AMDGPU: Generalize matching of v_med3_f32
I think this is safe as long as no inputs are known to ever
be nans.
Also add an intrinsic for fmed3 to be able to handle all safe
math cases.
llvm-svn: 293598
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp b/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
index 774810e..e02ced0 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUISelDAGToDAG.cpp
@@ -80,6 +80,7 @@
private:
SDValue foldFrameIndex(SDValue N) const;
+ bool isNoNanSrc(SDValue N) const;
bool isInlineImmediate(const SDNode *N) const;
bool FoldOperand(SDValue &Src, SDValue &Sel, SDValue &Neg, SDValue &Abs,
const R600InstrInfo *TII);
@@ -143,6 +144,8 @@
bool SelectSMRDBufferImm32(SDValue Addr, SDValue &Offset) const;
bool SelectSMRDBufferSgpr(SDValue Addr, SDValue &Offset) const;
bool SelectMOVRELOffset(SDValue Index, SDValue &Base, SDValue &Offset) const;
+
+ bool SelectVOP3Mods_NNaN(SDValue In, SDValue &Src, SDValue &SrcMods) const;
bool SelectVOP3Mods(SDValue In, SDValue &Src, SDValue &SrcMods) const;
bool SelectVOP3NoMods(SDValue In, SDValue &Src, SDValue &SrcMods) const;
bool SelectVOP3Mods0(SDValue In, SDValue &Src, SDValue &SrcMods,
@@ -188,6 +191,17 @@
return SelectionDAGISel::runOnMachineFunction(MF);
}
+bool AMDGPUDAGToDAGISel::isNoNanSrc(SDValue N) const {
+ if (TM.Options.NoNaNsFPMath)
+ return true;
+
+ // TODO: Move into isKnownNeverNaN
+ if (const auto *BO = dyn_cast<BinaryWithFlagsSDNode>(N))
+ return BO->Flags.hasNoNaNs();
+
+ return CurDAG->isKnownNeverNaN(N);
+}
+
bool AMDGPUDAGToDAGISel::isInlineImmediate(const SDNode *N) const {
const SIInstrInfo *TII
= static_cast<const SISubtarget *>(Subtarget)->getInstrInfo();
@@ -1569,6 +1583,12 @@
return true;
}
+bool AMDGPUDAGToDAGISel::SelectVOP3Mods_NNaN(SDValue In, SDValue &Src,
+ SDValue &SrcMods) const {
+ SelectVOP3Mods(In, Src, SrcMods);
+ return isNoNanSrc(Src);
+}
+
bool AMDGPUDAGToDAGISel::SelectVOP3NoMods(SDValue In, SDValue &Src,
SDValue &SrcMods) const {
bool Res = SelectVOP3Mods(In, Src, SrcMods);