[X86] Add target combine rules for horizontal add/sub.
This patch adds new target specific combine rules to identify horizontal
add/sub idioms from BUILD_VECTOR dag nodes.
This patch also teaches the DAGCombiner how to canonicalize sequences of
insert_vector_elt dag nodes according to the following rule:
(insert_vector_elt (insert_vector_elt A, I0), I1) ->
(insert_vecto_elt (insert_vector_elt A, I1), I0)
This new canonicalization rule only triggers if the inner insert_vector
dag node has exactly one use; also, both indices must be known constants,
and I1 < I0.
This last rule made it possible to write a simpler algorithm to identify
horizontal add/sub patterns because now we don't have to worry about the
ordering of insert_vector_elt dag nodes.
llvm-svn: 210477
diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 8ec0c45..b9da13a 100644
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -9721,6 +9721,27 @@
return SDValue();
unsigned Elt = cast<ConstantSDNode>(EltNo)->getZExtValue();
+ // Canonicalize insert_vector_elt dag nodes.
+ // Example:
+ // (insert_vector_elt (insert_vector_elt A, Idx0), Idx1)
+ // -> (insert_vector_elt (insert_vector_elt A, Idx1), Idx0)
+ //
+ // Do this only if the child insert_vector node has one use; also
+ // do this only if indices are both constants and Idx1 < Idx0.
+ if (InVec.getOpcode() == ISD::INSERT_VECTOR_ELT && InVec.hasOneUse()
+ && isa<ConstantSDNode>(InVec.getOperand(2))) {
+ unsigned OtherElt =
+ cast<ConstantSDNode>(InVec.getOperand(2))->getZExtValue();
+ if (Elt < OtherElt) {
+ // Swap nodes.
+ SDValue NewOp = DAG.getNode(ISD::INSERT_VECTOR_ELT, SDLoc(N), VT,
+ InVec.getOperand(0), InVal, EltNo);
+ AddToWorkList(NewOp.getNode());
+ return DAG.getNode(ISD::INSERT_VECTOR_ELT, SDLoc(InVec.getNode()),
+ VT, NewOp, InVec.getOperand(1), InVec.getOperand(2));
+ }
+ }
+
// Check that the operand is a BUILD_VECTOR (or UNDEF, which can essentially
// be converted to a BUILD_VECTOR). Fill in the Ops vector with the
// vector elements.