[ctx_prof] Extend WorkloadImportsManager to use the contextual profile (#98682)

Keeping the json-based input as it's useful for diagnostics or for driving the import by other means than contextual composition.

The support for the contextual profile is just another modality for constructing the import list (`WorkloadImportsManager::Workloads`).

Everything else - i.e. the actual importing logic - is already independent from how that list was obtained.

Author: mtrofin

llvm/lib/Transforms/IPO/FunctionImport.cpp

@@ -19,7 +19,6 @@
 #include "llvm/ADT/StringRef.h"
 #include "llvm/Bitcode/BitcodeReader.h"
 #include "llvm/IR/AutoUpgrade.h"
-#include "llvm/IR/Constants.h"
 #include "llvm/IR/Function.h"
 #include "llvm/IR/GlobalAlias.h"
 #include "llvm/IR/GlobalObject.h"
@@ -30,6 +29,7 @@
 #include "llvm/IR/ModuleSummaryIndex.h"
 #include "llvm/IRReader/IRReader.h"
 #include "llvm/Linker/IRMover.h"
+#include "llvm/ProfileData/PGOCtxProfReader.h"
 #include "llvm/Support/Casting.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
@@ -185,6 +185,10 @@ static cl::opt<bool> ImportAssumeUniqueLocal(
         "user specify the full module path."),
     cl::Hidden);
 
+static cl::opt<std::string>
+    ContextualProfile("thinlto-pgo-ctx-prof",
+                      cl::desc("Path to a contextual profile."), cl::Hidden);
+
 namespace llvm {
 extern cl::opt<bool> EnableMemProfContextDisambiguation;
 }
@@ -604,13 +608,7 @@ class WorkloadImportsManager : public ModuleImportsManager {
     LLVM_DEBUG(dbgs() << "[Workload] Done\n");
   }
 
-public:
-  WorkloadImportsManager(
-      function_ref<bool(GlobalValue::GUID, const GlobalValueSummary *)>
-          IsPrevailing,
-      const ModuleSummaryIndex &Index,
-      DenseMap<StringRef, FunctionImporter::ExportSetTy> *ExportLists)
-      : ModuleImportsManager(IsPrevailing, Index, ExportLists) {
+  void loadFromJson() {
     // Since the workload def uses names, we need a quick lookup
     // name->ValueInfo.
     StringMap<ValueInfo> NameToValueInfo;
@@ -680,15 +678,81 @@ class WorkloadImportsManager : public ModuleImportsManager {
         }
         Set.insert(ElemIt->second);
       }
-      LLVM_DEBUG({
+    }
+  }
+
+  void loadFromCtxProf() {
+    std::error_code EC;
+    auto BufferOrErr = MemoryBuffer::getFileOrSTDIN(ContextualProfile);
+    if (std::error_code EC = BufferOrErr.getError()) {
+      report_fatal_error("Failed to open contextual profile file");
+      return;
+    }
+    auto Buffer = std::move(BufferOrErr.get());
+
+    PGOCtxProfileReader Reader(Buffer->getBuffer());
+    auto Ctx = Reader.loadContexts();
+    if (!Ctx) {
+      report_fatal_error("Failed to parse contextual profiles");
+      return;
+    }
+    const auto &CtxMap = *Ctx;
+    DenseSet<GlobalValue::GUID> ContainedGUIDs;
+    for (const auto &[RootGuid, Root] : CtxMap) {
+      // Avoid ContainedGUIDs to get in/out of scope. Reuse its memory for
+      // subsequent roots, but clear its contents.
+      ContainedGUIDs.clear();
+
+      auto RootVI = Index.getValueInfo(RootGuid);
+      if (!RootVI) {
+        LLVM_DEBUG(dbgs() << "[Workload] Root " << RootGuid
+                          << " not found in this linkage unit.\n");
+        continue;
+      }
+      if (RootVI.getSummaryList().size() != 1) {
+        LLVM_DEBUG(dbgs() << "[Workload] Root " << RootGuid
+                          << " should have exactly one summary, but has "
+                          << RootVI.getSummaryList().size() << ". Skipping.\n");
+        continue;
+      }
+      StringRef RootDefiningModule =
+          RootVI.getSummaryList().front()->modulePath();
+      LLVM_DEBUG(dbgs() << "[Workload] Root defining module for " << RootGuid
+                        << " is : " << RootDefiningModule << "\n");
+      auto &Set = Workloads[RootDefiningModule];
+      Root.getContainedGuids(ContainedGUIDs);
+      for (auto Guid : ContainedGUIDs)
+        if (auto VI = Index.getValueInfo(Guid))
+          Set.insert(VI);
+    }
+  }
+
+public:
+  WorkloadImportsManager(
+      function_ref<bool(GlobalValue::GUID, const GlobalValueSummary *)>
+          IsPrevailing,
+      const ModuleSummaryIndex &Index,
+      DenseMap<StringRef, FunctionImporter::ExportSetTy> *ExportLists)
+      : ModuleImportsManager(IsPrevailing, Index, ExportLists) {
+    if (ContextualProfile.empty() == WorkloadDefinitions.empty()) {
+      report_fatal_error(
+          "Pass only one of: -thinlto-pgo-ctx-prof or -thinlto-workload-def");
+      return;
+    }
+    if (!ContextualProfile.empty())
+      loadFromCtxProf();
+    else
+      loadFromJson();
+    LLVM_DEBUG({
+      for (const auto &[Root, Set] : Workloads) {
         dbgs() << "[Workload] Root: " << Root << " we have " << Set.size()
                << " distinct callees.\n";
         for (const auto &VI : Set) {
           dbgs() << "[Workload] Root: " << Root
                  << " Would include: " << VI.getGUID() << "\n";
         }
-      });
-    }
+      }
+    });
   }
 };
 
@@ -697,7 +761,7 @@ std::unique_ptr<ModuleImportsManager> ModuleImportsManager::create(
         IsPrevailing,
     const ModuleSummaryIndex &Index,
     DenseMap<StringRef, FunctionImporter::ExportSetTy> *ExportLists) {
-  if (WorkloadDefinitions.empty()) {
+  if (WorkloadDefinitions.empty() && ContextualProfile.empty()) {
     LLVM_DEBUG(dbgs() << "[Workload] Using the regular imports manager.\n");
     return std::unique_ptr<ModuleImportsManager>(
         new ModuleImportsManager(IsPrevailing, Index, ExportLists));

llvm/test/ThinLTO/X86/ctxprof.ll

@@ -0,0 +1,73 @@
+; Test workload based importing via -thinlto-pgo-ctx-prof
+; Use external linkage symbols so we don't depend on module paths which are
+; used when computing the GUIDs of internal linkage symbols.
+; The functionality is shared with what workload.ll tests, so here we only care
+; about testing the ctx profile is loaded and handled correctly.
+;
+; Set up
+; RUN: rm -rf %t
+; RUN: mkdir -p %t
+; RUN: split-file %s %t
+;
+; RUN: opt -module-summary %t/m1.ll -o %t/m1.bc
+; RUN: opt -module-summary %t/m2.ll -o %t/m2.bc
+; RUN: llvm-dis %t/m1.bc -o - | FileCheck %s --check-prefix=GUIDS-1
+; RUN: llvm-dis %t/m2.bc -o - | FileCheck %s --check-prefix=GUIDS-2
+;
+; GUIDS-1: name: "m1_f1"
+; GUIDS-1-SAME: guid = 6019442868614718803
+; GUIDS-2: name: "m2_f1"
+; GUIDS-2-SAME: guid = 15593096274670919754
+;
+; RUN: rm -rf %t_baseline
+; RUN: rm -rf %t_exp
+; RUN: mkdir -p %t_baseline
+; RUN: mkdir -p %t_exp
+;
+; Normal run. m1 shouldn't get m2_f1 because it's not referenced from there, and
+; m1_f1 shouldn't go to m2.
+;
+; RUN: llvm-lto2 run %t/m1.bc %t/m2.bc \
+; RUN:  -o %t_baseline/result.o -save-temps \
+; RUN:  -r %t/m1.bc,m1_f1,plx \
+; RUN:  -r %t/m2.bc,m2_f1,plx
+; RUN: llvm-dis %t_baseline/result.o.1.3.import.bc -o - | FileCheck %s --check-prefix=NOPROF-1
+; RUN: llvm-dis %t_baseline/result.o.2.3.import.bc -o - | FileCheck %s --check-prefix=NOPROF-2
+;
+; NOPROF-1-NOT: m2_f1()
+; NOPROF-2-NOT: m1_f1()
+;
+; The run with workload definitions - same other options.
+;
+; RUN: echo '[ \
+; RUN:        {"Guid": 6019442868614718803, "Counters": [1], "Callsites": [[{"Guid": 15593096274670919754, "Counters": [1]}]]}, \
+; RUN:        {"Guid": 15593096274670919754, "Counters": [1], "Callsites": [[{"Guid": 6019442868614718803, "Counters": [1]}]]} \
+; RUN:  ]' > %t_exp/ctxprof.json
+; RUN: llvm-ctxprof-util fromJSON --input %t_exp/ctxprof.json --output %t_exp/ctxprof.bitstream
+; RUN: llvm-lto2 run %t/m1.bc %t/m2.bc \
+; RUN:  -o %t_exp/result.o -save-temps \
+; RUN:  -thinlto-pgo-ctx-prof=%t_exp/ctxprof.bitstream \
+; RUN:  -r %t/m1.bc,m1_f1,plx \
+; RUN:  -r %t/m2.bc,m2_f1,plx
+; RUN: llvm-dis %t_exp/result.o.1.3.import.bc -o - | FileCheck %s --check-prefix=FIRST
+; RUN: llvm-dis %t_exp/result.o.2.3.import.bc -o - | FileCheck %s --check-prefix=SECOND
+;
+;
+; FIRST: m2_f1()
+; SECOND: m1_f1()
+;
+;--- m1.ll
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-pc-linux-gnu"
+
+define dso_local void @m1_f1() {
+  ret void
+}
+
+;--- m2.ll
+target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-pc-linux-gnu"
+
+define dso_local void @m2_f1() {
+  ret void
+}