[LoopIdiom] Preserve alias information for memset_pattern

[wsmoses]

Summary

TBAA/NoAlias/AliasScope and other information is currently preserved
when upgrading to a memcpy/memset. However, this is missing when upgrading to
the macOS memset_pattern function. This adds the same alias information preservation
to memset_pattern

[efriedma]

llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp

1102

Please refactor so this code isn't repeated.

[wsmoses]

Reduce redundant code

[efriedma]

llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp

1093

if (!SplatValue && !isLibFuncEmittable(M, TLI, LibFunc_memset_pattern16))
  return Changed;

[wsmoses]

Address comments

[efriedma]

LGTM

llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp

1082

Whitespace

llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp

bool LoopIdiomRecognize::processLoopStridedStore(
   // TODO: ideally we should still be able to generate memset if SCEV expander
   // is taught to generate the dependencies at the latest point.
   if (!Expander.isSafeToExpand(NumBytesS))
     return Changed;
 
   Value *NumBytes =
       Expander.expandCodeFor(NumBytesS, IntIdxTy, Preheader->getTerminator());
 
-  CallInst *NewCall;
-  if (SplatValue) {
-    AAMDNodes AATags = TheStore->getAAMetadata();
-    for (Instruction *Store : Stores)
-      AATags = AATags.merge(Store->getAAMetadata());
-    if (auto CI = dyn_cast<ConstantInt>(NumBytes))
-      AATags = AATags.extendTo(CI->getZExtValue());
-    else
-      AATags = AATags.extendTo(-1);
+  AAMDNodes AATags;
+
+  if (!SplatValue && !isLibFuncEmittable(M, TLI, LibFunc_memset_pattern16))
+    return Changed;
+
+  AATags  = TheStore->getAAMetadata();
 
+  CallInst *NewCall;
+  if (SplatValue) {
     NewCall = Builder.CreateMemSet(
         BasePtr, SplatValue, NumBytes, MaybeAlign(StoreAlignment),
         /*isVolatile=*/false, AATags.TBAA, AATags.Scope, AATags.NoAlias);
-  } else if (isLibFuncEmittable(M, TLI, LibFunc_memset_pattern16)) {
+  } else {
+    assert (isLibFuncEmittable(M, TLI, LibFunc_memset_pattern16));
     // Everything is emitted in default address space
     Type *Int8PtrTy = DestInt8PtrTy;
 
     StringRef FuncName = "memset_pattern16";
     FunctionCallee MSP = getOrInsertLibFunc(M, *TLI, LibFunc_memset_pattern16,
                             Builder.getVoidTy(), Int8PtrTy, Int8PtrTy, IntIdxTy);
     inferNonMandatoryLibFuncAttrs(M, FuncName, *TLI);
 
     // Otherwise we should form a memset_pattern16.  PatternValue is known to be
     // an constant array of 16-bytes.  Plop the value into a mergable global.
     GlobalVariable *GV = new GlobalVariable(*M, PatternValue->getType(), true,
                                             GlobalValue::PrivateLinkage,
                                             PatternValue, ".memset_pattern");
     GV->setUnnamedAddr(GlobalValue::UnnamedAddr::Global); // Ok to merge these.
     GV->setAlignment(Align(16));
     Value *PatternPtr = ConstantExpr::getBitCast(GV, Int8PtrTy);
     NewCall = Builder.CreateCall(MSP, {BasePtr, PatternPtr, NumBytes});
-  } else
-    return Changed;
+    
+    // Set the TBAA info if present.
+    if (AATags.TBAA)
+      NewCall->setMetadata(LLVMContext::MD_tbaa, AATags.TBAA);
+
+    if (AATags.Scope)
+      NewCall->setMetadata(LLVMContext::MD_alias_scope, AATags.Scope);
+
+    if (AATags.NoAlias)
+      NewCall->setMetadata(LLVMContext::MD_noalias, AATags.NoAlias);
+  } 
 
   NewCall->setDebugLoc(TheStore->getDebugLoc());
 
   if (MSSAU) {
     MemoryAccess *NewMemAcc = MSSAU->createMemoryAccessInBB(
         NewCall, nullptr, NewCall->getParent(), MemorySSA::BeforeTerminator);
     MSSAU->insertDef(cast<MemoryDef>(NewMemAcc), true);
   }

llvm/test/Transforms/LoopIdiom/memset-pattern-tbaa.ll

+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -passes="loop-idiom" < %s -S | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
+
+target triple = "x86_64-apple-darwin10.0.0"
+
+
+define dso_local void @double_memset(ptr nocapture %p) {
+; CHECK-LABEL: @double_memset(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    call void @memset_pattern16(ptr [[P:%.*]], ptr @.memset_pattern, i64 128), !tbaa [[TBAA0:![0-9]+]]
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.cond.cleanup:
+; CHECK-NEXT:    ret void
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_07:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[PTR1:%.*]] = getelementptr inbounds double, ptr [[P]], i64 [[I_07]]
+; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_07]], 1
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 16
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+;
+entry:
+  br label %for.body
+
+for.cond.cleanup:
+  ret void
+
+for.body:
+  %i.07 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %ptr1 = getelementptr inbounds double, ptr %p, i64 %i.07
+  store double 3.14159e+00, ptr %ptr1, align 1, !tbaa !5
+  %inc = add nuw nsw i64 %i.07, 1
+  %exitcond.not = icmp eq i64 %inc, 16
+  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+}
+
+
+define dso_local void @struct_memset(ptr nocapture %p) {
+; CHECK-LABEL: @struct_memset(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    call void @memset_pattern16(ptr [[P:%.*]], ptr @.memset_pattern.1, i64 128), !tbaa [[TBAA4:![0-9]+]]
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.cond.cleanup:
+; CHECK-NEXT:    ret void
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_07:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[PTR1:%.*]] = getelementptr inbounds double, ptr [[P]], i64 [[I_07]]
+; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_07]], 1
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], 16
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+;
+entry:
+  br label %for.body
+
+for.cond.cleanup:
+  ret void
+
+for.body:
+  %i.07 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %ptr1 = getelementptr inbounds double, ptr %p, i64 %i.07
+  store double 3.14159e+00, ptr %ptr1, align 1, !tbaa !10
+  %inc = add nuw nsw i64 %i.07, 1
+  %exitcond.not = icmp eq i64 %inc, 16
+  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+}
+
+define dso_local void @var_memset(ptr nocapture %p, i64 %len) {
+; CHECK-LABEL: @var_memset(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = shl nuw i64 [[LEN:%.*]], 3
+; CHECK-NEXT:    call void @memset_pattern16(ptr [[P:%.*]], ptr @.memset_pattern.2, i64 [[TMP0]])
+; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
+; CHECK:       for.cond.cleanup:
+; CHECK-NEXT:    ret void
+; CHECK:       for.body:
+; CHECK-NEXT:    [[I_07:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[PTR1:%.*]] = getelementptr inbounds double, ptr [[P]], i64 [[I_07]]
+; CHECK-NEXT:    [[INC]] = add nuw nsw i64 [[I_07]], 1
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp eq i64 [[INC]], [[LEN]]
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
+;
+entry:
+  br label %for.body
+
+for.cond.cleanup:
+  ret void
+
+for.body:
+  %i.07 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
+  %ptr1 = getelementptr inbounds double, ptr %p, i64 %i.07
+  store double 3.14159e+00, ptr %ptr1, align 1, !tbaa !10
+  %inc = add nuw nsw i64 %i.07, 1
+  %exitcond.not = icmp eq i64 %inc, %len
+  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+}
+
+!5 = !{!6, !6, i64 0}
+!6 = !{!"double", !7, i64 0}
+!7 = !{!"omnipotent char", !8, i64 0}
+!8 = !{!"Simple C++ TBAA"}
+
+!15 = !{!8, i64 0, !"omnipotent char"}
+!17 = !{!15, i64 8, !"double"}
+!9 = !{!15, i64 32, !"_ZTS1A", !17, i64 0, i64 8, !17, i64 8, i64 8, !17, i64 16, i64 8, !17, i64 24, i64 8}
+!10 = !{!9, !17, i64 0, i64 1}
+
+!18 = !{!19, !20, i64 0}
+!19 = !{!"A", !20, i64 0, !22, i64 8}
+!20 = !{!"any pointer", !7, i64 0}
+!21 = !{!22, !20, i64 0}
+!22 = !{!"B", !20, i64 0}