diff options
| author | Cameron Zwarich <zwarich@apple.com> | 2011-07-08 21:39:21 +0000 |
|---|---|---|
| committer | Cameron Zwarich <zwarich@apple.com> | 2011-07-08 21:39:21 +0000 |
| commit | 33390848a7eca75301d04a59b89b516d83e19ee0 (patch) | |
| tree | 78f81419440b86ae4fa8a150780b7f211668b781 /lib/CodeGen/SelectionDAG/LegalizeDAG.cpp | |
| parent | cc0ddc707d5a7b1dd11141881df0bf4210f8aeee (diff) | |
Add an intrinsic and codegen support for fused multiply-accumulate. The intent
is to use this for architectures that have a native FMA instruction.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@134742 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'lib/CodeGen/SelectionDAG/LegalizeDAG.cpp')
| -rw-r--r-- | lib/CodeGen/SelectionDAG/LegalizeDAG.cpp | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp b/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp index 4b6d3ef547..308150fe54 100644 --- a/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp +++ b/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp @@ -3351,6 +3351,10 @@ void SelectionDAGLegalize::ExpandNode(SDNode *Node, Results.push_back(ExpandFPLibCall(Node, RTLIB::REM_F32, RTLIB::REM_F64, RTLIB::REM_F80, RTLIB::REM_PPCF128)); break; + case ISD::FMA: + Results.push_back(ExpandFPLibCall(Node, RTLIB::FMA_F32, RTLIB::FMA_F64, + RTLIB::FMA_F80, RTLIB::FMA_PPCF128)); + break; case ISD::FP16_TO_FP32: Results.push_back(ExpandLibCall(RTLIB::FPEXT_F16_F32, Node, false)); break; |