[Pipeliner] Add two pragmas to control software pipelining optimization

#pragma clang loop pipeline(disable)
  
    Disable SWP optimization for the next loop.
    “disable” is the only possible value.
  
#pragma clang loop pipeline_initiation_interval(number)
  
    Set value of initiation interval for SWP
    optimization to specified number value for
    the next loop. Number is the positive value
    greater than 0.
  
These pragmas could be used for debugging or reducing
compile time purposes. It is possible to disable SWP for
concrete loops to save compilation time or to find bugs
by not doing SWP to certain loops. It is possible to set
value of initiation interval to concrete number to save
compilation time by not doing extra pipeliner passes or
to check created schedule for specific initiation interval.

That is llvm part of the fix

Clang part of fix: https://reviews.llvm.org/D55710

Patch by Alexey Lapshin!

Differential Revision: https://reviews.llvm.org/D56403

llvm-svn: 351923

llvm/include/llvm/CodeGen/MachinePipeliner.h

@@ -62,6 +62,8 @@ public:
   const InstrItineraryData *InstrItins;
   const TargetInstrInfo *TII = nullptr;
   RegisterClassInfo RegClassInfo;
+  bool disabledByPragma = false;
+  unsigned II_setByPragma = 0;
 
 #ifndef NDEBUG
   static int NumTries;
@@ -99,6 +101,7 @@ private:
   bool canPipelineLoop(MachineLoop &L);
   bool scheduleLoop(MachineLoop &L);
   bool swingModuloScheduler(MachineLoop &L);
+  void setPragmaPipelineOptions(MachineLoop &L);
 };
 
 /// This class builds the dependence graph for the instructions in a loop,
@@ -107,11 +110,14 @@ class SwingSchedulerDAG : public ScheduleDAGInstrs {
   MachinePipeliner &Pass;
   /// The minimum initiation interval between iterations for this schedule.
   unsigned MII = 0;
+  /// The maximum initiation interval between iterations for this schedule.
+  unsigned MAX_II = 0;
   /// Set to true if a valid pipelined schedule is found for the loop.
   bool Scheduled = false;
   MachineLoop &Loop;
   LiveIntervals &LIS;
   const RegisterClassInfo &RegClassInfo;
+  unsigned II_setByPragma = 0;
 
   /// A toplogical ordering of the SUnits, which is needed for changing
   /// dependences and iterating over the SUnits.
@@ -189,9 +195,9 @@ class SwingSchedulerDAG : public ScheduleDAGInstrs {
 
 public:
   SwingSchedulerDAG(MachinePipeliner &P, MachineLoop &L, LiveIntervals &lis,
-                    const RegisterClassInfo &rci)
+                    const RegisterClassInfo &rci, unsigned II)
       : ScheduleDAGInstrs(*P.MF, P.MLI, false), Pass(P), Loop(L), LIS(lis),
-        RegClassInfo(rci), Topo(SUnits, &ExitSU) {
+        RegClassInfo(rci), II_setByPragma(II), Topo(SUnits, &ExitSU) {
     P.MF->getSubtarget().getSMSMutations(Mutations);
     if (SwpEnableCopyToPhi)
       Mutations.push_back(llvm::make_unique<CopyToPhiMutation>());
@@ -252,9 +258,6 @@ public:
     return 0;
   }
 
-  /// Set the Minimum Initiation Interval for this schedule attempt.
-  void setMII(unsigned mii) { MII = mii; }
-
   void applyInstrChange(MachineInstr *MI, SMSchedule &Schedule);
 
   void fixupRegisterOverlaps(std::deque<SUnit *> &Instrs);
@@ -345,6 +348,10 @@ private:
                              unsigned &OffsetPos, unsigned &NewBase,
                              int64_t &NewOffset);
   void postprocessDAG();
+  /// Set the Minimum Initiation Interval for this schedule attempt.
+  void setMII(unsigned ResMII, unsigned RecMII);
+  /// Set the Maximum Initiation Interval for this schedule attempt.
+  void setMAX_II();
 };
 
 /// A NodeSet contains a set of SUnit DAG nodes with additional information

llvm/lib/CodeGen/MachinePipeliner.cpp

@@ -210,8 +210,11 @@ bool MachinePipeliner::scheduleLoop(MachineLoop &L) {
   }
 #endif
 
-  if (!canPipelineLoop(L))
+  setPragmaPipelineOptions(L);
+  if (!canPipelineLoop(L)) {
+    LLVM_DEBUG(dbgs() << "\n!!! Can not pipeline loop.\n");
     return Changed;
+  }
 
   ++NumTrytoPipeline;
 
@@ -220,6 +223,50 @@ bool MachinePipeliner::scheduleLoop(MachineLoop &L) {
   return Changed;
 }
 
+void MachinePipeliner::setPragmaPipelineOptions(MachineLoop &L) {
+  MachineBasicBlock *LBLK = L.getTopBlock();
+
+  if (LBLK == nullptr)
+    return;
+
+  const BasicBlock *BBLK = LBLK->getBasicBlock();
+  if (BBLK == nullptr)
+    return;
+
+  const Instruction *TI = BBLK->getTerminator();
+  if (TI == nullptr)
+    return;
+
+  MDNode *LoopID = TI->getMetadata(LLVMContext::MD_loop);
+  if (LoopID == nullptr)
+    return;
+
+  assert(LoopID->getNumOperands() > 0 && "requires atleast one operand");
+  assert(LoopID->getOperand(0) == LoopID && "invalid loop");
+
+  for (unsigned i = 1, e = LoopID->getNumOperands(); i < e; ++i) {
+    MDNode *MD = dyn_cast<MDNode>(LoopID->getOperand(i));
+
+    if (MD == nullptr)
+      continue;
+
+    MDString *S = dyn_cast<MDString>(MD->getOperand(0));
+
+    if (S == nullptr)
+      continue;
+
+    if (S->getString() == "llvm.loop.pipeline.initiationinterval") {
+      assert(MD->getNumOperands() == 2 &&
+             "Pipeline initiation interval hint metadata should have two operands.");
+      II_setByPragma =
+          mdconst::extract<ConstantInt>(MD->getOperand(1))->getZExtValue();
+      assert(II_setByPragma >= 1 && "Pipeline initiation interval must be positive.");
+    } else if (S->getString() == "llvm.loop.pipeline.disable") {
+      disabledByPragma = true;
+    }
+  }
+}
+
 /// Return true if the loop can be software pipelined.  The algorithm is
 /// restricted to loops with a single basic block.  Make sure that the
 /// branch in the loop can be analyzed.
@@ -227,6 +274,9 @@ bool MachinePipeliner::canPipelineLoop(MachineLoop &L) {
   if (L.getNumBlocks() != 1)
     return false;
 
+  if (disabledByPragma)
+    return false;
+
   // Check if the branch can't be understood because we can't do pipelining
   // if that's the case.
   LI.TBB = nullptr;
@@ -285,7 +335,8 @@ void MachinePipeliner::preprocessPhiNodes(MachineBasicBlock &B) {
 bool MachinePipeliner::swingModuloScheduler(MachineLoop &L) {
   assert(L.getBlocks().size() == 1 && "SMS works on single blocks only.");
 
-  SwingSchedulerDAG SMS(*this, L, getAnalysis<LiveIntervals>(), RegClassInfo);
+  SwingSchedulerDAG SMS(*this, L, getAnalysis<LiveIntervals>(), RegClassInfo,
+                        II_setByPragma);
 
   MachineBasicBlock *MBB = L.getHeader();
   // The kernel should not include any terminator instructions.  These
@@ -308,6 +359,20 @@ bool MachinePipeliner::swingModuloScheduler(MachineLoop &L) {
   return SMS.hasNewSchedule();
 }
 
+void SwingSchedulerDAG::setMII(unsigned ResMII, unsigned RecMII) {
+  if (II_setByPragma > 0)
+    MII = II_setByPragma;
+  else
+    MII = std::max(ResMII, RecMII);
+}
+
+void SwingSchedulerDAG::setMAX_II() {
+  if (II_setByPragma > 0)
+    MAX_II = II_setByPragma;
+  else
+    MAX_II = MII + 10;
+}
+
 /// We override the schedule function in ScheduleDAGInstrs to implement the
 /// scheduling part of the Swing Modulo Scheduling algorithm.
 void SwingSchedulerDAG::schedule() {
@@ -334,9 +399,11 @@ void SwingSchedulerDAG::schedule() {
   if (SwpIgnoreRecMII)
     RecMII = 0;
 
-  MII = std::max(ResMII, RecMII);
-  LLVM_DEBUG(dbgs() << "MII = " << MII << " (rec=" << RecMII
-                    << ", res=" << ResMII << ")\n");
+  setMII(ResMII, RecMII);
+  setMAX_II();
+
+  LLVM_DEBUG(dbgs() << "MII = " << MII << " MAX_II = " << MAX_II
+                    << " (rec=" << RecMII << ", res=" << ResMII << ")\n");
 
   // Can't schedule a loop without a valid MII.
   if (MII == 0)
@@ -1744,8 +1811,9 @@ bool SwingSchedulerDAG::schedulePipeline(SMSchedule &Schedule) {
     return false;
 
   bool scheduleFound = false;
+  unsigned II = 0;
   // Keep increasing II until a valid schedule is found.
-  for (unsigned II = MII; II < MII + 10 && !scheduleFound; ++II) {
+  for (II = MII; II <= MAX_II && !scheduleFound; ++II) {
     Schedule.reset();
     Schedule.setInitiationInterval(II);
     LLVM_DEBUG(dbgs() << "Try to schedule with " << II << "\n");
@@ -1817,7 +1885,8 @@ bool SwingSchedulerDAG::schedulePipeline(SMSchedule &Schedule) {
       scheduleFound = Schedule.isValidSchedule(this);
   }
 
-  LLVM_DEBUG(dbgs() << "Schedule Found? " << scheduleFound << "\n");
+  LLVM_DEBUG(dbgs() << "Schedule Found? " << scheduleFound << " (II=" << II
+                    << ")\n");
 
   if (scheduleFound)
     Schedule.finalizeSchedule(this);

llvm/test/CodeGen/Hexagon/swp-pragma-disable.ii

@@ -0,0 +1,49 @@
+; RUN: llc -disable-lsr -march=hexagon -enable-pipeliner  \
+; RUN:     -debug-only=pipeliner < %s 2>&1 > /dev/null | FileCheck %s
+; REQUIRES: asserts
+;
+; Test that checks if pipeliner disabled by pragma 
+
+; CHECK: Can not pipeline loop 
+
+; Function Attrs: nounwind
+define void @f0(i32* nocapture %a0, i32 %a1) #0 {
+b0:
+  %v0 = icmp sgt i32 %a1, 1
+  br i1 %v0, label %b1, label %b4
+
+b1:                                               ; preds = %b0
+  %v1 = load i32, i32* %a0, align 4
+  %v2 = add i32 %v1, 10
+  %v3 = getelementptr i32, i32* %a0, i32 1
+  %v4 = add i32 %a1, -1
+  br label %b2
+
+b2:                                               ; preds = %b2, %b1
+  %v5 = phi i32 [ %v12, %b2 ], [ %v4, %b1 ]
+  %v6 = phi i32* [ %v11, %b2 ], [ %v3, %b1 ]
+  %v7 = phi i32 [ %v10, %b2 ], [ %v2, %b1 ]
+  store i32 %v7, i32* %v6, align 4
+  %v8 = add i32 %v7, 10
+  %v9 = getelementptr i32, i32* %v6, i32 -1
+  store i32 %v8, i32* %v9, align 4
+  %v10 = add i32 %v7, 10
+  %v11 = getelementptr i32, i32* %v6, i32 1
+  %v12 = add i32 %v5, -1
+  %v13 = icmp eq i32 %v12, 0
+  br i1 %v13, label %b3, label %b2
+
+b3:                                               ; preds = %b2
+  br label %b4 , !llvm.loop !2
+
+b4:                                               ; preds = %b3, %b0
+  ret void
+}
+
+attributes #0 = { nounwind }
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{!2, !2, i64 0}
+!2 = distinct !{!2, !3}
+!3 = !{!"llvm.loop.pipeline.disable", i1 true}
+

llvm/test/CodeGen/Hexagon/swp-pragma-initiation-interval.ii

@@ -0,0 +1,49 @@
+; RUN: llc -disable-lsr -march=hexagon -enable-pipeliner  \
+; RUN:     -debug-only=pipeliner < %s 2>&1 > /dev/null | FileCheck %s
+; REQUIRES: asserts
+;
+; Test that checks if the II set by pragma was taken by pipeliner.
+
+; CHECK: MII = 2 MAX_II = 2 
+
+; Function Attrs: nounwind
+define void @f0(i32* nocapture %a0, i32 %a1) #0 {
+b0:
+  %v0 = icmp sgt i32 %a1, 1
+  br i1 %v0, label %b1, label %b4
+
+b1:                                               ; preds = %b0
+  %v1 = load i32, i32* %a0, align 4
+  %v2 = add i32 %v1, 10
+  %v3 = getelementptr i32, i32* %a0, i32 1
+  %v4 = add i32 %a1, -1
+  br label %b2
+
+b2:                                               ; preds = %b2, %b1
+  %v5 = phi i32 [ %v12, %b2 ], [ %v4, %b1 ]
+  %v6 = phi i32* [ %v11, %b2 ], [ %v3, %b1 ]
+  %v7 = phi i32 [ %v10, %b2 ], [ %v2, %b1 ]
+  store i32 %v7, i32* %v6, align 4
+  %v8 = add i32 %v7, 10
+  %v9 = getelementptr i32, i32* %v6, i32 -1
+  store i32 %v8, i32* %v9, align 4
+  %v10 = add i32 %v7, 10
+  %v11 = getelementptr i32, i32* %v6, i32 1
+  %v12 = add i32 %v5, -1
+  %v13 = icmp eq i32 %v12, 0
+  br i1 %v13, label %b3, label %b2
+
+b3:                                               ; preds = %b2
+  br label %b4 , !llvm.loop !2
+
+b4:                                               ; preds = %b3, %b0
+  ret void
+}
+
+attributes #0 = { nounwind }
+
+!0 = !{i32 1, !"wchar_size", i32 4}
+!1 = !{!2, !2, i64 0}
+!2 = distinct !{!2, !3}
+!3 = !{!"llvm.loop.pipeline.initiationinterval", i32 2}
+

llvm/test/CodeGen/Hexagon/swp-resmii-1.ll

@@ -3,7 +3,7 @@
 
 ; Test that checks that we compute the correct ResMII for haar.
 
-; CHECK: MII = 4 (rec=1, res=4)
+; CHECK: MII = 4 MAX_II = 14 (rec=1, res=4)
 
 ; Function Attrs: nounwind
 define void @f0(i16* noalias nocapture readonly %a0, i32 %a1, i32 %a2, i32 %a3, i8* noalias nocapture %a4, i32 %a5) #0 {

llvm/test/CodeGen/Hexagon/swp-resmii.ll

@@ -4,7 +4,7 @@
 ;
 ; Test that checks if the ResMII is 1.
 
-; CHECK: MII = 1 (rec=1, res=1)
+; CHECK: MII = 1 MAX_II = 11 (rec=1, res=1)
 
 ; Function Attrs: nounwind
 define void @f0(i32* nocapture %a0, i32 %a1) #0 {