setOperationAction(ISD::FROUND, MVT::f32, Legal);
setOperationAction(ISD::FTRUNC, MVT::f32, Legal);
+ setOperationAction(ISD::FREM, MVT::f32, Custom);
+ setOperationAction(ISD::FREM, MVT::f64, Custom);
+
// Lower floating point store/load to integer store/load to reduce the number
// of patterns in tablegen.
setOperationAction(ISD::STORE, MVT::f32, Promote);
setOperationAction(ISD::FDIV, VT, Expand);
setOperationAction(ISD::FEXP2, VT, Expand);
setOperationAction(ISD::FLOG2, VT, Expand);
+ setOperationAction(ISD::FREM, VT, Expand);
setOperationAction(ISD::FPOW, VT, Expand);
setOperationAction(ISD::FFLOOR, VT, Expand);
setOperationAction(ISD::FTRUNC, VT, Expand);
// There are no integer divide instructions, and these expand to a pretty
// large sequence of instructions.
setIntDivIsCheap(false);
- setPow2DivIsCheap(false);
+ setPow2SDivIsCheap(false);
// TODO: Investigate this when 64-bit divides are implemented.
addBypassSlowDiv(64, 32);
bool AMDGPUTargetLowering::isFAbsFree(EVT VT) const {
assert(VT.isFloatingPoint());
- return VT == MVT::f32;
+ return VT == MVT::f32 || VT == MVT::f64;
}
bool AMDGPUTargetLowering::isFNegFree(EVT VT) const {
assert(VT.isFloatingPoint());
- return VT == MVT::f32;
+ return VT == MVT::f32 || VT == MVT::f64;
}
bool AMDGPUTargetLowering::isTruncateFree(EVT Source, EVT Dest) const {
case ISD::INTRINSIC_WO_CHAIN: return LowerINTRINSIC_WO_CHAIN(Op, DAG);
case ISD::UDIVREM: return LowerUDIVREM(Op, DAG);
case ISD::SDIVREM: return LowerSDIVREM(Op, DAG);
+ case ISD::FREM: return LowerFREM(Op, DAG);
case ISD::FCEIL: return LowerFCEIL(Op, DAG);
case ISD::FTRUNC: return LowerFTRUNC(Op, DAG);
case ISD::FRINT: return LowerFRINT(Op, DAG);
case Intrinsic::AMDGPU_rsq_clamped:
return DAG.getNode(AMDGPUISD::RSQ_CLAMPED, DL, VT, Op.getOperand(1));
+ case Intrinsic::AMDGPU_ldexp:
+ return DAG.getNode(AMDGPUISD::LDEXP, DL, VT, Op.getOperand(1),
+ Op.getOperand(2));
+
case AMDGPUIntrinsic::AMDGPU_imax:
return DAG.getNode(AMDGPUISD::SMAX, DL, VT, Op.getOperand(1),
Op.getOperand(2));
return DAG.getMergeValues(Res, DL);
}
+// (frem x, y) -> (fsub x, (fmul (ftrunc (fdiv x, y)), y))
+SDValue AMDGPUTargetLowering::LowerFREM(SDValue Op, SelectionDAG &DAG) const {
+ SDLoc SL(Op);
+ EVT VT = Op.getValueType();
+ SDValue X = Op.getOperand(0);
+ SDValue Y = Op.getOperand(1);
+
+ SDValue Div = DAG.getNode(ISD::FDIV, SL, VT, X, Y);
+ SDValue Floor = DAG.getNode(ISD::FTRUNC, SL, VT, Div);
+ SDValue Mul = DAG.getNode(ISD::FMUL, SL, VT, Floor, Y);
+
+ return DAG.getNode(ISD::FSUB, SL, VT, X, Mul);
+}
+
SDValue AMDGPUTargetLowering::LowerFCEIL(SDValue Op, SelectionDAG &DAG) const {
SDLoc SL(Op);
SDValue Src = Op.getOperand(0);
NODE_NAME_CASE(DWORDADDR)
NODE_NAME_CASE(FRACT)
NODE_NAME_CASE(CLAMP)
+ NODE_NAME_CASE(MAD)
NODE_NAME_CASE(FMAX)
NODE_NAME_CASE(SMAX)
NODE_NAME_CASE(UMAX)
NODE_NAME_CASE(RSQ)
NODE_NAME_CASE(RSQ_LEGACY)
NODE_NAME_CASE(RSQ_CLAMPED)
+ NODE_NAME_CASE(LDEXP)
NODE_NAME_CASE(DOT4)
NODE_NAME_CASE(BFE_U32)
NODE_NAME_CASE(BFE_I32)