[clang] [llvm] [clang-tools-extra] [LLVM] Add IRNormalizer Pass (PR #68176)

2023-11-19 Thread Justin Fargnoli via cfe-commits

https://github.com/justinfargnoli edited 
https://github.com/llvm/llvm-project/pull/68176
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits


[clang] [llvm] [clang-tools-extra] [LLVM] Add IRNormalizer Pass (PR #68176)

2023-11-11 Thread Justin Fargnoli via cfe-commits

https://github.com/justinfargnoli edited 
https://github.com/llvm/llvm-project/pull/68176
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits


[clang] [llvm] [clang-tools-extra] [LLVM] Add IRNormalizer Pass (PR #68176)

2023-11-11 Thread Justin Fargnoli via cfe-commits


@@ -0,0 +1,637 @@
+//===--- IRNormalizer.cpp - IR Normalizer ---===//
+//
+// 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
+//
+//===--===//
+/// \file
+/// This file implements the IRNormalizer class which aims to transform LLVM
+/// Modules into a canonical form by reordering and renaming instructions while
+/// preserving the same semantics. The normalizer makes it easier to spot
+/// semantic differences while diffing two modules which have undergone
+/// different passes.
+///
+//===--===//
+
+#include "llvm/Transforms/Utils/IRNormalizer.h"
+#include "llvm/ADT/SetVector.h"
+#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/SmallString.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/IR/BasicBlock.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/InstIterator.h"
+#include "llvm/IR/Module.h"
+#include "llvm/InitializePasses.h"
+#include "llvm/Pass.h"
+#include "llvm/PassRegistry.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Transforms/Utils.h"
+#include 
+#include 
+
+#define DEBUG_TYPE "normalize"
+
+using namespace llvm;
+
+namespace {
+/// IRNormalizer aims to transform LLVM IR into canonical form.
+class IRNormalizer {
+public:
+  /// \name Normalizer flags.
+  /// @{
+  /// Preserves original order of instructions.
+  static cl::opt PreserveOrder;
+  /// Renames all instructions (including user-named).
+  static cl::opt RenameAll;
+  /// Folds all regular instructions (including pre-outputs).
+  static cl::opt FoldPreoutputs;
+  /// Sorts and reorders operands in commutative instructions.
+  static cl::opt ReorderOperands;
+  /// @}
+
+  bool runOnFunction(Function );
+
+private:
+  // Random constant for hashing, so the state isn't zero.
+  const uint64_t MagicHashConstant = 0x6acaa36bef8325c5ULL;
+  DenseSet NamedInstructions;
+
+  /// \name Naming.
+  /// @{
+  void nameFunctionArguments(Function );
+  void nameBasicBlocks(Function );
+  void nameInstruction(Instruction *I);
+  void nameAsInitialInstruction(Instruction *I);
+  void nameAsRegularInstruction(Instruction *I);
+  void foldInstructionName(Instruction *I);
+  /// @}
+
+  /// \name Reordering.
+  /// @{
+  void reorderInstructions(SmallVector );
+  void reorderInstruction(Instruction *Used, Instruction *User,
+  SmallPtrSet );
+  void reorderInstructionOperandsByNames(Instruction *I);
+  void reorderPHIIncomingValues(PHINode *PN);
+  /// @}
+
+  /// \name Utility methods.
+  /// @{
+  SmallVector collectOutputInstructions(Function );
+  bool isOutput(const Instruction *I);
+  bool isInitialInstruction(const Instruction *I);
+  bool hasOnlyImmediateOperands(const Instruction *I);
+  SetVector
+  getOutputFootprint(Instruction *I,
+ SmallPtrSet );
+  /// @}
+};
+} // namespace
+
+cl::opt IRNormalizer::PreserveOrder(
+"preserve-order", cl::Hidden,
+cl::desc("Preserves original instruction order"));
+cl::opt IRNormalizer::RenameAll(
+"rename-all", cl::Hidden,
+cl::desc("Renames all instructions (including user-named)"));
+cl::opt IRNormalizer::FoldPreoutputs(
+"fold-all", cl::Hidden,
+cl::desc("Folds all regular instructions (including pre-outputs)"));
+cl::opt IRNormalizer::ReorderOperands(
+"reorder-operands", cl::Hidden,
+cl::desc("Sorts and reorders operands in commutative instructions"));
+
+/// Entry method to the IRNormalizer.
+///
+/// \param M Module to normalize.
+bool IRNormalizer::runOnFunction(Function ) {
+  nameFunctionArguments(F);
+  nameBasicBlocks(F);
+
+  SmallVector Outputs = collectOutputInstructions(F);
+
+  if (!PreserveOrder)
+reorderInstructions(Outputs);
+
+  for (auto  : Outputs)
+nameInstruction(I);
+
+  for (auto  : instructions(F)) {
+if (!PreserveOrder) {
+  if (ReorderOperands && I.isCommutative())
+reorderInstructionOperandsByNames();
+
+  if (auto *PN = dyn_cast())
+reorderPHIIncomingValues(PN);
+}
+
+foldInstructionName();
+  }
+
+  return true;
+}
+
+/// Numbers arguments.
+///
+/// \param F Function whose arguments will be renamed.
+void IRNormalizer::nameFunctionArguments(Function ) {
+  int ArgumentCounter = 0;
+  for (auto  : F.args()) {
+if (RenameAll || A.getName().empty()) {
+  A.setName("a" + Twine(ArgumentCounter));
+  ++ArgumentCounter;
+}
+  }
+}
+
+/// Names basic blocks using a generated hash for each basic block in
+/// a function considering the opcode and the order of output instructions.
+///
+/// \param F Function containing basic blocks to rename.
+void IRNormalizer::nameBasicBlocks(Function ) {
+  for (auto  : F) {
+// Initialize to a magic constant, so the state 

[clang] [llvm] [clang-tools-extra] [LLVM] Add IRNormalizer Pass (PR #68176)

2023-11-04 Thread Nikita Popov via cfe-commits


@@ -0,0 +1,637 @@
+//===--- IRNormalizer.cpp - IR Normalizer ---===//
+//
+// 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
+//
+//===--===//
+/// \file
+/// This file implements the IRNormalizer class which aims to transform LLVM
+/// Modules into a canonical form by reordering and renaming instructions while
+/// preserving the same semantics. The normalizer makes it easier to spot
+/// semantic differences while diffing two modules which have undergone
+/// different passes.
+///
+//===--===//
+
+#include "llvm/Transforms/Utils/IRNormalizer.h"
+#include "llvm/ADT/SetVector.h"
+#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/SmallString.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/IR/BasicBlock.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/InstIterator.h"
+#include "llvm/IR/Module.h"
+#include "llvm/InitializePasses.h"
+#include "llvm/Pass.h"
+#include "llvm/PassRegistry.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Transforms/Utils.h"
+#include 
+#include 
+
+#define DEBUG_TYPE "normalize"
+
+using namespace llvm;
+
+namespace {
+/// IRNormalizer aims to transform LLVM IR into canonical form.
+class IRNormalizer {
+public:
+  /// \name Normalizer flags.
+  /// @{
+  /// Preserves original order of instructions.
+  static cl::opt PreserveOrder;
+  /// Renames all instructions (including user-named).
+  static cl::opt RenameAll;
+  /// Folds all regular instructions (including pre-outputs).
+  static cl::opt FoldPreoutputs;
+  /// Sorts and reorders operands in commutative instructions.
+  static cl::opt ReorderOperands;
+  /// @}
+
+  bool runOnFunction(Function );
+
+private:
+  // Random constant for hashing, so the state isn't zero.
+  const uint64_t MagicHashConstant = 0x6acaa36bef8325c5ULL;
+  DenseSet NamedInstructions;
+
+  /// \name Naming.
+  /// @{
+  void nameFunctionArguments(Function );
+  void nameBasicBlocks(Function );
+  void nameInstruction(Instruction *I);
+  void nameAsInitialInstruction(Instruction *I);
+  void nameAsRegularInstruction(Instruction *I);
+  void foldInstructionName(Instruction *I);
+  /// @}
+
+  /// \name Reordering.
+  /// @{
+  void reorderInstructions(SmallVector );
+  void reorderInstruction(Instruction *Used, Instruction *User,
+  SmallPtrSet );
+  void reorderInstructionOperandsByNames(Instruction *I);
+  void reorderPHIIncomingValues(PHINode *PN);
+  /// @}
+
+  /// \name Utility methods.
+  /// @{
+  SmallVector collectOutputInstructions(Function );
+  bool isOutput(const Instruction *I);
+  bool isInitialInstruction(const Instruction *I);
+  bool hasOnlyImmediateOperands(const Instruction *I);
+  SetVector
+  getOutputFootprint(Instruction *I,
+ SmallPtrSet );
+  /// @}
+};
+} // namespace
+
+cl::opt IRNormalizer::PreserveOrder(
+"preserve-order", cl::Hidden,
+cl::desc("Preserves original instruction order"));
+cl::opt IRNormalizer::RenameAll(
+"rename-all", cl::Hidden,
+cl::desc("Renames all instructions (including user-named)"));
+cl::opt IRNormalizer::FoldPreoutputs(
+"fold-all", cl::Hidden,
+cl::desc("Folds all regular instructions (including pre-outputs)"));
+cl::opt IRNormalizer::ReorderOperands(
+"reorder-operands", cl::Hidden,
+cl::desc("Sorts and reorders operands in commutative instructions"));
+
+/// Entry method to the IRNormalizer.
+///
+/// \param M Module to normalize.
+bool IRNormalizer::runOnFunction(Function ) {
+  nameFunctionArguments(F);
+  nameBasicBlocks(F);
+
+  SmallVector Outputs = collectOutputInstructions(F);
+
+  if (!PreserveOrder)
+reorderInstructions(Outputs);
+
+  for (auto  : Outputs)
+nameInstruction(I);
+
+  for (auto  : instructions(F)) {
+if (!PreserveOrder) {
+  if (ReorderOperands && I.isCommutative())
+reorderInstructionOperandsByNames();
+
+  if (auto *PN = dyn_cast())
+reorderPHIIncomingValues(PN);
+}
+
+foldInstructionName();
+  }
+
+  return true;
+}
+
+/// Numbers arguments.
+///
+/// \param F Function whose arguments will be renamed.
+void IRNormalizer::nameFunctionArguments(Function ) {
+  int ArgumentCounter = 0;
+  for (auto  : F.args()) {
+if (RenameAll || A.getName().empty()) {
+  A.setName("a" + Twine(ArgumentCounter));
+  ++ArgumentCounter;
+}
+  }
+}
+
+/// Names basic blocks using a generated hash for each basic block in
+/// a function considering the opcode and the order of output instructions.
+///
+/// \param F Function containing basic blocks to rename.
+void IRNormalizer::nameBasicBlocks(Function ) {
+  for (auto  : F) {
+// Initialize to a magic constant, so the state 

[clang] [llvm] [clang-tools-extra] [LLVM] Add IRNormalizer Pass (PR #68176)

2023-11-04 Thread Nikita Popov via cfe-commits

https://github.com/nikic edited https://github.com/llvm/llvm-project/pull/68176
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits


[clang] [llvm] [clang-tools-extra] [LLVM] Add IRNormalizer Pass (PR #68176)

2023-11-04 Thread Nikita Popov via cfe-commits


@@ -0,0 +1,637 @@
+//===--- IRNormalizer.cpp - IR Normalizer ---===//
+//
+// 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
+//
+//===--===//
+/// \file
+/// This file implements the IRNormalizer class which aims to transform LLVM
+/// Modules into a canonical form by reordering and renaming instructions while
+/// preserving the same semantics. The normalizer makes it easier to spot
+/// semantic differences while diffing two modules which have undergone
+/// different passes.
+///
+//===--===//
+
+#include "llvm/Transforms/Utils/IRNormalizer.h"
+#include "llvm/ADT/SetVector.h"
+#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/SmallString.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/IR/BasicBlock.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/IRBuilder.h"
+#include "llvm/IR/InstIterator.h"
+#include "llvm/IR/Module.h"
+#include "llvm/InitializePasses.h"
+#include "llvm/Pass.h"
+#include "llvm/PassRegistry.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Transforms/Utils.h"
+#include 
+#include 
+
+#define DEBUG_TYPE "normalize"
+
+using namespace llvm;
+
+namespace {
+/// IRNormalizer aims to transform LLVM IR into canonical form.
+class IRNormalizer {
+public:
+  /// \name Normalizer flags.
+  /// @{
+  /// Preserves original order of instructions.
+  static cl::opt PreserveOrder;
+  /// Renames all instructions (including user-named).
+  static cl::opt RenameAll;
+  /// Folds all regular instructions (including pre-outputs).
+  static cl::opt FoldPreoutputs;
+  /// Sorts and reorders operands in commutative instructions.
+  static cl::opt ReorderOperands;
+  /// @}
+
+  bool runOnFunction(Function );
+
+private:
+  // Random constant for hashing, so the state isn't zero.
+  const uint64_t MagicHashConstant = 0x6acaa36bef8325c5ULL;
+  DenseSet NamedInstructions;
+
+  /// \name Naming.
+  /// @{
+  void nameFunctionArguments(Function );
+  void nameBasicBlocks(Function );
+  void nameInstruction(Instruction *I);
+  void nameAsInitialInstruction(Instruction *I);
+  void nameAsRegularInstruction(Instruction *I);
+  void foldInstructionName(Instruction *I);
+  /// @}
+
+  /// \name Reordering.
+  /// @{
+  void reorderInstructions(SmallVector );
+  void reorderInstruction(Instruction *Used, Instruction *User,
+  SmallPtrSet );
+  void reorderInstructionOperandsByNames(Instruction *I);
+  void reorderPHIIncomingValues(PHINode *PN);
+  /// @}
+
+  /// \name Utility methods.
+  /// @{
+  SmallVector collectOutputInstructions(Function );
+  bool isOutput(const Instruction *I);
+  bool isInitialInstruction(const Instruction *I);
+  bool hasOnlyImmediateOperands(const Instruction *I);
+  SetVector
+  getOutputFootprint(Instruction *I,
+ SmallPtrSet );
+  /// @}
+};
+} // namespace
+
+cl::opt IRNormalizer::PreserveOrder(
+"preserve-order", cl::Hidden,
+cl::desc("Preserves original instruction order"));
+cl::opt IRNormalizer::RenameAll(
+"rename-all", cl::Hidden,
+cl::desc("Renames all instructions (including user-named)"));
+cl::opt IRNormalizer::FoldPreoutputs(
+"fold-all", cl::Hidden,
+cl::desc("Folds all regular instructions (including pre-outputs)"));
+cl::opt IRNormalizer::ReorderOperands(
+"reorder-operands", cl::Hidden,
+cl::desc("Sorts and reorders operands in commutative instructions"));

nikic wrote:

Should probably prefix these option names? They're in the global namespace.

https://github.com/llvm/llvm-project/pull/68176
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits