[LV] Avoid vectorizing unsafe dependencies in uniform address

Summary:
Currently, when vectorizing stores to uniform addresses, the only
instance we prevent vectorization is if there are multiple stores to the
same uniform address causing an unsafe dependency.
This patch teaches LAA to avoid vectorizing loops that have an unsafe
cross-iteration dependency between a load and a store to the same uniform address.

Fixes PR39653.

Reviewers: Ayal, efriedma

Subscribers: rkruppe, llvm-commits

Differential Revision: https://reviews.llvm.org/D54538

llvm-svn: 347220

include/llvm/Analysis/LoopAccessAnalysis.h

@@ -564,10 +564,10 @@ public:
   /// Print the information about the memory accesses in the loop.
   void print(raw_ostream &OS, unsigned Depth = 0) const;
 
-  /// If the loop has multiple stores to an invariant address, then
-  /// return true, else return false.
-  bool hasMultipleStoresToLoopInvariantAddress() const {
-    return HasMultipleStoresToLoopInvariantAddress;
+  /// If the loop has memory dependence involving an invariant address, i.e. two
+  /// stores or a store and a load, then return true, else return false.
+  bool hasDependenceInvolvingLoopInvariantAddress() const {
+    return HasDependenceInvolvingLoopInvariantAddress;
   }
 
   /// Used to add runtime SCEV checks. Simplifies SCEV expressions and converts
@@ -620,8 +620,8 @@ private:
   /// Cache the result of analyzeLoop.
   bool CanVecMem;
 
-  /// Indicator that there are multiple stores to a uniform address.
-  bool HasMultipleStoresToLoopInvariantAddress;
+  /// Indicator that there are non vectorizable stores to a uniform address.
+  bool HasDependenceInvolvingLoopInvariantAddress;
 
   /// The diagnostics report generated for the analysis.  E.g. why we
   /// couldn't analyze the loop.

lib/Analysis/LoopAccessAnalysis.cpp

@@ -1870,7 +1870,7 @@ void LoopAccessInfo::analyzeLoop(AliasAnalysis *AA, LoopInfo *LI,
     Value *Ptr = ST->getPointerOperand();
 
     if (isUniform(Ptr))
-      HasMultipleStoresToLoopInvariantAddress |=
+      HasDependenceInvolvingLoopInvariantAddress |=
           !UniformStores.insert(Ptr).second;
 
     // If we did *not* see this pointer before, insert it to  the read-write
@@ -1914,6 +1914,14 @@ void LoopAccessInfo::analyzeLoop(AliasAnalysis *AA, LoopInfo *LI,
       IsReadOnlyPtr = true;
     }
 
+    // See if there is an unsafe dependency between a load to a uniform address and
+    // store to the same uniform address.
+    if (UniformStores.count(Ptr)) {
+      LLVM_DEBUG(dbgs() << "LAA: Found an unsafe dependency between a uniform "
+                           "load and uniform store to the same address!\n");
+      HasDependenceInvolvingLoopInvariantAddress = true;
+    }
+
     MemoryLocation Loc = MemoryLocation::get(LD);
     // The TBAA metadata could have a control dependency on the predication
     // condition, so we cannot rely on it when determining whether or not we
@@ -2272,7 +2280,7 @@ LoopAccessInfo::LoopAccessInfo(Loop *L, ScalarEvolution *SE,
       PtrRtChecking(llvm::make_unique<RuntimePointerChecking>(SE)),
       DepChecker(llvm::make_unique<MemoryDepChecker>(*PSE, L)), TheLoop(L),
       NumLoads(0), NumStores(0), MaxSafeDepDistBytes(-1), CanVecMem(false),
-      HasMultipleStoresToLoopInvariantAddress(false) {
+      HasDependenceInvolvingLoopInvariantAddress(false) {
   if (canAnalyzeLoop())
     analyzeLoop(AA, LI, TLI, DT);
 }
@@ -2304,8 +2312,8 @@ void LoopAccessInfo::print(raw_ostream &OS, unsigned Depth) const {
   PtrRtChecking->print(OS, Depth);
   OS << "\n";
 
-  OS.indent(Depth) << "Multiple stores to invariant address were "
-                   << (HasMultipleStoresToLoopInvariantAddress ? "" : "not ")
+  OS.indent(Depth) << "Non vectorizable stores to invariant address were "
+                   << (HasDependenceInvolvingLoopInvariantAddress ? "" : "not ")
                    << "found in loop.\n";
 
   OS.indent(Depth) << "SCEV assumptions:\n";

lib/Transforms/Vectorize/LoopVectorizationLegality.cpp

@@ -817,15 +817,14 @@ bool LoopVectorizationLegality::canVectorizeMemory() {
   if (!LAI->canVectorizeMemory())
     return false;
 
-  if (LAI->hasMultipleStoresToLoopInvariantAddress()) {
+  if (LAI->hasDependenceInvolvingLoopInvariantAddress()) {
     ORE->emit(createMissedAnalysis("CantVectorizeStoreToLoopInvariantAddress")
-              << "multiple writes to a loop invariant address could not "
+              << "write to a loop invariant address could not "
                  "be vectorized");
     LLVM_DEBUG(
-        dbgs() << "LV: We don't allow multiple stores to a uniform address\n");
+        dbgs() << "LV: Non vectorizable stores to a uniform address\n");
     return false;
   }
-
   Requirements->addRuntimePointerChecks(LAI->getNumRuntimePointerChecks());
   PSE.addPredicate(LAI->getPSE().getUnionPredicate());
 

test/Analysis/LoopAccessAnalysis/memcheck-wrapping-pointers.ll

@@ -39,7 +39,7 @@ target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
 ; CHECK-NEXT:      Group
 ; CHECK-NEXT:        (Low: %b High: ((4 * (1 umax %x)) + %b))
 ; CHECK-NEXT:          Member: {%b,+,4}<%for.body>
-; CHECK:         Multiple stores to invariant address were not found in loop.
+; CHECK:         Non vectorizable stores to invariant address were not found in loop.
 ; CHECK-NEXT:    SCEV assumptions:
 ; CHECK-NEXT:    {1,+,1}<%for.body> Added Flags: <nusw>
 ; CHECK-NEXT:    {0,+,1}<%for.body> Added Flags: <nusw>

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

@@ -14,14 +14,14 @@
 ; The LAA with the new PM is a loop pass so we go from inner to outer loops.
 
 ; OLDPM: for.cond1.preheader:
-; OLDPM:   Multiple stores to invariant address were not found in loop.
+; OLDPM:   Non vectorizable stores to invariant address were not found in loop.
 ; OLDPM: for.body3:
-; OLDPM:   Multiple stores to invariant address were found in loop.
+; OLDPM:   Non vectorizable stores to invariant address were found in loop.
 
 ; NEWPM: for.body3:
-; NEWPM:   Multiple stores to invariant address were found in loop.
+; NEWPM:   Non vectorizable stores to invariant address were found in loop.
 ; NEWPM: for.cond1.preheader:
-; NEWPM:   Multiple stores to invariant address were not found in loop.
+; NEWPM:   Non vectorizable stores to invariant address were not found in loop.
 
 define i32 @foo(i32* nocapture %var1, i32* nocapture readonly %var2, i32 %itr) #0 {
 entry:

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

@@ -10,8 +10,8 @@
 ;    }
 ;  }
 
-; CHECK: Multiple stores to invariant address were not found in loop.
-; CHECK-NOT: Multiple stores to invariant address were found in loop.
+; CHECK: Non vectorizable stores to invariant address were not found in loop.
+; CHECK-NOT: Non vectorizable stores to invariant address were found in loop.
 
 
 define i32 @foo(i32* nocapture readonly %var1, i32* nocapture %var2, i32 %itr) #0 {

test/Analysis/LoopAccessAnalysis/store-to-invariant-check3.ll

@@ -10,7 +10,7 @@
 ;    }
 ;  }
 
-; CHECK: Multiple stores to invariant address were not found in loop.
+; CHECK: Non vectorizable stores to invariant address were not found in loop.
 
 define void @foo(i32* nocapture %var1, i32* nocapture %var2, i32 %itr) #0 {
 entry:

test/Transforms/LoopVectorize/invariant-store-vectorization.ll

@@ -551,3 +551,45 @@ for.inc8:                                         ; preds = %for.body3, %for.con
 for.end10:                                        ; preds = %for.inc8, %entry
   ret i32 undef
 }
+
+; cannot vectorize loop with unsafe dependency between uniform load (%tmp10) and store
+; (%tmp12) to the same address
+; PR39653
+; Note: %tmp10 could be replaced by phi(%arg4, %tmp12), a potentially vectorizable
+; 1st-order-recurrence
+define void @unsafe_dep_uniform_load_store(i32 %arg, i32 %arg1, i64 %arg2, i16* %arg3, i32 %arg4, i64 %arg5) {
+; CHECK-LABEL: unsafe_dep_uniform_load_store
+; CHECK-NOT: <4 x i32>
+bb:
+  %tmp = alloca i32
+  store i32 %arg4, i32* %tmp
+  %tmp6 = getelementptr inbounds i16, i16* %arg3, i64 %arg5
+  br label %bb7
+
+bb7:
+  %tmp8 = phi i64 [ 0, %bb ], [ %tmp24, %bb7 ]
+  %tmp9 = phi i32 [ %arg1, %bb ], [ %tmp23, %bb7 ]
+  %tmp10 = load i32, i32* %tmp
+  %tmp11 = mul nsw i32 %tmp9, %tmp10
+  %tmp12 = srem i32 %tmp11, 65536
+  %tmp13 = add nsw i32 %tmp12, %tmp9
+  %tmp14 = trunc i32 %tmp13 to i16
+  %tmp15 = trunc i64 %tmp8 to i32
+  %tmp16 = add i32 %arg, %tmp15
+  %tmp17 = zext i32 %tmp16 to i64
+  %tmp18 = getelementptr inbounds i16, i16* %tmp6, i64 %tmp17
+  store i16 %tmp14, i16* %tmp18, align 2
+  %tmp19 = add i32 %tmp13, %tmp9
+  %tmp20 = trunc i32 %tmp19 to i16
+  %tmp21 = and i16 %tmp20, 255
+  %tmp22 = getelementptr inbounds i16, i16* %arg3, i64 %tmp17
+  store i16 %tmp21, i16* %tmp22, align 2
+  %tmp23 = add nsw i32 %tmp9, 1
+  %tmp24 = add nuw nsw i64 %tmp8, 1
+  %tmp25 = icmp eq i64 %tmp24, %arg2
+  store i32 %tmp12, i32* %tmp
+  br i1 %tmp25, label %bb26, label %bb7
+
+bb26:
+  ret void
+}