Martien.exhaustiveswp

llvm/lib/Target/AIE/AIEBaseSubtarget.cpp

@@ -704,6 +704,8 @@ AIEBaseSubtarget::getPostRAMutationsImpl(const Triple &TT) {
   std::vector<std::unique_ptr<ScheduleDAGMutation>> Mutations;
   Mutations.emplace_back(std::make_unique<LockDelays>());
   if (!TT.isAIE1()) {
+    if (EnableWAWStickyRegisters)
+      Mutations.emplace_back(std::make_unique<WAWStickyRegistersEdges>());
     Mutations.emplace_back(std::make_unique<RegionEndEdges>());
     Mutations.emplace_back(std::make_unique<MemoryEdges>());
     Mutations.emplace_back(std::make_unique<MachineSchedWAWEdges>());

llvm/lib/Target/AIE/AIEMachineScheduler.cpp

@@ -1320,8 +1320,9 @@ void llvm::AIEPostRASchedStrategy::buildGraph(ScheduleDAGMI &DAG, AAResults *AA,
     assert(BS.getRegions().size() == 1);
     // Try to wrap the linear schedule within II.
     // We virtually unroll the body by the stagecount, computed from rounding
-    // up the length divided by II.
-    NCopies = (BS.getScheduleLength() + II - 1) / II;
+    // up the length divided by II, adding one more stage to account for
+    // the added resource contention
+    NCopies = (BS.getScheduleLength() + II - 1) / II + 1;
   }
   DEBUG_BLOCKS(dbgs() << "    buildGraph, NCopies=" << NCopies << "\n");
   for (int S = 0; S < NCopies; S++) {
@@ -1386,6 +1387,8 @@ void AIEScheduleDAGMI::schedule() {
     // If it succeeds, we need to implement it, if we fail we fall back on the
     // normal loop schedule
     SchedImpl->buildGraph(*this, AA);
+    postProcessDAG();
+
     auto &PostSWP = BS.getPostSWP();
     if (PostSWP.schedule(*this, BS.FixPoint.II)) {
       BS.setPipelined();