Reland "[Propeller] Promote functions with propeller profiles to .text.hot."

This relands commit 4d8d258.

The major change here is using 'addUsedIfAvailable<BasicBlockSectionsProfileReader>()` to make sure we don't change the pipeline tests.

Differential Revision: https://reviews.llvm.org/D126518

Author: rlavaee

llvm/include/llvm/CodeGen/BasicBlockSectionsProfileReader.h

@@ -0,0 +1,109 @@
+//===-- BasicBlockSectionsProfileReader.h - BB sections profile reader pass ==//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This pass creates the basic block cluster info by reading the basic block
+// sections profile. The cluster info will be used by the basic-block-sections
+// pass to arrange basic blocks in their sections.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_ANALYSIS_BASICBLOCKSECTIONSINFO_H
+#define LLVM_ANALYSIS_BASICBLOCKSECTIONSINFO_H
+
+#include "llvm/ADT/Optional.h"
+#include "llvm/ADT/SmallSet.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/ADT/StringMap.h"
+#include "llvm/ADT/StringRef.h"
+#include "llvm/InitializePasses.h"
+#include "llvm/Pass.h"
+#include "llvm/Support/Error.h"
+#include "llvm/Support/LineIterator.h"
+#include "llvm/Support/MemoryBuffer.h"
+
+using namespace llvm;
+
+namespace llvm {
+
+// The cluster information for a machine basic block.
+struct BBClusterInfo {
+  // MachineBasicBlock ID.
+  unsigned MBBNumber;
+  // Cluster ID this basic block belongs to.
+  unsigned ClusterID;
+  // Position of basic block within the cluster.
+  unsigned PositionInCluster;
+};
+
+using ProgramBBClusterInfoMapTy = StringMap<SmallVector<BBClusterInfo>>;
+
+class BasicBlockSectionsProfileReader : public ImmutablePass {
+public:
+  static char ID;
+
+  BasicBlockSectionsProfileReader(const MemoryBuffer *Buf)
+      : ImmutablePass(ID), MBuf(Buf) {
+    initializeBasicBlockSectionsProfileReaderPass(
+        *PassRegistry::getPassRegistry());
+  };
+
+  BasicBlockSectionsProfileReader() : ImmutablePass(ID) {
+    initializeBasicBlockSectionsProfileReaderPass(
+        *PassRegistry::getPassRegistry());
+  }
+
+  StringRef getPassName() const override {
+    return "Basic Block Sections Profile Reader";
+  }
+
+  // Returns true if basic block sections profile exist for function \p
+  // FuncName.
+  bool isFunctionHot(StringRef FuncName) const;
+
+  // Returns a pair with first element representing whether basic block sections
+  // profile exist for the function \p FuncName, and the second element
+  // representing the basic block sections profile (cluster info) for this
+  // function. If the first element is true and the second element is empty, it
+  // means unique basic block sections are desired for all basic blocks of the
+  // function.
+  std::pair<bool, SmallVector<BBClusterInfo>>
+  getBBClusterInfoForFunction(StringRef FuncName) const;
+
+  /// Read profiles of basic blocks if available here.
+  void initializePass() override;
+
+private:
+  StringRef getAliasName(StringRef FuncName) const {
+    auto R = FuncAliasMap.find(FuncName);
+    return R == FuncAliasMap.end() ? FuncName : R->second;
+  }
+
+  // This contains the basic-block-sections profile.
+  const MemoryBuffer *MBuf = nullptr;
+
+  // This encapsulates the BB cluster information for the whole program.
+  //
+  // For every function name, it contains the cluster information for (all or
+  // some of) its basic blocks. The cluster information for every basic block
+  // includes its cluster ID along with the position of the basic block in that
+  // cluster.
+  ProgramBBClusterInfoMapTy ProgramBBClusterInfo;
+
+  // Some functions have alias names. We use this map to find the main alias
+  // name for which we have mapping in ProgramBBClusterInfo.
+  StringMap<StringRef> FuncAliasMap;
+};
+
+// Creates a BasicBlockSectionsProfileReader pass to parse the basic block
+// sections profile. \p Buf is a memory buffer that contains the list of
+// functions and basic block ids to selectively enable basic block sections.
+ImmutablePass *
+createBasicBlockSectionsProfileReaderPass(const MemoryBuffer *Buf);
+
+} // namespace llvm
+#endif // LLVM_ANALYSIS_BASICBLOCKSECTIONSINFO_H

llvm/include/llvm/CodeGen/Passes.h

@@ -51,10 +51,8 @@ namespace llvm {
   FunctionPass *createUnreachableBlockEliminationPass();
 
   /// createBasicBlockSections Pass - This pass assigns sections to machine
-  /// basic blocks and is enabled with -fbasic-block-sections. Buf is a memory
-  /// buffer that contains the list of functions and basic block ids to
-  /// selectively enable basic block sections.
-  MachineFunctionPass *createBasicBlockSectionsPass(const MemoryBuffer *Buf);
+  /// basic blocks and is enabled with -fbasic-block-sections.
+  MachineFunctionPass *createBasicBlockSectionsPass();
 
   /// createMachineFunctionSplitterPass - This pass splits machine functions
   /// using profile information.

llvm/include/llvm/InitializePasses.h

@@ -76,6 +76,7 @@ void initializeAssumptionCacheTrackerPass(PassRegistry&);
 void initializeAtomicExpandPass(PassRegistry&);
 void initializeAttributorLegacyPassPass(PassRegistry&);
 void initializeAttributorCGSCCLegacyPassPass(PassRegistry &);
+void initializeBasicBlockSectionsProfileReaderPass(PassRegistry &);
 void initializeBasicBlockSectionsPass(PassRegistry &);
 void initializeBDCELegacyPassPass(PassRegistry&);
 void initializeBarrierNoopPass(PassRegistry&);

llvm/lib/CodeGen/BasicBlockSections.cpp

@@ -69,25 +69,17 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/ADT/Optional.h"
-#include "llvm/ADT/SmallSet.h"
 #include "llvm/ADT/SmallVector.h"
-#include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/CodeGen/BasicBlockSectionsProfileReader.h"
 #include "llvm/CodeGen/BasicBlockSectionUtils.h"
 #include "llvm/CodeGen/MachineFunction.h"
 #include "llvm/CodeGen/MachineFunctionPass.h"
 #include "llvm/CodeGen/Passes.h"
 #include "llvm/CodeGen/TargetInstrInfo.h"
 #include "llvm/InitializePasses.h"
-#include "llvm/Support/Error.h"
-#include "llvm/Support/LineIterator.h"
-#include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Target/TargetMachine.h"
 
-using llvm::SmallSet;
-using llvm::SmallVector;
-using llvm::StringMap;
-using llvm::StringRef;
 using namespace llvm;
 
 // Placing the cold clusters in a separate section mitigates against poor
@@ -107,41 +99,11 @@ cl::opt<bool> BBSectionsDetectSourceDrift(
 
 namespace {
 
-// This struct represents the cluster information for a machine basic block.
-struct BBClusterInfo {
-  // MachineBasicBlock ID.
-  unsigned MBBNumber;
-  // Cluster ID this basic block belongs to.
-  unsigned ClusterID;
-  // Position of basic block within the cluster.
-  unsigned PositionInCluster;
-};
-
-using ProgramBBClusterInfoMapTy = StringMap<SmallVector<BBClusterInfo, 4>>;
-
 class BasicBlockSections : public MachineFunctionPass {
 public:
   static char ID;
 
-  // This contains the basic-block-sections profile.
-  const MemoryBuffer *MBuf = nullptr;
-
-  // This encapsulates the BB cluster information for the whole program.
-  //
-  // For every function name, it contains the cluster information for (all or
-  // some of) its basic blocks. The cluster information for every basic block
-  // includes its cluster ID along with the position of the basic block in that
-  // cluster.
-  ProgramBBClusterInfoMapTy ProgramBBClusterInfo;
-
-  // Some functions have alias names. We use this map to find the main alias
-  // name for which we have mapping in ProgramBBClusterInfo.
-  StringMap<StringRef> FuncAliasMap;
-
-  BasicBlockSections(const MemoryBuffer *Buf)
-      : MachineFunctionPass(ID), MBuf(Buf) {
-    initializeBasicBlockSectionsPass(*PassRegistry::getPassRegistry());
-  };
+  BasicBlockSectionsProfileReader *BBSectionsProfileReader = nullptr;
 
   BasicBlockSections() : MachineFunctionPass(ID) {
     initializeBasicBlockSectionsPass(*PassRegistry::getPassRegistry());
@@ -153,9 +115,6 @@ class BasicBlockSections : public MachineFunctionPass {
 
   void getAnalysisUsage(AnalysisUsage &AU) const override;
 
-  /// Read profiles of basic blocks if available here.
-  bool doInitialization(Module &M) override;
-
   /// Identify basic blocks that need separate sections and prepare to emit them
   /// accordingly.
   bool runOnMachineFunction(MachineFunction &MF) override;
@@ -205,29 +164,26 @@ static void updateBranches(
 
 // This function provides the BBCluster information associated with a function.
 // Returns true if a valid association exists and false otherwise.
-static bool getBBClusterInfoForFunction(
-    const MachineFunction &MF, const StringMap<StringRef> FuncAliasMap,
-    const ProgramBBClusterInfoMapTy &ProgramBBClusterInfo,
+bool getBBClusterInfoForFunction(
+    const MachineFunction &MF,
+    BasicBlockSectionsProfileReader *BBSectionsProfileReader,
     std::vector<Optional<BBClusterInfo>> &V) {
-  // Get the main alias name for the function.
-  auto FuncName = MF.getName();
-  auto R = FuncAliasMap.find(FuncName);
-  StringRef AliasName = R == FuncAliasMap.end() ? FuncName : R->second;
 
   // Find the assoicated cluster information.
-  auto P = ProgramBBClusterInfo.find(AliasName);
-  if (P == ProgramBBClusterInfo.end())
+  std::pair<bool, SmallVector<BBClusterInfo, 4>> P =
+      BBSectionsProfileReader->getBBClusterInfoForFunction(MF.getName());
+  if (!P.first)
     return false;
 
-  if (P->second.empty()) {
+  if (P.second.empty()) {
     // This indicates that sections are desired for all basic blocks of this
     // function. We clear the BBClusterInfo vector to denote this.
     V.clear();
     return true;
   }
 
   V.resize(MF.getNumBlockIDs());
-  for (auto bbClusterInfo : P->second) {
+  for (auto bbClusterInfo : P.second) {
     // Bail out if the cluster information contains invalid MBB numbers.
     if (bbClusterInfo.MBBNumber >= MF.getNumBlockIDs())
       return false;
@@ -376,9 +332,11 @@ bool BasicBlockSections::runOnMachineFunction(MachineFunction &MF) {
     return true;
   }
 
+  BBSectionsProfileReader = &getAnalysis<BasicBlockSectionsProfileReader>();
+
   std::vector<Optional<BBClusterInfo>> FuncBBClusterInfo;
   if (BBSectionsType == BasicBlockSection::List &&
-      !getBBClusterInfoForFunction(MF, FuncAliasMap, ProgramBBClusterInfo,
+      !getBBClusterInfoForFunction(MF, BBSectionsProfileReader,
                                    FuncBBClusterInfo))
     return true;
   MF.setBBSectionsType(BBSectionsType);
@@ -426,107 +384,12 @@ bool BasicBlockSections::runOnMachineFunction(MachineFunction &MF) {
   return true;
 }
 
-// Basic Block Sections can be enabled for a subset of machine basic blocks.
-// This is done by passing a file containing names of functions for which basic
-// block sections are desired.  Additionally, machine basic block ids of the
-// functions can also be specified for a finer granularity. Moreover, a cluster
-// of basic blocks could be assigned to the same section.
-// A file with basic block sections for all of function main and three blocks
-// for function foo (of which 1 and 2 are placed in a cluster) looks like this:
-// ----------------------------
-// list.txt:
-// !main
-// !foo
-// !!1 2
-// !!4
-static Error getBBClusterInfo(const MemoryBuffer *MBuf,
-                              ProgramBBClusterInfoMapTy &ProgramBBClusterInfo,
-                              StringMap<StringRef> &FuncAliasMap) {
-  assert(MBuf);
-  line_iterator LineIt(*MBuf, /*SkipBlanks=*/true, /*CommentMarker=*/'#');
-
-  auto invalidProfileError = [&](auto Message) {
-    return make_error<StringError>(
-        Twine("Invalid profile " + MBuf->getBufferIdentifier() + " at line " +
-              Twine(LineIt.line_number()) + ": " + Message),
-        inconvertibleErrorCode());
-  };
-
-  auto FI = ProgramBBClusterInfo.end();
-
-  // Current cluster ID corresponding to this function.
-  unsigned CurrentCluster = 0;
-  // Current position in the current cluster.
-  unsigned CurrentPosition = 0;
-
-  // Temporary set to ensure every basic block ID appears once in the clusters
-  // of a function.
-  SmallSet<unsigned, 4> FuncBBIDs;
-
-  for (; !LineIt.is_at_eof(); ++LineIt) {
-    StringRef S(*LineIt);
-    if (S[0] == '@')
-      continue;
-    // Check for the leading "!"
-    if (!S.consume_front("!") || S.empty())
-      break;
-    // Check for second "!" which indicates a cluster of basic blocks.
-    if (S.consume_front("!")) {
-      if (FI == ProgramBBClusterInfo.end())
-        return invalidProfileError(
-            "Cluster list does not follow a function name specifier.");
-      SmallVector<StringRef, 4> BBIndexes;
-      S.split(BBIndexes, ' ');
-      // Reset current cluster position.
-      CurrentPosition = 0;
-      for (auto BBIndexStr : BBIndexes) {
-        unsigned long long BBIndex;
-        if (getAsUnsignedInteger(BBIndexStr, 10, BBIndex))
-          return invalidProfileError(Twine("Unsigned integer expected: '") +
-                                     BBIndexStr + "'.");
-        if (!FuncBBIDs.insert(BBIndex).second)
-          return invalidProfileError(Twine("Duplicate basic block id found '") +
-                                     BBIndexStr + "'.");
-        if (!BBIndex && CurrentPosition)
-          return invalidProfileError("Entry BB (0) does not begin a cluster.");
-
-        FI->second.emplace_back(BBClusterInfo{
-            ((unsigned)BBIndex), CurrentCluster, CurrentPosition++});
-      }
-      CurrentCluster++;
-    } else { // This is a function name specifier.
-      // Function aliases are separated using '/'. We use the first function
-      // name for the cluster info mapping and delegate all other aliases to
-      // this one.
-      SmallVector<StringRef, 4> Aliases;
-      S.split(Aliases, '/');
-      for (size_t i = 1; i < Aliases.size(); ++i)
-        FuncAliasMap.try_emplace(Aliases[i], Aliases.front());
-
-      // Prepare for parsing clusters of this function name.
-      // Start a new cluster map for this function name.
-      FI = ProgramBBClusterInfo.try_emplace(Aliases.front()).first;
-      CurrentCluster = 0;
-      FuncBBIDs.clear();
-    }
-  }
-  return Error::success();
-}
-
-bool BasicBlockSections::doInitialization(Module &M) {
-  if (!MBuf)
-    return false;
-  if (auto Err = getBBClusterInfo(MBuf, ProgramBBClusterInfo, FuncAliasMap))
-    report_fatal_error(std::move(Err));
-  return false;
-}
-
 void BasicBlockSections::getAnalysisUsage(AnalysisUsage &AU) const {
   AU.setPreservesAll();
+  AU.addRequired<BasicBlockSectionsProfileReader>();
   MachineFunctionPass::getAnalysisUsage(AU);
 }
 
-MachineFunctionPass *
-llvm::createBasicBlockSectionsPass(const MemoryBuffer *Buf) {
-  return new BasicBlockSections(Buf);
+MachineFunctionPass *llvm::createBasicBlockSectionsPass() {
+  return new BasicBlockSections();
 }