[AMDGPU] Fix bug with tracking processed blocks in SIInsertWaitcnts

[scott.linder]

Summary

BlockWaitcntProcessedSet was not being cleared between calls, so it was producing incorrect counts in cases where MBB addresses happened to coincide across multiple calls.

I was not able to reproduce this consistently (depends on non-deterministic addresses), so I could not include a test.

[msearles]

LGTM

lib/Target/AMDGPU/SIInsertWaitcnts.cpp

bool SIInsertWaitcnts::runOnMachineFunction(MachineFunction &MF) {
   RegisterEncoding.SGPR0 = TRI->getEncodingValue(AMDGPU::SGPR0);
   RegisterEncoding.SGPRL =
       RegisterEncoding.SGPR0 + HardwareLimits.NumSGPRsMax - 1;
 
   TrackedWaitcntSet.clear();
   BlockVisitedSet.clear();
   VCCZBugHandledSet.clear();
   LoopWaitcntDataMap.clear();
+  BlockWaitcntProcessedSet.clear();
 
   // Walk over the blocks in reverse post-dominator order, inserting
   // s_waitcnt where needed.
   ReversePostOrderTraversal<MachineFunction *> RPOT(&MF);
   bool Modified = false;
   for (ReversePostOrderTraversal<MachineFunction *>::rpo_iterator
            I = RPOT.begin(),
            E = RPOT.end(), J = RPOT.begin();