From e46b765907f275ffe98efb694b55877368e4fa3a Mon Sep 17 00:00:00 2001
From: Jonas Paulsson <paulsson@linux.vnet.ibm.com>
Date: Wed, 7 Mar 2018 08:54:32 +0000
Subject: [PATCH] [SystemZ]  Improve getCurrCycleIdx() in
 SystemZHazardRecognizer.

getCurrCycleIdx() returns the decoder cycle index which the next candidate SU
will be placed on.

This patch improves this method by passing the candidate SU to it so that if
SU will begin a new group, the index of that group is returned instead.

Review: Ulrich Weigand
llvm-svn: 326880
---
 .../SystemZ/SystemZHazardRecognizer.cpp       | 21 +++++++++++++------
 lib/Target/SystemZ/SystemZHazardRecognizer.h  |  8 ++++---
 2 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/lib/Target/SystemZ/SystemZHazardRecognizer.cpp b/lib/Target/SystemZ/SystemZHazardRecognizer.cpp
index d71d1fd1ccf..9a3fe3da530 100644
--- a/lib/Target/SystemZ/SystemZHazardRecognizer.cpp
+++ b/lib/Target/SystemZ/SystemZHazardRecognizer.cpp
@@ -59,10 +59,18 @@ getNumDecoderSlots(SUnit *SU) const {
   return 1; // Normal instruction
 }
 
-unsigned SystemZHazardRecognizer::getCurrCycleIdx() const {
+unsigned SystemZHazardRecognizer::getCurrCycleIdx(SUnit *SU) const {
   unsigned Idx = CurrGroupSize;
   if (GrpCount % 2)
     Idx += 3;
+
+  if (SU != nullptr && !fitsIntoCurrentGroup(SU)) {
+    if (Idx == 1 || Idx == 2)
+      Idx = 3;
+    else if (Idx == 4 || Idx == 5)
+      Idx = 0;
+  }
+
   return Idx;
 }
 
@@ -278,7 +286,7 @@ EmitInstruction(SUnit *SU) {
 
   // Make note of an instruction that uses a blocking resource (FPd).
   if (SU->isUnbuffered) {
-    LastFPdOpCycleIdx = getCurrCycleIdx();
+    LastFPdOpCycleIdx = getCurrCycleIdx(SU);
     DEBUG(dbgs() << "++ Last FPd cycle index: "
           << LastFPdOpCycleIdx << "\n";);
   }
@@ -321,7 +329,7 @@ int SystemZHazardRecognizer::groupingCost(SUnit *SU) const {
   return 0;
 }
 
-bool SystemZHazardRecognizer::isFPdOpPreferred_distance(const SUnit *SU) {
+bool SystemZHazardRecognizer::isFPdOpPreferred_distance(SUnit *SU) const {
   assert (SU->isUnbuffered);
   // If this is the first FPd op, it should be scheduled high.
   if (LastFPdOpCycleIdx == UINT_MAX)
@@ -330,9 +338,10 @@ bool SystemZHazardRecognizer::isFPdOpPreferred_distance(const SUnit *SU) {
   // of the processor to use the other FPd unit there. This should
   // generally happen if two FPd ops are placed with 2 other
   // instructions between them (modulo 6).
-  if (LastFPdOpCycleIdx > getCurrCycleIdx())
-    return ((LastFPdOpCycleIdx - getCurrCycleIdx()) == 3);
-  return ((getCurrCycleIdx() - LastFPdOpCycleIdx) == 3);
+  unsigned SUCycleIdx = getCurrCycleIdx(SU);
+  if (LastFPdOpCycleIdx > SUCycleIdx)
+    return ((LastFPdOpCycleIdx - SUCycleIdx) == 3);
+  return ((SUCycleIdx - LastFPdOpCycleIdx) == 3);
 }
 
 int SystemZHazardRecognizer::
diff --git a/lib/Target/SystemZ/SystemZHazardRecognizer.h b/lib/Target/SystemZ/SystemZHazardRecognizer.h
index 31cdf8cfed5..40cb3acc700 100644
--- a/lib/Target/SystemZ/SystemZHazardRecognizer.h
+++ b/lib/Target/SystemZ/SystemZHazardRecognizer.h
@@ -75,8 +75,10 @@ class SystemZHazardRecognizer : public ScheduleHazardRecognizer {
 
   /// Two decoder groups per cycle are formed (for z13), meaning 2x3
   /// instructions. This function returns a number between 0 and 5,
-  /// representing the current decoder slot of the current cycle.
-  unsigned getCurrCycleIdx() const;
+  /// representing the current decoder slot of the current cycle.  If an SU
+  /// is passed which will begin a new decoder group, the returned value is
+  /// the cycle index of the next group.
+  unsigned getCurrCycleIdx(SUnit *SU = nullptr) const;
 
   /// LastFPdOpCycleIdx stores the numbeer returned by getCurrCycleIdx()
   /// when a stalling operation is scheduled (which uses the FPd resource).
@@ -95,7 +97,7 @@ class SystemZHazardRecognizer : public ScheduleHazardRecognizer {
 
   /// With the goal of alternating processor sides for stalling (FPd)
   /// ops, return true if it seems good to schedule an FPd op next.
-  bool isFPdOpPreferred_distance(const SUnit *SU);
+  bool isFPdOpPreferred_distance(SUnit *SU) const;
 
   /// Last emitted instruction or nullptr.
   MachineInstr *LastEmittedMI;