Skip to content

[MemCpyOpt] No need to create memcpy(a <- a) #98321

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Jul 11, 2024
Merged

[MemCpyOpt] No need to create memcpy(a <- a) #98321

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4e61f5d
Pre-commit test cases
dianqk Jul 10, 2024
ec1ab1c
[MemCpyOpt] No need to create `memcpy(a <- a)`
dianqk Jul 10, 2024
385ace3
Address comments
dianqk Jul 10, 2024
dd9c190
Address comments
dianqk Jul 10, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 8 additions & 0 deletions llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1161,6 +1161,14 @@ bool MemCpyOptPass::processMemCpyMemCpyDependence(MemCpyInst *M,
MSSA->getMemoryAccess(MDep), MSSA->getMemoryAccess(M)))
return false;

// No need to create `memcpy(a <- a)`.
if (BAA.isMustAlias(M->getDest(), MDep->getSource())) {
// Remove the instruction we're replacing.
eraseInstruction(M);
++NumMemCpyInstr;
return true;
}

// If the dest of the second might alias the source of the first, then the
// source and dest might overlap. In addition, if the source of the first
// points to constant memory, they won't overlap by definition. Otherwise, we
Expand Down
31 changes: 31 additions & 0 deletions llvm/test/Transforms/MemCpyOpt/memcpy.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,6 +139,37 @@ define void @test6_memcpy(ptr %src, ptr %dest) nounwind {
ret void
}

; When forwarding to memcpy(arg+1, arg+1), we don't need to create this memcpy.
define void @test6_memcpy_forward_back(ptr %arg) nounwind {
; CHECK-LABEL: @test6_memcpy_forward_back(
; CHECK-NEXT: [[DEST:%.*]] = getelementptr inbounds i8, ptr [[ARG:%.*]], i64 1
; CHECK-NEXT: ret void
;
%tmp = alloca [16 x i8], align 1
%src = getelementptr inbounds i8, ptr %arg, i64 1
%dest = getelementptr inbounds i8, ptr %arg, i64 1
call void @llvm.memcpy.inline.p0.p0.i32(ptr align 1 %tmp, ptr align 1 %src, i32 16, i1 false)
call void @llvm.memcpy.inline.p0.p0.i32(ptr align 1 %dest, ptr align 1 %tmp, i32 16, i1 false)
ret void
}

; We have to retain this `memcpy(arg+2, arg+1)` forwarding.
define void @test6_memcpy_forward_not_back(ptr %arg) nounwind {
; CHECK-LABEL: @test6_memcpy_forward_not_back(
; CHECK-NEXT: [[TMP:%.*]] = alloca [16 x i8], align 1
; CHECK-NEXT: [[SRC:%.*]] = getelementptr inbounds i8, ptr [[ARG:%.*]], i64 1
; CHECK-NEXT: [[DEST:%.*]] = getelementptr inbounds i8, ptr [[ARG]], i64 2
; CHECK-NEXT: call void @llvm.memcpy.inline.p0.p0.i32(ptr align 1 [[TMP]], ptr align 1 [[SRC]], i32 16, i1 false)
; CHECK-NEXT: call void @llvm.memcpy.inline.p0.p0.i32(ptr align 1 [[DEST]], ptr align 1 [[TMP]], i32 16, i1 false)
; CHECK-NEXT: ret void
;
%tmp = alloca [16 x i8], align 1
%src = getelementptr inbounds i8, ptr %arg, i64 1
%dest = getelementptr inbounds i8, ptr %arg, i64 2
call void @llvm.memcpy.inline.p0.p0.i32(ptr align 1 %tmp, ptr align 1 %src, i32 16, i1 false)
call void @llvm.memcpy.inline.p0.p0.i32(ptr align 1 %dest, ptr align 1 %tmp, i32 16, i1 false)
ret void
}

@x = external global %0

Expand Down
Loading