[Inliner] Attribute callsites with inline remarks

Summary:
Sometimes reading an output *.ll file it is not easy to understand why some callsites are not inlined. We can read output of inline remarks (option --pass-remarks-missed=inline) and try correlating its messages with the callsites.

An easier way proposed by this patch is to add to every callsite processed by Inliner an attribute with the latest message that describes the cause of not inlining this callsite. The attribute is called //inline-remark//. By default this feature is off. It can be switched on by the option //-inline-remark-attribute//.

For example in the provided test the result method //@test1// has two callsites //@bar// and inline remarks report different inlining missed reasons:
  remark: <unknown>:0:0: bar not inlined into test1 because too costly to inline (cost=-5, threshold=-6)
  remark: <unknown>:0:0: bar not inlined into test1 because it should never be inlined (cost=never): recursive

It is not clear which remark correspond to which callsite. With the inline remark attribute enabled we get the reasons attached to their callsites:
  define void @test1() {
    call void @bar(i1 true) #0
    call void @bar(i1 false) #2
    ret void
  }
  attributes #0 = { "inline-remark"="(cost=-5, threshold=-6)" }
  ..
  attributes #2 = { "inline-remark"="(cost=never): recursive" }

Patch by: yrouban (Yevgeny Rouban)

Reviewers: xbolva00, tejohnson, apilipenko

Reviewed By: xbolva00, tejohnson

Subscribers: eraman, llvm-commits

Differential Revision: https://reviews.llvm.org/D50435

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@340834 91177308-0d34-0410-b5e6-96231b3b80d8

Author: davidbolvansky

lib/Transforms/IPO/Inliner.cpp

@@ -113,6 +113,14 @@ static cl::opt<InlinerFunctionImportStatsOpts> InlinerFunctionImportStats(
                           "printing of statistics for each inlined function")),
     cl::Hidden, cl::desc("Enable inliner stats for imported functions"));
 
+/// Flag to add inline messages as callsite attributes 'inline-remark'.
+static cl::opt<bool>
+    InlineRemarkAttribute("inline-remark-attribute", cl::init(false),
+                          cl::Hidden,
+                          cl::desc("Enable adding inline-remark attribute to"
+                                   " callsites processed by inliner but decided"
+                                   " to be not inlined"));
+
 LegacyInlinerBase::LegacyInlinerBase(char &ID) : CallGraphSCCPass(ID) {}
 
 LegacyInlinerBase::LegacyInlinerBase(char &ID, bool InsertLifetime)
@@ -264,7 +272,7 @@ static void mergeInlinedArrayAllocas(
 /// available from other functions inlined into the caller.  If we are able to
 /// inline this call site we attempt to reuse already available allocas or add
 /// any new allocas to the set if not possible.
-static bool InlineCallIfPossible(
+static InlineResult InlineCallIfPossible(
     CallSite CS, InlineFunctionInfo &IFI,
     InlinedArrayAllocasTy &InlinedArrayAllocas, int InlineHistory,
     bool InsertLifetime, function_ref<AAResults &(Function &)> &AARGetter,
@@ -367,12 +375,10 @@ shouldBeDeferred(Function *Caller, CallSite CS, InlineCost IC,
   return false;
 }
 
-#ifndef NDEBUG
 static std::basic_ostream<char> &operator<<(std::basic_ostream<char> &R,
                                             const ore::NV &Arg) {
   return R << Arg.Val;
 }
-#endif
 
 template <class RemarkT>
 RemarkT &operator<<(RemarkT &&R, const InlineCost &IC) {
@@ -390,13 +396,11 @@ RemarkT &operator<<(RemarkT &&R, const InlineCost &IC) {
   return R;
 }
 
-#ifndef NDEBUG
 static std::string inlineCostStr(const InlineCost &IC) {
   std::stringstream Remark;
   Remark << IC;
   return Remark.str();
 }
-#endif
 
 /// Return the cost only if the inliner should attempt to inline at the given
 /// CallSite. If we return the cost, we will emit an optimisation remark later
@@ -502,6 +506,14 @@ static void emit_inlined_into(OptimizationRemarkEmitter &ORE, DebugLoc &DLoc,
   });
 }
 
+static void setInlineRemark(CallSite &CS, StringRef message) {
+  if (!InlineRemarkAttribute)
+    return;
+
+  Attribute attr = Attribute::get(CS->getContext(), "inline-remark", message);
+  CS.addAttribute(AttributeList::FunctionIndex, attr);
+}
+
 static bool
 inlineCallsImpl(CallGraphSCC &SCC, CallGraph &CG,
                 std::function<AssumptionCache &(Function &)> GetAssumptionCache,
@@ -551,6 +563,7 @@ inlineCallsImpl(CallGraphSCC &SCC, CallGraph &CG,
           if (Callee->isDeclaration()) {
             using namespace ore;
 
+            setInlineRemark(CS, "unavailable definition");
             ORE.emit([&]() {
               return OptimizationRemarkMissed(DEBUG_TYPE, "NoDefinition", &I)
                      << NV("Callee", Callee) << " will not be inlined into "
@@ -614,8 +627,10 @@ inlineCallsImpl(CallGraphSCC &SCC, CallGraph &CG,
         // infinitely inline.
         InlineHistoryID = CallSites[CSi].second;
         if (InlineHistoryID != -1 &&
-            InlineHistoryIncludes(Callee, InlineHistoryID, InlineHistory))
+            InlineHistoryIncludes(Callee, InlineHistoryID, InlineHistory)) {
+          setInlineRemark(CS, "recursive");
           continue;
+        }
       }
 
       // FIXME for new PM: because of the old PM we currently generate ORE and
@@ -626,7 +641,15 @@ inlineCallsImpl(CallGraphSCC &SCC, CallGraph &CG,
       Optional<InlineCost> OIC = shouldInline(CS, GetInlineCost, ORE);
       // If the policy determines that we should inline this function,
       // delete the call instead.
-      if (!OIC || !*OIC) {
+      if (!OIC.hasValue()) {
+        setInlineRemark(CS, "deferred");
+        continue;
+      }
+
+      if (!OIC.getValue()) {
+        // shouldInline() call returned a negative inline cost that explains
+        // why this callsite should not be inlined.
+        setInlineRemark(CS, inlineCostStr(*OIC));
         continue;
       }
 
@@ -637,6 +660,7 @@ inlineCallsImpl(CallGraphSCC &SCC, CallGraph &CG,
       if (IsTriviallyDead) {
         LLVM_DEBUG(dbgs() << "    -> Deleting dead call: " << *Instr << "\n");
         // Update the call graph by deleting the edge from Callee to Caller.
+        setInlineRemark(CS, "trivially dead");
         CG[Caller]->removeCallEdgeFor(CS);
         Instr->eraseFromParent();
         ++NumCallsDeleted;
@@ -652,6 +676,7 @@ inlineCallsImpl(CallGraphSCC &SCC, CallGraph &CG,
             CS, InlineInfo, InlinedArrayAllocas, InlineHistoryID,
             InsertLifetime, AARGetter, ImportedFunctionsStats);
         if (!IR) {
+          setInlineRemark(CS, std::string(IR) + "; " + inlineCostStr(*OIC));
           ORE.emit([&]() {
             return OptimizationRemarkMissed(DEBUG_TYPE, "NotInlined", DLoc,
                                             Block)
@@ -894,6 +919,7 @@ PreservedAnalyses InlinerPass::run(LazyCallGraph::SCC &InitialC,
             Calls.push_back({CS, -1});
           else if (!isa<IntrinsicInst>(I)) {
             using namespace ore;
+            setInlineRemark(CS, "unavailable definition");
             ORE.emit([&]() {
               return OptimizationRemarkMissed(DEBUG_TYPE, "NoDefinition", &I)
                      << NV("Callee", Callee) << " will not be inlined into "
@@ -937,8 +963,10 @@ PreservedAnalyses InlinerPass::run(LazyCallGraph::SCC &InitialC,
     LazyCallGraph::Node &N = *CG.lookup(F);
     if (CG.lookupSCC(N) != C)
       continue;
-    if (F.hasFnAttribute(Attribute::OptimizeNone))
+    if (F.hasFnAttribute(Attribute::OptimizeNone)) {
+      setInlineRemark(Calls[i].first, "optnone attribute");
       continue;
+    }
 
     LLVM_DEBUG(dbgs() << "Inlining calls in: " << F.getName() << "\n");
 
@@ -982,8 +1010,10 @@ PreservedAnalyses InlinerPass::run(LazyCallGraph::SCC &InitialC,
       Function &Callee = *CS.getCalledFunction();
 
       if (InlineHistoryID != -1 &&
-          InlineHistoryIncludes(&Callee, InlineHistoryID, InlineHistory))
+          InlineHistoryIncludes(&Callee, InlineHistoryID, InlineHistory)) {
+        setInlineRemark(CS, "recursive");
         continue;
+      }
 
       // Check if this inlining may repeat breaking an SCC apart that has
       // already been split once before. In that case, inlining here may
@@ -995,13 +1025,23 @@ PreservedAnalyses InlinerPass::run(LazyCallGraph::SCC &InitialC,
         LLVM_DEBUG(dbgs() << "Skipping inlining internal SCC edge from a node "
                              "previously split out of this SCC by inlining: "
                           << F.getName() << " -> " << Callee.getName() << "\n");
+        setInlineRemark(CS, "recursive SCC split");
         continue;
       }
 
       Optional<InlineCost> OIC = shouldInline(CS, GetInlineCost, ORE);
       // Check whether we want to inline this callsite.
-      if (!OIC || !*OIC)
+      if (!OIC.hasValue()) {
+        setInlineRemark(CS, "deferred");
         continue;
+      }
+
+      if (!OIC.getValue()) {
+        // shouldInline() call returned a negative inline cost that explains
+        // why this callsite should not be inlined.
+        setInlineRemark(CS, inlineCostStr(*OIC));
+        continue;
+      }
 
       // Setup the data structure used to plumb customization into the
       // `InlineFunction` routine.
@@ -1018,6 +1058,7 @@ PreservedAnalyses InlinerPass::run(LazyCallGraph::SCC &InitialC,
 
       InlineResult IR = InlineFunction(CS, IFI);
       if (!IR) {
+        setInlineRemark(CS, std::string(IR) + "; " + inlineCostStr(*OIC));
         ORE.emit([&]() {
           return OptimizationRemarkMissed(DEBUG_TYPE, "NotInlined", DLoc, Block)
                  << NV("Callee", &Callee) << " will not be inlined into "

test/Transforms/Inline/inline-remark.ll

@@ -0,0 +1,48 @@
+; RUN: opt < %s -inline -inline-remark-attribute --inline-threshold=-2 -S | FileCheck %s
+
+; Test that the inliner adds inline remark attributes to non-inlined callsites.
+
+define void @foo() {
+  call void @bar(i1 true)
+  ret void
+}
+
+define void @bar(i1 %p) {
+  br i1 %p, label %bb1, label %bb2
+
+bb1:
+  call void @foo()
+  ret void
+
+bb2:
+  call void @bar(i1 true)
+  ret void
+}
+
+;; Test 1 - Add different inline remarks to similar callsites.
+define void @test1() {
+; CHECK-LABEL: @test1
+; CHECK-NEXT: call void @bar(i1 true) [[ATTR1:#[0-9]+]]
+; CHECK-NEXT: call void @bar(i1 false) [[ATTR2:#[0-9]+]]
+  call void @bar(i1 true)
+  call void @bar(i1 false)
+  ret void
+}
+
+define void @noop() {
+  ret void
+}
+
+;; Test 2 - Printed InlineResult messages are followed by InlineCost.
+define void @test2(i8*) {
+; CHECK-LABEL: @test2
+; CHECK-NEXT: call void @noop() [[ATTR3:#[0-9]+]] [ "CUSTOM_OPERAND_BUNDLE"() ]
+; CHECK-NEXT: ret void
+  call void @noop() ; extepected to be inlined
+  call void @noop() [ "CUSTOM_OPERAND_BUNDLE"() ] ; cannot be inlined because of unsupported operand bundle
+  ret void
+}
+
+; CHECK: attributes [[ATTR1]] = { "inline-remark"="(cost=-5, threshold=-6)" }
+; CHECK: attributes [[ATTR2]] = { "inline-remark"="(cost=never): recursive" }
+; CHECK: attributes [[ATTR3]] = { "inline-remark"="unsupported operand bundle; (cost={{.*}}, threshold={{.*}})" }