maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[AArch64] Share search bookkeeping in combines. NFCI. 

Share predecessor search bookkeeping in both perform PostLD1Combine
and performNEONPostLDSTCombine. This should be approximately a 4x and
2x performance improvement.

llvm-svn: 342986
This commit is contained in:
Nirav Dave 2018-09-25 15:30:22 +00:00
parent a2f514d672
commit e40e2bbd37
1 changed files with 17 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
View File

@ -10175,15 +10175,6 @@ static SDValue performPostLD1Combine(SDNode *N,
|| UI.getUse().getResNo() != Addr.getResNo())
continue;
// Check that the add is independent of the load. Otherwise, folding it
// would create a cycle.
if (User->isPredecessorOf(LD) || LD->isPredecessorOf(User))
continue;
// Also check that add is not used in the vector operand. This would also
// create a cycle.
if (User->isPredecessorOf(Vector.getNode()))
continue;
// If the increment is a constant, it must match the memory ref size.
SDValue Inc = User->getOperand(User->getOperand(0) == Addr ? 1 : 0);
if (ConstantSDNode *CInc = dyn_cast<ConstantSDNode>(Inc.getNode())) {
@ -10194,11 +10185,16 @@ static SDValue performPostLD1Combine(SDNode *N,
Inc = DAG.getRegister(AArch64::XZR, MVT::i64);
}
// Finally, check that the vector doesn't depend on the load.
// Again, this would create a cycle.
// The load depending on the vector is fine, as that's the case for the
// LD1*post we'll eventually generate anyway.
if (LoadSDN->isPredecessorOf(Vector.getNode()))
// To avoid cycle construction make sure that neither the load nor the add
// are predecessors to each other or the Vector.
SmallPtrSet<const SDNode *, 32> Visited;
SmallVector<const SDNode *, 16> Worklist;
Visited.insert(N);
Worklist.push_back(User);
Worklist.push_back(LD);
Worklist.push_back(Vector.getNode());
if (SDNode::hasPredecessorHelper(LD, Visited, Worklist) ||
SDNode::hasPredecessorHelper(User, Visited, Worklist))
continue;
SmallVector<SDValue, 8> Ops;
@ -10284,7 +10280,13 @@ static SDValue performNEONPostLDSTCombine(SDNode *N,
// Check that the add is independent of the load/store. Otherwise, folding
// it would create a cycle.
if (User->isPredecessorOf(N) || N->isPredecessorOf(User))
SmallPtrSet<const SDNode *, 32> Visited;
SmallVector<const SDNode *, 16> Worklist;
Visited.insert(Addr.getNode());
Worklist.push_back(N);
Worklist.push_back(User);
if (SDNode::hasPredecessorHelper(N, Visited, Worklist) ||
SDNode::hasPredecessorHelper(User, Visited, Worklist))
continue;
// Find the new opcode for the updating load/store.