Skip to content

[LLVM][MemCpyOpt] Unify alias tags if we optimize allocas #129537

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 10 commits into from
Apr 10, 2025
Merged

[LLVM][MemCpyOpt] Unify alias tags if we optimize allocas #129537

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
4c49512
[LLVM][MemCpyOpt] Unify alias tags if we optimize allocas
DominikAdamski Feb 24, 2025
5e04c39
Simplified test
DominikAdamski Mar 3, 2025
dddcc8a
Fix style
DominikAdamski Mar 18, 2025
ae4139a
Fix style
DominikAdamski Mar 18, 2025
3ab8a71
Applied remarks
DominikAdamski Mar 18, 2025
0824f68
Applied remarks
DominikAdamski Mar 21, 2025
b9cb648
Applied remarks
DominikAdamski Apr 7, 2025
7fc13ac
Applied remarks
DominikAdamski Apr 8, 2025
2f00aa7
Remove alias.scope
DominikAdamski Apr 8, 2025
92584ea
Merge branch 'main' into fix_memcpy_tbaa_tags
DominikAdamski Apr 8, 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
24 changes: 20 additions & 4 deletions llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1516,6 +1516,8 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
SmallVector<Instruction *, 4> LifetimeMarkers;
SmallSet<Instruction *, 4> NoAliasInstrs;
bool SrcNotDom = false;
SmallSet<Instruction *, 4> SrcAllocaInstUsers;
SmallSet<Instruction *, 4> DestAllocaInstUsers;

// Recursively track the user and check whether modified alias exist.
auto IsDereferenceableOrNull = [](Value *V, const DataLayout &DL) -> bool {
Expand All @@ -1524,8 +1526,8 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
};

auto CaptureTrackingWithModRef =
[&](Instruction *AI,
function_ref<bool(Instruction *)> ModRefCallback) -> bool {
[&](Instruction *AI, function_ref<bool(Instruction *)> ModRefCallback,
SmallSet<Instruction *, 4> &AllocaInstUsersWithTBAA) -> bool {
Copy link
Contributor

@nikic nikic Apr 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No need for the argument, the variable is captured.

Copy link
Contributor Author

@DominikAdamski DominikAdamski Apr 7, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Done

SmallVector<Instruction *, 8> Worklist;
Worklist.push_back(AI);
unsigned MaxUsesToExplore = getDefaultMaxUsesToExploreForCaptureTracking();
Expand Down Expand Up @@ -1569,6 +1571,9 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
continue;
}
}
if (UI != Store && UI->hasMetadata(LLVMContext::MD_tbaa)) {
AllocaInstUsersWithTBAA.insert(UI);
}
if (UI->hasMetadata(LLVMContext::MD_noalias))
NoAliasInstrs.insert(UI);
if (!ModRefCallback(UI))
Expand Down Expand Up @@ -1621,7 +1626,8 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
return true;
};

if (!CaptureTrackingWithModRef(DestAlloca, DestModRefCallback))
if (!CaptureTrackingWithModRef(DestAlloca, DestModRefCallback,
DestAllocaInstUsers))
return false;
// Bailout if Dest may have any ModRef before Store.
if (!ReachabilityWorklist.empty() &&
Expand All @@ -1647,7 +1653,8 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
return true;
};

if (!CaptureTrackingWithModRef(SrcAlloca, SrcModRefCallback))
if (!CaptureTrackingWithModRef(SrcAlloca, SrcModRefCallback,
SrcAllocaInstUsers))
return false;

// We can do the transformation. First, move the SrcAlloca to the start of the
Expand Down Expand Up @@ -1681,6 +1688,15 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
for (Instruction *I : NoAliasInstrs)
I->setMetadata(LLVMContext::MD_noalias, nullptr);

// If we merge two allocas we need to uniform alias tags as well
if (!SrcAllocaInstUsers.empty()) {
MDNode *mergeTBAA =
(*SrcAllocaInstUsers.begin())->getMetadata(LLVMContext::MD_tbaa);
for (Instruction *it : DestAllocaInstUsers) {
it->setMetadata(LLVMContext::MD_tbaa, mergeTBAA);
}
}

LLVM_DEBUG(dbgs() << "Stack Move: Performed staack-move optimization\n");
NumStackMove++;
return true;
Expand Down
99 changes: 99 additions & 0 deletions llvm/test/Transforms/MemCpyOpt/memcpy-tbaa.ll
View file
Open in desktop
Copy link
Contributor

@nikic nikic Mar 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This test still doesn't look minimal. Wouldn't it be sufficient to have a store with one tbaa tag, a memcpy and a load with another tag?

Copy link
Contributor Author

@DominikAdamski DominikAdamski Mar 21, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I removed unnecessary instructions.

Original file line number Diff line number Diff line change
@@ -0,0 +1,99 @@
; RUN: opt < %s -passes=memcpyopt,dse -S -verify-memoryssa | FileCheck %s
; The aim of this test is to check if MemCpyOpt pass merges alias tags
; after memcpy optimization

; ModuleID = 'FIRModule'
source_filename = "FIRModule"
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-i128:128-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
Copy link
Contributor

@shiltian shiltian Mar 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

not needed

Copy link
Contributor Author

@DominikAdamski DominikAdamski Mar 18, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the review, I applied your suggestion.


@data_arr = internal unnamed_addr constant [31 x float] [float 0x3E68DA0CA0000000, float 0x3E692863A0000000, float 0x3E6AEF5000000000, float 0x3E6E2272C0000000, float 0x3E7271B720000000, float 0x3E777DA440000000, float 0x3E7E8C46C0000000, float 0x3E8458EFC0000000, float 0x3E8D0123C0000000, float 0x3E95E78260000000, float 0x3EA0AB7AC0000000, float 0x3EA89F4B40000000, float 0x3EB10FFB60000000, float 0x3EB5F1D140000000, float 0x3EBB435260000000, float 0x3EC0DE9700000000, float 0x3EC51B11A0000000, float 0x3ECA419FC0000000, float 0x3ED01B2B20000000, float 0x3ED3B9CEC0000000, float 0x3ED7028C40000000, float 0x3EDA60C320000000, float 0x3EDD54AD40000000, float 0x3EDF6E9F00000000, float 0x3EE130BB20000000, float 0x3EE4332400000000, float 0x3EE7575F80000000, float 0x3EE8088A60000000, float 0x3EE3B0AE60000000, float 0x3ED9BB6800000000, float 0x3ED9BB6800000000]

; CHECK-LABEL: @test(
; CHECK: [[ARR_UNDER_TEST:%.*]] = alloca [31 x float], align 4
; CHECK: store float 0x3E6AA51880000000, ptr [[ARR_UNDER_TEST]], align 4, !tbaa [[ARR_TAG:!.[0-9]+]]
; CHECK-LABEL: init_loop:
; CHECK: store float [[TMP0:%.*]], ptr [[TMP1:%.*]], align 4, !tbaa [[ARR_TAG]]
; CHECK-LABEL: loop:
; CHECK: [[TMP2:%.*]] = getelementptr float, ptr [[ARR_UNDER_TEST]], i64 [[TMP3:%.*]]
; CHECK: [[TMP4:%.*]] = load float, ptr [[TMP2]], align 4, !tbaa [[ARR_TAG]]
define void @test(ptr captures(none) %0, ptr readonly captures(none) %1, ptr readonly captures(none) %2, ptr readonly captures(none) %3) local_unnamed_addr #0 {
%5 = alloca [32 x float], align 4
%6 = alloca [31 x float], align 4
%7 = alloca [31 x float], align 4
%8 = load i32, ptr %2, align 4, !tbaa !4
%9 = sext i32 %8 to i64
%10 = load i32, ptr %3, align 4, !tbaa !10
%11 = add i32 %10, 1
%12 = sext i32 %11 to i64
%13 = sub nsw i64 %12, %9
%14 = tail call i64 @llvm.smax.i64(i64 %13, i64 -1)
%15 = add nsw i64 %14, 1
%16 = alloca float, i64 %15, align 4
store float 0x3E6AA51880000000, ptr %7, align 4, !tbaa !12
br label %init_loop

init_loop:
%19 = phi float [ 0x3E68DA0CA0000000, %4 ], [ %22, %init_loop ]
%indvars.iv = phi i64 [ 2, %4 ], [ %indvars.iv.next, %init_loop ]
%20 = add nsw i64 %indvars.iv, -1
%21 = getelementptr float, ptr @data_arr, i64 %20
%22 = load float, ptr %21, align 4, !tbaa !15
%23 = fsub contract float %22, %19
%33 = getelementptr float, ptr %7, i64 %20
store float %23, ptr %33, align 4, !tbaa !12
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond.not = icmp eq i64 %indvars.iv.next, 32
br i1 %exitcond.not, label %.preheader55.preheader, label %init_loop

.preheader55.preheader:
call void @llvm.memcpy.p0.p0.i64(ptr noundef nonnull align 4 dereferenceable(124) %6, ptr noundef nonnull align 4 dereferenceable(124) %7, i64 124, i1 false), !tbaa !22
%154 = icmp sgt i64 %13, -1
br i1 %154, label %loop, label %._crit_edge56

loop: ; preds = %.preheader, %211
%indvars.iv73 = phi i64 [ 0, %.preheader55.preheader ], [ %indvars.iv.next74, %loop ]
%indvars.iv.next74 = add nuw nsw i64 %indvars.iv73, 1
%223 = getelementptr float, ptr %6, i64 %indvars.iv73
%225 = load float, ptr %223, align 4, !tbaa !31
%exitcond76.not = icmp eq i64 %indvars.iv.next74, 32
br i1 %exitcond76.not, label %loop, label %._crit_edge56

._crit_edge56: ; preds = %loop, %._crit_edge
ret void
}

; Function Attrs: nocallback nofree nosync nounwind speculatable willreturn memory(none)
declare i64 @llvm.smax.i64(i64, i64) #1

; Function Attrs: nocallback nofree nounwind willreturn memory(argmem: readwrite)
declare void @llvm.memcpy.p0.p0.i64(ptr noalias writeonly captures(none), ptr noalias readonly captures(none), i64, i1 immarg) #2

attributes #0 = { "target-cpu"="x86-64" }
attributes #1 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
attributes #2 = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }

!llvm.module.flags = !{!0, !1, !2}
!llvm.ident = !{!3}

!0 = !{i32 2, !"Debug Info Version", i32 3}
!1 = !{i32 8, !"PIC Level", i32 2}
!2 = !{i32 7, !"PIE Level", i32 2}
!3 = !{!"flang version 21.0.0 (https://github.com/llvm/llvm-project.git 4d79f420ce5b5100f72f720eab2d3881f97abd0d)"}
!4 = !{!5, !5, i64 0}
!5 = !{!"dummy arg data/param_1", !6, i64 0}
!6 = !{!"dummy arg data", !7, i64 0}
!7 = !{!"any data access", !8, i64 0}
!8 = !{!"any access", !9, i64 0}
!9 = !{!"Flang function root test"}
!10 = !{!11, !11, i64 0}
!11 = !{!"dummy arg data/param_2", !6, i64 0}
!12 = !{!13, !13, i64 0}
!13 = !{!"allocated data/test_array_a", !14, i64 0}
!14 = !{!"allocated data", !7, i64 0}
!15 = !{!16, !16, i64 0}
!16 = !{!"global data/data_arr", !17, i64 0}
!17 = !{!"global data", !7, i64 0}
!22 = !{!14, !14, i64 0}
!31 = !{!32, !32, i64 0}
!32 = !{!"allocated data/test_array_b", !14, i64 0}