RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 03:02:36 +01:00
Code Issues Projects Releases Wiki Activity

[MachineScheduler][NFC] Don't swap when we can't cluster

Browse Source 
https://reviews.llvm.org/D72706 tried to reduce reordering due to mem op
clustering. This patch avoid doing the swap when we can't cluster.

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D72800
This commit is contained in:
Jinsong Ji 2020-01-15 21:19:34 +00:00
parent 53ae48b077
commit 1d416d3cac
1 changed files with 20 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
lib/CodeGen/MachineScheduler.cpp
View File

@ -1573,26 +1573,28 @@ void BaseMemOpClusterMutation::clusterNeighboringMemOps(
for (unsigned Idx = 0, End = MemOpRecords.size(); Idx < (End - 1); ++Idx) {
SUnit *SUa = MemOpRecords[Idx].SU;
SUnit *SUb = MemOpRecords[Idx+1].SU;
if (SUa->NodeNum > SUb->NodeNum)
std::swap(SUa, SUb);
if (TII->shouldClusterMemOps(*MemOpRecords[Idx].BaseOp,
*MemOpRecords[Idx + 1].BaseOp,
ClusterLength) &&
DAG->addEdge(SUb, SDep(SUa, SDep::Cluster))) {
LLVM_DEBUG(dbgs() << "Cluster ld/st SU(" << SUa->NodeNum << ") - SU("
<< SUb->NodeNum << ")\n");
// Copy successor edges from SUa to SUb. Interleaving computation
// dependent on SUa can prevent load combining due to register reuse.
// Predecessor edges do not need to be copied from SUb to SUa since nearby
// loads should have effectively the same inputs.
for (const SDep &Succ : SUa->Succs) {
if (Succ.getSUnit() == SUb)
continue;
LLVM_DEBUG(dbgs() << " Copy Succ SU(" << Succ.getSUnit()->NodeNum
<< ")\n");
DAG->addEdge(Succ.getSUnit(), SDep(SUb, SDep::Artificial));
}
++ClusterLength;
ClusterLength)) {
if (SUa->NodeNum > SUb->NodeNum)
std::swap(SUa, SUb);
if (DAG->addEdge(SUb, SDep(SUa, SDep::Cluster))) {
LLVM_DEBUG(dbgs() << "Cluster ld/st SU(" << SUa->NodeNum << ") - SU("
<< SUb->NodeNum << ")\n");
// Copy successor edges from SUa to SUb. Interleaving computation
// dependent on SUa can prevent load combining due to register reuse.
// Predecessor edges do not need to be copied from SUb to SUa since
// nearby loads should have effectively the same inputs.
for (const SDep &Succ : SUa->Succs) {
if (Succ.getSUnit() == SUb)
continue;
LLVM_DEBUG(dbgs()
<< " Copy Succ SU(" << Succ.getSUnit()->NodeNum << ")\n");
DAG->addEdge(Succ.getSUnit(), SDep(SUb, SDep::Artificial));
}
++ClusterLength;
} else
ClusterLength = 1;
} else
ClusterLength = 1;
}