[NewPM][Unswitch] Add option to disable -O3 non-trivial unswitching

[aeubanks]

Summary

Some benchmarks regress with non-trivial unswitching, so add an option
to opt-out of performing non-trivial unswitching while investigating.

[asbirlea]

lgtm.

llvm/lib/Passes/PassBuilder.cpp

static cl::opt<bool> EnableMemProfiler("enable-mem-prof", cl::init(false),
                                        cl::Hidden, cl::ZeroOrMore,
                                        cl::desc("Enable memory profiler"));
 
 static cl::opt<bool> PerformMandatoryInliningsFirst(
     "mandatory-inlining-first", cl::init(true), cl::Hidden, cl::ZeroOrMore,
     cl::desc("Perform mandatory inlinings module-wide, before performing "
              "inlining."));
 
+static cl::opt<bool> EnableO3NonTrivialUnswitching(
+    "enable-npm-O3-nontrivial-unswitch", cl::init(true), cl::Hidden,
+    cl::ZeroOrMore, cl::desc("Enable non-trivial loop unswitching for -O3"));
+
 PipelineTuningOptions::PipelineTuningOptions() {
   LoopInterleaving = true;
   LoopVectorization = true;
   SLPVectorization = false;
   LoopUnrolling = true;
   ForgetAllSCEVInLoopUnroll = ForgetSCEVInLoopUnroll;
   Coroutines = false;
   LicmMssaOptCap = SetLicmMssaOptCap;
PassBuilder::buildFunctionSimplificationPipeline(OptimizationLevel Level,
   LPM1.addPass(LoopInstSimplifyPass());
   LPM1.addPass(LoopSimplifyCFGPass());
 
   // Disable header duplication in loop rotation at -Oz.
   LPM1.addPass(LoopRotatePass(Level != OptimizationLevel::Oz));
   // TODO: Investigate promotion cap for O1.
   LPM1.addPass(LICMPass(PTO.LicmMssaOptCap, PTO.LicmMssaNoAccForPromotionCap));
   LPM1.addPass(
-      SimpleLoopUnswitchPass(/* NonTrivial */ Level == OptimizationLevel::O3));
+      SimpleLoopUnswitchPass(/* NonTrivial */ Level == OptimizationLevel::O3 &&
+                             EnableO3NonTrivialUnswitching));
   LPM2.addPass(LoopIdiomRecognizePass());
   LPM2.addPass(IndVarSimplifyPass());
 
   for (auto &C : LateLoopOptimizationsEPCallbacks)
     C(LPM2, Level);
 
   LPM2.addPass(LoopDeletionPass());
   // Do not enable unrolling in PreLinkThinLTO phase during sample PGO

llvm/test/Transforms/SimpleLoopUnswitch/pipeline.ll

 ; RUN: opt < %s -S -passes="default<O1>" | FileCheck %s -check-prefixes=TRIVIAL,CHECK
 ; RUN: opt < %s -S -passes="default<O2>" | FileCheck %s -check-prefixes=TRIVIAL,CHECK
 ; RUN: opt < %s -S -passes="default<O3>" | FileCheck %s -check-prefixes=NONTRIVIAL,CHECK
+; RUN: opt < %s -S -passes="default<O3>" -enable-npm-O3-nontrivial-unswitch=0 | FileCheck %s -check-prefixes=TRIVIAL,CHECK
 ; RUN: opt < %s -S -passes="default<Os>" | FileCheck %s -check-prefixes=TRIVIAL,CHECK
 ; RUN: opt < %s -S -passes="default<Oz>" | FileCheck %s -check-prefixes=TRIVIAL,CHECK
 
 declare i32 @a()
 declare i32 @b()
 declare i32 @c()
 
 ; TRIVIAL-NOT: loop_begin.us: