[midend-Loop-LICM][fix]检查load能否外提时其内存地址在循环中是否会被修改，需要判断函数调用对load内存地址的影响。

src/include/midend/Pass/Analysis/LoopCharacteristics.h

@@ -350,7 +350,11 @@ private:
     std::set<Value*>& visited
   );
   bool isBasicInductionVariable(Value* val, Loop* loop);
-  bool hasSimpleMemoryPattern(Loop* loop); // 简单的内存模式检查
+  // ========== 循环不变量分析辅助方法 ==========
+  bool isInvariantOperands(Instruction* inst, Loop* loop, const std::unordered_set<Value*>& invariants);
+  bool isMemoryLocationModifiedInLoop(Value* ptr, Loop* loop);
+  bool isMemoryLocationLoadedInLoop(Value* ptr, Loop* loop, Instruction* excludeInst = nullptr);
+  bool isPureFunction(Function* calledFunc);
 };
 
 } // namespace sysy

src/include/midend/Pass/Optimize/GVN.h

@@ -0,0 +1,87 @@
+#pragma once
+
+#include "Pass.h"
+#include "IR.h"
+#include "Dom.h"
+#include "SideEffectAnalysis.h"
+#include <unordered_map>
+#include <unordered_set>
+#include <vector>
+#include <string>
+#include <sstream>
+
+namespace sysy {
+
+// GVN优化遍的核心逻辑封装类
+class GVNContext {
+public:
+    // 运行GVN优化的主要方法
+    void run(Function* func, AnalysisManager* AM, bool& changed);
+
+private:
+    // 新的值编号系统
+    std::unordered_map<Value*, unsigned> valueToNumber;      // Value -> 值编号
+    std::unordered_map<unsigned, Value*> numberToValue;      // 值编号 -> 代表值
+    std::unordered_map<std::string, unsigned> expressionToNumber; // 表达式 -> 值编号
+    unsigned nextValueNumber = 1;
+    
+    // 已访问的基本块集合
+    std::unordered_set<BasicBlock*> visited;
+    
+    // 逆后序遍历的基本块列表
+    std::vector<BasicBlock*> rpoBlocks;
+    
+    // 需要删除的指令集合
+    std::unordered_set<Instruction*> needRemove;
+    
+    // 分析结果
+    DominatorTree* domTree = nullptr;
+    SideEffectAnalysisResult* sideEffectAnalysis = nullptr;
+    
+    // 计算逆后序遍历
+    void computeRPO(Function* func);
+    void dfs(BasicBlock* bb);
+    
+    // 新的值编号方法
+    unsigned getValueNumber(Value* value);
+    unsigned assignValueNumber(Value* value);
+    
+    // 基本块处理
+    void processBasicBlock(BasicBlock* bb, bool& changed);
+    
+    // 指令处理
+    bool processInstruction(Instruction* inst);
+    
+    // 表达式构建和查找
+    std::string buildExpressionKey(Instruction* inst);
+    Value* findExistingValue(const std::string& exprKey, Instruction* inst);
+    
+    // 支配关系和安全性检查
+    bool dominates(Instruction* a, Instruction* b);
+    bool isMemorySafe(LoadInst* earlierLoad, LoadInst* laterLoad);
+    
+    // 清理方法
+    void eliminateRedundantInstructions(bool& changed);
+    void invalidateMemoryValues(StoreInst* store);
+};
+
+// GVN优化遍类
+class GVN : public OptimizationPass {
+public:
+    // 静态成员，作为该遍的唯一ID
+    static void* ID;
+    
+    GVN() : OptimizationPass("GVN", Granularity::Function) {}
+    
+    // 在函数上运行优化
+    bool runOnFunction(Function* func, AnalysisManager& AM) override;
+    
+    // 返回该遍的唯一ID
+    void* getPassID() const override { return ID; }
+    
+    // 声明分析依赖
+    void getAnalysisUsage(std::set<void*>& analysisDependencies, 
+                         std::set<void*>& analysisInvalidations) const override;
+};
+
+} // namespace sysy

src/midend/CMakeLists.txt

@@ -15,6 +15,7 @@ add_library(midend_lib STATIC
     Pass/Optimize/DCE.cpp
     Pass/Optimize/Mem2Reg.cpp
     Pass/Optimize/Reg2Mem.cpp
+    Pass/Optimize/GVN.cpp
     Pass/Optimize/SysYIRCFGOpt.cpp
     Pass/Optimize/SCCP.cpp
     Pass/Optimize/LoopNormalization.cpp

src/midend/IR.cpp

@@ -847,7 +847,7 @@ void CondBrInst::print(std::ostream &os) const {
   
   os << "%tmp_cond_" << condName << "_" << uniqueSuffix << " = icmp ne i32 ";
   printOperand(os, condition);
-  os << ", 0\n  br i1 %tmp_cond_" << condName << "_" << uniqueSuffix;
+  os << ", 0\n    br i1 %tmp_cond_" << condName << "_" << uniqueSuffix;
   
   os << ", label %";
   printBlockName(os, getThenBlock());
@@ -886,7 +886,7 @@ void MemsetInst::print(std::ostream &os) const {
   // This is done at print time to avoid modifying the IR structure
   os << "%tmp_bitcast_" << ptr->getName() << " = bitcast " << *ptr->getType() << " ";
   printOperand(os, ptr);
-  os << " to i8*\n  ";
+  os << " to i8*\n    ";
   
   // Now call memset with the bitcast result
   os << "call void @llvm.memset.p0i8.i32(i8* %tmp_bitcast_" << ptr->getName() << ", i8 ";

src/midend/Pass/Analysis/LoopCharacteristics.cpp

@@ -776,38 +776,324 @@ void LoopCharacteristicsPass::findDerivedInductionVars(
   }
 }
 
-// 递归/推进式判定
-bool LoopCharacteristicsPass::isClassicLoopInvariant(Value* val, Loop* loop, const std::unordered_set<Value*>& invariants) {
-  // 1. 常量
-  if (auto* constval = dynamic_cast<ConstantValue*>(val)) return true;
-
-  // 2. 参数（函数参数）通常不在任何BasicBlock内，直接判定为不变量
-  if (auto* arg = dynamic_cast<Argument*>(val)) return true;
-
-  // 3. 指令且定义在循环外
-  if (auto* inst = dynamic_cast<Instruction*>(val)) {
-    if (!loop->contains(inst->getParent()))
-      return true;
-
-    // 4. 跳转 phi指令 副作用 不外提
-    if (inst->isTerminator() || inst->isPhi() || sideEffectAnalysis->hasSideEffect(inst))
+// 检查操作数是否都是不变量
+bool LoopCharacteristicsPass::isInvariantOperands(Instruction* inst, Loop* loop, const std::unordered_set<Value*>& invariants) {
+  for (size_t i = 0; i < inst->getNumOperands(); ++i) {
+    Value* op = inst->getOperand(i);
+    if (!isClassicLoopInvariant(op, loop, invariants) && !invariants.count(op)) {
       return false;
-
-    // 5. 所有操作数都是不变量
-    for (size_t i = 0; i < inst->getNumOperands(); ++i) {
-      Value* op = inst->getOperand(i);
-      if (!isClassicLoopInvariant(op, loop, invariants) && !invariants.count(op))
-        return false;
     }
-    return true;
   }
-  // 其它情况
+  return true;
+}
+
+// 检查内存位置是否在循环中被修改
+bool LoopCharacteristicsPass::isMemoryLocationModifiedInLoop(Value* ptr, Loop* loop) {
+  // 遍历循环中的所有指令，检查是否有对该内存位置的写入
+  for (BasicBlock* bb : loop->getBlocks()) {
+    for (auto& inst : bb->getInstructions()) {
+      // 1. 检查直接的Store指令
+      if (auto* storeInst = dynamic_cast<StoreInst*>(inst.get())) {
+        Value* storeTar = storeInst->getPointer();
+        
+        // 使用别名分析检查是否可能别名
+        if (aliasAnalysis) {
+          auto aliasType = aliasAnalysis->queryAlias(ptr, storeTar);
+          if (aliasType != AliasType::NO_ALIAS) {
+            if (DEBUG) {
+              std::cout << "      Memory location " << ptr->getName() 
+                        << " may be modified by store to " << storeTar->getName() << std::endl;
+            }
+            return true;
+          }
+        } else {
+          // 如果没有别名分析，保守处理 - 只检查精确匹配
+          if (ptr == storeTar) {
+            return true;
+          }
+        }
+      }
+      
+      // 2. 检查函数调用是否可能修改该内存位置
+      else if (auto* callInst = dynamic_cast<CallInst*>(inst.get())) {
+        Function* calledFunc = callInst->getCallee();
+        
+        // 如果是纯函数，不会修改内存
+        if (isPureFunction(calledFunc)) {
+          continue;
+        }
+        
+        // 检查函数参数中是否有该内存位置的指针
+        for (size_t i = 1; i < callInst->getNumOperands(); ++i) { // 跳过函数指针
+          Value* arg = callInst->getOperand(i);
+          
+          // 检查参数是否是指针类型且可能指向该内存位置
+          if (auto* ptrType = dynamic_cast<PointerType*>(arg->getType())) {
+            // 使用别名分析检查
+            if (aliasAnalysis) {
+              auto aliasType = aliasAnalysis->queryAlias(ptr, arg);
+              if (aliasType != AliasType::NO_ALIAS) {
+                if (DEBUG) {
+                  std::cout << "      Memory location " << ptr->getName() 
+                            << " may be modified by function call " << calledFunc->getName()
+                            << " through parameter " << arg->getName() << std::endl;
+                }
+                return true;
+              }
+            } else {
+              // 没有别名分析，检查精确匹配
+              if (ptr == arg) {
+                if (DEBUG) {
+                  std::cout << "      Memory location " << ptr->getName() 
+                            << " may be modified by function call " << calledFunc->getName()
+                            << " (exact match)" << std::endl;
+                }
+                return true;
+              }
+            }
+          }
+        }
+      }
+    }
+  }
   return false;
 }
 
-bool LoopCharacteristicsPass::hasSimpleMemoryPattern(Loop* loop) {
-  // 检查是否有简单的内存访问模式
-  return true; // 暂时简化处理
+// 检查内存位置是否在循环中被读取
+bool LoopCharacteristicsPass::isMemoryLocationLoadedInLoop(Value* ptr, Loop* loop, Instruction* excludeInst) {
+  // 遍历循环中的所有Load指令，检查是否有对该内存位置的读取
+  for (BasicBlock* bb : loop->getBlocks()) {
+    for (auto& inst : bb->getInstructions()) {
+      if (inst.get() == excludeInst) continue; // 排除当前指令本身
+      
+      if (auto* loadInst = dynamic_cast<LoadInst*>(inst.get())) {
+        Value* loadSrc = loadInst->getPointer();
+        
+        // 使用别名分析检查是否可能别名
+        if (aliasAnalysis) {
+          auto aliasType = aliasAnalysis->queryAlias(ptr, loadSrc);
+          if (aliasType != AliasType::NO_ALIAS) {
+            return true;
+          }
+        } else {
+          // 如果没有别名分析，保守处理 - 只检查精确匹配
+          if (ptr == loadSrc) {
+            return true;
+          }
+        }
+      }
+    }
+  }
+  return false;
 }
 
+// 检查函数调用是否为纯函数
+bool LoopCharacteristicsPass::isPureFunction(Function* calledFunc) {
+  if (!calledFunc) return false;
+  
+  // 使用副作用分析检查函数是否为纯函数
+  if (sideEffectAnalysis && sideEffectAnalysis->isPureFunction(calledFunc)) {
+    return true;
+  }
+  
+  // 检查是否为内置纯函数（如数学函数）
+  std::string funcName = calledFunc->getName();
+  static const std::set<std::string> pureFunctions = {
+    "abs", "fabs", "sqrt", "sin", "cos", "tan", "exp", "log", "pow",
+    "floor", "ceil", "round", "min", "max"
+  };
+  
+  return pureFunctions.count(funcName) > 0;
+}
+
+// 递归/推进式判定 - 完善版本
+bool LoopCharacteristicsPass::isClassicLoopInvariant(Value* val, Loop* loop, const std::unordered_set<Value*>& invariants) {
+  if (DEBUG >= 2) {
+    std::cout << "    Checking loop invariant for: " << val->getName() << std::endl;
+  }
+  
+  // 1. 常量
+  if (auto* constval = dynamic_cast<ConstantValue*>(val)) {
+    if (DEBUG >= 2) std::cout << "    -> Constant: YES" << std::endl;
+    return true;
+  }
+
+  // 2. 参数（函数参数）通常不在任何BasicBlock内，直接判定为不变量
+  // 在SSA形式下，参数不会被重新赋值
+  if (auto* arg = dynamic_cast<Argument*>(val)) {
+    if (DEBUG >= 2) std::cout << "    -> Function argument: YES" << std::endl;
+    return true;
+  }
+
+  // 3. 指令且定义在循环外
+  if (auto* inst = dynamic_cast<Instruction*>(val)) {
+    if (!loop->contains(inst->getParent())) {
+      if (DEBUG >= 2) std::cout << "    -> Defined outside loop: YES" << std::endl;
+      return true;
+    }
+
+    // 4. 跳转指令、phi指令不能外提
+    if (inst->isTerminator() || inst->isPhi()) {
+      if (DEBUG >= 2) std::cout << "    -> Terminator or PHI: NO" << std::endl;
+      return false;
+    }
+
+    // 5. 根据指令类型进行具体分析
+    switch (inst->getKind()) {
+      case Instruction::Kind::kStore: {
+        // Store指令：检查循环内是否有对该内存的load
+        auto* storeInst = dynamic_cast<StoreInst*>(inst);
+        Value* storePtr = storeInst->getPointer();
+        
+        // 首先检查操作数是否不变
+        if (!isInvariantOperands(inst, loop, invariants)) {
+          if (DEBUG >= 2) std::cout << "    -> Store: operands not invariant: NO" << std::endl;
+          return false;
+        }
+        
+        // 检查是否有对该内存位置的load
+        if (isMemoryLocationLoadedInLoop(storePtr, loop, inst)) {
+          if (DEBUG >= 2) std::cout << "    -> Store: memory location loaded in loop: NO" << std::endl;
+          return false;
+        }
+        
+        if (DEBUG >= 2) std::cout << "    -> Store: safe to hoist: YES" << std::endl;
+        return true;
+      }
+      
+      case Instruction::Kind::kLoad: {
+        // Load指令：检查循环内是否有对该内存的store
+        auto* loadInst = dynamic_cast<LoadInst*>(inst);
+        Value* loadPtr = loadInst->getPointer();
+        
+        // 首先检查指针操作数是否不变
+        if (!isInvariantOperands(inst, loop, invariants)) {
+          if (DEBUG >= 2) std::cout << "    -> Load: pointer not invariant: NO" << std::endl;
+          return false;
+        }
+        
+        // 检查是否有对该内存位置的store
+        if (isMemoryLocationModifiedInLoop(loadPtr, loop)) {
+          if (DEBUG >= 2) std::cout << "    -> Load: memory location modified in loop: NO" << std::endl;
+          return false;
+        }
+        
+        if (DEBUG >= 2) std::cout << "    -> Load: safe to hoist: YES" << std::endl;
+        return true;
+      }
+      
+      case Instruction::Kind::kCall: {
+        // Call指令：检查是否为纯函数且参数不变
+        auto* callInst = dynamic_cast<CallInst*>(inst);
+        Function* calledFunc = callInst->getCallee();
+        
+        // 检查是否为纯函数
+        if (!isPureFunction(calledFunc)) {
+          if (DEBUG >= 2) std::cout << "    -> Call: not pure function: NO" << std::endl;
+          return false;
+        }
+        
+        // 检查参数是否都不变
+        if (!isInvariantOperands(inst, loop, invariants)) {
+          if (DEBUG >= 2) std::cout << "    -> Call: arguments not invariant: NO" << std::endl;
+          return false;
+        }
+        
+        if (DEBUG >= 2) std::cout << "    -> Call: pure function with invariant args: YES" << std::endl;
+        return true;
+      }
+      
+      case Instruction::Kind::kGetElementPtr: {
+        // GEP指令：检查基址和索引是否都不变
+        if (!isInvariantOperands(inst, loop, invariants)) {
+          if (DEBUG >= 2) std::cout << "    -> GEP: base or indices not invariant: NO" << std::endl;
+          return false;
+        }
+        
+        if (DEBUG >= 2) std::cout << "    -> GEP: base and indices invariant: YES" << std::endl;
+        return true;
+      }
+      
+      // 一元运算指令
+      case Instruction::Kind::kNeg:
+      case Instruction::Kind::kNot:
+      case Instruction::Kind::kFNeg:
+      case Instruction::Kind::kFNot:
+      case Instruction::Kind::kFtoI:
+      case Instruction::Kind::kItoF:
+      case Instruction::Kind::kBitItoF:
+      case Instruction::Kind::kBitFtoI: {
+        // 检查操作数是否不变
+        if (!isInvariantOperands(inst, loop, invariants)) {
+          if (DEBUG >= 2) std::cout << "    -> Unary op: operand not invariant: NO" << std::endl;
+          return false;
+        }
+        
+        if (DEBUG >= 2) std::cout << "    -> Unary op: operand invariant: YES" << std::endl;
+        return true;
+      }
+      
+      // 二元运算指令
+      case Instruction::Kind::kAdd:
+      case Instruction::Kind::kSub:
+      case Instruction::Kind::kMul:
+      case Instruction::Kind::kDiv:
+      case Instruction::Kind::kRem:
+      case Instruction::Kind::kSll:
+      case Instruction::Kind::kSrl:
+      case Instruction::Kind::kSra:
+      case Instruction::Kind::kAnd:
+      case Instruction::Kind::kOr:
+      case Instruction::Kind::kFAdd:
+      case Instruction::Kind::kFSub:
+      case Instruction::Kind::kFMul:
+      case Instruction::Kind::kFDiv:
+      case Instruction::Kind::kICmpEQ:
+      case Instruction::Kind::kICmpNE:
+      case Instruction::Kind::kICmpLT:
+      case Instruction::Kind::kICmpGT:
+      case Instruction::Kind::kICmpLE:
+      case Instruction::Kind::kICmpGE:
+      case Instruction::Kind::kFCmpEQ:
+      case Instruction::Kind::kFCmpNE:
+      case Instruction::Kind::kFCmpLT:
+      case Instruction::Kind::kFCmpGT:
+      case Instruction::Kind::kFCmpLE:
+      case Instruction::Kind::kFCmpGE:
+      case Instruction::Kind::kMulh: {
+        // 检查所有操作数是否不变
+        if (!isInvariantOperands(inst, loop, invariants)) {
+          if (DEBUG >= 2) std::cout << "    -> Binary op: operands not invariant: NO" << std::endl;
+          return false;
+        }
+        
+        if (DEBUG >= 2) std::cout << "    -> Binary op: operands invariant: YES" << std::endl;
+        return true;
+      }
+      
+      default: {
+        // 其他指令：使用副作用分析
+        if (sideEffectAnalysis && sideEffectAnalysis->hasSideEffect(inst)) {
+          if (DEBUG >= 2) std::cout << "    -> Other inst: has side effect: NO" << std::endl;
+          return false;
+        }
+        
+        // 检查操作数是否都不变
+        if (!isInvariantOperands(inst, loop, invariants)) {
+          if (DEBUG >= 2) std::cout << "    -> Other inst: operands not invariant: NO" << std::endl;
+          return false;
+        }
+        
+        if (DEBUG >= 2) std::cout << "    -> Other inst: no side effect, operands invariant: YES" << std::endl;
+        return true;
+      }
+    }
+  }
+  
+  // 其它情况
+  if (DEBUG >= 2) std::cout << "    -> Other value type: NO" << std::endl;
+  return false;
+}
+
+
 } // namespace sysy

src/midend/Pass/Analysis/SideEffectAnalysis.cpp

@@ -26,10 +26,21 @@ const SideEffectInfo &SideEffectAnalysisResult::getInstructionSideEffect(Instruc
 }
 
 const SideEffectInfo &SideEffectAnalysisResult::getFunctionSideEffect(Function *func) const {
+  // 首先检查分析过的用户定义函数
   auto it = functionSideEffects.find(func);
   if (it != functionSideEffects.end()) {
     return it->second;
   }
+  
+  // 如果没有找到，检查是否为已知的库函数
+  if (func) {
+    std::string funcName = func->getName();
+    const SideEffectInfo *knownInfo = getKnownFunctionSideEffect(funcName);
+    if (knownInfo) {
+      return *knownInfo;
+    }
+  }
+  
   // 返回默认的无副作用信息
   static SideEffectInfo noEffect;
   return noEffect;

src/midend/Pass/Optimize/GVN.cpp

@@ -0,0 +1,492 @@
+#include "GVN.h"
+#include "Dom.h"
+#include "SysYIROptUtils.h"
+#include <algorithm>
+#include <cassert>
+#include <iostream>
+#include <unordered_map>
+#include <unordered_set>
+
+extern int DEBUG;
+
+namespace sysy {
+
+// GVN 遍的静态 ID
+void *GVN::ID = (void *)&GVN::ID;
+
+// ======================================================================
+// GVN 类的实现
+// ======================================================================
+
+bool GVN::runOnFunction(Function *func, AnalysisManager &AM) {
+  if (func->getBasicBlocks().empty()) {
+    return false;
+  }
+
+  if (DEBUG) {
+    std::cout << "\n=== Running GVN on function: " << func->getName() << " ===" << std::endl;
+  }
+
+  bool changed = false;
+  GVNContext context;
+  context.run(func, &AM, changed);
+
+  if (DEBUG) {
+    if (changed) {
+      std::cout << "GVN: Function " << func->getName() << " was modified" << std::endl;
+    } else {
+      std::cout << "GVN: Function " << func->getName() << " was not modified" << std::endl;
+    }
+    std::cout << "=== GVN completed for function: " << func->getName() << " ===" << std::endl;
+  }
+
+  return changed;
+}
+
+void GVN::getAnalysisUsage(std::set<void *> &analysisDependencies, std::set<void *> &analysisInvalidations) const {
+  // GVN依赖以下分析：
+  // 1. 支配树分析 - 用于检查指令的支配关系，确保替换的安全性
+  analysisDependencies.insert(&DominatorTreeAnalysisPass::ID);
+  
+  // 2. 副作用分析 - 用于判断函数调用是否可以进行GVN
+  analysisDependencies.insert(&SysYSideEffectAnalysisPass::ID);
+
+  // GVN不会使任何分析失效，因为：
+  // - GVN只删除冗余计算，不改变CFG结构
+  // - GVN不修改程序的语义，只是消除重复计算
+  // - 支配关系保持不变
+  // - 副作用分析结果保持不变
+  // analysisInvalidations 保持为空
+  
+  if (DEBUG) {
+    std::cout << "GVN: Declared analysis dependencies (DominatorTree, SideEffectAnalysis)" << std::endl;
+  }
+}
+
+// ======================================================================
+// GVNContext 类的实现 - 重构版本
+// ======================================================================
+
+// 简单的表达式哈希结构
+struct ExpressionKey {
+  enum Type { BINARY, UNARY, LOAD, GEP, CALL } type;
+  int opcode;
+  std::vector<Value*> operands;
+  Type* resultType;
+  
+  bool operator==(const ExpressionKey& other) const {
+    return type == other.type && opcode == other.opcode && 
+           operands == other.operands && resultType == other.resultType;
+  }
+};
+
+struct ExpressionKeyHash {
+  size_t operator()(const ExpressionKey& key) const {
+    size_t hash = std::hash<int>()(static_cast<int>(key.type)) ^ 
+                  std::hash<int>()(key.opcode);
+    for (auto op : key.operands) {
+      hash ^= std::hash<Value*>()(op) + 0x9e3779b9 + (hash << 6) + (hash >> 2);
+    }
+    return hash;
+  }
+};
+
+void GVNContext::run(Function *func, AnalysisManager *AM, bool &changed) {
+  if (DEBUG) {
+    std::cout << "  Starting GVN analysis for function: " << func->getName() << std::endl;
+  }
+
+  // 获取分析结果
+  if (AM) {
+    domTree = AM->getAnalysisResult<DominatorTree, DominatorTreeAnalysisPass>(func);
+    sideEffectAnalysis = AM->getAnalysisResult<SideEffectAnalysisResult, SysYSideEffectAnalysisPass>();
+
+    if (DEBUG) {
+      if (domTree) {
+        std::cout << "    GVN: Using dominator tree analysis" << std::endl;
+      } else {
+        std::cout << "    GVN: Warning - dominator tree analysis not available" << std::endl;
+      }
+      if (sideEffectAnalysis) {
+        std::cout << "    GVN: Using side effect analysis" << std::endl;
+      } else {
+        std::cout << "    GVN: Warning - side effect analysis not available" << std::endl;
+      }
+    }
+  }
+
+  // 清空状态
+  valueToNumber.clear();
+  numberToValue.clear();
+  expressionToNumber.clear();
+  nextValueNumber = 1;
+  visited.clear();
+  rpoBlocks.clear();
+  needRemove.clear();
+
+  // 计算逆后序遍历
+  computeRPO(func);
+
+  if (DEBUG) {
+    std::cout << "    Computed RPO with " << rpoBlocks.size() << " blocks" << std::endl;
+  }
+
+  // 按逆后序遍历基本块进行GVN
+  int blockCount = 0;
+  for (auto bb : rpoBlocks) {
+    if (DEBUG) {
+      std::cout << "    Processing block " << ++blockCount << "/" << rpoBlocks.size() 
+                << ": " << bb->getName() << std::endl;
+    }
+    
+    processBasicBlock(bb, changed);
+  }
+
+  if (DEBUG) {
+    std::cout << "    Found " << needRemove.size() << " redundant instructions to remove" << std::endl;
+  }
+
+  // 删除冗余指令
+  eliminateRedundantInstructions(changed);
+
+  if (DEBUG) {
+    std::cout << "  GVN analysis completed for function: " << func->getName() << std::endl;
+    std::cout << "    Total values numbered: " << valueToNumber.size() << std::endl;
+    std::cout << "    Instructions eliminated: " << needRemove.size() << std::endl;
+  }
+}
+
+void GVNContext::computeRPO(Function *func) {
+  rpoBlocks.clear();
+  visited.clear();
+
+  auto entry = func->getEntryBlock();
+  if (entry) {
+    dfs(entry);
+    std::reverse(rpoBlocks.begin(), rpoBlocks.end());
+  }
+}
+
+void GVNContext::dfs(BasicBlock *bb) {
+  if (!bb || visited.count(bb)) {
+    return;
+  }
+
+  visited.insert(bb);
+
+  // 访问所有后继基本块
+  for (auto succ : bb->getSuccessors()) {
+    if (visited.find(succ) == visited.end()) {
+      dfs(succ);
+    }
+  }
+
+  rpoBlocks.push_back(bb);
+}
+
+unsigned GVNContext::getValueNumber(Value* value) {
+  // 如果已经有值编号，直接返回
+  auto it = valueToNumber.find(value);
+  if (it != valueToNumber.end()) {
+    return it->second;
+  }
+  
+  // 为新值分配编号
+  return assignValueNumber(value);
+}
+
+unsigned GVNContext::assignValueNumber(Value* value) {
+  unsigned number = nextValueNumber++;
+  valueToNumber[value] = number;
+  numberToValue[number] = value;
+  
+  if (DEBUG >= 2) {
+    std::cout << "            Assigned value number " << number 
+              << " to " << value->getName() << std::endl;
+  }
+  
+  return number;
+}
+
+void GVNContext::processBasicBlock(BasicBlock* bb, bool& changed) {
+  int instCount = 0;
+  for (auto &instPtr : bb->getInstructions()) {
+    if (DEBUG) {
+      std::cout << "      Processing instruction " << ++instCount 
+                << ": " << instPtr->getName() << std::endl;
+    }
+    
+    if (processInstruction(instPtr.get())) {
+      changed = true;
+    }
+  }
+}
+
+bool GVNContext::processInstruction(Instruction* inst) {
+  // 跳过分支指令和其他不可优化的指令
+  if (inst->isBranch() || dynamic_cast<ReturnInst*>(inst) || 
+      dynamic_cast<AllocaInst*>(inst) || dynamic_cast<StoreInst*>(inst)) {
+    
+    // 如果是store指令，需要使相关的内存值失效
+    if (auto store = dynamic_cast<StoreInst*>(inst)) {
+      invalidateMemoryValues(store);
+    }
+    
+    // 为这些指令分配值编号但不尝试优化
+    getValueNumber(inst);
+    return false;
+  }
+  
+  if (DEBUG) {
+    std::cout << "        Processing optimizable instruction: " << inst->getName() 
+              << " (kind: " << static_cast<int>(inst->getKind()) << ")" << std::endl;
+  }
+  
+  // 构建表达式键
+  std::string exprKey = buildExpressionKey(inst);
+  if (exprKey.empty()) {
+    // 不可优化的指令，只分配值编号
+    getValueNumber(inst);
+    return false;
+  }
+  
+  if (DEBUG >= 2) {
+    std::cout << "          Expression key: " << exprKey << std::endl;
+  }
+  
+  // 查找已存在的等价值
+  Value* existing = findExistingValue(exprKey, inst);
+  if (existing && existing != inst) {
+    // 检查支配关系
+    if (auto existingInst = dynamic_cast<Instruction*>(existing)) {
+      if (dominates(existingInst, inst)) {
+        if (DEBUG) {
+          std::cout << "        GVN: Replacing " << inst->getName() 
+                    << " with existing " << existing->getName() << std::endl;
+        }
+        
+        // 用已存在的值替换当前指令
+        inst->replaceAllUsesWith(existing);
+        needRemove.insert(inst);
+        
+        // 将当前指令的值编号指向已存在的值
+        unsigned existingNumber = getValueNumber(existing);
+        valueToNumber[inst] = existingNumber;
+        
+        return true;
+      } else {
+        if (DEBUG) {
+          std::cout << "          Found equivalent but dominance check failed" << std::endl;
+        }
+      }
+    }
+  }
+  
+  // 没有找到等价值，为这个表达式分配新的值编号
+  unsigned number = assignValueNumber(inst);
+  expressionToNumber[exprKey] = number;
+  
+  if (DEBUG) {
+    std::cout << "        Instruction " << inst->getName() << " is unique" << std::endl;
+  }
+  
+  return false;
+}
+
+std::string GVNContext::buildExpressionKey(Instruction* inst) {
+  std::ostringstream oss;
+  
+  if (auto binary = dynamic_cast<BinaryInst*>(inst)) {
+    oss << "binary_" << static_cast<int>(binary->getKind()) << "_";
+    oss << getValueNumber(binary->getLhs()) << "_" << getValueNumber(binary->getRhs());
+    
+    // 对于可交换操作，确保操作数顺序一致
+    if (binary->isCommutative()) {
+      unsigned lhsNum = getValueNumber(binary->getLhs());
+      unsigned rhsNum = getValueNumber(binary->getRhs());
+      if (lhsNum > rhsNum) {
+        oss.str("");
+        oss << "binary_" << static_cast<int>(binary->getKind()) << "_";
+        oss << rhsNum << "_" << lhsNum;
+      }
+    }
+  } else if (auto unary = dynamic_cast<UnaryInst*>(inst)) {
+    oss << "unary_" << static_cast<int>(unary->getKind()) << "_";
+    oss << getValueNumber(unary->getOperand());
+  } else if (auto gep = dynamic_cast<GetElementPtrInst*>(inst)) {
+    oss << "gep_" << getValueNumber(gep->getBasePointer());
+    for (unsigned i = 0; i < gep->getNumIndices(); ++i) {
+      oss << "_" << getValueNumber(gep->getIndex(i));
+    }
+  } else if (auto load = dynamic_cast<LoadInst*>(inst)) {
+    oss << "load_" << getValueNumber(load->getPointer());
+    oss << "_" << reinterpret_cast<uintptr_t>(load->getType()); // 类型区分
+  } else if (auto call = dynamic_cast<CallInst*>(inst)) {
+    // 只为无副作用的函数调用建立表达式
+    if (sideEffectAnalysis && sideEffectAnalysis->isPureFunction(call->getCallee())) {
+      oss << "call_" << call->getCallee()->getName();
+      for (size_t i = 1; i < call->getNumOperands(); ++i) { // 跳过函数指针
+        oss << "_" << getValueNumber(call->getOperand(i));
+      }
+    } else {
+      return ""; // 有副作用的函数调用不可优化
+    }
+  } else {
+    return ""; // 不支持的指令类型
+  }
+  
+  return oss.str();
+}
+
+Value* GVNContext::findExistingValue(const std::string& exprKey, Instruction* inst) {
+  auto it = expressionToNumber.find(exprKey);
+  if (it != expressionToNumber.end()) {
+    unsigned number = it->second;
+    auto valueIt = numberToValue.find(number);
+    if (valueIt != numberToValue.end()) {
+      Value* existing = valueIt->second;
+      
+      // 对于load指令，需要额外检查内存安全性
+      if (auto loadInst = dynamic_cast<LoadInst*>(inst)) {
+        if (auto existingLoad = dynamic_cast<LoadInst*>(existing)) {
+          if (!isMemorySafe(existingLoad, loadInst)) {
+            return nullptr;
+          }
+        }
+      }
+      
+      return existing;
+    }
+  }
+  return nullptr;
+}
+
+bool GVNContext::dominates(Instruction* a, Instruction* b) {
+  auto aBB = a->getParent();
+  auto bBB = b->getParent();
+  
+  // 同一基本块内的情况
+  if (aBB == bBB) {
+    auto &insts = aBB->getInstructions();
+    auto aIt = std::find_if(insts.begin(), insts.end(), 
+                           [a](const auto &ptr) { return ptr.get() == a; });
+    auto bIt = std::find_if(insts.begin(), insts.end(),
+                           [b](const auto &ptr) { return ptr.get() == b; });
+    
+    if (aIt == insts.end() || bIt == insts.end()) {
+      return false;
+    }
+    
+    return std::distance(insts.begin(), aIt) < std::distance(insts.begin(), bIt);
+  }
+  
+  // 不同基本块的情况，使用支配树
+  if (domTree) {
+    auto dominators = domTree->getDominators(bBB);
+    return dominators && dominators->count(aBB);
+  }
+  
+  return false; // 保守做法
+}
+
+bool GVNContext::isMemorySafe(LoadInst* earlierLoad, LoadInst* laterLoad) {
+  // 检查两个load是否访问相同的内存位置
+  unsigned earlierPtr = getValueNumber(earlierLoad->getPointer());
+  unsigned laterPtr = getValueNumber(laterLoad->getPointer());
+  
+  if (earlierPtr != laterPtr) {
+    return false; // 不同的内存位置
+  }
+  
+  // 检查类型是否匹配
+  if (earlierLoad->getType() != laterLoad->getType()) {
+    return false;
+  }
+  
+  // 简单情况：如果在同一个基本块且没有中间的store，则安全
+  auto earlierBB = earlierLoad->getParent();
+  auto laterBB = laterLoad->getParent();
+  
+  if (earlierBB != laterBB) {
+    // 跨基本块的情况需要更复杂的分析，暂时保守处理
+    return false;
+  }
+  
+  // 同一基本块内检查是否有中间的store
+  auto &insts = earlierBB->getInstructions();
+  auto earlierIt = std::find_if(insts.begin(), insts.end(),
+                               [earlierLoad](const auto &ptr) { return ptr.get() == earlierLoad; });
+  auto laterIt = std::find_if(insts.begin(), insts.end(),
+                              [laterLoad](const auto &ptr) { return ptr.get() == laterLoad; });
+  
+  if (earlierIt == insts.end() || laterIt == insts.end()) {
+    return false;
+  }
+  
+  // 确保earlierLoad真的在laterLoad之前
+  if (std::distance(insts.begin(), earlierIt) >= std::distance(insts.begin(), laterIt)) {
+    return false;
+  }
+  
+  // 检查中间是否有store指令修改了相同的内存位置
+  for (auto it = std::next(earlierIt); it != laterIt; ++it) {
+    if (auto store = dynamic_cast<StoreInst*>(it->get())) {
+      unsigned storePtr = getValueNumber(store->getPointer());
+      if (storePtr == earlierPtr) {
+        return false; // 找到中间的store
+      }
+    }
+    
+    // 检查函数调用是否可能修改内存
+    if (auto call = dynamic_cast<CallInst*>(it->get())) {
+      if (sideEffectAnalysis && !sideEffectAnalysis->isPureFunction(call->getCallee())) {
+        // 保守处理：有副作用的函数可能修改内存
+        return false;
+      }
+    }
+  }
+  
+  return true; // 安全
+}
+
+void GVNContext::invalidateMemoryValues(StoreInst* store) {
+  unsigned storePtr = getValueNumber(store->getPointer());
+  
+  if (DEBUG) {
+    std::cout << "        Invalidating memory values affected by store" << std::endl;
+  }
+  
+  // 找到所有可能被这个store影响的load表达式
+  std::vector<std::string> toRemove;
+  
+  for (auto& [exprKey, number] : expressionToNumber) {
+    if (exprKey.find("load_" + std::to_string(storePtr)) == 0) {
+      toRemove.push_back(exprKey);
+      if (DEBUG) {
+        std::cout << "          Invalidating expression: " << exprKey << std::endl;
+      }
+    }
+  }
+  
+  // 移除失效的表达式
+  for (const auto& key : toRemove) {
+    expressionToNumber.erase(key);
+  }
+}
+
+void GVNContext::eliminateRedundantInstructions(bool& changed) {
+  int removeCount = 0;
+  for (auto inst : needRemove) {
+    if (DEBUG) {
+      std::cout << "    Removing redundant instruction " << ++removeCount 
+                << "/" << needRemove.size() << ": " << inst->getName() << std::endl;
+    }
+    
+    // 删除指令前先断开所有使用关系
+    // inst->replaceAllUsesWith 已在 processInstruction 中调用
+    SysYIROptUtils::usedelete(inst);
+    changed = true;
+  }
+}
+
+} // namespace sysy

src/midend/Pass/Optimize/LICM.cpp

@@ -18,62 +18,214 @@ bool LICMContext::hoistInstructions() {
   // 1. 先收集所有可外提指令
   std::unordered_set<Instruction *> workSet(chars->invariantInsts.begin(), chars->invariantInsts.end());
 
+  if (DEBUG) {
+    std::cout << "LICM: Found " << workSet.size() << " candidate invariant instructions to hoist:" << std::endl;
+    for (auto *inst : workSet) {
+      std::cout << "  - " << inst->getName() << " (kind: " << static_cast<int>(inst->getKind()) 
+                << ", in BB: " << inst->getParent()->getName() << ")" << std::endl;
+    }
+  }
+
   // 2. 计算每个指令被依赖的次数（入度）
   std::unordered_map<Instruction *, int> indegree;
+  std::unordered_map<Instruction *, std::vector<Instruction *>> dependencies; // 记录依赖关系
+  std::unordered_map<Instruction *, std::vector<Instruction *>> dependents;   // 记录被依赖关系
+  
   for (auto *inst : workSet) {
     indegree[inst] = 0;
+    dependencies[inst] = {};
+    dependents[inst] = {};
   }
+  
+  if (DEBUG) {
+    std::cout << "LICM: Analyzing dependencies between invariant instructions..." << std::endl;
+  }
+  
   for (auto *inst : workSet) {
     for (size_t i = 0; i < inst->getNumOperands(); ++i) {
       if (auto *dep = dynamic_cast<Instruction *>(inst->getOperand(i))) {
         if (workSet.count(dep)) {
           indegree[inst]++;
+          dependencies[inst].push_back(dep);
+          dependents[dep].push_back(inst);
+          
+          if (DEBUG) {
+            std::cout << "  Dependency: " << inst->getName() << " depends on " << dep->getName() << std::endl;
+          }
         }
       }
     }
   }
 
+  if (DEBUG) {
+    std::cout << "LICM: Initial indegree analysis:" << std::endl;
+    for (auto &[inst, deg] : indegree) {
+      std::cout << "  " << inst->getName() << ": indegree=" << deg;
+      if (deg > 0) {
+        std::cout << ", depends on: ";
+        for (auto *dep : dependencies[inst]) {
+          std::cout << dep->getName() << " ";
+        }
+      }
+      std::cout << std::endl;
+    }
+  }
+
   // 3. Kahn拓扑排序
   std::vector<Instruction *> sorted;
   std::queue<Instruction *> q;
-  for (auto &[inst, deg] : indegree) {
-    if (deg == 0)
-      q.push(inst);
+  
+  if (DEBUG) {
+    std::cout << "LICM: Starting topological sort..." << std::endl;
   }
+  
+  for (auto &[inst, deg] : indegree) {
+    if (deg == 0) {
+      q.push(inst);
+      if (DEBUG) {
+        std::cout << "  Initial zero-indegree instruction: " << inst->getName() << std::endl;
+      }
+    }
+  }
+  
+  int sortStep = 0;
   while (!q.empty()) {
     auto *inst = q.front();
     q.pop();
     sorted.push_back(inst);
-    for (size_t i = 0; i < inst->getNumOperands(); ++i) {
-      if (auto *dep = dynamic_cast<Instruction *>(inst->getOperand(i))) {
-        if (workSet.count(dep)) {
-          indegree[dep]--;
-          if (indegree[dep] == 0)
-            q.push(dep);
+    
+    if (DEBUG) {
+      std::cout << "  Step " << (++sortStep) << ": Processing " << inst->getName() << std::endl;
+    }
+    
+    if (DEBUG) {
+      std::cout << "    Reducing indegree of dependents of " << inst->getName() << std::endl;
+    }
+    
+    // 正确的拓扑排序：当处理一个指令时，应该减少其所有使用者（dependents）的入度
+    for (auto *dependent : dependents[inst]) {
+      indegree[dependent]--;
+      if (DEBUG) {
+        std::cout << "      Reducing indegree of " << dependent->getName() << " to " << indegree[dependent] << std::endl;
+      }
+      if (indegree[dependent] == 0) {
+        q.push(dependent);
+        if (DEBUG) {
+          std::cout << "      Adding " << dependent->getName() << " to queue (indegree=0)" << std::endl;
         }
       }
     }
   }
 
-  // 检查是否全部排序，若未全部排序，说明有环（理论上不会）
+  // 检查是否全部排序，若未全部排序，打印错误信息
+  // 这可能是因为存在循环依赖或其他问题导致无法完成拓扑排序
   if (sorted.size() != workSet.size()) {
-    if (DEBUG)
-      std::cerr << "LICM: Topological sort failed, possible dependency cycle." << std::endl;
+    if (DEBUG) {
+      std::cout << "LICM: Topological sort failed! Sorted " << sorted.size() 
+                << " instructions out of " << workSet.size() << " total." << std::endl;
+      
+      // 找出未被排序的指令（形成循环依赖的指令）
+      std::unordered_set<Instruction *> remaining;
+      for (auto *inst : workSet) {
+        bool found = false;
+        for (auto *sortedInst : sorted) {
+          if (inst == sortedInst) {
+            found = true;
+            break;
+          }
+        }
+        if (!found) {
+          remaining.insert(inst);
+        }
+      }
+      
+      std::cout << "LICM: Instructions involved in dependency cycle:" << std::endl;
+      for (auto *inst : remaining) {
+        std::cout << "  - " << inst->getName() << " (indegree=" << indegree[inst] << ")" << std::endl;
+        std::cout << "    Dependencies within cycle: ";
+        for (auto *dep : dependencies[inst]) {
+          if (remaining.count(dep)) {
+            std::cout << dep->getName() << " ";
+          }
+        }
+        std::cout << std::endl;
+        std::cout << "    Dependents within cycle: ";
+        for (auto *dependent : dependents[inst]) {
+          if (remaining.count(dependent)) {
+            std::cout << dependent->getName() << " ";
+          }
+        }
+        std::cout << std::endl;
+      }
+      
+      // 尝试找出一个具体的循环路径
+      std::cout << "LICM: Attempting to trace a dependency cycle:" << std::endl;
+      if (!remaining.empty()) {
+        auto *start = *remaining.begin();
+        std::unordered_set<Instruction *> visited;
+        std::vector<Instruction *> path;
+        
+        std::function<bool(Instruction *)> findCycle = [&](Instruction *current) -> bool {
+          if (visited.count(current)) {
+            // 找到环
+            auto it = std::find(path.begin(), path.end(), current);
+            if (it != path.end()) {
+              std::cout << "  Cycle found: ";
+              for (auto cycleIt = it; cycleIt != path.end(); ++cycleIt) {
+                std::cout << (*cycleIt)->getName() << " -> ";
+              }
+              std::cout << current->getName() << std::endl;
+              return true;
+            }
+            return false;
+          }
+          
+          visited.insert(current);
+          path.push_back(current);
+          
+          for (auto *dep : dependencies[current]) {
+            if (remaining.count(dep)) {
+              if (findCycle(dep)) {
+                return true;
+              }
+            }
+          }
+          
+          path.pop_back();
+          return false;
+        };
+        
+        findCycle(start);
+      }
+    }
     return false;
   }
 
   // 4. 按拓扑序外提
+  if (DEBUG) {
+    std::cout << "LICM: Successfully completed topological sort. Hoisting instructions in order:" << std::endl;
+  }
+  
   for (auto *inst : sorted) {
     if (!inst)
       continue;
     BasicBlock *parent = inst->getParent();
     if (parent && loop->contains(parent)) {
+      if (DEBUG) {
+        std::cout << "  Hoisting " << inst->getName() << " from " << parent->getName() 
+                  << " to preheader " << preheader->getName() << std::endl;
+      }
       auto sourcePos = parent->findInstIterator(inst);
       auto targetPos = preheader->terminator();
       parent->moveInst(sourcePos, targetPos, preheader);
       changed = true;
     }
   }
+  
+  if (DEBUG && changed) {
+    std::cout << "LICM: Successfully hoisted " << sorted.size() << " invariant instructions" << std::endl;
+  }
+  
   return changed;
 }
 // ---- LICM Pass Implementation ----

src/midend/Pass/Pass.cpp

@@ -10,6 +10,7 @@
 #include "DCE.h"
 #include "Mem2Reg.h"
 #include "Reg2Mem.h"
+#include "GVN.h"
 #include "SCCP.h"
 #include "BuildCFG.h"
 #include "LargeArrayToGlobal.h"
@@ -59,6 +60,8 @@ void PassManager::runOptimizationPipeline(Module* moduleIR, IRBuilder* builderIR
     // 注册优化遍
     registerOptimizationPass<BuildCFG>();
     registerOptimizationPass<LargeArrayToGlobalPass>();
+
+    registerOptimizationPass<GVN>();
     
     registerOptimizationPass<SysYDelInstAfterBrPass>();
     registerOptimizationPass<SysYDelNoPreBLockPass>();
@@ -129,6 +132,15 @@ void PassManager::runOptimizationPipeline(Module* moduleIR, IRBuilder* builderIR
         printPasses();
       }
 
+      this->clearPasses();
+      this->addPass(&GVN::ID);
+      this->run();
+
+      if(DEBUG) {
+        std::cout << "=== IR After GVN Optimizations ===\n";
+        printPasses();
+      }
+
       this->clearPasses();
       this->addPass(&SCCP::ID);
       this->run();
@@ -141,12 +153,29 @@ void PassManager::runOptimizationPipeline(Module* moduleIR, IRBuilder* builderIR
       this->clearPasses();
       this->addPass(&LoopNormalizationPass::ID);
       this->addPass(&InductionVariableElimination::ID);
+      this->run();
+
+      if(DEBUG) {
+        std::cout << "=== IR After Loop Normalization, Induction Variable Elimination ===\n";
+        printPasses();
+      }
+      
+
+      this->clearPasses();
       this->addPass(&LICM::ID);
+      this->run();
+
+      if(DEBUG) {
+        std::cout << "=== IR After LICM ===\n";
+        printPasses();
+      }
+      
+      this->clearPasses();
       this->addPass(&LoopStrengthReduction::ID);
       this->run();
 
       if(DEBUG) {
-        std::cout << "=== IR After Loop Normalization, LICM, and Strength Reduction Optimizations ===\n";
+        std::cout << "=== IR After Loop Normalization, and Strength Reduction Optimizations ===\n";
         printPasses();
       }