Skip to content

[GlobalOpt] Prevent widenDestArray from shrinking an alloca. #144641

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

Closed
wants to merge 2 commits into from
Closed

[GlobalOpt] Prevent widenDestArray from shrinking an alloca. #144641

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0eebbdc
Pre-commit test
topperc Jun 18, 2025
4f5b59f
[GlobalOpt] Preven widenDestArray from shrinking an alloca.
topperc Jun 18, 2025
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
4 changes: 4 additions & 0 deletions llvm/lib/Transforms/IPO/GlobalOpt.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2103,6 +2103,10 @@ static void widenDestArray(CallInst *CI, const unsigned NumBytesToPad,
unsigned ElementByteWidth = SourceDataArray->getElementByteSize();
unsigned int TotalBytes = NumBytesToCopy + NumBytesToPad;
unsigned NumElementsToCopy = divideCeil(TotalBytes, ElementByteWidth);
// Don't change size if already wide enough.
if (Alloca->getAllocatedType()->getArrayNumElements() >= NumElementsToCopy)
return;

// Update destination array to be word aligned (memcpy(X,...,...))
IRBuilder<> BuildAlloca(Alloca);
AllocaInst *NewAlloca = BuildAlloca.CreateAlloca(ArrayType::get(
Expand Down
27 changes: 27 additions & 0 deletions llvm/test/Transforms/GlobalOpt/ARM/arm-widen-large-alloca.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,27 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt < %s -mtriple=arm-none-eabi -passes=globalopt -S | FileCheck %s

@.i8 = private unnamed_addr constant [3 x i8] [i8 1, i8 2, i8 3] , align 1

define void @memcpy() {
; CHECK-LABEL: define void @memcpy() local_unnamed_addr {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: [[ALLOCA1:%.*]] = alloca [4 x i8], align 1
; CHECK-NEXT: [[ALLOCA2:%.*]] = alloca [5 x i8], align 1
; CHECK-NEXT: [[CALL1:%.*]] = call i32 @bar(ptr nonnull [[ALLOCA1]])
; CHECK-NEXT: [[CALL2:%.*]] = call i32 @bar(ptr nonnull [[ALLOCA2]])
; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr noundef nonnull align 1 dereferenceable(3) [[ALLOCA1]], ptr noundef nonnull align 1 dereferenceable(3) @.i8, i32 4, i1 false)
; CHECK-NEXT: call void @llvm.memcpy.p0.p0.i32(ptr noundef nonnull align 1 dereferenceable(5) [[ALLOCA2]], ptr noundef nonnull align 1 dereferenceable(3) @.i8, i32 4, i1 false)
; CHECK-NEXT: ret void
;
entry:
%alloca1 = alloca [3 x i8], align 1
%alloca2 = alloca [5 x i8], align 1
%call1 = call i32 @bar(ptr nonnull %alloca1)
%call2 = call i32 @bar(ptr nonnull %alloca2)
call void @llvm.memcpy.p0.p0.i32(ptr noundef nonnull align 1 dereferenceable(3) %alloca1, ptr noundef nonnull align 1 dereferenceable(3) @.i8, i32 3, i1 false)
call void @llvm.memcpy.p0.p0.i32(ptr noundef nonnull align 1 dereferenceable(5) %alloca2, ptr noundef nonnull align 1 dereferenceable(3) @.i8, i32 3, i1 false)
ret void
}

declare i32 @bar(...)
Loading