow folding
based on a future ftz fast math flag.
Diffstat (limited to 'llvm/lib/Target/AMDGPU/SIISelLowering.h')
| -rw-r--r-- | llvm/lib/Target/AMDGPU/SIISelLowering.h | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.h b/llvm/lib/Target/AMDGPU/SIISelLowering.h index b36574f8ff6..c3605a3f158 100644 --- a/llvm/lib/Target/AMDGPU/SIISelLowering.h +++ b/llvm/lib/Target/AMDGPU/SIISelLowering.h @@ -349,6 +349,9 @@ public: EVT VT) const override; MVT getScalarShiftAmountTy(const DataLayout &, EVT) const override; bool isFMAFasterThanFMulAndFAdd(EVT VT) const override; + bool isFMADLegalForFAddFSub(const SelectionDAG &DAG, + const SDNode *N) const override; + SDValue splitUnaryVectorOp(SDValue Op, SelectionDAG &DAG) const; SDValue splitBinaryVectorOp(SDValue Op, SelectionDAG &DAG) const; SDValue splitTernaryVectorOp(SDValue Op, SelectionDAG &DAG) const; |
