Index: llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
@@ -373,11 +373,12 @@
       if (auto *I = dyn_cast<Instruction>(U)) {
         if (AliasScope && I->mayReadOrWriteMemory()) {
           MDNode *AS = I->getMetadata(LLVMContext::MD_alias_scope);
-          AS = MDNode::concatenate(AS, AliasScope);
+          AS = (AS ? MDNode::getMostGenericAliasScope(AS, AliasScope)
+                   : AliasScope);
           I->setMetadata(LLVMContext::MD_alias_scope, AS);
 
           MDNode *NA = I->getMetadata(LLVMContext::MD_noalias);
-          NA = MDNode::concatenate(NA, NoAlias);
+          NA = (NA ? MDNode::intersect(NA, NoAlias) : NoAlias);
           I->setMetadata(LLVMContext::MD_noalias, NA);
         }
       }
Index: llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-memcpy.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-memcpy.ll
@@ -0,0 +1,44 @@
+; RUN: llc -march=amdgcn -mcpu=gfx900 -O3 < %s | FileCheck -check-prefix=GCN %s
+; RUN: opt -S -mtriple=amdgcn-- -amdgpu-lower-module-lds < %s | FileCheck %s
+; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s | FileCheck %s
+
+%vec_type = type { %vec_base }
+%vec_base = type { %union.anon }
+%union.anon = type { %"vec_base<char, 3>::n_vec_" }
+%"vec_base<char, 3>::n_vec_" = type { [3 x i8] }
+
+$_f1 = comdat any
+$_f2 = comdat any
+@_f1 = linkonce_odr hidden local_unnamed_addr addrspace(3) global %vec_type undef, comdat, align 1
+@_f2 = linkonce_odr hidden local_unnamed_addr addrspace(3) global %vec_type undef, comdat, align 1
+
+; GCN-LABEL: @test
+; GCN: v_mov_b32_e32 [[REG:v[0-9]+]], 1
+; GCN-NEXT: global_store_byte v{{[0-9]+}}, [[REG]]
+
+; CHECK-LABEL: @test
+; CHECK: store i8 3, i8 addrspace(3)* %0, align 4, !alias.scope !0, !noalias !3
+; CHECK: tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* noundef align 1 dereferenceable(3) %2, i8 addrspace(3)* noundef align 1 dereferenceable(3) %1, i64 3, i1 false), !alias.scope !6, !noalias !7
+; CHECK: %4 = load i8, i8 addrspace(3)* %3, align 4, !alias.scope !8, !noalias !9
+; CHECK: tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* noundef align 1 dereferenceable(3) %7, i8 addrspace(3)* noundef align 1 dereferenceable(3) %6, i64 3, i1 false), !alias.scope !6, !noalias !7
+; CHECK: %9 = load i8, i8 addrspace(3)* %8, align 4, !alias.scope !8, !noalias !9
+
+define protected amdgpu_kernel void @test(i8 addrspace(1)* nocapture %ptr.coerce) local_unnamed_addr #0 {
+entry:
+  store i8 3, i8 addrspace(3)* getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), align 1
+  tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* noundef align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i8 addrspace(3)* noundef align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i64 3, i1 false)
+  %0 = load i8, i8 addrspace(3)* getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), align 1
+  %cmp.i.i = icmp eq i8 %0, 3
+  store i8 2, i8 addrspace(3)* getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), align 1
+  tail call void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* noundef align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i8 addrspace(3)* noundef align 1 dereferenceable(3) getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), i64 3, i1 false)
+  %1 = load i8, i8 addrspace(3)* getelementptr inbounds (%vec_type, %vec_type addrspace(3)* @_f2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0), align 1
+  %cmp.i.i19 = icmp eq i8 %1, 2
+  %2 = and i1 %cmp.i.i19, %cmp.i.i
+  %frombool8 = zext i1 %2 to i8
+  store i8 %frombool8, i8 addrspace(1)* %ptr.coerce, align 1
+  ret void
+}
+
+declare void @llvm.memcpy.p3i8.p3i8.i64(i8 addrspace(3)* noalias nocapture writeonly, i8 addrspace(3)* noalias nocapture readonly, i64, i1 immarg) #1
+
+
Index: llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-merge.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-merge.ll
+++ llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-merge.ll
@@ -5,19 +5,19 @@
 @b = internal unnamed_addr addrspace(3) global [64 x i32] undef, align 4
 
 ; CHECK-LABEL: @no_clobber_ds_load_stores_x2_preexisting_aa
-; CHECK: store i32 1, i32 addrspace(3)* %0, align 16, !tbaa !0, !alias.scope !5, !noalias !10
-; CHECK: %val.a = load i32, i32 addrspace(3)* %gep.a, align 4, !tbaa !0, !alias.scope !5, !noalias !10
-; CHECK: store i32 2, i32 addrspace(3)* %1, align 16, !tbaa !0, !alias.scope !10, !noalias !5
-; CHECK: %val.b = load i32, i32 addrspace(3)* %gep.b, align 4, !tbaa !0, !alias.scope !10, !noalias !5
+; CHECK: store i32 1, i32 addrspace(3)* %0, align 16, !tbaa !0, !noalias !5
+; CHECK: %val.a = load i32, i32 addrspace(3)* %gep.a, align 4, !tbaa !0, !noalias !5
+; CHECK: store i32 2, i32 addrspace(3)* %1, align 16, !tbaa !0, !noalias !5
+; CHECK: %val.b = load i32, i32 addrspace(3)* %gep.b, align 4, !tbaa !0, !noalias !5
 
 define amdgpu_kernel void @no_clobber_ds_load_stores_x2_preexisting_aa(i32 addrspace(1)* %arg, i32 %i) {
 bb:
   store i32 1, i32 addrspace(3)* getelementptr inbounds ([64 x i32], [64 x i32] addrspace(3)* @a, i32 0, i32 0), align 4, !alias.scope !0, !noalias !3, !tbaa !5
   %gep.a = getelementptr inbounds [64 x i32], [64 x i32] addrspace(3)* @a, i32 0, i32 %i
-  %val.a = load i32, i32 addrspace(3)* %gep.a, align 4, !alias.scope !0, !noalias !3, !tbaa !5
-  store i32 2, i32 addrspace(3)* getelementptr inbounds ([64 x i32], [64 x i32] addrspace(3)* @b, i32 0, i32 0), align 4, !alias.scope !3, !noalias !0, !tbaa !5
+  %val.a = load i32, i32 addrspace(3)* %gep.a, align 4,  !alias.scope !0, !noalias !3, !tbaa !5
+  store i32 2, i32 addrspace(3)* getelementptr inbounds ([64 x i32], [64 x i32] addrspace(3)* @b, i32 0, i32 0), align 4,  !alias.scope !3, !noalias !0, !tbaa !5
   %gep.b = getelementptr inbounds [64 x i32], [64 x i32] addrspace(3)* @b, i32 0, i32 %i
-  %val.b = load i32, i32 addrspace(3)* %gep.b, align 4, !alias.scope !3, !noalias !0, !tbaa !5
+  %val.b = load i32, i32 addrspace(3)* %gep.b, align 4,  !alias.scope !3, !noalias !0, !tbaa !5
   %val = add i32 %val.a, %val.b
   store i32 %val, i32 addrspace(1)* %arg, align 4
   ret void
@@ -39,11 +39,4 @@
 ; CHECK:!2 = !{!"int", !3, i64 0}
 ; CHECK:!3 = !{!"omnipotent char", !4, i64 0}
 ; CHECK:!4 = !{!"Simple C++ TBAA"}
-; CHECK:!5 = !{!6, !8}
-; CHECK:!6 = distinct !{!6, !7}
-; CHECK:!7 = distinct !{!7}
-; CHECK:!8 = distinct !{!8, !9}
-; CHECK:!9 = distinct !{!9}
-; CHECK:!10 = !{!11, !12}
-; CHECK:!11 = distinct !{!11, !7}
-; CHECK:!12 = distinct !{!12, !9}
+; CHECK:!5 = !{}