setOperationAction(ISD::FTRUNC, VT, Expand);
setOperationAction(ISD::FMUL, VT, Expand);
setOperationAction(ISD::FRINT, VT, Expand);
+ setOperationAction(ISD::FNEARBYINT, VT, Expand);
setOperationAction(ISD::FSQRT, VT, Expand);
setOperationAction(ISD::FSIN, VT, Expand);
setOperationAction(ISD::FSUB, VT, Expand);
setOperationAction(ISD::FCOPYSIGN, VT, Expand);
}
+ setOperationAction(ISD::FNEARBYINT, MVT::f32, Custom);
+ setOperationAction(ISD::FNEARBYINT, MVT::f64, Custom);
+
setTargetDAGCombine(ISD::MUL);
setTargetDAGCombine(ISD::SELECT_CC);
case ISD::FCEIL: return LowerFCEIL(Op, DAG);
case ISD::FTRUNC: return LowerFTRUNC(Op, DAG);
case ISD::FRINT: return LowerFRINT(Op, DAG);
+ case ISD::FNEARBYINT: return LowerFNEARBYINT(Op, DAG);
case ISD::FFLOOR: return LowerFFLOOR(Op, DAG);
case ISD::UINT_TO_FP: return LowerUINT_TO_FP(Op, DAG);
return DAG.getSelect(SL, MVT::f64, Cond, Src, Tmp2);
}
+SDValue AMDGPUTargetLowering::LowerFNEARBYINT(SDValue Op, SelectionDAG &DAG) const {
+ // FNEARBYINT and FRINT are the same, except in their handling of FP
+ // exceptions. Those aren't really meaningful for us, and OpenCL only has
+ // rint, so just treat them as equivalent.
+ return DAG.getNode(ISD::FRINT, SDLoc(Op), Op.getValueType(), Op.getOperand(0));
+}
+
SDValue AMDGPUTargetLowering::LowerFFLOOR(SDValue Op, SelectionDAG &DAG) const {
SDLoc SL(Op);
SDValue Src = Op.getOperand(0);
SDValue LowerFCEIL(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFTRUNC(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFRINT(SDValue Op, SelectionDAG &DAG) const;
+ SDValue LowerFNEARBYINT(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerFFLOOR(SDValue Op, SelectionDAG &DAG) const;
SDValue LowerUINT_TO_FP(SDValue Op, SelectionDAG &DAG) const;
--- /dev/null
+; RUN: llc -march=r600 -mcpu=SI -verify-machineinstrs < %s
+; RUN: llc -march=r600 -mcpu=bonaire -verify-machineinstrs < %s
+
+; This should have the exactly the same output as the test for rint,
+; so no need to check anything.
+
+declare float @llvm.nearbyint.f32(float) #0
+declare <2 x float> @llvm.nearbyint.v2f32(<2 x float>) #0
+declare <4 x float> @llvm.nearbyint.v4f32(<4 x float>) #0
+declare double @llvm.nearbyint.f64(double) #0
+declare <2 x double> @llvm.nearbyint.v2f64(<2 x double>) #0
+declare <4 x double> @llvm.nearbyint.v4f64(<4 x double>) #0
+
+
+define void @fnearbyint_f32(float addrspace(1)* %out, float %in) #1 {
+entry:
+ %0 = call float @llvm.nearbyint.f32(float %in)
+ store float %0, float addrspace(1)* %out
+ ret void
+}
+
+define void @fnearbyint_v2f32(<2 x float> addrspace(1)* %out, <2 x float> %in) #1 {
+entry:
+ %0 = call <2 x float> @llvm.nearbyint.v2f32(<2 x float> %in)
+ store <2 x float> %0, <2 x float> addrspace(1)* %out
+ ret void
+}
+
+define void @fnearbyint_v4f32(<4 x float> addrspace(1)* %out, <4 x float> %in) #1 {
+entry:
+ %0 = call <4 x float> @llvm.nearbyint.v4f32(<4 x float> %in)
+ store <4 x float> %0, <4 x float> addrspace(1)* %out
+ ret void
+}
+
+define void @nearbyint_f64(double addrspace(1)* %out, double %in) {
+entry:
+ %0 = call double @llvm.nearbyint.f64(double %in)
+ store double %0, double addrspace(1)* %out
+ ret void
+}
+define void @nearbyint_v2f64(<2 x double> addrspace(1)* %out, <2 x double> %in) {
+entry:
+ %0 = call <2 x double> @llvm.nearbyint.v2f64(<2 x double> %in)
+ store <2 x double> %0, <2 x double> addrspace(1)* %out
+ ret void
+}
+
+define void @nearbyint_v4f64(<4 x double> addrspace(1)* %out, <4 x double> %in) {
+entry:
+ %0 = call <4 x double> @llvm.nearbyint.v4f64(<4 x double> %in)
+ store <4 x double> %0, <4 x double> addrspace(1)* %out
+ ret void
+}
+
+attributes #0 = { nounwind readonly }
+attributes #1 = { nounwind }