[PATCH] D60864: [AMDGPU] Ignore non-SUnits edges

[Piotr Sobczak via Phabricator via llvm-commits]

This revision was automatically updated to reflect the committed changes.
Closed by commit rL358740: [AMDGPU] Ignore non-SUnits edges (authored by piotr, committed by ).

Repository:
  rL LLVM

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D60864/new/

https://reviews.llvm.org/D60864

Files:
  llvm/trunk/lib/Target/AMDGPU/SIMachineScheduler.cpp


Index: llvm/trunk/lib/Target/AMDGPU/SIMachineScheduler.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/SIMachineScheduler.cpp
+++ llvm/trunk/lib/Target/AMDGPU/SIMachineScheduler.cpp
@@ -1874,6 +1874,8 @@
       bool CopyForLowLat = false;
       for (SDep& SuccDep : SU->Succs) {
         SUnit *Succ = SuccDep.getSUnit();
+        if (SuccDep.isWeak() || Succ->NodeNum >= DAGSize)
+          continue;
         if (SITII->isLowLatencyInstruction(*Succ->getInstr())) {
           CopyForLowLat = true;
         }


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D60864.195862.patch
Type: text/x-patch
Size: 570 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20190419/2b0b4814/attachment.bin>