[CSSPGO] Turn on ext-tsp by default for CSSPGO.

[hoy]

Summary

I'm seeing ext-tsp helps CSSPGO for our intern large benchmarks so I'm turning on it for CSSPGO. For non-CS AutoFDO, ext-tsp doesn't seem to help, probably because of lower profile counts quality.

[wenlei]

lgtm, thanks

llvm/lib/CodeGen/MachineBlockPlacement.cpp

 // Heuristic for triangle chains.
 static cl::opt<unsigned> TriangleChainCount(
     "triangle-chain-count",
     cl::desc("Number of triangle-shaped-CFG's that need to be in a row for the "
              "triangle tail duplication heuristic to kick in. 0 to disable."),
     cl::init(2),
     cl::Hidden);
 
-static cl::opt<bool> EnableExtTspBlockPlacement(
-    "enable-ext-tsp-block-placement", cl::Hidden, cl::init(false),
-    cl::desc("Enable machine block placement based on the ext-tsp model, "
-             "optimizing I-cache utilization."));
+extern cl::opt<bool> EnableExtTspBlockPlacement;
 
 namespace llvm {
 extern cl::opt<unsigned> StaticLikelyProb;
 extern cl::opt<unsigned> ProfileLikelyProb;
 
 // Internal option used to control BFI display only after MBP pass.
 // Defined in CodeGen/MachineBlockFrequencyInfo.cpp:
 // -view-block-layout-with-bfi=

llvm/lib/Transforms/IPO/SampleProfile.cpp

MaxNumPromotions("sample-profile-icp-max-prom", cl::init(3), cl::Hidden,
                      cl::ZeroOrMore,
                      cl::desc("Max number of promotions for a single indirect "
                               "call callsite in sample profile loader"));
 
 static cl::opt<bool> OverwriteExistingWeights(
     "overwrite-existing-weights", cl::Hidden, cl::init(false),
     cl::desc("Ignore existing branch weights on IR and always overwrite."));
 
+extern cl::opt<bool> EnableExtTspBlockPlacement;
+
 namespace {
 
 using BlockWeightMap = DenseMap<const BasicBlock *, uint64_t>;
 using EquivalenceClassMap = DenseMap<const BasicBlock *, const BasicBlock *>;
 using Edge = std::pair<const BasicBlock *, const BasicBlock *>;
 using EdgeWeightMap = DenseMap<Edge, uint64_t>;
 using BlockEdgeMap =
     DenseMap<const BasicBlock *, SmallVector<const BasicBlock *, 8>>;
if (Reader->profileIsCSFlat() || Reader->profileIsCSNested()) {
 
     // Enable iterative-BFI by default for CSSPGO.
     if (!UseIterativeBFIInference.getNumOccurrences())
       UseIterativeBFIInference = true;
     // Enable Profi by default for CSSPGO.
     if (!SampleProfileUseProfi.getNumOccurrences())
       SampleProfileUseProfi = true;
 
+    // Enable EXT-TSP block layout for CSSPGO.
+    if (!EnableExtTspBlockPlacement.getNumOccurrences())
+      EnableExtTspBlockPlacement = true;
+
     if (FunctionSamples::ProfileIsCSFlat) {
       // Tracker for profiles under different context
       ContextTracker = std::make_unique<SampleContextTracker>(
           Reader->getProfiles(), &GUIDToFuncNameMap);
     }
   }
 
   // Load pseudo probe descriptors for probe-based function samples.

llvm/lib/Transforms/Utils/CodeLayout.cpp

 
 #include "llvm/Transforms/Utils/CodeLayout.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
 
 using namespace llvm;
 #define DEBUG_TYPE "code-layout"
 
+cl::opt<bool> EnableExtTspBlockPlacement(
+    "enable-ext-tsp-block-placement", cl::Hidden, cl::init(false),
+    cl::desc("Enable machine block placement based on the ext-tsp model, "
+             "optimizing I-cache utilization."));
+
 // Algorithm-specific constants. The values are tuned for the best performance
 // of large-scale front-end bound binaries.
 static cl::opt<double>
     ForwardWeight("ext-tsp-forward-weight", cl::Hidden, cl::init(0.1),
                   cl::desc("The weight of forward jumps for ExtTSP value"));
 
 static cl::opt<double>
     BackwardWeight("ext-tsp-backward-weight", cl::Hidden, cl::init(0.1),