Convert floating point division by a constant into multiplication by the
reciprocal if converting to the reciprocal is exact. Do it even if inexact
if -ffast-math. This substantially speeds up ac.f90 from the polyhedron
benchmarks.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154265 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index e036687..e0fd3ab 100644
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -5725,6 +5725,19 @@
if (N0CFP && N1CFP && VT != MVT::ppcf128)
return DAG.getNode(ISD::FDIV, N->getDebugLoc(), VT, N0, N1);
+ // fold (fdiv X, c2) -> fmul X, 1/c2 if there is no precision loss or if
+ // losing precision is acceptable.
+ if (N1CFP && VT != MVT::ppcf128) {
+ // Compute the reciprocal 1.0 / c2.
+ APFloat N1APF = N1CFP->getValueAPF();
+ APFloat Recip(N1APF.getSemantics(), 1); // 1.0
+ APFloat::opStatus st = Recip.divide(N1APF, APFloat::rmNearestTiesToEven);
+ // Only do the transform if the reciprocal is not too horrible (eg not NaN).
+ if (st == APFloat::opOK || (st == APFloat::opInexact &&
+ DAG.getTarget().Options.UnsafeFPMath))
+ return DAG.getNode(ISD::FMUL, N->getDebugLoc(), VT, N0,
+ DAG.getConstantFP(Recip, VT));
+ }
// (fdiv (fneg X), (fneg Y)) -> (fdiv X, Y)
if (char LHSNeg = isNegatibleForFree(N0, LegalOperations, TLI,