summaryrefslogtreecommitdiffstats
path: root/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
diff options
context:
space:
mode:
authorNemanja Ivanovic <nemanja.i.ibm@gmail.com>2019-02-08 19:50:58 +0000
committerNemanja Ivanovic <nemanja.i.ibm@gmail.com>2019-02-08 19:50:58 +0000
commit92a8c36735ec3dc2a9c1604916153293497eaedb (patch)
tree7ec73f2c717413f602c093cf05fa58f51e8dafe9 /llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
parent67b1b451b5f44e4c069735d55266d5153c6544fc (diff)
downloadbcm5719-llvm-92a8c36735ec3dc2a9c1604916153293497eaedb.tar.gz
bcm5719-llvm-92a8c36735ec3dc2a9c1604916153293497eaedb.zip
[DAGCombine] Optimize pow(X, 0.75) to sqrt(X) * sqrt(sqrt(X))
The sqrt case is faster and we already do this for the case where the exponent is 0.25. This adds the 0.75 case which is also not sensitive to signed zeros. Patch by Whitney Tsang (Whitney) Differential revision: https://reviews.llvm.org/D57434 llvm-svn: 353557
Diffstat (limited to 'llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp')
-rw-r--r--llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp18
1 files changed, 14 insertions, 4 deletions
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index b462aabad2f..96b6aec78d5 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -11912,18 +11912,24 @@ SDValue DAGCombiner::visitFPOW(SDNode *N) {
return DAG.getNode(ISD::FCBRT, SDLoc(N), VT, N->getOperand(0), Flags);
}
- // Try to convert x ** (1/4) into square roots.
+ // Try to convert x ** (1/4) and x ** (3/4) into square roots.
// x ** (1/2) is canonicalized to sqrt, so we do not bother with that case.
// TODO: This could be extended (using a target hook) to handle smaller
// power-of-2 fractional exponents.
- if (ExponentC->getValueAPF().isExactlyValue(0.25)) {
+ bool ExponentIs025 = ExponentC->getValueAPF().isExactlyValue(0.25);
+ bool ExponentIs075 = ExponentC->getValueAPF().isExactlyValue(0.75);
+ if (ExponentIs025 || ExponentIs075) {
// pow(-0.0, 0.25) = +0.0; sqrt(sqrt(-0.0)) = -0.0.
// pow(-inf, 0.25) = +inf; sqrt(sqrt(-inf)) = NaN.
+ // pow(-0.0, 0.75) = +0.0; sqrt(-0.0) * sqrt(sqrt(-0.0)) = +0.0.
+ // pow(-inf, 0.75) = +inf; sqrt(-inf) * sqrt(sqrt(-inf)) = NaN.
// For regular numbers, rounding may cause the results to differ.
// Therefore, we require { nsz ninf afn } for this transform.
// TODO: We could select out the special cases if we don't have nsz/ninf.
SDNodeFlags Flags = N->getFlags();
- if (!Flags.hasNoSignedZeros() || !Flags.hasNoInfs() ||
+
+ // We only need no signed zeros for the 0.25 case.
+ if ((!Flags.hasNoSignedZeros() && ExponentIs025) || !Flags.hasNoInfs() ||
!Flags.hasApproximateFuncs())
return SDValue();
@@ -11939,7 +11945,11 @@ SDValue DAGCombiner::visitFPOW(SDNode *N) {
// pow(X, 0.25) --> sqrt(sqrt(X))
SDLoc DL(N);
SDValue Sqrt = DAG.getNode(ISD::FSQRT, DL, VT, N->getOperand(0), Flags);
- return DAG.getNode(ISD::FSQRT, DL, VT, Sqrt, Flags);
+ SDValue SqrtSqrt = DAG.getNode(ISD::FSQRT, DL, VT, Sqrt, Flags);
+ if (ExponentIs025)
+ return SqrtSqrt;
+ // pow(X, 0.75) --> sqrt(X) * sqrt(sqrt(X))
+ return DAG.getNode(ISD::FMUL, DL, VT, Sqrt, SqrtSqrt, Flags);
}
return SDValue();
OpenPOWER on IntegriCloud