[Strict FP] Allow more relaxed scheduling

Reimplement scheduling constraints for strict FP instructions in
ScheduleDAGInstrs::buildSchedGraph to allow for more relaxed
scheduling.  Specifially, allow one strict FP instruction to
be scheduled across another, as long as it is not moved across
any global barrier.

Differential Revision: https://reviews.llvm.org/D64412

Reviewed By: cameron.mcinally

llvm-svn: 366222

1 files changed, 21 insertions, 10 deletions

diff --git a/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp b/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
index a5380108896..d5ad7e92299 100644
--- a/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
+++ b/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
@@ -712,7 +712,6 @@ void ScheduleDAGInstrs::buildSchedGraph(AliasAnalysis *AA,
   AAForDep = UseAA ? AA : nullptr;
 
   BarrierChain = nullptr;
-  SUnit *FPBarrierChain = nullptr;
 
   this->TrackLaneMasks = TrackLaneMasks;
   MISUnitMap.clear();
@@ -744,6 +743,14 @@ void ScheduleDAGInstrs::buildSchedGraph(AliasAnalysis *AA,
   // done.
   Value2SUsMap NonAliasStores, NonAliasLoads(1 /*TrueMemOrderLatency*/);
 
+  // Track all instructions that may raise floating-point exceptions.
+  // These do not depend on one other (or normal loads or stores), but
+  // must not be rescheduled across global barriers.  Note that we don't
+  // really need a "map" here since we don't track those MIs by value;
+  // using the same Value2SUsMap data type here is simply a matter of
+  // convenience.
+  Value2SUsMap FPExceptions;
+
   // Remove any stale debug info; sometimes BuildSchedGraph is called again
   // without emitting the info from the previous call.
   DbgValues.clear();
@@ -871,20 +878,24 @@ void ScheduleDAGInstrs::buildSchedGraph(AliasAnalysis *AA,
       addBarrierChain(Loads);
       addBarrierChain(NonAliasStores);
       addBarrierChain(NonAliasLoads);
-
-      // Add dependency against previous FP barrier and reset FP barrier.
-      if (FPBarrierChain)
-        FPBarrierChain->addPredBarrier(BarrierChain);
-      FPBarrierChain = BarrierChain;
+      addBarrierChain(FPExceptions);
 
       continue;
     }
 
-    // Instructions that may raise FP exceptions depend on each other.
+    // Instructions that may raise FP exceptions may not be moved
+    // across any global barriers.
     if (MI.mayRaiseFPException()) {
-      if (FPBarrierChain)
-        FPBarrierChain->addPredBarrier(SU);
-      FPBarrierChain = SU;
+      if (BarrierChain)
+        BarrierChain->addPredBarrier(SU);
+
+      FPExceptions.insert(SU, UnknownValue);
+
+      if (FPExceptions.size() >= HugeRegion) {
+        LLVM_DEBUG(dbgs() << "Reducing FPExceptions map.\n";);
+        Value2SUsMap empty;
+        reduceHugeMemNodeMaps(FPExceptions, empty, getReductionSize());
+      }
     }
 
     // If it's not a store or a variant load, we're done.