[AMDGPU] Fix spurious NoAlias results

After a30e50f, 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.

Author: frasercrmck

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

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
+}