[PATCH] D75424: [MachinePipeliner] Fix a bug in Output Dependency chains

[Lama via Phabricator via llvm-commits]

lsaba created this revision.
lsaba added reviewers: kparzysz, bcahoon, jsji.
Herald added a subscriber: hiraditya.
Herald added a project: LLVM.

The current implementation collects all Preds/Succs of a Dep of kind Output, creating a long chain and subsequently a schedule with an unnecessarily large II.
Was this done on purpose for a reason I'm missing?


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D75424

Files:
  llvm/lib/CodeGen/MachinePipeliner.cpp


Index: llvm/lib/CodeGen/MachinePipeliner.cpp
===================================================================
--- llvm/lib/CodeGen/MachinePipeliner.cpp
+++ llvm/lib/CodeGen/MachinePipeliner.cpp
@@ -2368,7 +2368,7 @@
       continue;
     EarlyCycle = std::min(EarlyCycle, it->second);
     for (const auto &PI : PrevSU->Preds)
-      if (PI.getKind() == SDep::Order || Dep.getKind() == SDep::Output)
+      if (PI.getKind() == SDep::Order || PI.getKind() == SDep::Output)
         Worklist.push_back(PI);
     Visited.insert(PrevSU);
   }
@@ -2391,7 +2391,7 @@
       continue;
     LateCycle = std::max(LateCycle, it->second);
     for (const auto &SI : SuccSU->Succs)
-      if (SI.getKind() == SDep::Order || Dep.getKind() == SDep::Output)
+      if (SI.getKind() == SDep::Order || SI.getKind() == SDep::Output)
         Worklist.push_back(SI);
     Visited.insert(SuccSU);
   }


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D75424.247505.patch
Type: text/x-patch
Size: 885 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20200301/c34104db/attachment.bin>