[Coro] Use DebugInfoCache to speed up cloning in CoroSplitPass

llvm/include/llvm/Transforms/Coroutines/ABI.h

@@ -15,6 +15,7 @@
 #ifndef LLVM_TRANSFORMS_COROUTINES_ABI_H
 #define LLVM_TRANSFORMS_COROUTINES_ABI_H
 
+#include "llvm/Analysis/DebugInfoCache.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Transforms/Coroutines/CoroShape.h"
 #include "llvm/Transforms/Coroutines/MaterializationUtils.h"
@@ -53,7 +54,8 @@ class BaseABI {
   // Perform the function splitting according to the ABI.
   virtual void splitCoroutine(Function &F, coro::Shape &Shape,
                               SmallVectorImpl<Function *> &Clones,
-                              TargetTransformInfo &TTI) = 0;
+                              TargetTransformInfo &TTI,
+                              const DebugInfoCache *DICache) = 0;
 
   Function &F;
   coro::Shape &Shape;
@@ -73,7 +75,8 @@ class SwitchABI : public BaseABI {
 
   void splitCoroutine(Function &F, coro::Shape &Shape,
                       SmallVectorImpl<Function *> &Clones,
-                      TargetTransformInfo &TTI) override;
+                      TargetTransformInfo &TTI,
+                      const DebugInfoCache *DICache) override;
 };
 
 class AsyncABI : public BaseABI {
@@ -86,7 +89,8 @@ class AsyncABI : public BaseABI {
 
   void splitCoroutine(Function &F, coro::Shape &Shape,
                       SmallVectorImpl<Function *> &Clones,
-                      TargetTransformInfo &TTI) override;
+                      TargetTransformInfo &TTI,
+                      const DebugInfoCache *DICache) override;
 };
 
 class AnyRetconABI : public BaseABI {
@@ -99,7 +103,8 @@ class AnyRetconABI : public BaseABI {
 
   void splitCoroutine(Function &F, coro::Shape &Shape,
                       SmallVectorImpl<Function *> &Clones,
-                      TargetTransformInfo &TTI) override;
+                      TargetTransformInfo &TTI,
+                      const DebugInfoCache *DICache) override;
 };
 
 } // end namespace coro

llvm/lib/Analysis/CGSCCPassManager.cpp

@@ -14,6 +14,7 @@
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/iterator_range.h"
+#include "llvm/Analysis/DebugInfoCache.h"
 #include "llvm/Analysis/LazyCallGraph.h"
 #include "llvm/IR/Constant.h"
 #include "llvm/IR/InstIterator.h"
@@ -139,6 +140,11 @@ ModuleToPostOrderCGSCCPassAdaptor::run(Module &M, ModuleAnalysisManager &AM) {
   // Get the call graph for this module.
   LazyCallGraph &CG = AM.getResult<LazyCallGraphAnalysis>(M);
 
+  // Prime DebugInfoCache.
+  // TODO: Currently, the only user is CoroSplitPass. Consider running
+  // conditionally.
+  AM.getResult<DebugInfoCacheAnalysis>(M);
+
   // Get Function analysis manager from its proxy.
   FunctionAnalysisManager &FAM =
       AM.getCachedResult<FunctionAnalysisManagerModuleProxy>(M)->getManager();
@@ -350,6 +356,7 @@ ModuleToPostOrderCGSCCPassAdaptor::run(Module &M, ModuleAnalysisManager &AM) {
   // analysis proxies by handling them above and in any nested pass managers.
   PA.preserveSet<AllAnalysesOn<LazyCallGraph::SCC>>();
   PA.preserve<LazyCallGraphAnalysis>();
+  PA.preserve<DebugInfoCacheAnalysis>();
   PA.preserve<CGSCCAnalysisManagerModuleProxy>();
   PA.preserve<FunctionAnalysisManagerModuleProxy>();
   return PA;

llvm/lib/Transforms/Coroutines/CoroSplit.cpp

@@ -32,6 +32,7 @@
 #include "llvm/Analysis/CFG.h"
 #include "llvm/Analysis/CallGraph.h"
 #include "llvm/Analysis/ConstantFolding.h"
+#include "llvm/Analysis/DebugInfoCache.h"
 #include "llvm/Analysis/LazyCallGraph.h"
 #include "llvm/Analysis/OptimizationRemarkEmitter.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
@@ -79,15 +80,38 @@ using namespace llvm;
 #define DEBUG_TYPE "coro-split"
 
 namespace {
+const DebugInfoFinder *cachedDIFinder(Function &F,
+                                      const DebugInfoCache *DICache) {
+  if (!DICache)
+    return nullptr;
+
+  auto *SP = F.getSubprogram();
+  auto *CU = SP ? SP->getUnit() : nullptr;
+  if (!CU)
+    return nullptr;
+
+  if (auto Found = DICache->Result.find(CU); Found != DICache->Result.end())
+    return &Found->getSecond();
+
+  return nullptr;
+}
+
 /// Collect (a known) subset of global debug info metadata potentially used by
 /// the function \p F.
 ///
 /// This metadata set can be used to avoid cloning debug info not owned by \p F
 /// and is shared among all potential clones \p F.
-MetadataSetTy collectCommonDebugInfo(Function &F) {
+MetadataSetTy collectCommonDebugInfo(Function &F,
+                                     const DebugInfoCache *DICache) {
   TimeTraceScope FunctionScope("CollectCommonDebugInfo");
 
   DebugInfoFinder DIFinder;
+
+  // Copy DIFinder from cache which is primed on F's compile unit when available
+  auto *PrimedDIFinder = cachedDIFinder(F, DICache);
+  if (PrimedDIFinder)
+    DIFinder = *PrimedDIFinder;
+
   DISubprogram *SPClonedWithinModule = CollectDebugInfoForCloning(
       F, CloneFunctionChangeType::LocalChangesOnly, DIFinder);
 
@@ -1393,10 +1417,10 @@ namespace {
 struct SwitchCoroutineSplitter {
   static void split(Function &F, coro::Shape &Shape,
                     SmallVectorImpl<Function *> &Clones,
-                    TargetTransformInfo &TTI) {
+                    TargetTransformInfo &TTI, const DebugInfoCache *DICache) {
     assert(Shape.ABI == coro::ABI::Switch);
 
-    MetadataSetTy CommonDebugInfo{collectCommonDebugInfo(F)};
+    MetadataSetTy CommonDebugInfo{collectCommonDebugInfo(F, DICache)};
 
     // Create a resume clone by cloning the body of the original function,
     // setting new entry block and replacing coro.suspend an appropriate value
@@ -1710,7 +1734,8 @@ CallInst *coro::createMustTailCall(DebugLoc Loc, Function *MustTailCallFn,
 
 void coro::AsyncABI::splitCoroutine(Function &F, coro::Shape &Shape,
                                     SmallVectorImpl<Function *> &Clones,
-                                    TargetTransformInfo &TTI) {
+                                    TargetTransformInfo &TTI,
+                                    const DebugInfoCache *DICache) {
   assert(Shape.ABI == coro::ABI::Async);
   assert(Clones.empty());
   // Reset various things that the optimizer might have decided it
@@ -1796,7 +1821,7 @@ void coro::AsyncABI::splitCoroutine(Function &F, coro::Shape &Shape,
 
   assert(Clones.size() == Shape.CoroSuspends.size());
 
-  MetadataSetTy CommonDebugInfo{collectCommonDebugInfo(F)};
+  MetadataSetTy CommonDebugInfo{collectCommonDebugInfo(F, DICache)};
 
   for (auto [Idx, CS] : llvm::enumerate(Shape.CoroSuspends)) {
     auto *Suspend = CS;
@@ -1809,7 +1834,8 @@ void coro::AsyncABI::splitCoroutine(Function &F, coro::Shape &Shape,
 
 void coro::AnyRetconABI::splitCoroutine(Function &F, coro::Shape &Shape,
                                         SmallVectorImpl<Function *> &Clones,
-                                        TargetTransformInfo &TTI) {
+                                        TargetTransformInfo &TTI,
+                                        const DebugInfoCache *DICache) {
   assert(Shape.ABI == coro::ABI::Retcon || Shape.ABI == coro::ABI::RetconOnce);
   assert(Clones.empty());
 
@@ -1930,7 +1956,7 @@ void coro::AnyRetconABI::splitCoroutine(Function &F, coro::Shape &Shape,
 
   assert(Clones.size() == Shape.CoroSuspends.size());
 
-  MetadataSetTy CommonDebugInfo{collectCommonDebugInfo(F)};
+  MetadataSetTy CommonDebugInfo{collectCommonDebugInfo(F, DICache)};
 
   for (auto [Idx, CS] : llvm::enumerate(Shape.CoroSuspends)) {
     auto Suspend = CS;
@@ -1984,13 +2010,15 @@ static bool hasSafeElideCaller(Function &F) {
 
 void coro::SwitchABI::splitCoroutine(Function &F, coro::Shape &Shape,
                                      SmallVectorImpl<Function *> &Clones,
-                                     TargetTransformInfo &TTI) {
-  SwitchCoroutineSplitter::split(F, Shape, Clones, TTI);
+                                     TargetTransformInfo &TTI,
+                                     const DebugInfoCache *DICache) {
+  SwitchCoroutineSplitter::split(F, Shape, Clones, TTI, DICache);
 }
 
 static void doSplitCoroutine(Function &F, SmallVectorImpl<Function *> &Clones,
                              coro::BaseABI &ABI, TargetTransformInfo &TTI,
-                             bool OptimizeFrame) {
+                             bool OptimizeFrame,
+                             const DebugInfoCache *DICache) {
   PrettyStackTraceFunction prettyStackTrace(F);
 
   auto &Shape = ABI.Shape;
@@ -2015,7 +2043,7 @@ static void doSplitCoroutine(Function &F, SmallVectorImpl<Function *> &Clones,
   if (isNoSuspendCoroutine) {
     handleNoSuspendCoroutine(Shape);
   } else {
-    ABI.splitCoroutine(F, Shape, Clones, TTI);
+    ABI.splitCoroutine(F, Shape, Clones, TTI, DICache);
   }
 
   // Replace all the swifterror operations in the original function.
@@ -2212,6 +2240,9 @@ PreservedAnalyses CoroSplitPass::run(LazyCallGraph::SCC &C,
   auto &FAM =
       AM.getResult<FunctionAnalysisManagerCGSCCProxy>(C, CG).getManager();
 
+  const auto &MAMProxy = AM.getResult<ModuleAnalysisManagerCGSCCProxy>(C, CG);
+  const auto *DICache = MAMProxy.getCachedResult<DebugInfoCacheAnalysis>(M);
+
   // Check for uses of llvm.coro.prepare.retcon/async.
   SmallVector<Function *, 2> PrepareFns;
   addPrepareFunction(M, PrepareFns, "llvm.coro.prepare.retcon");
@@ -2248,7 +2279,7 @@ PreservedAnalyses CoroSplitPass::run(LazyCallGraph::SCC &C,
 
     SmallVector<Function *, 4> Clones;
     auto &TTI = FAM.getResult<TargetIRAnalysis>(F);
-    doSplitCoroutine(F, Clones, *ABI, TTI, OptimizeFrame);
+    doSplitCoroutine(F, Clones, *ABI, TTI, OptimizeFrame, DICache);
     CurrentSCC = &updateCallGraphAfterCoroutineSplit(
         *N, Shape, Clones, *CurrentSCC, CG, AM, UR, FAM);
 

llvm/test/Other/new-pass-manager.ll

@@ -23,6 +23,7 @@
 ; CHECK-CGSCC-PASS-NEXT: Running analysis: InnerAnalysisManagerProxy<{{.*(FunctionAnalysisManager|AnalysisManager<.*Function.*>).*}},{{.*}}Module>
 ; CHECK-CGSCC-PASS-NEXT: Running analysis: LazyCallGraphAnalysis
 ; CHECK-CGSCC-PASS-NEXT: Running analysis: TargetLibraryAnalysis
+; CHECK-CGSCC-PASS-NEXT: Running analysis: DebugInfoCacheAnalysis
 ; CHECK-CGSCC-PASS-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy
 ; CHECK-CGSCC-PASS-NEXT: Running analysis: OuterAnalysisManagerProxy<{{.*}}LazyCallGraph::SCC{{.*}}>
 ; CHECK-CGSCC-PASS-NEXT: Running pass: NoOpCGSCCPass

llvm/test/Other/new-pm-defaults.ll

@@ -139,6 +139,7 @@
 ; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}ProfileSummaryAnalysis
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Running analysis: LazyCallGraphAnalysis
+; CHECK-O-NEXT: Running analysis: DebugInfoCacheAnalysis
 ; CHECK-O-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy
 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy<{{.*}}LazyCallGraph::SCC{{.*}}>
 ; CHECK-O-NEXT: Running pass: DevirtSCCRepeatedPass

llvm/test/Other/new-pm-lto-defaults.ll

@@ -43,6 +43,7 @@
 ; CHECK-O23SZ-NEXT: Running analysis: OptimizationRemarkEmitterAnalysis
 ; CHECK-O23SZ-NEXT: Running analysis: InnerAnalysisManagerProxy<{{.*}}SCC
 ; CHECK-O23SZ-NEXT: Running analysis: LazyCallGraphAnalysis
+; CHECK-O23SZ-NEXT: Running analysis: DebugInfoCacheAnalysis
 ; CHECK-O23SZ-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy
 ; CHECK-O23SZ-NEXT: Running analysis: OuterAnalysisManagerProxy<{{.*}}LazyCallGraph{{.*}}>
 ; CHECK-O23SZ-NEXT: Running pass: PostOrderFunctionAttrsPass

llvm/test/Other/new-pm-pgo-preinline.ll

@@ -5,6 +5,7 @@
 ; CHECK-Osz-NEXT: Running analysis: InlineAdvisorAnalysis
 ; CHECK-Osz-NEXT: Running analysis: InnerAnalysisManagerProxy
 ; CHECK-Osz-NEXT: Running analysis: LazyCallGraphAnalysis
+; CHECK-Osz-NEXT: Running analysis: DebugInfoCacheAnalysis
 ; CHECK-Osz-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy on (foo)
 ; CHECK-Osz-NEXT: Running analysis: OuterAnalysisManagerProxy
 ; CHECK-Osz-NEXT: Running pass: InlinerPass on (foo)

llvm/test/Other/new-pm-thinlto-postlink-defaults.ll

@@ -74,6 +74,7 @@
 ; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}ProfileSummaryAnalysis
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Running analysis: LazyCallGraphAnalysis
+; CHECK-O-NEXT: Running analysis: DebugInfoCacheAnalysis
 ; CHECK-O-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy
 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
 ; CHECK-O-NEXT: Running pass: DevirtSCCRepeatedPass

llvm/test/Other/new-pm-thinlto-postlink-pgo-defaults.ll

@@ -62,6 +62,7 @@
 ; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}ProfileSummaryAnalysis
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Running analysis: LazyCallGraphAnalysis
+; CHECK-O-NEXT: Running analysis: DebugInfoCacheAnalysis
 ; CHECK-O-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy
 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy<{{.*}}LazyCallGraph::SCC{{.*}}>
 ; CHECK-O-NEXT: Running pass: DevirtSCCRepeatedPass

llvm/test/Other/new-pm-thinlto-postlink-samplepgo-defaults.ll

@@ -71,6 +71,7 @@
 ; CHECK-O-NEXT: Invalidating analysis: AAManager
 ; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}ProfileSummaryAnalysis
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
+; CHECK-O-NEXT: Running analysis: DebugInfoCacheAnalysis
 ; CHECK-O-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy
 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
 ; CHECK-O-NEXT: Running pass: DevirtSCCRepeatedPass

llvm/test/Other/new-pm-thinlto-prelink-defaults.ll

@@ -106,6 +106,7 @@
 ; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}ProfileSummaryAnalysis
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Running analysis: LazyCallGraphAnalysis
+; CHECK-O-NEXT: Running analysis: DebugInfoCacheAnalysis
 ; CHECK-O-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy
 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
 ; CHECK-O-NEXT: Running pass: DevirtSCCRepeatedPass

llvm/test/Other/new-pm-thinlto-prelink-pgo-defaults.ll

@@ -62,6 +62,7 @@
 ; CHECK-O-NEXT: Running analysis: InlineAdvisorAnalysis
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Running analysis: LazyCallGraphAnalysis
+; CHECK-O-NEXT: Running analysis: DebugInfoCacheAnalysis
 ; CHECK-O-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy on (foo)
 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy
 ; CHECK-O-NEXT: Running pass: InlinerPass on (foo)
@@ -81,6 +82,7 @@
 ; CHECK-O-NEXT: Invalidating analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Invalidating analysis: LazyCallGraphAnalysis on
 ; CHECK-O-NEXT: Invalidating analysis: InnerAnalysisManagerProxy
+; CHECK-O-NEXT: Invalidating analysis: DebugInfoCacheAnalysis
 ; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}ProfileSummaryAnalysis
 ; CHECK-O-NEXT: Running pass: PGOIndirectCallPromotion on
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
@@ -97,6 +99,7 @@
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
 ; CHECK-O-NEXT: Running analysis: LazyCallGraphAnalysis
 ; CHECK-O-NEXT: Running analysis: TargetLibraryAnalysis on foo
+; CHECK-O-NEXT: Running analysis: DebugInfoCacheAnalysis
 ; CHECK-O-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy
 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy<{{.*}}LazyCallGraph::SCC{{.*}}>
 ; CHECK-O-NEXT: Running pass: DevirtSCCRepeatedPass

llvm/test/Other/new-pm-thinlto-prelink-samplepgo-defaults.ll

@@ -76,6 +76,7 @@
 ; CHECK-O-NEXT: Invalidating analysis: AAManager
 ; CHECK-O-NEXT: Running pass: RequireAnalysisPass<{{.*}}ProfileSummaryAnalysis
 ; CHECK-O-NEXT: Running analysis: InnerAnalysisManagerProxy
+; CHECK-O-NEXT: Running analysis: DebugInfoCacheAnalysis
 ; CHECK-O-NEXT: Running analysis: FunctionAnalysisManagerCGSCCProxy
 ; CHECK-O-NEXT: Running analysis: OuterAnalysisManagerProxy<{{.*}}LazyCallGraph::SCC{{.*}}>
 ; CHECK-O-NEXT: Running pass: DevirtSCCRepeatedPass

llvm/unittests/Analysis/CGSCCPassManagerTest.cpp

@@ -7,6 +7,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/Analysis/CGSCCPassManager.h"
+#include "llvm/Analysis/DebugInfoCache.h"
 #include "llvm/Analysis/LazyCallGraph.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/AsmParser/Parser.h"
@@ -16,8 +17,8 @@
 #include "llvm/IR/Instructions.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/Module.h"
-#include "llvm/IR/PassManager.h"
 #include "llvm/IR/PassInstrumentation.h"
+#include "llvm/IR/PassManager.h"
 #include "llvm/IR/Verifier.h"
 #include "llvm/Support/SourceMgr.h"
 #include "llvm/Transforms/Utils/CallGraphUpdater.h"
@@ -255,6 +256,7 @@ class CGSCCPassManagerTest : public ::testing::Test {
             "}\n")) {
     FAM.registerPass([&] { return TargetLibraryAnalysis(); });
     MAM.registerPass([&] { return LazyCallGraphAnalysis(); });
+    MAM.registerPass([&] { return DebugInfoCacheAnalysis(); });
     MAM.registerPass([&] { return FunctionAnalysisManagerModuleProxy(FAM); });
 
     // Register required pass instrumentation analysis.