Refactor reciprocal and reciprocal square root estimate into target-independent functions (part 2).
This is purely refactoring. No functional changes intended. PowerPC is the only target
that is currently using this interface.
The ultimate goal is to allow targets other than PowerPC (certainly X86 and Aarch64) to turn this:
z = y / sqrt(x)
into:
z = y * rsqrte(x)
And:
z = y / x
into:
z = y * rcpe(x)
using whatever HW magic they can use. See http://llvm.org/bugs/show_bug.cgi?id=20900 .
There is one hook in TargetLowering to get the target-specific opcode for an estimate instruction
along with the number of refinement steps needed to make the estimate usable.
Differential Revision: http://reviews.llvm.org/D5484
llvm-svn: 218553
diff --git a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
index e216a72c..5750e2f 100644
--- a/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
+++ b/llvm/lib/Target/PowerPC/PPCISelLowering.cpp
@@ -7458,138 +7458,34 @@
// Target Optimization Hooks
//===----------------------------------------------------------------------===//
-SDValue PPCTargetLowering::DAGCombineFastRecip(SDValue Op,
- DAGCombinerInfo &DCI) const {
- if (DCI.isAfterLegalizeVectorOps())
- return SDValue();
-
- EVT VT = Op.getValueType();
-
- if ((VT == MVT::f32 && Subtarget.hasFRES()) ||
- (VT == MVT::f64 && Subtarget.hasFRE()) ||
- (VT == MVT::v4f32 && Subtarget.hasAltivec()) ||
- (VT == MVT::v2f64 && Subtarget.hasVSX())) {
-
- // Newton iteration for a function: F(X) is X_{i+1} = X_i - F(X_i)/F'(X_i)
- // For the reciprocal, we need to find the zero of the function:
- // F(X) = A X - 1 [which has a zero at X = 1/A]
- // =>
- // X_{i+1} = X_i (2 - A X_i) = X_i + X_i (1 - A X_i) [this second form
- // does not require additional intermediate precision]
-
- // Convergence is quadratic, so we essentially double the number of digits
- // correct after every iteration. The minimum architected relative
- // accuracy is 2^-5. When hasRecipPrec(), this is 2^-14. IEEE float has
- // 23 digits and double has 52 digits.
- int Iterations = Subtarget.hasRecipPrec() ? 1 : 3;
- if (VT.getScalarType() == MVT::f64)
- ++Iterations;
-
- SelectionDAG &DAG = DCI.DAG;
- SDLoc dl(Op);
-
- SDValue FPOne =
- DAG.getConstantFP(1.0, VT.getScalarType());
- if (VT.isVector()) {
- assert(VT.getVectorNumElements() == 4 &&
- "Unknown vector type");
- FPOne = DAG.getNode(ISD::BUILD_VECTOR, dl, VT,
- FPOne, FPOne, FPOne, FPOne);
- }
-
- SDValue Est = DAG.getNode(PPCISD::FRE, dl, VT, Op);
- DCI.AddToWorklist(Est.getNode());
-
- // Newton iterations: Est = Est + Est (1 - Arg * Est)
- for (int i = 0; i < Iterations; ++i) {
- SDValue NewEst = DAG.getNode(ISD::FMUL, dl, VT, Op, Est);
- DCI.AddToWorklist(NewEst.getNode());
-
- NewEst = DAG.getNode(ISD::FSUB, dl, VT, FPOne, NewEst);
- DCI.AddToWorklist(NewEst.getNode());
-
- NewEst = DAG.getNode(ISD::FMUL, dl, VT, Est, NewEst);
- DCI.AddToWorklist(NewEst.getNode());
-
- Est = DAG.getNode(ISD::FADD, dl, VT, Est, NewEst);
- DCI.AddToWorklist(Est.getNode());
- }
-
- return Est;
+SDValue PPCTargetLowering::getEstimate(unsigned Opcode, SDValue Operand,
+ DAGCombinerInfo &DCI,
+ unsigned &RefinementSteps) const {
+ EVT VT = Operand.getValueType();
+ SDValue RV;
+ if (Opcode == ISD::FSQRT) {
+ if ((VT == MVT::f32 && Subtarget.hasFRSQRTES()) ||
+ (VT == MVT::f64 && Subtarget.hasFRSQRTE()) ||
+ (VT == MVT::v4f32 && Subtarget.hasAltivec()) ||
+ (VT == MVT::v2f64 && Subtarget.hasVSX()))
+ RV = DCI.DAG.getNode(PPCISD::FRSQRTE, SDLoc(Operand), VT, Operand);
+ } else if (Opcode == ISD::FDIV) {
+ if ((VT == MVT::f32 && Subtarget.hasFRES()) ||
+ (VT == MVT::f64 && Subtarget.hasFRE()) ||
+ (VT == MVT::v4f32 && Subtarget.hasAltivec()) ||
+ (VT == MVT::v2f64 && Subtarget.hasVSX()))
+ RV = DCI.DAG.getNode(PPCISD::FRE, SDLoc(Operand), VT, Operand);
}
-
- return SDValue();
-}
-
-SDValue PPCTargetLowering::BuildRSQRTE(SDValue Op, DAGCombinerInfo &DCI) const {
- if (DCI.isAfterLegalizeVectorOps())
- return SDValue();
-
- EVT VT = Op.getValueType();
-
- if ((VT == MVT::f32 && Subtarget.hasFRSQRTES()) ||
- (VT == MVT::f64 && Subtarget.hasFRSQRTE()) ||
- (VT == MVT::v4f32 && Subtarget.hasAltivec()) ||
- (VT == MVT::v2f64 && Subtarget.hasVSX())) {
-
- // Newton iteration for a function: F(X) is X_{i+1} = X_i - F(X_i)/F'(X_i)
- // For the reciprocal sqrt, we need to find the zero of the function:
- // F(X) = 1/X^2 - A [which has a zero at X = 1/sqrt(A)]
- // =>
- // X_{i+1} = X_i (1.5 - A X_i^2 / 2)
- // As a result, we precompute A/2 prior to the iteration loop.
-
+ if (RV.getNode()) {
// Convergence is quadratic, so we essentially double the number of digits
- // correct after every iteration. The minimum architected relative
- // accuracy is 2^-5. When hasRecipPrec(), this is 2^-14. IEEE float has
- // 23 digits and double has 52 digits.
- int Iterations = Subtarget.hasRecipPrec() ? 1 : 3;
+ // correct after every iteration. For both FRE and FRSQRTE, the minimum
+ // architected relative accuracy is 2^-5. When hasRecipPrec(), this is
+ // 2^-14. IEEE float has 23 digits and double has 52 digits.
+ RefinementSteps = Subtarget.hasRecipPrec() ? 1 : 3;
if (VT.getScalarType() == MVT::f64)
- ++Iterations;
-
- SelectionDAG &DAG = DCI.DAG;
- SDLoc dl(Op);
-
- SDValue FPThreeHalves =
- DAG.getConstantFP(1.5, VT.getScalarType());
- if (VT.isVector()) {
- assert(VT.getVectorNumElements() == 4 &&
- "Unknown vector type");
- FPThreeHalves = DAG.getNode(ISD::BUILD_VECTOR, dl, VT,
- FPThreeHalves, FPThreeHalves,
- FPThreeHalves, FPThreeHalves);
- }
-
- SDValue Est = DAG.getNode(PPCISD::FRSQRTE, dl, VT, Op);
- DCI.AddToWorklist(Est.getNode());
-
- // We now need 0.5*Arg which we can write as (1.5*Arg - Arg) so that
- // this entire sequence requires only one FP constant.
- SDValue HalfArg = DAG.getNode(ISD::FMUL, dl, VT, FPThreeHalves, Op);
- DCI.AddToWorklist(HalfArg.getNode());
-
- HalfArg = DAG.getNode(ISD::FSUB, dl, VT, HalfArg, Op);
- DCI.AddToWorklist(HalfArg.getNode());
-
- // Newton iterations: Est = Est * (1.5 - HalfArg * Est * Est)
- for (int i = 0; i < Iterations; ++i) {
- SDValue NewEst = DAG.getNode(ISD::FMUL, dl, VT, Est, Est);
- DCI.AddToWorklist(NewEst.getNode());
-
- NewEst = DAG.getNode(ISD::FMUL, dl, VT, HalfArg, NewEst);
- DCI.AddToWorklist(NewEst.getNode());
-
- NewEst = DAG.getNode(ISD::FSUB, dl, VT, FPThreeHalves, NewEst);
- DCI.AddToWorklist(NewEst.getNode());
-
- Est = DAG.getNode(ISD::FMUL, dl, VT, Est, NewEst);
- DCI.AddToWorklist(Est.getNode());
- }
-
- return Est;
+ ++RefinementSteps;
}
-
- return SDValue();
+ return RV;
}
static bool isConsecutiveLSLoc(SDValue Loc, EVT VT, LSBaseSDNode *Base,
@@ -8316,55 +8212,6 @@
case ISD::SETCC:
case ISD::SELECT_CC:
return DAGCombineTruncBoolExt(N, DCI);
- case ISD::FDIV: {
- assert(TM.Options.UnsafeFPMath &&
- "Reciprocal estimates require UnsafeFPMath");
-
- SDValue RV = DAGCombineFastRecip(N->getOperand(1), DCI);
- if (RV.getNode()) {
- DCI.AddToWorklist(RV.getNode());
- return DAG.getNode(ISD::FMUL, dl, N->getValueType(0),
- N->getOperand(0), RV);
- }
-
- }
- break;
- case ISD::FSQRT: {
- assert(TM.Options.UnsafeFPMath &&
- "Reciprocal estimates require UnsafeFPMath");
-
- // Compute this as 1/(1/sqrt(X)), which is the reciprocal of the
- // reciprocal sqrt.
- SDValue RV = BuildRSQRTE(N->getOperand(0), DCI);
- if (RV.getNode()) {
- DCI.AddToWorklist(RV.getNode());
- RV = DAGCombineFastRecip(RV, DCI);
- if (RV.getNode()) {
- // Unfortunately, RV is now NaN if the input was exactly 0. Select out
- // this case and force the answer to 0.
-
- EVT VT = RV.getValueType();
-
- SDValue Zero = DAG.getConstantFP(0.0, VT.getScalarType());
- if (VT.isVector()) {
- assert(VT.getVectorNumElements() == 4 && "Unknown vector type");
- Zero = DAG.getNode(ISD::BUILD_VECTOR, dl, VT, Zero, Zero, Zero, Zero);
- }
-
- SDValue ZeroCmp =
- DAG.getSetCC(dl, getSetCCResultType(*DAG.getContext(), VT),
- N->getOperand(0), Zero, ISD::SETEQ);
- DCI.AddToWorklist(ZeroCmp.getNode());
- DCI.AddToWorklist(RV.getNode());
-
- RV = DAG.getNode(VT.isVector() ? ISD::VSELECT : ISD::SELECT, dl, VT,
- ZeroCmp, Zero, RV);
- return RV;
- }
- }
-
- }
- break;
case ISD::SINT_TO_FP:
if (TM.getSubtarget<PPCSubtarget>().has64BitSupport()) {
if (N->getOperand(0).getOpcode() == ISD::FP_TO_SINT) {