[NewPassManager] Add tuning option: SLPVectorization [NFC].

[asbirlea]

Summary

Mirror tuning option from old pass manager in new pass manager.

[chandlerc]

LGTM

Eric was hoping for some API improvements here as we add more tuning options, but I don't think these need to be sequenced.

[jvesely]

@asbirlea, are you sure this was enabled by default before? (cl::init(true))
I've traced regressions in r600 and amdgcn to this patch.
Both can be fixed by changing the default to false.
While those regressions look like backend bugs, the commit message says NFC.

[asbirlea]

@jvesely: Yes, you are right. D61955 should resolve this.

llvm/trunk/include/llvm/Passes/PassBuilder.h

public:
   /// Tuning option to set loop interleaving on/off. Its default value is that
   /// of the flag: `-interleave-loops`.
   bool LoopInterleaving;
 
   /// Tuning option to enable/disable loop vectorization. Its default value is
   /// that of the flag: `-vectorize-loops`.
   bool LoopVectorization;
 
+  /// Tuning option to enable/disable slp loop vectorization. Its default value
+  /// is that of the flag: `vectorize-slp`.
+  bool SLPVectorization;
+
   /// Tuning option to cap the number of calls to retrive clobbering accesses in
   /// MemorySSA, in LICM.
   unsigned LicmMssaOptCap;
 
   /// Tuning option to disable promotion to scalars in LICM with MemorySSA, if
   /// the number of access is too large.
   unsigned LicmMssaNoAccForPromotionCap;
 };

llvm/trunk/include/llvm/Transforms/Vectorize/SLPVectorizer.h

 /// A private "module" namespace for types and utilities used by this pass.
 /// These are implementation details and should not be used by clients.
 namespace slpvectorizer {
 
 class BoUpSLP;
 
 } // end namespace slpvectorizer
 
+extern cl::opt<bool> RunSLPVectorization;
+
 struct SLPVectorizerPass : public PassInfoMixin<SLPVectorizerPass> {
   using StoreList = SmallVector<StoreInst *, 8>;
   using StoreListMap = MapVector<Value *, StoreList>;
   using WeakTrackingVHList = SmallVector<WeakTrackingVH, 8>;
   using WeakTrackingVHListMap = MapVector<Value *, WeakTrackingVHList>;
 
   ScalarEvolution *SE = nullptr;
   TargetTransformInfo *TTI = nullptr;

llvm/trunk/lib/Passes/PassBuilder.cpp

 // profile loading.
 static cl::opt<bool>
     EnableCHR("enable-chr-npm", cl::init(true), cl::Hidden,
               cl::desc("Enable control height reduction optimization (CHR)"));
 
 PipelineTuningOptions::PipelineTuningOptions() {
   LoopInterleaving = EnableLoopInterleaving;
   LoopVectorization = EnableLoopVectorization;
+  SLPVectorization = RunSLPVectorization;
   LicmMssaOptCap = SetLicmMssaOptCap;
   LicmMssaNoAccForPromotionCap = SetLicmMssaNoAccForPromotionCap;
 }
 
 extern cl::opt<bool> EnableHotColdSplit;
 extern cl::opt<bool> EnableOrderFileInstrumentation;
 
 extern cl::opt<bool> FlattenedProfileUsed;
ModulePassManager PassBuilder::buildModuleOptimizationPipeline(
   // before SLP vectorization.
   OptimizePM.addPass(SimplifyCFGPass(SimplifyCFGOptions().
                                      forwardSwitchCondToPhi(true).
                                      convertSwitchToLookupTable(true).
                                      needCanonicalLoops(false).
                                      sinkCommonInsts(true)));
 
   // Optimize parallel scalar instruction chains into SIMD instructions.
+  if (PTO.SLPVectorization)
     OptimizePM.addPass(SLPVectorizerPass());
 
   OptimizePM.addPass(InstCombinePass());
 
   // Unroll small loops to hide loop backedge latency and saturate any parallel
   // execution resources of an out-of-order processor. We also then need to
   // clean up redundancies and loop invariant code.
   // FIXME: It would be really good to use a loop-integrated instruction
   // combiner for cleanup here so that the unrolling and LICM can be pipelined

llvm/trunk/lib/Transforms/IPO/PassManagerBuilder.cpp

 #include "llvm/Transforms/Scalar.h"
 #include "llvm/Transforms/Scalar/GVN.h"
 #include "llvm/Transforms/Scalar/InstSimplifyPass.h"
 #include "llvm/Transforms/Scalar/LICM.h"
 #include "llvm/Transforms/Scalar/SimpleLoopUnswitch.h"
 #include "llvm/Transforms/Utils.h"
 #include "llvm/Transforms/Vectorize.h"
 #include "llvm/Transforms/Vectorize/LoopVectorize.h"
+#include "llvm/Transforms/Vectorize/SLPVectorizer.h"
 
 using namespace llvm;
 
 static cl::opt<bool>
     RunPartialInlining("enable-partial-inlining", cl::init(false), cl::Hidden,
                        cl::ZeroOrMore, cl::desc("Run Partial inlinining pass"));
 
 static cl::opt<bool>
-RunSLPVectorization("vectorize-slp", cl::Hidden,
-                    cl::desc("Run the SLP vectorization passes"));
-
-static cl::opt<bool>
 UseGVNAfterVectorization("use-gvn-after-vectorization",
   cl::init(false), cl::Hidden,
   cl::desc("Run GVN instead of Early CSE after vectorization passes"));
 
 static cl::opt<bool> ExtraVectorizerPasses(
     "extra-vectorizer-passes", cl::init(false), cl::Hidden,
     cl::desc("Run cleanup optimization passes after vectorization."));
 

llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp

 using namespace llvm::PatternMatch;
 using namespace slpvectorizer;
 
 #define SV_NAME "slp-vectorizer"
 #define DEBUG_TYPE "SLP"
 
 STATISTIC(NumVectorInstructions, "Number of vector instructions generated");
 
+cl::opt<bool>
+    llvm::RunSLPVectorization("vectorize-slp", cl::init(true), cl::Hidden,
+                              cl::desc("Run the SLP vectorization passes"));
+
 static cl::opt<int>
     SLPCostThreshold("slp-threshold", cl::init(0), cl::Hidden,
                      cl::desc("Only vectorize if you gain more than this "
                               "number "));
 
 static cl::opt<bool>
 ShouldVectorizeHor("slp-vectorize-hor", cl::init(true), cl::Hidden,
                    cl::desc("Attempt to vectorize horizontal reductions"));