[llvm] [MemCpyOpt] Allow stack move optimization if one address captured (PR #165527)

[Nikita Popov via llvm-commits]

https://github.com/nikic created https://github.com/llvm/llvm-project/pull/165527

Allow the stack move optimization (which merges two allocas) when the address of only one alloca is captured (and the provenance is not captured). Both addresses need to be captured to observe that the allocas were merged.

Fixes https://github.com/llvm/llvm-project/issues/165484.

>From ae1521f2f890e250d11b70d094261ce0c0109cc6 Mon Sep 17 00:00:00 2001
From: Nikita Popov <npopov at redhat.com>
Date: Wed, 29 Oct 2025 09:45:41 +0100
Subject: [PATCH] [MemCpyOpt] Allow stack move optimization if one address
 captured

Allow the stack move optimization (which merges two allocas)
when the address of only one alloca is captured (and the provenance
is not captured). Both addresses need to be captured to observe
that the allocas were merged.
---
 .../lib/Transforms/Scalar/MemCpyOptimizer.cpp | 20 +++++--
 llvm/test/Transforms/MemCpyOpt/stack-move.ll  | 58 +++++++++++++++++++
 2 files changed, 73 insertions(+), 5 deletions(-)

diff --git a/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp b/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
index e043d072a7638..08be5df9872b7 100644
--- a/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
+++ b/llvm/lib/Transforms/Scalar/MemCpyOptimizer.cpp
@@ -1534,8 +1534,8 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
   bool SrcNotDom = false;
 
   auto CaptureTrackingWithModRef =
-      [&](Instruction *AI,
-          function_ref<bool(Instruction *)> ModRefCallback) -> bool {
+      [&](Instruction *AI, function_ref<bool(Instruction *)> ModRefCallback,
+          bool &AddressCaptured) -> bool {
     SmallVector<Instruction *, 8> Worklist;
     Worklist.push_back(AI);
     unsigned MaxUsesToExplore = getDefaultMaxUsesToExploreForCaptureTracking();
@@ -1559,8 +1559,9 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
         if (!Visited.insert(&U).second)
           continue;
         UseCaptureInfo CI = DetermineUseCaptureKind(U, AI);
-        if (capturesAnything(CI.UseCC))
+        if (capturesAnyProvenance(CI.UseCC))
           return false;
+        AddressCaptured |= capturesAddress(CI.UseCC);
 
         if (UI->mayReadOrWriteMemory()) {
           if (UI->isLifetimeStartOrEnd()) {
@@ -1627,7 +1628,9 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
     return true;
   };
 
-  if (!CaptureTrackingWithModRef(DestAlloca, DestModRefCallback))
+  bool DestAddressCaptured = false;
+  if (!CaptureTrackingWithModRef(DestAlloca, DestModRefCallback,
+                                 DestAddressCaptured))
     return false;
   // Bailout if Dest may have any ModRef before Store.
   if (!ReachabilityWorklist.empty() &&
@@ -1653,7 +1656,14 @@ bool MemCpyOptPass::performStackMoveOptzn(Instruction *Load, Instruction *Store,
     return true;
   };
 
-  if (!CaptureTrackingWithModRef(SrcAlloca, SrcModRefCallback))
+  bool SrcAddressCaptured = false;
+  if (!CaptureTrackingWithModRef(SrcAlloca, SrcModRefCallback,
+                                 SrcAddressCaptured))
+    return false;
+
+  // If both the source and destination address are captured, the fact that they
+  // are no longer two separate allocations may be observed.
+  if (DestAddressCaptured && SrcAddressCaptured)
     return false;
 
   // We can do the transformation. First, move the SrcAlloca to the start of the
diff --git a/llvm/test/Transforms/MemCpyOpt/stack-move.ll b/llvm/test/Transforms/MemCpyOpt/stack-move.ll
index 940e30ec46881..0c2e05fa8fed6 100644
--- a/llvm/test/Transforms/MemCpyOpt/stack-move.ll
+++ b/llvm/test/Transforms/MemCpyOpt/stack-move.ll
@@ -1729,3 +1729,61 @@ define i32 @test_ret_only_capture() {
   %v = load i32, ptr %a
   ret i32 %v
 }
+
+declare ptr @captures_address_only(ptr captures(address))
+
+; Can transform: Only one address captured.
+define void @test_captures_address_captures_none() {
+; CHECK-LABEL: define void @test_captures_address_captures_none() {
+; CHECK-NEXT:    [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4
+; CHECK-NEXT:    store [[STRUCT_FOO]] { i32 10, i32 20, i32 30 }, ptr [[SRC]], align 4
+; CHECK-NEXT:    call void @captures_address_only(ptr [[SRC]])
+; CHECK-NEXT:    call void @use_nocapture(ptr [[SRC]])
+; CHECK-NEXT:    ret void
+;
+  %src = alloca %struct.Foo, align 4
+  %dst = alloca %struct.Foo, align 4
+  store %struct.Foo { i32 10, i32 20, i32 30 }, ptr %src
+  call void @captures_address_only(ptr %src)
+  call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dst, ptr align 4 %src, i64 12, i1 false)
+  call void @use_nocapture(ptr %dst)
+  ret void
+}
+
+; Can transform: Only one address captured.
+define void @test_captures_none_and_captures_address() {
+; CHECK-LABEL: define void @test_captures_none_and_captures_address() {
+; CHECK-NEXT:    [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4
+; CHECK-NEXT:    store [[STRUCT_FOO]] { i32 10, i32 20, i32 30 }, ptr [[SRC]], align 4
+; CHECK-NEXT:    call void @use_nocapture(ptr [[SRC]])
+; CHECK-NEXT:    call void @captures_address_only(ptr [[SRC]])
+; CHECK-NEXT:    ret void
+;
+  %src = alloca %struct.Foo, align 4
+  %dst = alloca %struct.Foo, align 4
+  store %struct.Foo { i32 10, i32 20, i32 30 }, ptr %src
+  call void @use_nocapture(ptr %src)
+  call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dst, ptr align 4 %src, i64 12, i1 false)
+  call void @captures_address_only(ptr %dst)
+  ret void
+}
+
+; Cannot transform: Both addresses captured.
+define void @test_captures_address_and_captures_address() {
+; CHECK-LABEL: define void @test_captures_address_and_captures_address() {
+; CHECK-NEXT:    [[SRC:%.*]] = alloca [[STRUCT_FOO:%.*]], align 4
+; CHECK-NEXT:    [[DST:%.*]] = alloca [[STRUCT_FOO]], align 4
+; CHECK-NEXT:    store [[STRUCT_FOO]] { i32 10, i32 20, i32 30 }, ptr [[SRC]], align 4
+; CHECK-NEXT:    call void @captures_address_only(ptr [[SRC]])
+; CHECK-NEXT:    call void @llvm.memcpy.p0.p0.i64(ptr align 4 [[DST]], ptr align 4 [[SRC]], i64 12, i1 false)
+; CHECK-NEXT:    call void @captures_address_only(ptr [[DST]])
+; CHECK-NEXT:    ret void
+;
+  %src = alloca %struct.Foo, align 4
+  %dst = alloca %struct.Foo, align 4
+  store %struct.Foo { i32 10, i32 20, i32 30 }, ptr %src
+  call void @captures_address_only(ptr %src)
+  call void @llvm.memcpy.p0.p0.i64(ptr align 4 %dst, ptr align 4 %src, i64 12, i1 false)
+  call void @captures_address_only(ptr %dst)
+  ret void
+}