[UnifyLoopExits] Fix non-deterministic iteration order

[foad]

Summary

This was causing random minor codegen differences in shaders compiled
with the AMDGPU backend.

[sameerds]

LGTM!

llvm/lib/Transforms/Utils/UnifyLoopExits.cpp

 // is redistributed to all the original exit blocks.
 //
 // Limitation: This assumes that all terminators in the CFG are direct branches
 //             (the "br" instruction). The presence of any other control flow
 //             such as indirectbr, switch or callbr will cause an assert.
 //
 //===----------------------------------------------------------------------===//
 
+#include "llvm/ADT/MapVector.h"
 #include "llvm/Analysis/LoopInfo.h"
 #include "llvm/IR/Dominators.h"
 #include "llvm/InitializePasses.h"
 #include "llvm/Transforms/Utils.h"
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
 
 #define DEBUG_TYPE "unify-loop-exits"
 

 //
 // The use of SSAUpdater seems like overkill for this operation. The location
 // for creating the new PHI is well-known, and also the set of incoming blocks
 // to the new PHI.
 static void restoreSSA(const DominatorTree &DT, const Loop *L,
                        const SetVector<BasicBlock *> &Incoming,
                        BasicBlock *LoopExitBlock) {
   using InstVector = SmallVector<Instruction *, 8>;
-  using IIMap = DenseMap<Instruction *, InstVector>;
+  using IIMap = MapVector<Instruction *, InstVector>;
   IIMap ExternalUsers;
   for (auto BB : L->blocks()) {
     for (auto &I : *BB) {
       for (auto &U : I.uses()) {
         auto UserInst = cast<Instruction>(U.getUser());
         auto UserBlock = UserInst->getParent();
         if (UserBlock == LoopExitBlock)
           continue;