diff options
| author | Hal Finkel <hfinkel@anl.gov> | 2012-06-22 00:49:52 +0000 |
|---|---|---|
| committer | Hal Finkel <hfinkel@anl.gov> | 2012-06-22 00:49:52 +0000 |
| commit | 070b8dba809dd75267327cc823118bf7e171d17d (patch) | |
| tree | 7a28804863a11bbc8c1c1e72555e3c4d511a460c /lib/Target/PowerPC/PPCISelLowering.h | |
| parent | cd88efe516510d3413c0e880217779e3eb56e956 (diff) | |
| download | external_llvm-070b8dba809dd75267327cc823118bf7e171d17d.zip external_llvm-070b8dba809dd75267327cc823118bf7e171d17d.tar.gz external_llvm-070b8dba809dd75267327cc823118bf7e171d17d.tar.bz2 | |
Convert the PPC backend to use the new FMA infrastructure.
The existing contraction patterns are replaced with fma/fneg.
Overall functionality should be the same.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@158955 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/Target/PowerPC/PPCISelLowering.h')
| -rw-r--r-- | lib/Target/PowerPC/PPCISelLowering.h | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/lib/Target/PowerPC/PPCISelLowering.h b/lib/Target/PowerPC/PPCISelLowering.h index 973800b..b0a013b 100644 --- a/lib/Target/PowerPC/PPCISelLowering.h +++ b/lib/Target/PowerPC/PPCISelLowering.h @@ -366,6 +366,12 @@ namespace llvm { bool IsZeroVal, bool MemcpyStrSrc, MachineFunction &MF) const; + /// isFMAFasterThanMulAndAdd - Return true if an FMA operation is faster than + /// a pair of mul and add instructions. fmuladd intrinsics will be expanded to + /// FMAs when this method returns true (and FMAs are legal), otherwise fmuladd + /// is expanded to mul + add. + virtual bool isFMAFasterThanMulAndAdd(EVT VT) const; + private: SDValue getFramePointerFrameIndex(SelectionDAG & DAG) const; SDValue getReturnAddrFrameIndex(SelectionDAG & DAG) const; |