diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst --- a/llvm/docs/LangRef.rst +++ b/llvm/docs/LangRef.rst @@ -12478,10 +12478,10 @@ Semantics: """""""""" -The '``llvm.memcpy.*``' intrinsics copy a block of memory from the -source location to the destination location, which are not allowed to -overlap. It copies "len" bytes of memory over. If the argument is known -to be aligned to some boundary, this can be specified as an attribute on +The '``llvm.memcpy.*``' intrinsics copy a block of memory from the source +location to the destination location, which must either completely overlap or +not overlap at all. It copies "len" bytes of memory over. If the argument is +known to be aligned to some boundary, this can be specified as an attribute on the argument. If "len" is 0, the pointers may be NULL, dangling, ``undef``, or ``poison`` diff --git a/llvm/lib/Analysis/BasicAliasAnalysis.cpp b/llvm/lib/Analysis/BasicAliasAnalysis.cpp --- a/llvm/lib/Analysis/BasicAliasAnalysis.cpp +++ b/llvm/lib/Analysis/BasicAliasAnalysis.cpp @@ -975,22 +975,14 @@ return ModRefInfo::NoModRef; } - // The semantics of memcpy intrinsics forbid overlap between their respective - // operands, i.e., source and destination of any given memcpy must no-alias. - // If Loc must-aliases either one of these two locations, then it necessarily - // no-aliases the other. + // The semantics of memcpy intrinsics either exactly overlap or do not + // overlap, i.e., source and destination of any given memcpy are either + // no-alias or must-alias. if (auto *Inst = dyn_cast(Call)) { - AliasResult SrcAA, DestAA; - - if ((SrcAA = getBestAAResults().alias(MemoryLocation::getForSource(Inst), - Loc, AAQI)) == MustAlias) - // Loc is exactly the memcpy source thus disjoint from memcpy dest. - return ModRefInfo::Ref; - if ((DestAA = getBestAAResults().alias(MemoryLocation::getForDest(Inst), - Loc, AAQI)) == MustAlias) - // The converse case. - return ModRefInfo::Mod; - + AliasResult SrcAA = + getBestAAResults().alias(MemoryLocation::getForSource(Inst), Loc, AAQI); + AliasResult DestAA = + getBestAAResults().alias(MemoryLocation::getForDest(Inst), Loc, AAQI); // It's also possible for Loc to alias both src and dest, or neither. ModRefInfo rv = ModRefInfo::NoModRef; if (SrcAA != NoAlias) diff --git a/llvm/test/Analysis/BasicAA/assume.ll b/llvm/test/Analysis/BasicAA/assume.ll --- a/llvm/test/Analysis/BasicAA/assume.ll +++ b/llvm/test/Analysis/BasicAA/assume.ll @@ -14,8 +14,8 @@ ; CHECK: MayAlias: i8* %P, i8* %Q ; CHECK: NoModRef: Ptr: i8* %P <-> tail call void @llvm.assume(i1 true) ; CHECK: NoModRef: Ptr: i8* %Q <-> tail call void @llvm.assume(i1 true) -; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) ; CHECK: NoModRef: tail call void @llvm.assume(i1 true) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) ; CHECK: NoModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <-> tail call void @llvm.assume(i1 true) } diff --git a/llvm/test/Analysis/BasicAA/cs-cs.ll b/llvm/test/Analysis/BasicAA/cs-cs.ll --- a/llvm/test/Analysis/BasicAA/cs-cs.ll +++ b/llvm/test/Analysis/BasicAA/cs-cs.ll @@ -17,12 +17,12 @@ ; CHECK-LABEL: Function: test2: ; CHECK: MayAlias: i8* %P, i8* %Q -; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) } define void @test2_atomic(i8* %P, i8* %Q) #3 { @@ -33,12 +33,12 @@ ; CHECK-LABEL: Function: test2_atomic: ; CHECK: MayAlias: i8* %P, i8* %Q -; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) -; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) -; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) -; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) -; CHECK: Just Mod: tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) -; CHECK: Just Mod: tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) +; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) +; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) +; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) +; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) +; CHECK: Both ModRef: tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) +; CHECK: Both ModRef: tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) <-> tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) } define void @test2a(i8* noalias %P, i8* noalias %Q) #3 { @@ -149,12 +149,12 @@ ; CHECK-LABEL: Function: test3: ; CHECK: MayAlias: i8* %P, i8* %Q -; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false) -; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false) -; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false) +; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false) +; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false) +; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 8, i1 false) } define void @test3a(i8* noalias %P, i8* noalias %Q) #3 { @@ -199,14 +199,14 @@ ; CHECK: MayAlias: i8* %P, i8* %Q ; CHECK: MayAlias: i8* %P, i8* %R ; CHECK: MayAlias: i8* %Q, i8* %R -; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) ; CHECK: Both ModRef: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) ; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) -; CHECK: Just Ref: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) -; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) -; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %R <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) +; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) +; CHECK: Both ModRef: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %R, i64 12, i1 false) <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) } define void @test5a(i8* noalias %P, i8* noalias %Q, i8* noalias %R) nounwind ssp { diff --git a/llvm/test/Analysis/BasicAA/guards.ll b/llvm/test/Analysis/BasicAA/guards.ll --- a/llvm/test/Analysis/BasicAA/guards.ll +++ b/llvm/test/Analysis/BasicAA/guards.ll @@ -14,8 +14,8 @@ ; CHECK: Just Ref: Ptr: i8* %P <-> tail call void (i1, ...) @llvm.experimental.guard(i1 true) [ "deopt"() ] ; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void (i1, ...) @llvm.experimental.guard(i1 true) [ "deopt"() ] -; CHECK: Just Mod: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) -; CHECK: Just Ref: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %P <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) +; CHECK: Both ModRef: Ptr: i8* %Q <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) ; CHECK: Just Ref: tail call void (i1, ...) @llvm.experimental.guard(i1 true) [ "deopt"() ] <-> tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) ; CHECK: Just Mod: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) <-> tail call void (i1, ...) @llvm.experimental.guard(i1 true) [ "deopt"() ] } diff --git a/llvm/test/Analysis/MemorySSA/basicaa-memcpy.ll b/llvm/test/Analysis/MemorySSA/basicaa-memcpy.ll --- a/llvm/test/Analysis/MemorySSA/basicaa-memcpy.ll +++ b/llvm/test/Analysis/MemorySSA/basicaa-memcpy.ll @@ -6,7 +6,7 @@ ; CHECK-LABEL: @source_clobber( ; CHECK-NEXT: ; 1 = MemoryDef(liveOnEntry) ; CHECK-NEXT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 128, i1 false) -; CHECK-NEXT: ; MemoryUse(liveOnEntry) +; CHECK-NEXT: ; MemoryUse(1) MayAlias ; CHECK-NEXT: [[X:%.*]] = load i8, i8* %b ; CHECK-NEXT: ret void ; diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/memset-and-memcpy.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/memset-and-memcpy.ll --- a/llvm/test/Transforms/DeadStoreElimination/MSSA/memset-and-memcpy.ll +++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/memset-and-memcpy.ll @@ -74,7 +74,8 @@ ; Previously this was not allowed (PR8728), also discussed in PR11763. define void @test18(i8* %P, i8* %Q, i8* %R) nounwind ssp { ; CHECK-LABEL: @test18( -; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[P:%.*]], i8* [[R:%.*]], i64 12, i1 false) +; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[P:%.*]], i8* [[Q:%.*]], i64 12, i1 false) +; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[P]], i8* [[R:%.*]], i64 12, i1 false) ; CHECK-NEXT: ret void ; tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* %P, i8* %Q, i64 12, i1 false) @@ -84,7 +85,8 @@ define void @test18_atomic(i8* %P, i8* %Q, i8* %R) nounwind ssp { ; CHECK-LABEL: @test18_atomic( -; CHECK-NEXT: tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 [[P:%.*]], i8* align 1 [[R:%.*]], i64 12, i32 1) +; CHECK-NEXT: tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 [[P:%.*]], i8* align 1 [[Q:%.*]], i64 12, i32 1) +; CHECK-NEXT: tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 [[P]], i8* align 1 [[R:%.*]], i64 12, i32 1) ; CHECK-NEXT: ret void ; tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 %P, i8* align 1 %Q, i64 12, i32 1) diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll --- a/llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll +++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll @@ -554,10 +554,12 @@ ret void } -; The memmove is dead, because memcpy arguments cannot overlap. +; See PR11763 - LLVM allows memcpy's source and destination to be equal (but not +; inequal and overlapping). define void @test38(i8* %P, i8* %Q, i8* %R) { ; CHECK-LABEL: @test38( -; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[P:%.*]], i8* [[R:%.*]], i64 12, i1 false) +; CHECK-NEXT: tail call void @llvm.memmove.p0i8.p0i8.i64(i8* [[P:%.*]], i8* [[Q:%.*]], i64 12, i1 false) +; CHECK-NEXT: tail call void @llvm.memcpy.p0i8.p0i8.i64(i8* [[P]], i8* [[R:%.*]], i64 12, i1 false) ; CHECK-NEXT: ret void ; @@ -566,10 +568,12 @@ ret void } -; The memmove is dead, because memcpy arguments cannot overlap. +; See PR11763 - LLVM allows memcpy's source and destination to be equal (but not +; inequal and overlapping). define void @test38_atomic(i8* %P, i8* %Q, i8* %R) { ; CHECK-LABEL: @test38_atomic( -; CHECK-NEXT: tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 [[P:%.*]], i8* align 1 [[R:%.*]], i64 12, i32 1) +; CHECK-NEXT: tail call void @llvm.memmove.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 [[P:%.*]], i8* align 1 [[Q:%.*]], i64 12, i32 1) +; CHECK-NEXT: tail call void @llvm.memcpy.element.unordered.atomic.p0i8.p0i8.i64(i8* align 1 [[P]], i8* align 1 [[R:%.*]], i64 12, i32 1) ; CHECK-NEXT: ret void ;