[llvm] 1ddb3a3 - [LangRef] Adjust guarantee for llvm.memcpy to also allow equal arguments.
Florian Hahn via llvm-commits
llvm-commits at lists.llvm.org
Sat Sep 5 11:18:50 PDT 2020
Author: Florian Hahn
Date: 2020-09-05T19:18:23+01:00
New Revision: 1ddb3a369f7ebdf738486cd60261c3143658c0e6
URL: https://github.com/llvm/llvm-project/commit/1ddb3a369f7ebdf738486cd60261c3143658c0e6
DIFF: https://github.com/llvm/llvm-project/commit/1ddb3a369f7ebdf738486cd60261c3143658c0e6.diff
LOG: [LangRef] Adjust guarantee for llvm.memcpy to also allow equal arguments.
This adjusts the description of `llvm.memcpy` to also allow operands
to be equal. This is in line with what Clang currently expects.
This change is intended to be temporary and followed by re-introduce
a variant with the non-overlapping guarantee for cases where we can
actually ensure that property in the front-end.
See the links below for more details:
http://lists.llvm.org/pipermail/cfe-dev/2020-August/066614.html
and PR11763.
Reviewed By: nikic
Differential Revision: https://reviews.llvm.org/D86815
Added:
Modified:
llvm/docs/LangRef.rst
llvm/lib/Analysis/BasicAliasAnalysis.cpp
llvm/test/Analysis/BasicAA/assume.ll
llvm/test/Analysis/BasicAA/cs-cs.ll
llvm/test/Analysis/BasicAA/guards.ll
llvm/test/Analysis/MemorySSA/basicaa-memcpy.ll
llvm/test/Transforms/DeadStoreElimination/MSSA/memset-and-memcpy.ll
llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll
Removed:
################################################################################
diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst
index 2bd7d09f698d..781b2385de50 100644
--- a/llvm/docs/LangRef.rst
+++ b/llvm/docs/LangRef.rst
@@ -12479,11 +12479,11 @@ very cleanly specified and it is unwise to depend on it.
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 argument.
+The '``llvm.memcpy.*``' intrinsics copy a block of memory from the source
+location to the destination location, which must either be equal or
+non-overlapping. 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``
pointers. However, they must still be appropriately aligned.
diff --git a/llvm/lib/Analysis/BasicAliasAnalysis.cpp b/llvm/lib/Analysis/BasicAliasAnalysis.cpp
index 2ede4baaf683..ca043b415b10 100644
--- a/llvm/lib/Analysis/BasicAliasAnalysis.cpp
+++ b/llvm/lib/Analysis/BasicAliasAnalysis.cpp
@@ -975,22 +975,14 @@ ModRefInfo BasicAAResult::getModRefInfo(const CallBase *Call,
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<AnyMemCpyInst>(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
index 1a7de5aa6afe..fe83a8c3df0e 100644
--- a/llvm/test/Analysis/BasicAA/assume.ll
+++ b/llvm/test/Analysis/BasicAA/assume.ll
@@ -14,8 +14,8 @@ define void @test1(i8* %P, i8* %Q) nounwind ssp {
; 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
index fa7a5f972aaf..49eedd427937 100644
--- a/llvm/test/Analysis/BasicAA/cs-cs.ll
+++ b/llvm/test/Analysis/BasicAA/cs-cs.ll
@@ -17,12 +17,12 @@ define void @test2(i8* %P, i8* %Q) #3 {
; 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 @@ define void @test2_atomic(i8* %P, i8* %Q) #3 {
; 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 @@ define void @test3(i8* %P, i8* %Q) #3 {
; 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 @@ define void @test5(i8* %P, i8* %Q, i8* %R) #3 {
; 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
index e6cee5f6d1e4..66293503ed4a 100644
--- a/llvm/test/Analysis/BasicAA/guards.ll
+++ b/llvm/test/Analysis/BasicAA/guards.ll
@@ -14,8 +14,8 @@ define void @test1(i8* %P, i8* %Q) {
; 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
index 83a554476847..678b652c6110 100644
--- a/llvm/test/Analysis/MemorySSA/basicaa-memcpy.ll
+++ b/llvm/test/Analysis/MemorySSA/basicaa-memcpy.ll
@@ -6,7 +6,7 @@ define void @source_clobber(i8* %a, i8* %b) {
; 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
index d54fe130d05f..5aeda1830972 100644
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/memset-and-memcpy.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/memset-and-memcpy.ll
@@ -68,13 +68,12 @@ define void @test17v(i8* %P, i8* %Q) nounwind ssp {
ret void
}
-; According to the current LangRef, memcpy's source and destination cannot
-; overlap, hence the first memcpy is dead.
-;
-; Previously this was not allowed (PR8728), also discussed in PR11763.
+; See PR11763 - LLVM allows memcpy's source and destination to be equal (but not
+; inequal and overlapping).
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 +83,8 @@ define void @test18(i8* %P, i8* %Q, i8* %R) nounwind ssp {
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
index 1ac6ad7d8158..9f719746f9f1 100644
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/simple.ll
@@ -554,10 +554,12 @@ define void @test37_atomic(i8* %P, i8* %Q, i8* %R) {
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 @@ define void @test38(i8* %P, i8* %Q, i8* %R) {
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
;
More information about the llvm-commits
mailing list