Revert "[LoopAccesses] Allow analysis to complete in the presence of uniform stores"

This reverts commit r234361.

It caused PR23157.

llvm-svn: 234387

llvm/include/llvm/Analysis/LoopAccessAnalysis.h

@@ -432,13 +432,6 @@ public:
   /// Only used in DEBUG build but we don't want NDEBUG-dependent ABI.
   unsigned NumSymbolicStrides;
 
-  /// \brief Checks existence of store to invariant address inside loop.
-  /// If the loop has any store to invariant address, then it returns true,
-  /// else returns false.
-  bool hasStoreToLoopInvariantAddress() const {
-    return StoreToLoopInvariantAddress;
-  }
-
 private:
   /// \brief Analyze the loop.  Substitute symbolic strides using Strides.
   void analyzeLoop(const ValueToValueMap &Strides);
@@ -476,10 +469,6 @@ private:
   /// \brief Cache the result of analyzeLoop.
   bool CanVecMem;
 
-  /// \brief Indicator for storing to uniform addresses.
-  /// If a loop has write to a loop invariant address then it should be true.
-  bool StoreToLoopInvariantAddress;
-
   /// \brief The diagnostics report generated for the analysis.  E.g. why we
   /// couldn't analyze the loop.
   Optional<LoopAccessReport> Report;

llvm/lib/Analysis/LoopAccessAnalysis.cpp

@@ -1044,8 +1044,16 @@ void LoopAccessInfo::analyzeLoop(const ValueToValueMap &Strides) {
   for (I = Stores.begin(), IE = Stores.end(); I != IE; ++I) {
     StoreInst *ST = cast<StoreInst>(*I);
     Value* Ptr = ST->getPointerOperand();
-    // Check for store to loop invariant address.
+
-    StoreToLoopInvariantAddress = isUniform(Ptr);
+    if (isUniform(Ptr)) {
+      emitAnalysis(
+          LoopAccessReport(ST)
+          << "write to a loop invariant address could not be vectorized");
+      DEBUG(dbgs() << "LAA: We don't allow storing to uniform addresses\n");
+      CanVecMem = false;
+      return;
+    }
+
     // If we did *not* see this pointer before, insert it to  the read-write
     // list. At this phase it is only a 'write' list.
     if (Seen.insert(Ptr).second) {
@@ -1306,8 +1314,7 @@ LoopAccessInfo::LoopAccessInfo(Loop *L, ScalarEvolution *SE,
                                const ValueToValueMap &Strides)
     : DepChecker(SE, L), NumComparisons(0), TheLoop(L), SE(SE), DL(DL),
       TLI(TLI), AA(AA), DT(DT), NumLoads(0), NumStores(0),
-      MaxSafeDepDistBytes(-1U), CanVecMem(false),
+      MaxSafeDepDistBytes(-1U), CanVecMem(false) {
-      StoreToLoopInvariantAddress(false) {
   if (canAnalyzeLoop())
     analyzeLoop(Strides);
 }
@@ -1320,10 +1327,6 @@ void LoopAccessInfo::print(raw_ostream &OS, unsigned Depth) const {
       OS.indent(Depth) << "Memory dependences are safe with run-time checks\n";
   }
 
-  OS.indent(Depth) << "Store to invariant address was "
-                   << (StoreToLoopInvariantAddress ? "" : "not ")
-                   << "found in loop.\n";
-
   if (Report)
     OS.indent(Depth) << "Report: " << Report->str() << "\n";
 

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -4009,14 +4009,6 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
   if (!LAI->canVectorizeMemory())
     return false;
 
-  if (LAI->hasStoreToLoopInvariantAddress()) {
-    emitAnalysis(
-        VectorizationReport()
-        << "write to a loop invariant address could not be vectorized");
-    DEBUG(dbgs() << "LV: We don't allow storing to uniform addresses\n");
-    return false;
-  }
-
   if (LAI->getNumRuntimePointerChecks() >
       VectorizerParams::RuntimeMemoryCheckThreshold) {
     emitAnalysis(VectorizationReport()

llvm/test/Analysis/LoopAccessAnalysis/store-to-invariant-check1.ll

@@ -1,53 +0,0 @@
-; RUN: opt < %s -loop-accesses -analyze | FileCheck %s
-
-; Test to confirm LAA will find store to invariant address.
-; Inner loop has a store to invariant address.
-;
-;  for(; i < itr; i++) {
-;    for(; j < itr; j++) {
-;      var1[i] = var2[j] + var1[i];
-;    }
-;  }
-
-; CHECK: Store to invariant address was found in loop.
-; CHECK-NOT: Store to invariant address was not found in loop.
-
-define i32 @foo(i32* nocapture %var1, i32* nocapture readonly %var2, i32 %itr) #0 {
-entry:
-  %cmp20 = icmp eq i32 %itr, 0
-  br i1 %cmp20, label %for.end10, label %for.cond1.preheader
-
-for.cond1.preheader:                              ; preds = %entry, %for.inc8
-  %indvars.iv23 = phi i64 [ %indvars.iv.next24, %for.inc8 ], [ 0, %entry ]
-  %j.022 = phi i32 [ %j.1.lcssa, %for.inc8 ], [ 0, %entry ]
-  %cmp218 = icmp ult i32 %j.022, %itr
-  br i1 %cmp218, label %for.body3.lr.ph, label %for.inc8
-
-for.body3.lr.ph:                                  ; preds = %for.cond1.preheader
-  %arrayidx5 = getelementptr inbounds i32, i32* %var1, i64 %indvars.iv23
-  %0 = zext i32 %j.022 to i64
-  br label %for.body3
-
-for.body3:                                        ; preds = %for.body3, %for.body3.lr.ph
-  %indvars.iv = phi i64 [ %0, %for.body3.lr.ph ], [ %indvars.iv.next, %for.body3 ]
-  %arrayidx = getelementptr inbounds i32, i32* %var2, i64 %indvars.iv
-  %1 = load i32, i32* %arrayidx, align 4
-  %2 = load i32, i32* %arrayidx5, align 4
-  %add = add nsw i32 %2, %1
-  store i32 %add, i32* %arrayidx5, align 4
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
-  %exitcond = icmp eq i32 %lftr.wideiv, %itr
-  br i1 %exitcond, label %for.inc8, label %for.body3
-
-for.inc8:                                         ; preds = %for.body3, %for.cond1.preheader
-  %j.1.lcssa = phi i32 [ %j.022, %for.cond1.preheader ], [ %itr, %for.body3 ]
-  %indvars.iv.next24 = add nuw nsw i64 %indvars.iv23, 1
-  %lftr.wideiv25 = trunc i64 %indvars.iv.next24 to i32
-  %exitcond26 = icmp eq i32 %lftr.wideiv25, %itr
-  br i1 %exitcond26, label %for.end10, label %for.cond1.preheader
-
-for.end10:                                        ; preds = %for.inc8, %entry
-  ret i32 undef
-}
-

llvm/test/Analysis/LoopAccessAnalysis/store-to-invariant-check2.ll

@@ -1,54 +0,0 @@
-; RUN: opt < %s -loop-accesses -analyze  | FileCheck %s
-
-; Test to confirm LAA will not find store to invariant address.
-; Inner loop has no store to invariant address.
-;
-;  for(; i < itr; i++) {
-;    for(; j < itr; j++) {
-;      var2[j] = var2[j] + var1[i];
-;    }
-;  }
-
-; CHECK: Store to invariant address was not found in loop.
-; CHECK-NOT: Store to invariant address was found in loop.
-
-
-define i32 @foo(i32* nocapture readonly %var1, i32* nocapture %var2, i32 %itr) #0 {
-entry:
-  %cmp20 = icmp eq i32 %itr, 0
-  br i1 %cmp20, label %for.end10, label %for.cond1.preheader
-
-for.cond1.preheader:                              ; preds = %entry, %for.inc8
-  %indvars.iv23 = phi i64 [ %indvars.iv.next24, %for.inc8 ], [ 0, %entry ]
-  %j.022 = phi i32 [ %j.1.lcssa, %for.inc8 ], [ 0, %entry ]
-  %cmp218 = icmp ult i32 %j.022, %itr
-  br i1 %cmp218, label %for.body3.lr.ph, label %for.inc8
-
-for.body3.lr.ph:                                  ; preds = %for.cond1.preheader
-  %arrayidx5 = getelementptr inbounds i32, i32* %var1, i64 %indvars.iv23
-  %0 = zext i32 %j.022 to i64
-  br label %for.body3
-
-for.body3:                                        ; preds = %for.body3, %for.body3.lr.ph
-  %indvars.iv = phi i64 [ %0, %for.body3.lr.ph ], [ %indvars.iv.next, %for.body3 ]
-  %arrayidx = getelementptr inbounds i32, i32* %var2, i64 %indvars.iv
-  %1 = load i32, i32* %arrayidx, align 4
-  %2 = load i32, i32* %arrayidx5, align 4
-  %add = add nsw i32 %2, %1
-  store i32 %add, i32* %arrayidx, align 4
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
-  %exitcond = icmp eq i32 %lftr.wideiv, %itr
-  br i1 %exitcond, label %for.inc8, label %for.body3
-
-for.inc8:                                         ; preds = %for.body3, %for.cond1.preheader
-  %j.1.lcssa = phi i32 [ %j.022, %for.cond1.preheader ], [ %itr, %for.body3 ]
-  %indvars.iv.next24 = add nuw nsw i64 %indvars.iv23, 1
-  %lftr.wideiv25 = trunc i64 %indvars.iv.next24 to i32
-  %exitcond26 = icmp eq i32 %lftr.wideiv25, %itr
-  br i1 %exitcond26, label %for.end10, label %for.cond1.preheader
-
-for.end10:                                        ; preds = %for.inc8, %entry
-  ret i32 undef
-}
-