[llvm] [AMDGPU] Fix spurious NoAlias results (PR #122309)
Fraser Cormack via llvm-commits
llvm-commits at lists.llvm.org
Mon Jan 13 02:26:11 PST 2025
https://github.com/frasercrmck updated https://github.com/llvm/llvm-project/pull/122309
>From d057782c04219c4c4d0c3df1dfc39b066e382d22 Mon Sep 17 00:00:00 2001
From: Fraser Cormack <fraser at codeplay.com>
Date: Thu, 9 Jan 2025 16:24:24 +0000
Subject: [PATCH 1/3] [AMDGPU] Fix spurious NoAlias results
After a30e50fc, AMDGPUAAResult is being called in more situations where
BasicAA isn't sure. This exposed some regressions where NoAlias is being
incorrectly returned for two identical pointers.
The fix is to check the underlying objects for equality before returning
NoAlias.
---
llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp | 7 +++++--
.../CodeGen/AMDGPU/amdgpu-alias-analysis.ll | 17 +++++++++++++++++
2 files changed, 22 insertions(+), 2 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp
index 8d3eac6868318e..c2177c18f3cc3d 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp
@@ -80,10 +80,13 @@ AliasResult AMDGPUAAResult::alias(const MemoryLocation &LocA,
} else if (const Argument *Arg = dyn_cast<Argument>(ObjA)) {
const Function *F = Arg->getParent();
switch (F->getCallingConv()) {
- case CallingConv::AMDGPU_KERNEL:
+ case CallingConv::AMDGPU_KERNEL: {
// In the kernel function, kernel arguments won't alias to (local)
// variables in shared or private address space.
- return AliasResult::NoAlias;
+ const auto *ObjB =
+ getUnderlyingObject(B.Ptr->stripPointerCastsForAliasAnalysis());
+ return (ObjA == ObjB) ? AliasResult::MustAlias : AliasResult::NoAlias;
+ }
default:
// TODO: In the regular function, if that local variable in the
// location B is not captured, that argument pointer won't alias to it
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll
index a13eb5c6d085f8..851c18dfccf5af 100644
--- a/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll
@@ -318,3 +318,20 @@ define void @test_9_9(ptr addrspace(9) %p, ptr addrspace(9) %p1) {
load i8, ptr addrspace(9) %p1
ret void
}
+
+; CHECK-LABEL: Function: test_kernel_arg_local_ptr
+; CHECK: MayAlias: i32 addrspace(3)* %arg, i32 addrspace(3)* %arg1
+; CHECK: MustAlias: i32 addrspace(3)* %arg, i32* %arg2
+; CHECK: MustAlias: i32 addrspace(3)* %arg1, i32* %arg2
+define amdgpu_kernel void @test_kernel_arg_local_ptr(ptr addrspace(3) noundef align 4 %arg) {
+entry:
+ %load1 = load i32, ptr addrspace(3) %arg, align 4
+ %arg.plus.1 = getelementptr inbounds nuw i8, ptr addrspace(3) %arg, i64 1
+ %arg1 = getelementptr inbounds nuw i8, ptr addrspace(3) %arg.plus.1, i64 -1
+ %load2 = load i32, ptr addrspace(3) %arg1, align 4
+ %arg.plus.4 = getelementptr inbounds nuw i8, ptr addrspace(3) %arg, i64 4
+ %acast = addrspacecast ptr addrspace(3) %arg.plus.4 to ptr
+ %arg2 = getelementptr inbounds i8, ptr %acast, i64 -4
+ %load3 = load i32, ptr %arg2, align 4
+ ret void
+}
>From a6e37b2b53b0f23e06bf910ea534cedeffcf2afb Mon Sep 17 00:00:00 2001
From: Fraser Cormack <fraser at codeplay.com>
Date: Thu, 9 Jan 2025 16:33:41 +0000
Subject: [PATCH 2/3] remove attributes
---
llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll
index 851c18dfccf5af..0c9fcbd7ac9298 100644
--- a/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll
@@ -323,7 +323,7 @@ define void @test_9_9(ptr addrspace(9) %p, ptr addrspace(9) %p1) {
; CHECK: MayAlias: i32 addrspace(3)* %arg, i32 addrspace(3)* %arg1
; CHECK: MustAlias: i32 addrspace(3)* %arg, i32* %arg2
; CHECK: MustAlias: i32 addrspace(3)* %arg1, i32* %arg2
-define amdgpu_kernel void @test_kernel_arg_local_ptr(ptr addrspace(3) noundef align 4 %arg) {
+define amdgpu_kernel void @test_kernel_arg_local_ptr(ptr addrspace(3) %arg) {
entry:
%load1 = load i32, ptr addrspace(3) %arg, align 4
%arg.plus.1 = getelementptr inbounds nuw i8, ptr addrspace(3) %arg, i64 1
>From 57b244824e5e19d66acdd0b26826a7f662e9e1fc Mon Sep 17 00:00:00 2001
From: Fraser Cormack <fraser at codeplay.com>
Date: Mon, 13 Jan 2025 10:25:56 +0000
Subject: [PATCH 3/3] used identifiedobject
---
llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp | 3 ++-
llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll | 6 +++---
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp
index c2177c18f3cc3d..01e230e7d079c7 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAliasAnalysis.cpp
@@ -85,7 +85,8 @@ AliasResult AMDGPUAAResult::alias(const MemoryLocation &LocA,
// variables in shared or private address space.
const auto *ObjB =
getUnderlyingObject(B.Ptr->stripPointerCastsForAliasAnalysis());
- return (ObjA == ObjB) ? AliasResult::MustAlias : AliasResult::NoAlias;
+ return isIdentifiedObject(ObjB) && ObjA != ObjB ? AliasResult::NoAlias
+ : AliasResult::MayAlias;
}
default:
// TODO: In the regular function, if that local variable in the
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll
index 0c9fcbd7ac9298..6b935a8768d3dc 100644
--- a/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-alias-analysis.ll
@@ -320,9 +320,9 @@ define void @test_9_9(ptr addrspace(9) %p, ptr addrspace(9) %p1) {
}
; CHECK-LABEL: Function: test_kernel_arg_local_ptr
-; CHECK: MayAlias: i32 addrspace(3)* %arg, i32 addrspace(3)* %arg1
-; CHECK: MustAlias: i32 addrspace(3)* %arg, i32* %arg2
-; CHECK: MustAlias: i32 addrspace(3)* %arg1, i32* %arg2
+; CHECK: MayAlias: i32 addrspace(3)* %arg, i32 addrspace(3)* %arg1
+; CHECK: MayAlias: i32 addrspace(3)* %arg, i32* %arg2
+; CHECK: MayAlias: i32 addrspace(3)* %arg1, i32* %arg2
define amdgpu_kernel void @test_kernel_arg_local_ptr(ptr addrspace(3) %arg) {
entry:
%load1 = load i32, ptr addrspace(3) %arg, align 4
More information about the llvm-commits
mailing list