[Inliner] Add another way to compute full inline cost.

[eraman]

Summary

Full inline cost is computed when -inline-cost-full is true or ORE is
non-null. This patch adds another way to compute full inline cost by
adding a field to InlineParams. This will be used by SampleProfileLoader
to check legality of inlining a callee that it wants to inline.

[haicheng]

LGTM

include/llvm/Analysis/InlineCost.h

struct InlineParams {
   Optional<int> HotCallSiteThreshold;
 
   /// Threshold to use when the callsite is considered hot relative to function
   /// entry.
   Optional<int> LocallyHotCallSiteThreshold;
 
   /// Threshold to use when the callsite is considered cold.
   Optional<int> ColdCallSiteThreshold;
+
+  /// Compute inline cost even when the cost has exceeded the threshold.
+  Optional<bool> ComputeFullInlineCost;
 };
 
 /// Generate the parameters to tune the inline cost analysis based only on the
 /// commandline options.
 InlineParams getInlineParams();
 
 /// Generate the parameters to tune the inline cost analysis based on command
 /// line options. If -inline-threshold option is not explicitly passed,

lib/Analysis/InlineCost.cpp

cl::desc("Maxmimum block frequency, expressed as a percentage of caller's "
              "profile information."));
 
 static cl::opt<int> HotCallSiteRelFreq(
     "hot-callsite-rel-freq", cl::Hidden, cl::init(60), cl::ZeroOrMore,
     cl::desc("Minimum block frequency, expressed as a multiple of caller's "
              "entry frequency, for a callsite to be hot in the absence of "
              "profile information."));
 
-static cl::opt<bool> ComputeFullInlineCost(
+static cl::opt<bool> OptComputeFullInlineCost(
     "inline-cost-full", cl::Hidden, cl::init(false),
     cl::desc("Compute the full inline cost of a call site even when the cost "
              "exceeds the threshold."));
 
 namespace {
 
 class CallAnalyzer : public InstVisitor<CallAnalyzer, bool> {
   typedef InstVisitor<CallAnalyzer, bool> Base;
class CallAnalyzer : public InstVisitor<CallAnalyzer, bool> {
   /// easily cacheable. Instead, use the cover function paramHasAttr.
   CallSite CandidateCS;
 
   /// Tunable parameters that control the analysis.
   const InlineParams &Params;
 
   int Threshold;
   int Cost;
+  bool ComputeFullInlineCost;
 
   bool IsCallerRecursive;
   bool IsRecursiveCall;
   bool ExposesReturnsTwice;
   bool HasDynamicAlloca;
   bool ContainsNoDuplicateCall;
   bool HasReturn;
   bool HasIndirectBr;
public:
   CallAnalyzer(const TargetTransformInfo &TTI,
                std::function<AssumptionCache &(Function &)> &GetAssumptionCache,
                Optional<function_ref<BlockFrequencyInfo &(Function &)>> &GetBFI,
                ProfileSummaryInfo *PSI, OptimizationRemarkEmitter *ORE,
                Function &Callee, CallSite CSArg, const InlineParams &Params)
       : TTI(TTI), GetAssumptionCache(GetAssumptionCache), GetBFI(GetBFI),
         PSI(PSI), F(Callee), DL(F.getParent()->getDataLayout()), ORE(ORE),
         CandidateCS(CSArg), Params(Params), Threshold(Params.DefaultThreshold),
-        Cost(0), IsCallerRecursive(false), IsRecursiveCall(false),
+        Cost(0), ComputeFullInlineCost(OptComputeFullInlineCost ||
+                                       Params.ComputeFullInlineCost || ORE),
+        IsCallerRecursive(false), IsRecursiveCall(false),
         ExposesReturnsTwice(false), HasDynamicAlloca(false),
         ContainsNoDuplicateCall(false), HasReturn(false), HasIndirectBr(false),
         HasFrameEscape(false), AllocatedSize(0), NumInstructions(0),
         NumVectorInstructions(0), VectorBonus(0), SingleBBBonus(0),
         NumConstantArgs(0), NumConstantOffsetPtrArgs(0), NumAllocaArgs(0),
         NumConstantPtrCmps(0), NumConstantPtrDiffs(0),
         NumInstructionsSimplified(0), SROACostSavings(0),
         SROACostSavingsLost(0) {}
InlineCost llvm::getInlineCost(
   // Don't inline functions which can be interposed at link-time.  Don't inline
   // functions marked noinline or call sites marked noinline.
   // Note: inlining non-exact non-interposable functions is fine, since we know
   // we have *a* correct implementation of the source level function.
   if (Callee->isInterposable() || Callee->hasFnAttribute(Attribute::NoInline) ||
       CS.isNoInline())
     return llvm::InlineCost::getNever();
 
-  if (ORE)
-    ComputeFullInlineCost = true;
-
   DEBUG(llvm::dbgs() << "      Analyzing call of " << Callee->getName()
                      << "... (caller:" << Caller->getName() << ")\n");
 
   CallAnalyzer CA(CalleeTTI, GetAssumptionCache, GetBFI, PSI, ORE, *Callee, CS,
                   Params);
   bool ShouldInline = CA.analyzeCall(CS);
 
   DEBUG(CA.dump());