AMDGPU: fix missing s_waitcnt

[timcorringham]

Summary

The pass that inserts s_waitcnt instructions where needed propagated
info used to track dependencies for each block by iterating over the
predecessor blocks. The iteration was terminated when a predecessor
that had not yet been processed was encountered. Any info in blocks
later in the list was therefore not processed, leading to the
possiblility of a required s_waitcnt not being inserted.

The fix is simply to change the "break" to "continue" for the
relevant loops, so that all visited blocks are processed. This
is likely what was intended when the code was written.

There is no test case provided for this fix because:

1. the only example that reproduces this is large and resistant to

being reduced

2. the change is trivial

[msearles]

I'm OK with this change, however, I have a different fix for nearly the same problem. See https://reviews.llvm.org/D40183 . It addresses the situation where not all predecessors have been processed nor will they be; in that case, you have incomplete information, so the pass is modified to conservatively insert a s_waitcnt 0. Feel free to merge your change and I'll adjust my patch as necessary.

lib/Target/AMDGPU/SIInsertWaitcnts.cpp

void SIInsertWaitcnts::mergeInputScoreBrackets(MachineBasicBlock &Block) {
 
   // See if there are any uninitialized predecessors. If so, emit an
   // s_waitcnt 0 at the beginning of the block.
   for (MachineBasicBlock *pred : Block.predecessors()) {
     BlockWaitcntBrackets *PredScoreBrackets =
         BlockWaitcntBracketsMap[pred].get();
     bool Visited = BlockVisitedSet.find(pred) != BlockVisitedSet.end();
     if (!Visited || PredScoreBrackets->getWaitAtBeginning()) {
-      break;
+      continue;
     }
     for (enum InstCounterType T = VM_CNT; T < NUM_INST_CNTS;
          T = (enum InstCounterType)(T + 1)) {
       int span =
           PredScoreBrackets->getScoreUB(T) - PredScoreBrackets->getScoreLB(T);
       MaxPending[T] = std::max(MaxPending[T], span);
       span =
           PredScoreBrackets->pendingFlat(T) - PredScoreBrackets->getScoreLB(T);
void SIInsertWaitcnts::mergeInputScoreBrackets(MachineBasicBlock &Block) {
   }
 
   // Special handling for GDS_GPR_LOCK and EXP_GPR_LOCK.
   for (MachineBasicBlock *Pred : Block.predecessors()) {
     BlockWaitcntBrackets *PredScoreBrackets =
         BlockWaitcntBracketsMap[Pred].get();
     bool Visited = BlockVisitedSet.find(Pred) != BlockVisitedSet.end();
     if (!Visited || PredScoreBrackets->getWaitAtBeginning()) {
-      break;
+      continue;
     }
 
     int GDSSpan = PredScoreBrackets->getEventUB(GDS_GPR_LOCK) -
                   PredScoreBrackets->getScoreLB(EXP_CNT);
     MaxPending[EXP_CNT] = std::max(MaxPending[EXP_CNT], GDSSpan);
     int EXPSpan = PredScoreBrackets->getEventUB(EXP_GPR_LOCK) -
                   PredScoreBrackets->getScoreLB(EXP_CNT);
     MaxPending[EXP_CNT] = std::max(MaxPending[EXP_CNT], EXPSpan);
for (enum InstCounterType T = VM_CNT; T < NUM_INST_CNTS;
     ScoreBrackets->setLastFlat(T, MaxFlat[T]);
   }
 
   ScoreBrackets->setMixedExpTypes(MixedExpTypes);
 
   // Set the register scoreboard.
   for (MachineBasicBlock *Pred : Block.predecessors()) {
     if (BlockVisitedSet.find(Pred) == BlockVisitedSet.end()) {
-      break;
+      continue;
     }
 
     BlockWaitcntBrackets *PredScoreBrackets =
         BlockWaitcntBracketsMap[Pred].get();
 
     // Now merge the gpr_reg_score information
     for (enum InstCounterType T = VM_CNT; T < NUM_INST_CNTS;
          T = (enum InstCounterType)(T + 1)) {
if (Block.succ_empty() && !KillWaitBrackets.empty()) {
     }
   }
 
   // Special case handling of GDS_GPR_LOCK and EXP_GPR_LOCK. Merge this for the
   // sequencing predecessors, because changes to EXEC require waitcnts due to
   // the delayed nature of these operations.
   for (MachineBasicBlock *Pred : Block.predecessors()) {
     if (BlockVisitedSet.find(Pred) == BlockVisitedSet.end()) {
-      break;
+      continue;
     }
 
     BlockWaitcntBrackets *PredScoreBrackets =
         BlockWaitcntBracketsMap[Pred].get();
 
     int pred_gds_ub = PredScoreBrackets->getEventUB(GDS_GPR_LOCK);
     if (pred_gds_ub > PredScoreBrackets->getScoreLB(EXP_CNT)) {
       int new_gds_ub = MaxPending[EXP_CNT] + pred_gds_ub -