[llvm] 8cb9c73 - [LoopIdiom] Keep TBAA when creating memcpy/memmove
William S. Moses via llvm-commits
llvm-commits at lists.llvm.org
Mon Jan 31 13:28:17 PST 2022
Author: William S. Moses
Date: 2022-01-31T16:28:13-05:00
New Revision: 8cb9c7360944b1e4dd2e8125a48ede3628b459f1
URL: https://github.com/llvm/llvm-project/commit/8cb9c7360944b1e4dd2e8125a48ede3628b459f1
DIFF: https://github.com/llvm/llvm-project/commit/8cb9c7360944b1e4dd2e8125a48ede3628b459f1.diff
LOG: [LoopIdiom] Keep TBAA when creating memcpy/memmove
When upgrading a loop of load/store to a memcpy, the existing pass does not keep existing aliasing information. This patch allows existing aliasing information to be kept.
Reviewed By: jeroen.dobbelaere
Differential Revision: https://reviews.llvm.org/D108221
Added:
llvm/test/Transforms/LoopIdiom/memcpy-tbaa.ll
llvm/test/Transforms/LoopIdiom/memmove-tbaa.ll
llvm/test/Transforms/LoopIdiom/memset-tbaa.ll
Modified:
llvm/include/llvm/IR/Metadata.h
llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp
llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
Removed:
################################################################################
diff --git a/llvm/include/llvm/IR/Metadata.h b/llvm/include/llvm/IR/Metadata.h
index 26d70b4db2d55..abd1dc33a78a5 100644
--- a/llvm/include/llvm/IR/Metadata.h
+++ b/llvm/include/llvm/IR/Metadata.h
@@ -682,6 +682,10 @@ struct AAMDNodes {
// Shift tbaa.struct Metadata node to start off bytes later
static MDNode *shiftTBAAStruct(MDNode *M, size_t off);
+ // Extend tbaa Metadata node to apply to a series of bytes of length len.
+ // A size of -1 denotes an unknown size.
+ static MDNode *extendToTBAA(MDNode *TBAA, ssize_t len);
+
/// Given two sets of AAMDNodes that apply to the same pointer,
/// give the best AAMDNodes that are compatible with both (i.e. a set of
/// nodes whose allowable aliasing conclusions are a subset of those
@@ -708,6 +712,21 @@ struct AAMDNodes {
return Result;
}
+ /// Create a new AAMDNode that describes this AAMDNode after extending it to
+ /// apply to a series of bytes of length Len. A size of -1 denotes an unknown
+ /// size.
+ AAMDNodes extendTo(ssize_t Len) const {
+ AAMDNodes Result;
+ Result.TBAA = TBAA ? extendToTBAA(TBAA, Len) : nullptr;
+ // tbaa.struct contains (offset, size, type) triples. Extending the length
+ // of the tbaa.struct doesn't require changing this (though more information
+ // could be provided by adding more triples at subsequent lengths).
+ Result.TBAAStruct = TBAAStruct;
+ Result.Scope = Scope;
+ Result.NoAlias = NoAlias;
+ return Result;
+ }
+
/// Given two sets of AAMDNodes applying to potentially
diff erent locations,
/// determine the best AAMDNodes that apply to both.
AAMDNodes merge(const AAMDNodes &Other) const;
diff --git a/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp b/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp
index 23dbb32f38de7..627a78a2a2fdb 100644
--- a/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp
+++ b/llvm/lib/Analysis/TypeBasedAliasAnalysis.cpp
@@ -786,3 +786,36 @@ MDNode *AAMDNodes::shiftTBAAStruct(MDNode *MD, size_t Offset) {
}
return MDNode::get(MD->getContext(), Sub);
}
+
+MDNode *AAMDNodes::extendToTBAA(MDNode *MD, ssize_t Len) {
+ // Fast path if 0-length
+ if (Len == 0)
+ return nullptr;
+
+ // Regular TBAA is invariant of length, so we only need to consider
+ // struct-path TBAA.
+ if (!isStructPathTBAA(MD))
+ return MD;
+
+ TBAAStructTagNode Tag(MD);
+
+ // Only new format TBAA has a size
+ if (!Tag.isNewFormat())
+ return MD;
+
+ // If unknown size, drop the TBAA.
+ if (Len == -1)
+ return nullptr;
+
+ // Otherwise, create TBAA with the new Len
+ SmallVector<Metadata *, 4> NextNodes(MD->operands());
+ ConstantInt *PreviousSize = mdconst::extract<ConstantInt>(NextNodes[3]);
+
+ // Don't create a new MDNode if it is the same length.
+ if (PreviousSize->equalsInt(Len))
+ return MD;
+
+ NextNodes[3] =
+ ConstantAsMetadata::get(ConstantInt::get(PreviousSize->getType(), Len));
+ return MDNode::get(MD->getContext(), NextNodes);
+}
diff --git a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
index 35ba4e2b4032d..318c4c06f0f70 100644
--- a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
@@ -1172,8 +1172,15 @@ bool LoopIdiomRecognize::processLoopStridedStore(
CallInst *NewCall;
if (SplatValue) {
- NewCall = Builder.CreateMemSet(BasePtr, SplatValue, NumBytes,
- MaybeAlign(StoreAlignment));
+ AAMDNodes AATags = TheStore->getAAMetadata();
+ if (auto CI = dyn_cast<ConstantInt>(NumBytes))
+ AATags = AATags.extendTo(CI->getZExtValue());
+ else
+ AATags = AATags.extendTo(-1);
+
+ NewCall = Builder.CreateMemSet(
+ BasePtr, SplatValue, NumBytes, MaybeAlign(StoreAlignment),
+ /*isVolatile=*/false, AATags.TBAA, AATags.Scope, AATags.NoAlias);
} else {
// Everything is emitted in default address space
Type *Int8PtrTy = DestInt8PtrTy;
@@ -1452,17 +1459,28 @@ bool LoopIdiomRecognize::processLoopStoreOfLoopLoad(
Value *NumBytes =
Expander.expandCodeFor(NumBytesS, IntIdxTy, Preheader->getTerminator());
+ AAMDNodes AATags = TheLoad->getAAMetadata();
+ AAMDNodes StoreAATags = TheStore->getAAMetadata();
+ AATags = AATags.merge(StoreAATags);
+ if (auto CI = dyn_cast<ConstantInt>(NumBytes))
+ AATags = AATags.extendTo(CI->getZExtValue());
+ else
+ AATags = AATags.extendTo(-1);
+
CallInst *NewCall = nullptr;
// Check whether to generate an unordered atomic memcpy:
// If the load or store are atomic, then they must necessarily be unordered
// by previous checks.
if (!TheStore->isAtomic() && !TheLoad->isAtomic()) {
if (UseMemMove)
- NewCall = Builder.CreateMemMove(StoreBasePtr, StoreAlign, LoadBasePtr,
- LoadAlign, NumBytes);
+ NewCall = Builder.CreateMemMove(
+ StoreBasePtr, StoreAlign, LoadBasePtr, LoadAlign, NumBytes,
+ /*isVolatile=*/false, AATags.TBAA, AATags.Scope, AATags.NoAlias);
else
- NewCall = Builder.CreateMemCpy(StoreBasePtr, StoreAlign, LoadBasePtr,
- LoadAlign, NumBytes);
+ NewCall =
+ Builder.CreateMemCpy(StoreBasePtr, StoreAlign, LoadBasePtr, LoadAlign,
+ NumBytes, /*isVolatile=*/false, AATags.TBAA,
+ AATags.TBAAStruct, AATags.Scope, AATags.NoAlias);
} else {
// For now don't support unordered atomic memmove.
if (UseMemMove)
@@ -1486,7 +1504,8 @@ bool LoopIdiomRecognize::processLoopStoreOfLoopLoad(
// have an alignment but non-atomic loads/stores may not.
NewCall = Builder.CreateElementUnorderedAtomicMemCpy(
StoreBasePtr, StoreAlign.getValue(), LoadBasePtr, LoadAlign.getValue(),
- NumBytes, StoreSize);
+ NumBytes, StoreSize, AATags.TBAA, AATags.TBAAStruct, AATags.Scope,
+ AATags.NoAlias);
}
NewCall->setDebugLoc(TheStore->getDebugLoc());
diff --git a/llvm/test/Transforms/LoopIdiom/memcpy-tbaa.ll b/llvm/test/Transforms/LoopIdiom/memcpy-tbaa.ll
new file mode 100644
index 0000000000000..5bb8131070d60
--- /dev/null
+++ b/llvm/test/Transforms/LoopIdiom/memcpy-tbaa.ll
@@ -0,0 +1,185 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -passes="loop-idiom" < %s -S | FileCheck %s
+
+define void @looper(double* noalias nocapture readonly %M, double* noalias nocapture %out) {
+; CHECK-LABEL: @looper(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[OUT1:%.*]] = bitcast double* [[OUT:%.*]] to i8*
+; CHECK-NEXT: [[M2:%.*]] = bitcast double* [[M:%.*]] to i8*
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[OUT1]], i8* align 8 [[M2]], i64 256, i1 false), !tbaa [[TBAA0:![0-9]+]]
+; CHECK-NEXT: br label [[FOR_BODY4:%.*]]
+; CHECK: for.body4:
+; CHECK-NEXT: [[J_020:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY4]] ]
+; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, double* [[M]], i64 [[J_020]]
+; CHECK-NEXT: [[A0:%.*]] = load double, double* [[ARRAYIDX]], align 8, !tbaa [[TBAA0]]
+; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[J_020]]
+; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[J_020]], 1
+; CHECK-NEXT: [[CMP2:%.*]] = icmp ult i64 [[J_020]], 31
+; CHECK-NEXT: br i1 [[CMP2]], label [[FOR_BODY4]], label [[FOR_COND_CLEANUP:%.*]]
+; CHECK: for.cond.cleanup:
+; CHECK-NEXT: ret void
+;
+entry:
+ br label %for.body4
+
+for.body4: ; preds = %for.cond1.preheader, %for.body4
+ %j.020 = phi i64 [ 0, %entry ], [ %inc, %for.body4 ]
+ %arrayidx = getelementptr inbounds double, double* %M, i64 %j.020
+ %a0 = load double, double* %arrayidx, align 8, !tbaa !5
+ %arrayidx8 = getelementptr inbounds double, double* %out, i64 %j.020
+ store double %a0, double* %arrayidx8, align 8, !tbaa !5
+ %inc = add nuw nsw i64 %j.020, 1
+ %cmp2 = icmp ult i64 %j.020, 31
+ br i1 %cmp2, label %for.body4, label %for.cond.cleanup
+
+for.cond.cleanup: ; preds = %for.cond.cleanup3
+ ret void
+}
+
+
+define void @looperBadMerge(double* noalias nocapture readonly %M, double* noalias nocapture %out) {
+; CHECK-LABEL: @looperBadMerge(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[OUT1:%.*]] = bitcast double* [[OUT:%.*]] to i8*
+; CHECK-NEXT: [[M2:%.*]] = bitcast double* [[M:%.*]] to i8*
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[OUT1]], i8* align 8 [[M2]], i64 256, i1 false), !tbaa [[TBAAF:![0-9]+]]
+; CHECK-NOT: tbaa
+; CHECK-NEXT: br label [[FOR_BODY4:%.*]]
+; CHECK: for.body4:
+; CHECK-NEXT: [[J_020:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY4]] ]
+; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, double* [[M]], i64 [[J_020]]
+; CHECK-NEXT: [[A0:%.*]] = load double, double* [[ARRAYIDX]], align 8, !tbaa [[TBAA0]]
+; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[J_020]]
+; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[J_020]], 1
+; CHECK-NEXT: [[CMP2:%.*]] = icmp ult i64 [[J_020]], 31
+; CHECK-NEXT: br i1 [[CMP2]], label [[FOR_BODY4]], label [[FOR_COND_CLEANUP:%.*]]
+; CHECK: for.cond.cleanup:
+; CHECK-NEXT: ret void
+;
+entry:
+ br label %for.body4
+
+for.body4: ; preds = %for.cond1.preheader, %for.body4
+ %j.020 = phi i64 [ 0, %entry ], [ %inc, %for.body4 ]
+ %arrayidx = getelementptr inbounds double, double* %M, i64 %j.020
+ %a0 = load double, double* %arrayidx, align 8, !tbaa !5
+ %arrayidx8 = getelementptr inbounds double, double* %out, i64 %j.020
+ store double %a0, double* %arrayidx8, align 8, !tbaa !3
+ %inc = add nuw nsw i64 %j.020, 1
+ %cmp2 = icmp ult i64 %j.020, 31
+ br i1 %cmp2, label %for.body4, label %for.cond.cleanup
+
+for.cond.cleanup: ; preds = %for.cond.cleanup3
+ ret void
+}
+
+define void @looperGoodMerge(double* noalias nocapture readonly %M, double* noalias nocapture %out) {
+; CHECK-LABEL: @looperGoodMerge(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[OUT1:%.*]] = bitcast double* [[OUT:%.*]] to i8*
+; CHECK-NEXT: [[M2:%.*]] = bitcast double* [[M:%.*]] to i8*
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[OUT1]], i8* align 8 [[M2]], i64 256, i1 false)
+; CHECK-NOT: !tbaa
+; CHECK-NEXT: br label [[FOR_BODY4:%.*]]
+; CHECK: for.body4:
+; CHECK-NEXT: [[J_020:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_BODY4]] ]
+; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds double, double* [[M]], i64 [[J_020]]
+; CHECK-NEXT: [[A0:%.*]] = load double, double* [[ARRAYIDX]], align 8, !tbaa [[TBAA0]]
+; CHECK-NEXT: [[ARRAYIDX8:%.*]] = getelementptr inbounds double, double* [[OUT]], i64 [[J_020]]
+; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[J_020]], 1
+; CHECK-NEXT: [[CMP2:%.*]] = icmp ult i64 [[J_020]], 31
+; CHECK-NEXT: br i1 [[CMP2]], label [[FOR_BODY4]], label [[FOR_COND_CLEANUP:%.*]]
+; CHECK: for.cond.cleanup:
+; CHECK-NEXT: ret void
+;
+entry:
+ br label %for.body4
+
+for.body4: ; preds = %for.cond1.preheader, %for.body4
+ %j.020 = phi i64 [ 0, %entry ], [ %inc, %for.body4 ]
+ %arrayidx = getelementptr inbounds double, double* %M, i64 %j.020
+ %a0 = load double, double* %arrayidx, align 8, !tbaa !5
+ %arrayidx8 = getelementptr inbounds double, double* %out, i64 %j.020
+ store double %a0, double* %arrayidx8, align 8
+ %inc = add nuw nsw i64 %j.020, 1
+ %cmp2 = icmp ult i64 %j.020, 31
+ br i1 %cmp2, label %for.body4, label %for.cond.cleanup
+
+for.cond.cleanup: ; preds = %for.cond.cleanup3
+ ret void
+}
+
+define void @looperConstantTBAAStruct(double* nocapture noalias %out, double* nocapture noalias %in) {
+; CHECK-LABEL: @looperConstantTBAAStruct(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[OUT1:%.*]] = bitcast double* [[OUT:%.*]] to i8*
+; CHECK-NEXT: [[IN1:%.*]] = bitcast double* [[IN:%.*]] to i8*
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[OUT1]], i8* align 8 [[IN1]], i64 32, i1 false), !tbaa [[TBAA8:![0-9]+]]
+;
+entry:
+ br label %for.body4
+
+for.body4: ; preds = %for.cond1.preheader, %for.body4
+ %j.020 = phi i64 [ 0, %entry ], [ %inc, %for.body4 ]
+ %arrayidx = getelementptr inbounds double, double* %in, i64 %j.020
+ %a0 = load double, double* %arrayidx, align 8, !tbaa !10
+ %arrayidx8 = getelementptr inbounds double, double* %out, i64 %j.020
+ store double %a0, double* %arrayidx8, align 8, !tbaa !10
+ %inc = add nuw nsw i64 %j.020, 1
+ %cmp2 = icmp ult i64 %j.020, 3
+ br i1 %cmp2, label %for.body4, label %for.cond.cleanup
+
+for.cond.cleanup: ; preds = %for.cond.cleanup3
+ ret void
+}
+
+define void @looperVarTBAAStruct(double* nocapture noalias %out, double* nocapture noalias %in, i64 %len) {
+; CHECK-LABEL: @looperVarTBAAStruct(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[OUT1:%.*]] = bitcast double* [[OUT:%.*]] to i8*
+; CHECK-NEXT: [[IN1:%.*]] = bitcast double* [[IN:%.*]] to i8*
+; CHECK-NEXT: [[umax:%.*]] = call i64 @llvm.umax.i64(i64 %len, i64 1)
+; CHECK-NEXT: [[I0:%.*]] = shl nuw i64 [[umax]], 3
+; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* align 8 [[OUT1]], i8* align 8 [[IN1]], i64 [[I0]], i1 false)
+; CHECK-NOT: !tbaa
+; CHECK-NEXT: br
+;
+entry:
+ br label %for.body4
+
+for.body4: ; preds = %for.cond1.preheader, %for.body4
+ %j.020 = phi i64 [ 0, %entry ], [ %inc, %for.body4 ]
+ %arrayidx = getelementptr inbounds double, double* %in, i64 %j.020
+ %a0 = load double, double* %arrayidx, align 8, !tbaa !10
+ %arrayidx8 = getelementptr inbounds double, double* %out, i64 %j.020
+ store double %a0, double* %arrayidx8, align 8, !tbaa !10
+ %inc = add nuw nsw i64 %j.020, 1
+ %cmp2 = icmp ult i64 %inc, %len
+ br i1 %cmp2, label %for.body4, label %for.cond.cleanup
+
+for.cond.cleanup: ; preds = %for.cond.cleanup3
+ ret void
+}
+
+
+; CHECK: [[TBAA0]] = !{[[TBAA1:.+]], [[TBAA1]], i64 0}
+; CHECK: [[TBAA1]] = !{!"double", [[TBAA2:.+]], i64 0}
+; CHECK: [[TBAA2]] = !{!"omnipotent char", [[TBAA3:.+]], i64 0}
+; CHECK: [[TBAAF]] = !{[[TBAA2]], [[TBAA2]], i64 0}
+
+; CHECK: [[TBAA8]] = !{[[TBAA5:.+]], [[TBAA6:.+]], i64 0, i64 32}
+; CHECK: [[TBAA5]] = !{[[TBAA7:.+]], i64 32, !"_ZTS1A", [[TBAA6]], i64 0, i64 8, [[TBAA6]], i64 8, i64 8, [[TBAA6]], i64 16, i64 8, [[TBAA6]], i64 24, i64 8}
+; CHECK: [[TBAA7]] = !{[[TBAA3]], i64 0, !"omnipotent char"}
+; CHECK: [[TBAA6]] = !{[[TBAA7]], i64 8, !"double"}
+
+!3 = !{!4, !4, i64 0}
+!4 = !{!"float", !7, i64 0}
+!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 8}
diff --git a/llvm/test/Transforms/LoopIdiom/memmove-tbaa.ll b/llvm/test/Transforms/LoopIdiom/memmove-tbaa.ll
new file mode 100644
index 0000000000000..5e6b36e843901
--- /dev/null
+++ b/llvm/test/Transforms/LoopIdiom/memmove-tbaa.ll
@@ -0,0 +1,96 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -passes="loop-idiom" < %s -S | FileCheck %s
+
+define void @looper(double* nocapture %out) {
+; CHECK-LABEL: @looper(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[OUT1:%.*]] = bitcast double* [[OUT:%.*]] to i8*
+; CHECK-NEXT: [[M:%.*]] = getelementptr double, double* %out, i32 16
+; CHECK-NEXT: [[M2:%.*]] = bitcast double* [[M]] to i8*
+; CHECK-NEXT: call void @llvm.memmove.p0i8.p0i8.i64(i8* align 8 [[OUT1]], i8* align 8 [[M2]], i64 256, i1 false), !tbaa [[TBAA0:![0-9]+]]
+;
+entry:
+ %M = getelementptr double, double* %out, i32 16
+ br label %for.body4
+
+for.body4: ; preds = %for.cond1.preheader, %for.body4
+ %j.020 = phi i64 [ 0, %entry ], [ %inc, %for.body4 ]
+ %arrayidx = getelementptr inbounds double, double* %M, i64 %j.020
+ %a0 = load double, double* %arrayidx, align 8, !tbaa !5
+ %arrayidx8 = getelementptr inbounds double, double* %out, i64 %j.020
+ store double %a0, double* %arrayidx8, align 8, !tbaa !5
+ %inc = add nuw nsw i64 %j.020, 1
+ %cmp2 = icmp ult i64 %j.020, 31
+ br i1 %cmp2, label %for.body4, label %for.cond.cleanup
+
+for.cond.cleanup: ; preds = %for.cond.cleanup3
+ ret void
+}
+
+
+define void @looperBadMerge(double* nocapture %out) {
+; CHECK-LABEL: @looperBadMerge(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[OUT1:%.*]] = bitcast double* [[OUT:%.*]] to i8*
+; CHECK-NEXT: [[M:%.*]] = getelementptr double, double* %out, i32 16
+; CHECK-NEXT: [[M2:%.*]] = bitcast double* [[M]] to i8*
+; CHECK-NEXT: call void @llvm.memmove.p0i8.p0i8.i64(i8* align 8 [[OUT1]], i8* align 8 [[M2]], i64 256, i1 false), !tbaa [[TBAAF:![0-9]+]]
+; CHECK-NEXT: br label [[FOR_BODY4:%.*]]
+;
+entry:
+ %M = getelementptr double, double* %out, i32 16
+ br label %for.body4
+
+for.body4: ; preds = %for.cond1.preheader, %for.body4
+ %j.020 = phi i64 [ 0, %entry ], [ %inc, %for.body4 ]
+ %arrayidx = getelementptr inbounds double, double* %M, i64 %j.020
+ %a0 = load double, double* %arrayidx, align 8, !tbaa !5
+ %arrayidx8 = getelementptr inbounds double, double* %out, i64 %j.020
+ store double %a0, double* %arrayidx8, align 8, !tbaa !3
+ %inc = add nuw nsw i64 %j.020, 1
+ %cmp2 = icmp ult i64 %j.020, 31
+ br i1 %cmp2, label %for.body4, label %for.cond.cleanup
+
+for.cond.cleanup: ; preds = %for.cond.cleanup3
+ ret void
+}
+
+define void @looperGoodMerge(double* nocapture %out) {
+; CHECK-LABEL: @looperGoodMerge(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[OUT1:%.*]] = bitcast double* [[OUT:%.*]] to i8*
+; CHECK-NEXT: [[M:%.*]] = getelementptr double, double* %out, i32 16
+; CHECK-NEXT: [[M2:%.*]] = bitcast double* [[M]] to i8*
+; CHECK-NEXT: call void @llvm.memmove.p0i8.p0i8.i64(i8* align 8 [[OUT1]], i8* align 8 [[M2]], i64 256, i1 false)
+; CHECK-NOT: !tbaa
+; CHECK-NEXT: br label [[FOR_BODY4:%.*]]
+;
+entry:
+ %M = getelementptr double, double* %out, i32 16
+ br label %for.body4
+
+for.body4: ; preds = %for.cond1.preheader, %for.body4
+ %j.020 = phi i64 [ 0, %entry ], [ %inc, %for.body4 ]
+ %arrayidx = getelementptr inbounds double, double* %M, i64 %j.020
+ %a0 = load double, double* %arrayidx, align 8, !tbaa !5
+ %arrayidx8 = getelementptr inbounds double, double* %out, i64 %j.020
+ store double %a0, double* %arrayidx8, align 8
+ %inc = add nuw nsw i64 %j.020, 1
+ %cmp2 = icmp ult i64 %j.020, 31
+ br i1 %cmp2, label %for.body4, label %for.cond.cleanup
+
+for.cond.cleanup: ; preds = %for.cond.cleanup3
+ ret void
+}
+
+; CHECK: [[TBAA0]] = !{[[TBAA1:.+]], [[TBAA1]], i64 0}
+; CHECK: [[TBAA1]] = !{!"double", [[TBAA2:.+]], i64 0}
+; CHECK: [[TBAA2]] = !{!"omnipotent char", [[TBAA3:.+]], i64 0}
+; CHECK: [[TBAAF]] = !{[[TBAA2]], [[TBAA2]], i64 0}
+
+!3 = !{!4, !4, i64 0}
+!4 = !{!"float", !7, i64 0}
+!5 = !{!6, !6, i64 0}
+!6 = !{!"double", !7, i64 0}
+!7 = !{!"omnipotent char", !8, i64 0}
+!8 = !{!"Simple C++ TBAA"}
diff --git a/llvm/test/Transforms/LoopIdiom/memset-tbaa.ll b/llvm/test/Transforms/LoopIdiom/memset-tbaa.ll
new file mode 100644
index 0000000000000..096056fa3be3c
--- /dev/null
+++ b/llvm/test/Transforms/LoopIdiom/memset-tbaa.ll
@@ -0,0 +1,111 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -passes="loop-idiom" < %s -S | FileCheck %s
+
+
+define dso_local void @double_memset(i8* nocapture %p) {
+; CHECK-LABEL: @double_memset(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[P:%.*]], i8 0, i64 16, i1 false), !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: [[INCDEC_PTR1:.+]] = getelementptr inbounds i8, i8* [[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_LOOPEXIT:%.*]], 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 i8, i8* %p, i64 %i.07
+ store i8 0, i8* %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(i8* nocapture %p) {
+; CHECK-LABEL: @struct_memset(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[P:%.*]], i8 0, i64 16, i1 false), !tbaa [[TBAA8:![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: [[INCDEC_PTR1:.+]] = getelementptr inbounds i8, i8* [[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_LOOPEXIT:%.*]], 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 i8, i8* %p, i64 %i.07
+ store i8 0, i8* %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(i8* nocapture %p, i64 %len) {
+; CHECK-LABEL: @var_memset(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* align 1 [[P:%.*]], i8 0, i64 %len, i1 false)
+; CHECK-NOT: !tbaa
+; 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: [[INCDEC_PTR1:.+]] = getelementptr inbounds i8, i8* [[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_LOOPEXIT:%.*]], 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 i8, i8* %p, i64 %i.07
+ store i8 0, i8* %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
+}
+
+; CHECK: [[TBAA0]] = !{[[TBAA1:.+]], [[TBAA1]], i64 0}
+; CHECK: [[TBAA1]] = !{!"double", [[TBAA2:.+]], i64 0}
+; CHECK: [[TBAA2]] = !{!"omnipotent char", [[TBAA3:.+]], i64 0}
+
+; CHECK: [[TBAA8]] = !{[[TBAA5:.+]], [[TBAA6:.+]], i64 0, i64 16}
+; CHECK: [[TBAA5]] = !{[[TBAA7:.+]], i64 32, !"_ZTS1A", [[TBAA6]], i64 0, i64 8, [[TBAA6]], i64 8, i64 8, [[TBAA6]], i64 16, i64 8, [[TBAA6]], i64 24, i64 8}
+; CHECK: [[TBAA7]] = !{[[TBAA3]], i64 0, !"omnipotent char"}
+; CHECK: [[TBAA6]] = !{[[TBAA7]], i64 8, !"double"}
+
+!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}
More information about the llvm-commits
mailing list