[GVN] Basic optimization remark support

[recommitting after the fix in r288307]

Follow-on patches will add more interesting cases.

The goal of this patch-set is to get the GVN messages printed in
opt-viewer from Dhrystone as was presented in my Dev Meeting talk.  This
is the optimization view for the function (the last remark in the
function has a bug which is fixed in this series):
http://lab.llvm.org:8080/artifacts/opt-view_test-suite/build/SingleSource/Benchmarks/Dhrystone/CMakeFiles/dry.dir/html/_org_test-suite_SingleSource_Benchmarks_Dhrystone_dry.c.html#L430

Differential Revision: https://reviews.llvm.org/D26488

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@288370 91177308-0d34-0410-b5e6-96231b3b80d8

include/llvm/IR/DiagnosticInfo.h

@@ -392,6 +392,7 @@ public:
 
     explicit Argument(StringRef Str = "") : Key("String"), Val(Str) {}
     Argument(StringRef Key, Value *V);
+    Argument(StringRef Key, Type *T);
     Argument(StringRef Key, int N);
     Argument(StringRef Key, unsigned N);
     Argument(StringRef Key, bool B) : Key(Key), Val(B ? "true" : "false") {}

include/llvm/Transforms/Scalar/GVN.h

@@ -29,6 +29,7 @@
 #include "llvm/IR/PassManager.h"
 
 namespace llvm {
+class OptimizationRemarkEmitter;
 
 /// A private "module" namespace for types and utilities used by GVN. These
 /// are implementation details and should not be used by clients.
@@ -110,6 +111,7 @@ private:
   const TargetLibraryInfo *TLI;
   AssumptionCache *AC;
   SetVector<BasicBlock *> DeadBlocks;
+  OptimizationRemarkEmitter *ORE;
 
   ValueTable VN;
 
@@ -135,7 +137,8 @@ private:
 
   bool runImpl(Function &F, AssumptionCache &RunAC, DominatorTree &RunDT,
                const TargetLibraryInfo &RunTLI, AAResults &RunAA,
-               MemoryDependenceResults *RunMD, LoopInfo *LI);
+               MemoryDependenceResults *RunMD, LoopInfo *LI,
+               OptimizationRemarkEmitter *ORE);
 
   /// Push a new Value to the LeaderTable onto the list for its value number.
   void addToLeaderTable(uint32_t N, Value *V, const BasicBlock *BB) {

lib/IR/DiagnosticInfo.cpp

@@ -180,6 +180,12 @@ DiagnosticInfoOptimizationBase::Argument::Argument(StringRef Key, Value *V)
     DLoc = I->getDebugLoc();
 }
 
+DiagnosticInfoOptimizationBase::Argument::Argument(StringRef Key, Type *T)
+    : Key(Key) {
+  raw_string_ostream OS(Val);
+  OS << *T;
+}
+
 DiagnosticInfoOptimizationBase::Argument::Argument(StringRef Key, int N)
     : Key(Key), Val(itostr(N)) {}
 

lib/Transforms/Scalar/GVN.cpp

@@ -33,6 +33,7 @@
 #include "llvm/Analysis/Loads.h"
 #include "llvm/Analysis/MemoryBuiltins.h"
 #include "llvm/Analysis/MemoryDependenceAnalysis.h"
+#include "llvm/Analysis/OptimizationDiagnosticInfo.h"
 #include "llvm/Analysis/PHITransAddr.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/ValueTracking.h"
@@ -587,7 +588,8 @@ PreservedAnalyses GVN::run(Function &F, FunctionAnalysisManager &AM) {
   auto &AA = AM.getResult<AAManager>(F);
   auto &MemDep = AM.getResult<MemoryDependenceAnalysis>(F);
   auto *LI = AM.getCachedResult<LoopAnalysis>(F);
-  bool Changed = runImpl(F, AC, DT, TLI, AA, &MemDep, LI);
+  auto &ORE = AM.getResult<OptimizationRemarkEmitterAnalysis>(F);
+  bool Changed = runImpl(F, AC, DT, TLI, AA, &MemDep, LI, &ORE);
   if (!Changed)
     return PreservedAnalyses::all();
   PreservedAnalyses PA;
@@ -1583,10 +1585,18 @@ bool GVN::PerformLoadPRE(LoadInst *LI, AvailValInBlkVect &ValuesPerBlock,
   if (V->getType()->getScalarType()->isPointerTy())
     MD->invalidateCachedPointerInfo(V);
   markInstructionForDeletion(LI);
+  ORE->emit(OptimizationRemark(DEBUG_TYPE, "LoadPRE", LI)
+            << "load eliminated by PRE");
   ++NumPRELoad;
   return true;
 }
 
+static void reportLoadElim(LoadInst *LI, OptimizationRemarkEmitter *ORE) {
+  ORE->emit(OptimizationRemark(DEBUG_TYPE, "LoadElim", LI)
+            << "load of type " << ore::NV("Type", LI->getType())
+            << " eliminated");
+}
+
 /// Attempt to eliminate a load whose dependencies are
 /// non-local by performing PHI construction.
 bool GVN::processNonLocalLoad(LoadInst *LI) {
@@ -1657,6 +1667,7 @@ bool GVN::processNonLocalLoad(LoadInst *LI) {
       MD->invalidateCachedPointerInfo(V);
     markInstructionForDeletion(LI);
     ++NumGVNLoad;
+    reportLoadElim(LI, ORE);
     return true;
   }
 
@@ -1803,6 +1814,7 @@ bool GVN::processLoad(LoadInst *L) {
     patchAndReplaceAllUsesWith(L, AvailableValue);
     markInstructionForDeletion(L);
     ++NumGVNLoad;
+    reportLoadElim(L, ORE);
     // Tell MDA to rexamine the reused pointer since we might have more
     // information after forwarding it.
     if (MD && AvailableValue->getType()->getScalarType()->isPointerTy())
@@ -2180,7 +2192,8 @@ bool GVN::processInstruction(Instruction *I) {
 /// runOnFunction - This is the main transformation entry point for a function.
 bool GVN::runImpl(Function &F, AssumptionCache &RunAC, DominatorTree &RunDT,
                   const TargetLibraryInfo &RunTLI, AAResults &RunAA,
-                  MemoryDependenceResults *RunMD, LoopInfo *LI) {
+                  MemoryDependenceResults *RunMD, LoopInfo *LI,
+                  OptimizationRemarkEmitter *RunORE) {
   AC = &RunAC;
   DT = &RunDT;
   VN.setDomTree(DT);
@@ -2188,6 +2201,7 @@ bool GVN::runImpl(Function &F, AssumptionCache &RunAC, DominatorTree &RunDT,
   VN.setAliasAnalysis(&RunAA);
   MD = RunMD;
   VN.setMemDep(MD);
+  ORE = RunORE;
 
   bool Changed = false;
   bool ShouldContinue = true;
@@ -2703,7 +2717,8 @@ public:
         getAnalysis<AAResultsWrapperPass>().getAAResults(),
         NoLoads ? nullptr
                 : &getAnalysis<MemoryDependenceWrapperPass>().getMemDep(),
-        LIWP ? &LIWP->getLoopInfo() : nullptr);
+        LIWP ? &LIWP->getLoopInfo() : nullptr,
+        &getAnalysis<OptimizationRemarkEmitterWrapperPass>().getORE());
   }
 
   void getAnalysisUsage(AnalysisUsage &AU) const override {
@@ -2716,6 +2731,7 @@ public:
 
     AU.addPreserved<DominatorTreeWrapperPass>();
     AU.addPreserved<GlobalsAAWrapperPass>();
+    AU.addRequired<OptimizationRemarkEmitterWrapperPass>();
   }
 
 private:
@@ -2737,4 +2753,5 @@ INITIALIZE_PASS_DEPENDENCY(DominatorTreeWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(TargetLibraryInfoWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(AAResultsWrapperPass)
 INITIALIZE_PASS_DEPENDENCY(GlobalsAAWrapperPass)
+INITIALIZE_PASS_DEPENDENCY(OptimizationRemarkEmitterWrapperPass)
 INITIALIZE_PASS_END(GVNLegacyPass, "gvn", "Global Value Numbering", false, false)

test/Transforms/GVN/opt-remarks.ll

@@ -0,0 +1,59 @@
+; RUN: opt < %s -gvn -o /dev/null  -pass-remarks-output=%t -S -pass-remarks=gvn \
+; RUN:     2>&1 | FileCheck %s
+; RUN: cat %t | FileCheck -check-prefix=YAML %s
+
+; CHECK:      remark: <unknown>:0:0: load of type i32 eliminated{{$}}
+; CHECK-NEXT: remark: <unknown>:0:0: load of type i32 eliminated{{$}}
+; CHECK-NEXT: remark: <unknown>:0:0: load of type i32 eliminated{{$}}
+; CHECK-NOT:  remark:
+
+; YAML:      --- !Passed
+; YAML-NEXT: Pass:            gvn
+; YAML-NEXT: Name:            LoadElim
+; YAML-NEXT: Function:        arg
+; YAML-NEXT: Args:
+; YAML-NEXT:   - String:          'load of type '
+; YAML-NEXT:   - Type:            i32
+; YAML-NEXT:   - String:          ' eliminated'
+; YAML-NEXT: ...
+; YAML-NEXT: --- !Passed
+; YAML-NEXT: Pass:            gvn
+; YAML-NEXT: Name:            LoadElim
+; YAML-NEXT: Function:        const
+; YAML-NEXT: Args:
+; YAML-NEXT:   - String:          'load of type '
+; YAML-NEXT:   - Type:            i32
+; YAML-NEXT:   - String:          ' eliminated'
+; YAML-NEXT: ...
+; YAML-NEXT: --- !Passed
+; YAML-NEXT: Pass:            gvn
+; YAML-NEXT: Name:            LoadElim
+; YAML-NEXT: Function:        inst
+; YAML-NEXT: Args:
+; YAML-NEXT:   - String:          'load of type '
+; YAML-NEXT:   - Type:            i32
+; YAML-NEXT:   - String:          ' eliminated'
+; YAML-NEXT: ...
+
+
+define i32 @arg(i32* %p, i32 %i) {
+entry:
+  store i32 %i, i32* %p
+  %load = load i32, i32* %p
+  ret i32 %load
+}
+
+define i32 @const(i32* %p) {
+entry:
+  store i32 4, i32* %p
+  %load = load i32, i32* %p
+  ret i32 %load
+}
+
+define i32 @inst(i32* %p) {
+entry:
+  %load1 = load i32, i32* %p
+  %load = load i32, i32* %p
+  %add = add i32 %load1, %load
+  ret i32 %add
+}