diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
index 34ba53cbe0f9e..f79069bd6d78b 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
@@ -1038,6 +1038,12 @@ class AMDGPULowerModuleLDS {
   }
 
   bool runOnModule(Module &M) {
+    // Check if we've already lowered this module. The pass may run more
+    // than once in the LTO pipeline, and multiple runs aren't supported.
+    if (M.getModuleFlag("amdgpu.lowered_lds"))
+      return false;
+    M.addModuleFlag(Module::ModFlagBehavior::Error, "amdgpu.lowered_lds", 1);
+
     CallGraph CG = CallGraph(M);
     bool Changed = superAlignLDSGlobals(M);
 
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll
index aae999ec0a99a..75913d5219af2 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/dropped_debug_info_assert.ll
@@ -9,46 +9,46 @@ define amdgpu_kernel void @call_debug_loc() {
   ; CHECK: bb.1.entry:
   ; CHECK-NEXT:   liveins: $sgpr14, $sgpr15, $sgpr16, $vgpr0, $vgpr1, $vgpr2, $sgpr4_sgpr5, $sgpr6_sgpr7, $sgpr8_sgpr9, $sgpr10_sgpr11
   ; CHECK-NEXT: {{  $}}
-  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr2, debug-location !7
-  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1, debug-location !7
-  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr0, debug-location !7
-  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr16, debug-location !7
-  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr15, debug-location !7
-  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr14, debug-location !7
-  ; CHECK-NEXT:   [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11, debug-location !7
-  ; CHECK-NEXT:   [[COPY7:%[0-9]+]]:sgpr_64 = COPY $sgpr6_sgpr7, debug-location !7
-  ; CHECK-NEXT:   [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5, debug-location !7
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr2, debug-location !8
+  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1, debug-location !8
+  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr0, debug-location !8
+  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:sgpr_32 = COPY $sgpr16, debug-location !8
+  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:sgpr_32 = COPY $sgpr15, debug-location !8
+  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:sgpr_32 = COPY $sgpr14, debug-location !8
+  ; CHECK-NEXT:   [[COPY6:%[0-9]+]]:sgpr_64 = COPY $sgpr10_sgpr11, debug-location !8
+  ; CHECK-NEXT:   [[COPY7:%[0-9]+]]:sgpr_64 = COPY $sgpr6_sgpr7, debug-location !8
+  ; CHECK-NEXT:   [[COPY8:%[0-9]+]]:sgpr_64 = COPY $sgpr4_sgpr5, debug-location !8
   ; CHECK-NEXT:   [[COPY9:%[0-9]+]]:sreg_64 = COPY $sgpr8_sgpr9
-  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def $scc, debug-location !7
-  ; CHECK-NEXT:   [[COPY10:%[0-9]+]]:sreg_64 = COPY [[COPY8]], debug-location !7
-  ; CHECK-NEXT:   [[COPY11:%[0-9]+]]:sreg_64 = COPY [[COPY7]], debug-location !7
-  ; CHECK-NEXT:   [[COPY12:%[0-9]+]]:sreg_64 = COPY [[COPY6]], debug-location !7
-  ; CHECK-NEXT:   [[COPY13:%[0-9]+]]:sreg_32 = COPY [[COPY5]], debug-location !7
-  ; CHECK-NEXT:   [[COPY14:%[0-9]+]]:sreg_32 = COPY [[COPY4]], debug-location !7
-  ; CHECK-NEXT:   [[COPY15:%[0-9]+]]:sreg_32 = COPY [[COPY3]], debug-location !7
-  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF debug-location !7
-  ; CHECK-NEXT:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 10, debug-location !7
-  ; CHECK-NEXT:   [[COPY16:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]], debug-location !7
-  ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[COPY16]], [[COPY1]], implicit $exec, debug-location !7
-  ; CHECK-NEXT:   [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 20, debug-location !7
-  ; CHECK-NEXT:   [[COPY17:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]], debug-location !7
-  ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[COPY17]], [[COPY]], implicit $exec, debug-location !7
-  ; CHECK-NEXT:   [[V_OR3_B32_e64_:%[0-9]+]]:vgpr_32 = V_OR3_B32_e64 [[COPY2]], [[V_LSHLREV_B32_e64_]], [[V_LSHLREV_B32_e64_1]], implicit $exec, debug-location !7
-  ; CHECK-NEXT:   [[COPY18:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3, debug-location !7
-  ; CHECK-NEXT:   $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY18]], debug-location !7
-  ; CHECK-NEXT:   $sgpr4_sgpr5 = COPY [[COPY10]], debug-location !7
-  ; CHECK-NEXT:   $sgpr6_sgpr7 = COPY [[COPY11]], debug-location !7
-  ; CHECK-NEXT:   $sgpr8_sgpr9 = COPY [[COPY9]], debug-location !7
-  ; CHECK-NEXT:   $sgpr10_sgpr11 = COPY [[COPY12]], debug-location !7
-  ; CHECK-NEXT:   $sgpr12 = COPY [[COPY13]], debug-location !7
-  ; CHECK-NEXT:   $sgpr13 = COPY [[COPY14]], debug-location !7
-  ; CHECK-NEXT:   $sgpr14 = COPY [[COPY15]], debug-location !7
-  ; CHECK-NEXT:   $sgpr15 = COPY [[DEF]], debug-location !7
-  ; CHECK-NEXT:   $vgpr31 = COPY [[V_OR3_B32_e64_]], debug-location !7
-  ; CHECK-NEXT:   [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee, target-flags(amdgpu-gotprel32-hi) @callee, implicit-def $scc, debug-location !7
-  ; CHECK-NEXT:   [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0, debug-location !7 :: (dereferenceable invariant load (p0) from got, addrspace 4)
-  ; CHECK-NEXT:   $sgpr30_sgpr31 = noconvergent SI_CALL [[S_LOAD_DWORDX2_IMM]], @callee, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31, debug-location !7
-  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def $scc, debug-location !7
+  ; CHECK-NEXT:   ADJCALLSTACKUP 0, 0, implicit-def $scc, debug-location !8
+  ; CHECK-NEXT:   [[COPY10:%[0-9]+]]:sreg_64 = COPY [[COPY8]], debug-location !8
+  ; CHECK-NEXT:   [[COPY11:%[0-9]+]]:sreg_64 = COPY [[COPY7]], debug-location !8
+  ; CHECK-NEXT:   [[COPY12:%[0-9]+]]:sreg_64 = COPY [[COPY6]], debug-location !8
+  ; CHECK-NEXT:   [[COPY13:%[0-9]+]]:sreg_32 = COPY [[COPY5]], debug-location !8
+  ; CHECK-NEXT:   [[COPY14:%[0-9]+]]:sreg_32 = COPY [[COPY4]], debug-location !8
+  ; CHECK-NEXT:   [[COPY15:%[0-9]+]]:sreg_32 = COPY [[COPY3]], debug-location !8
+  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:sreg_32 = IMPLICIT_DEF debug-location !8
+  ; CHECK-NEXT:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 10, debug-location !8
+  ; CHECK-NEXT:   [[COPY16:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]], debug-location !8
+  ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[COPY16]], [[COPY1]], implicit $exec, debug-location !8
+  ; CHECK-NEXT:   [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 20, debug-location !8
+  ; CHECK-NEXT:   [[COPY17:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]], debug-location !8
+  ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[COPY17]], [[COPY]], implicit $exec, debug-location !8
+  ; CHECK-NEXT:   [[V_OR3_B32_e64_:%[0-9]+]]:vgpr_32 = V_OR3_B32_e64 [[COPY2]], [[V_LSHLREV_B32_e64_]], [[V_LSHLREV_B32_e64_1]], implicit $exec, debug-location !8
+  ; CHECK-NEXT:   [[COPY18:%[0-9]+]]:sgpr_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3, debug-location !8
+  ; CHECK-NEXT:   $sgpr0_sgpr1_sgpr2_sgpr3 = COPY [[COPY18]], debug-location !8
+  ; CHECK-NEXT:   $sgpr4_sgpr5 = COPY [[COPY10]], debug-location !8
+  ; CHECK-NEXT:   $sgpr6_sgpr7 = COPY [[COPY11]], debug-location !8
+  ; CHECK-NEXT:   $sgpr8_sgpr9 = COPY [[COPY9]], debug-location !8
+  ; CHECK-NEXT:   $sgpr10_sgpr11 = COPY [[COPY12]], debug-location !8
+  ; CHECK-NEXT:   $sgpr12 = COPY [[COPY13]], debug-location !8
+  ; CHECK-NEXT:   $sgpr13 = COPY [[COPY14]], debug-location !8
+  ; CHECK-NEXT:   $sgpr14 = COPY [[COPY15]], debug-location !8
+  ; CHECK-NEXT:   $sgpr15 = COPY [[DEF]], debug-location !8
+  ; CHECK-NEXT:   $vgpr31 = COPY [[V_OR3_B32_e64_]], debug-location !8
+  ; CHECK-NEXT:   [[SI_PC_ADD_REL_OFFSET:%[0-9]+]]:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-gotprel32-lo) @callee, target-flags(amdgpu-gotprel32-hi) @callee, implicit-def $scc, debug-location !8
+  ; CHECK-NEXT:   [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM [[SI_PC_ADD_REL_OFFSET]], 0, 0, debug-location !8 :: (dereferenceable invariant load (p0) from got, addrspace 4)
+  ; CHECK-NEXT:   $sgpr30_sgpr31 = noconvergent SI_CALL [[S_LOAD_DWORDX2_IMM]], @callee, csr_amdgpu, implicit $sgpr0_sgpr1_sgpr2_sgpr3, implicit $sgpr4_sgpr5, implicit $sgpr6_sgpr7, implicit $sgpr8_sgpr9, implicit $sgpr10_sgpr11, implicit $sgpr12, implicit $sgpr13, implicit $sgpr14, implicit $sgpr15, implicit $vgpr31, debug-location !8
+  ; CHECK-NEXT:   ADJCALLSTACKDOWN 0, 0, implicit-def $scc, debug-location !8
   ; CHECK-NEXT:   S_ENDPGM 0
 entry:
   call void @callee(), !dbg !6
@@ -60,11 +60,11 @@ define void @returnaddress_debug_loc(ptr addrspace(1) %ptr) {
   ; CHECK: bb.1.entry:
   ; CHECK-NEXT:   liveins: $vgpr0, $vgpr1, $sgpr30_sgpr31
   ; CHECK-NEXT: {{  $}}
-  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr30_sgpr31, debug-location !7
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr30_sgpr31, debug-location !8
   ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1
-  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:vreg_64 = COPY [[COPY]], debug-location !7
+  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:vreg_64 = COPY [[COPY]], debug-location !8
   ; CHECK-NEXT:   GLOBAL_STORE_DWORDX2 [[REG_SEQUENCE]], [[COPY3]], 0, 0, implicit $exec :: (store (p0) into %ir.ptr, addrspace 1)
   ; CHECK-NEXT:   SI_RETURN
 entry:
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-inline-asm.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-inline-asm.ll
index 96c9f40e317ea..3da3355e51cf9 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-inline-asm.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-inline-asm.ll
@@ -7,7 +7,7 @@ define amdgpu_kernel void @asm_convergent() convergent{
   ; CHECK-NEXT:   liveins: $sgpr8_sgpr9
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(p4) = COPY $sgpr8_sgpr9
-  ; CHECK-NEXT:   INLINEASM &s_barrier, 33 /* sideeffect isconvergent attdialect */, !1
+  ; CHECK-NEXT:   INLINEASM &s_barrier, 33 /* sideeffect isconvergent attdialect */, !2
   ; CHECK-NEXT:   S_ENDPGM 0
   call void asm sideeffect "s_barrier", ""() convergent, !srcloc !0
   ret void
@@ -19,8 +19,8 @@ define amdgpu_kernel void @asm_simple_memory_clobber() {
   ; CHECK-NEXT:   liveins: $sgpr8_sgpr9
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(p4) = COPY $sgpr8_sgpr9
-  ; CHECK-NEXT:   INLINEASM &"", 25 /* sideeffect mayload maystore attdialect */, !1
-  ; CHECK-NEXT:   INLINEASM &"", 1 /* sideeffect attdialect */, !1
+  ; CHECK-NEXT:   INLINEASM &"", 25 /* sideeffect mayload maystore attdialect */, !2
+  ; CHECK-NEXT:   INLINEASM &"", 1 /* sideeffect attdialect */, !2
   ; CHECK-NEXT:   S_ENDPGM 0
   call void asm sideeffect "", "~{memory}"(), !srcloc !0
   call void asm sideeffect "", ""(), !srcloc !0
@@ -33,7 +33,7 @@ define amdgpu_kernel void @asm_simple_vgpr_clobber() {
   ; CHECK-NEXT:   liveins: $sgpr8_sgpr9
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(p4) = COPY $sgpr8_sgpr9
-  ; CHECK-NEXT:   INLINEASM &"v_mov_b32 v0, 7", 1 /* sideeffect attdialect */, 12 /* clobber */, implicit-def early-clobber $vgpr0, !1
+  ; CHECK-NEXT:   INLINEASM &"v_mov_b32 v0, 7", 1 /* sideeffect attdialect */, 12 /* clobber */, implicit-def early-clobber $vgpr0, !2
   ; CHECK-NEXT:   S_ENDPGM 0
   call void asm sideeffect "v_mov_b32 v0, 7", "~{v0}"(), !srcloc !0
   ret void
@@ -45,7 +45,7 @@ define amdgpu_kernel void @asm_simple_sgpr_clobber() {
   ; CHECK-NEXT:   liveins: $sgpr8_sgpr9
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(p4) = COPY $sgpr8_sgpr9
-  ; CHECK-NEXT:   INLINEASM &"s_mov_b32 s0, 7", 1 /* sideeffect attdialect */, 12 /* clobber */, implicit-def early-clobber $sgpr0, !1
+  ; CHECK-NEXT:   INLINEASM &"s_mov_b32 s0, 7", 1 /* sideeffect attdialect */, 12 /* clobber */, implicit-def early-clobber $sgpr0, !2
   ; CHECK-NEXT:   S_ENDPGM 0
   call void asm sideeffect "s_mov_b32 s0, 7", "~{s0}"(), !srcloc !0
   ret void
@@ -57,7 +57,7 @@ define amdgpu_kernel void @asm_simple_agpr_clobber() {
   ; CHECK-NEXT:   liveins: $sgpr8_sgpr9
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(p4) = COPY $sgpr8_sgpr9
-  ; CHECK-NEXT:   INLINEASM &"; def a0", 1 /* sideeffect attdialect */, 12 /* clobber */, implicit-def early-clobber $agpr0, !1
+  ; CHECK-NEXT:   INLINEASM &"; def a0", 1 /* sideeffect attdialect */, 12 /* clobber */, implicit-def early-clobber $agpr0, !2
   ; CHECK-NEXT:   S_ENDPGM 0
   call void asm sideeffect "; def a0", "~{a0}"(), !srcloc !0
   ret void
@@ -66,7 +66,7 @@ define amdgpu_kernel void @asm_simple_agpr_clobber() {
 define i32 @asm_vgpr_early_clobber() {
   ; CHECK-LABEL: name: asm_vgpr_early_clobber
   ; CHECK: bb.1 (%ir-block.0):
-  ; CHECK-NEXT:   INLINEASM &"v_mov_b32 $0, 7; v_mov_b32 $1, 7", 1 /* sideeffect attdialect */, 2228235 /* regdef-ec:VGPR_32 */, def early-clobber %8, 2228235 /* regdef-ec:VGPR_32 */, def early-clobber %9, !1
+  ; CHECK-NEXT:   INLINEASM &"v_mov_b32 $0, 7; v_mov_b32 $1, 7", 1 /* sideeffect attdialect */, 2228235 /* regdef-ec:VGPR_32 */, def early-clobber %8, 2228235 /* regdef-ec:VGPR_32 */, def early-clobber %9, !2
   ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(s32) = COPY %8
   ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:_(s32) = COPY %9
   ; CHECK-NEXT:   [[ADD:%[0-9]+]]:_(s32) = G_ADD [[COPY]], [[COPY1]]
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-metadata.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-metadata.ll
index 101bb6c0ed123..296eeaed0a287 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-metadata.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-metadata.ll
@@ -5,8 +5,7 @@
 define i32 @reloc_constant() {
   ; CHECK-LABEL: name: reloc_constant
   ; CHECK: bb.1 (%ir-block.0):
-  ; CHECK-NEXT:   [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.reloc.constant), !0
-  ; We cannot have any specific metadata check here as ConstantAsMetadata is printed as <raw_ptr_val>
+  ; CHECK-NEXT:   [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.reloc.constant), !1
   ; CHECK-NEXT:   [[INT1:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.reloc.constant), <0x{{[0-9a-f]+}}>
   ; CHECK-NEXT:   [[ADD:%[0-9]+]]:_(s32) = G_ADD [[INT]], [[INT1]]
   ; CHECK-NEXT:   $vgpr0 = COPY [[ADD]](s32)
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/load-legalize-range-metadata.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/load-legalize-range-metadata.ll
index b6b4301dadc7a..f1800dc6afcb9 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/load-legalize-range-metadata.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/load-legalize-range-metadata.ll
@@ -77,7 +77,7 @@ define <2 x i64> @global_load_v2i64_align16__rangemd(ptr addrspace(1) %ptr) {
   ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
   ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
   ; CHECK-NEXT:   [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
-  ; CHECK-NEXT:   [[LOAD:%[0-9]+]]:_(<2 x s64>) = G_LOAD [[MV]](p1) :: (load (<2 x s64>) from %ir.ptr, !range !2, addrspace 1)
+  ; CHECK-NEXT:   [[LOAD:%[0-9]+]]:_(<2 x s64>) = G_LOAD [[MV]](p1) :: (load (<2 x s64>) from %ir.ptr, !range !3, addrspace 1)
   ; CHECK-NEXT:   [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[LOAD]](<2 x s64>)
   ; CHECK-NEXT:   $vgpr0 = COPY [[UV]](s32)
   ; CHECK-NEXT:   $vgpr1 = COPY [[UV1]](s32)
@@ -119,7 +119,7 @@ define i32 @global_sextload_i8_align1__rangemd(ptr addrspace(1) %ptr) {
   ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
   ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
   ; CHECK-NEXT:   [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
-  ; CHECK-NEXT:   [[SEXTLOAD:%[0-9]+]]:_(s32) = G_SEXTLOAD [[MV]](p1) :: (load (s8) from %ir.ptr, !range !0, addrspace 1)
+  ; CHECK-NEXT:   [[SEXTLOAD:%[0-9]+]]:_(s32) = G_SEXTLOAD [[MV]](p1) :: (load (s8) from %ir.ptr, !range !1, addrspace 1)
   ; CHECK-NEXT:   $vgpr0 = COPY [[SEXTLOAD]](s32)
   ; CHECK-NEXT:   SI_RETURN implicit $vgpr0
   %load = load i8, ptr addrspace(1) %ptr, align 1, !range !0, !noundef !1
@@ -135,7 +135,7 @@ define i32 @global_zextload_i8_align1__rangemd(ptr addrspace(1) %ptr) {
   ; CHECK-NEXT:   [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
   ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
   ; CHECK-NEXT:   [[MV:%[0-9]+]]:_(p1) = G_MERGE_VALUES [[COPY]](s32), [[COPY1]](s32)
-  ; CHECK-NEXT:   [[SEXTLOAD:%[0-9]+]]:_(s32) = G_SEXTLOAD [[MV]](p1) :: (load (s8) from %ir.ptr, !range !4, addrspace 1)
+  ; CHECK-NEXT:   [[SEXTLOAD:%[0-9]+]]:_(s32) = G_SEXTLOAD [[MV]](p1) :: (load (s8) from %ir.ptr, !range !5, addrspace 1)
   ; CHECK-NEXT:   $vgpr0 = COPY [[SEXTLOAD]](s32)
   ; CHECK-NEXT:   SI_RETURN implicit $vgpr0
   %load = load i8, ptr addrspace(1) %ptr, align 1, !range !4, !noundef !1
diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/mmra.ll b/llvm/test/CodeGen/AMDGPU/GlobalISel/mmra.ll
index 44b12a9f6fe81..80243d658ae00 100644
--- a/llvm/test/CodeGen/AMDGPU/GlobalISel/mmra.ll
+++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/mmra.ll
@@ -12,11 +12,11 @@ define void @fence_loads(ptr %ptr) {
   ; CHECK-NEXT:   [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
-  ; CHECK-NEXT:   ATOMIC_FENCE 5, 1, mmra !0
-  ; CHECK-NEXT:   [[FLAT_LOAD_UBYTE:%[0-9]+]]:vgpr_32 = FLAT_LOAD_UBYTE [[REG_SEQUENCE]], 0, 0, implicit $exec, implicit $flat_scr, mmra !1 :: (load acquire (s8) from %ir.ptr, align 4)
+  ; CHECK-NEXT:   ATOMIC_FENCE 5, 1, mmra !1
+  ; CHECK-NEXT:   [[FLAT_LOAD_UBYTE:%[0-9]+]]:vgpr_32 = FLAT_LOAD_UBYTE [[REG_SEQUENCE]], 0, 0, implicit $exec, implicit $flat_scr, mmra !2 :: (load acquire (s8) from %ir.ptr, align 4)
   ; CHECK-NEXT:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 1
   ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
-  ; CHECK-NEXT:   FLAT_STORE_BYTE [[REG_SEQUENCE]], [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr, mmra !2 :: (store release (s8) into %ir.ptr, align 4)
+  ; CHECK-NEXT:   FLAT_STORE_BYTE [[REG_SEQUENCE]], [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr, mmra !3 :: (store release (s8) into %ir.ptr, align 4)
   ; CHECK-NEXT:   SI_RETURN
   fence release,                                        !mmra !0
   %ld = load atomic i8, ptr %ptr acquire, align 4,      !mmra !2
diff --git a/llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll b/llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll
index 92d0a05f35732..b2ebf2e33e29f 100644
--- a/llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll
@@ -23,10 +23,10 @@
 ;.
 define amdgpu_kernel void @k0() #0 {
 ; CHECK-LABEL: @k0() #0
-; CHECK-NEXT: store i8 1, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 3), align 2, !alias.scope !1, !noalias !4
-; CHECK-NEXT: store i8 2, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 2), align 4, !alias.scope !8, !noalias !9
-; CHECK-NEXT: store i8 4, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 1), align 16, !alias.scope !10, !noalias !11
-; CHECK-NEXT: store i8 16, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, align 16, !alias.scope !12, !noalias !13
+; CHECK-NEXT: store i8 1, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 3), align 2, !alias.scope !2, !noalias !5
+; CHECK-NEXT: store i8 2, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 2), align 4, !alias.scope !9, !noalias !10
+; CHECK-NEXT: store i8 4, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 1), align 16, !alias.scope !11, !noalias !12
+; CHECK-NEXT: store i8 16, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, align 16, !alias.scope !13, !noalias !14
 ; CHECK-NEXT:    ret void
   store i8 1, ptr addrspace(3) @lds.size.1.align.1, align 1
 
@@ -41,9 +41,9 @@ define amdgpu_kernel void @k0() #0 {
 
 define amdgpu_kernel void @k1() #0 {
 ; CHECK-LABEL: @k1() #1
-; CHECK-NEXT: store i8 2, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k1.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, i32 0, i32 2), align 4, !alias.scope !14, !noalias !17
-; CHECK-NEXT: store i8 4, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k1.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, i32 0, i32 1), align 16, !alias.scope !20, !noalias !21
-; CHECK-NEXT: store i8 16, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, align 16, !alias.scope !22, !noalias !23
+; CHECK-NEXT: store i8 2, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k1.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, i32 0, i32 2), align 4, !alias.scope !15, !noalias !18
+; CHECK-NEXT: store i8 4, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k1.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, i32 0, i32 1), align 16, !alias.scope !21, !noalias !22
+; CHECK-NEXT: store i8 16, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, align 16, !alias.scope !23, !noalias !24
 ; CHECK-NEXT:    ret void
 ;
   store i8 2, ptr addrspace(3) @lds.size.2.align.2, align 2
@@ -83,8 +83,8 @@ define amdgpu_kernel void @calls_f0() {
 
 define void @f0() {
 ; CHECK-LABEL: define void @f0()
-; CHECK-NEXT: store i8 1, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.module.lds.t, ptr addrspace(3) @llvm.amdgcn.module.lds, i32 0, i32 1), align 8, !noalias !24
-; CHECK-NEXT: store i8 8, ptr addrspace(3) @llvm.amdgcn.module.lds, align 8, !noalias !29
+; CHECK-NEXT: store i8 1, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.module.lds.t, ptr addrspace(3) @llvm.amdgcn.module.lds, i32 0, i32 1), align 8, !noalias !25
+; CHECK-NEXT: store i8 8, ptr addrspace(3) @llvm.amdgcn.module.lds, align 8, !noalias !30
 ; CHECK-NEXT: ret void
   store i8 1, ptr addrspace(3) @lds.size.1.align.1, align 1
 
diff --git a/llvm/test/CodeGen/AMDGPU/lower-kernel-lds.ll b/llvm/test/CodeGen/AMDGPU/lower-kernel-lds.ll
index 70142fa4b5b29..37ae05bfab86f 100644
--- a/llvm/test/CodeGen/AMDGPU/lower-kernel-lds.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-kernel-lds.ll
@@ -16,10 +16,10 @@
 ;.
 define amdgpu_kernel void @k0() {
 ; CHECK-LABEL: @k0(
-; CHECK-NEXT: store i8 1, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 3), align 2, !alias.scope !1, !noalias !4
-; CHECK-NEXT: store i8 2, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 2), align 4, !alias.scope !8, !noalias !9
-; CHECK-NEXT: store i8 4, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 1), align 16, !alias.scope !10, !noalias !11
-; CHECK-NEXT: store i8 16, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, align 16, !alias.scope !12, !noalias !13
+; CHECK-NEXT: store i8 1, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 3), align 2, !alias.scope !2, !noalias !5
+; CHECK-NEXT: store i8 2, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 2), align 4, !alias.scope !9, !noalias !10
+; CHECK-NEXT: store i8 4, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, i32 0, i32 1), align 16, !alias.scope !11, !noalias !12
+; CHECK-NEXT: store i8 16, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, align 16, !alias.scope !13, !noalias !14
 ; CHECK-NEXT: ret void
   store i8 1, ptr addrspace(3) @lds.size.1.align.1, align 1
 
@@ -34,9 +34,9 @@ define amdgpu_kernel void @k0() {
 
 define amdgpu_kernel void @k1() {
 ; CHECK-LABEL: @k1(
-; CHECK-NEXT: store i8 2, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k1.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, i32 0, i32 2), align 4, !alias.scope !14, !noalias !17
-; CHECK-NEXT: store i8 4, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k1.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, i32 0, i32 1), align 16, !alias.scope !20, !noalias !21
-; CHECK-NEXT: store i8 16, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, align 16, !alias.scope !22, !noalias !23
+; CHECK-NEXT: store i8 2, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k1.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, i32 0, i32 2), align 4, !alias.scope !15, !noalias !18
+; CHECK-NEXT: store i8 4, ptr addrspace(3) getelementptr inbounds (%llvm.amdgcn.kernel.k1.lds.t, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, i32 0, i32 1), align 16, !alias.scope !21, !noalias !22
+; CHECK-NEXT: store i8 16, ptr addrspace(3) @llvm.amdgcn.kernel.k1.lds, align 16, !alias.scope !23, !noalias !24
 ; CHECK-NEXT: ret void
 ;
   store i8 2, ptr addrspace(3) @lds.size.2.align.2, align 2
diff --git a/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-memcpy.ll b/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-memcpy.ll
index 4ab05c2923fdb..dbab9e520f989 100644
--- a/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-memcpy.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-memcpy.ll
@@ -34,19 +34,20 @@ define protected amdgpu_kernel void @test(ptr addrspace(1) nocapture %ptr.coerce
 ; GCN-NEXT:    s_endpgm
 ; CHECK-LABEL: define protected amdgpu_kernel void @test(
 ; CHECK-SAME: ptr addrspace(1) captures(none) [[PTR_COERCE:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
-; CHECK-NEXT:  entry:
-; CHECK-NEXT:    store i8 3, ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, align 4, !alias.scope !1, !noalias !4
-; CHECK-NEXT:    tail call void @llvm.memcpy.p3.p3.i64(ptr addrspace(3) noundef align 1 dereferenceable(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_TEST_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, i32 0, i32 2), ptr addrspace(3) noundef align 1 dereferenceable(3) @llvm.amdgcn.kernel.test.lds, i64 3, i1 false), !alias.scope !6, !noalias !7
-; CHECK-NEXT:    [[TMP0:%.*]] = load i8, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_TEST_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, i32 0, i32 2), align 4, !alias.scope !4, !noalias !1
+; CHECK-NEXT:  [[ENTRY:.*:]]
+; CHECK-NEXT:    store i8 3, ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, align 4, !alias.scope [[META2:![0-9]+]], !noalias [[META5:![0-9]+]]
+; CHECK-NEXT:    tail call void @llvm.memcpy.p3.p3.i64(ptr addrspace(3) noundef align 1 dereferenceable(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_TEST_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, i32 0, i32 2), ptr addrspace(3) noundef align 1 dereferenceable(3) @llvm.amdgcn.kernel.test.lds, i64 3, i1 false), !alias.scope [[META7:![0-9]+]], !noalias [[META8:![0-9]+]]
+; CHECK-NEXT:    [[TMP0:%.*]] = load i8, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_TEST_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, i32 0, i32 2), align 4, !alias.scope [[META5]], !noalias [[META2]]
 ; CHECK-NEXT:    [[CMP_I_I:%.*]] = icmp eq i8 [[TMP0]], 3
-; CHECK-NEXT:    store i8 2, ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, align 4, !alias.scope !1, !noalias !4
-; CHECK-NEXT:    tail call void @llvm.memcpy.p3.p3.i64(ptr addrspace(3) noundef align 1 dereferenceable(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_TEST_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, i32 0, i32 2), ptr addrspace(3) noundef align 1 dereferenceable(3) @llvm.amdgcn.kernel.test.lds, i64 3, i1 false), !alias.scope !6, !noalias !7
-; CHECK-NEXT:    [[TMP1:%.*]] = load i8, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_TEST_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, i32 0, i32 2), align 4, !alias.scope !4, !noalias !1
+; CHECK-NEXT:    store i8 2, ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, align 4, !alias.scope [[META2]], !noalias [[META5]]
+; CHECK-NEXT:    tail call void @llvm.memcpy.p3.p3.i64(ptr addrspace(3) noundef align 1 dereferenceable(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_TEST_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, i32 0, i32 2), ptr addrspace(3) noundef align 1 dereferenceable(3) @llvm.amdgcn.kernel.test.lds, i64 3, i1 false), !alias.scope [[META7]], !noalias [[META8]]
+; CHECK-NEXT:    [[TMP1:%.*]] = load i8, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_TEST_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.test.lds, i32 0, i32 2), align 4, !alias.scope [[META5]], !noalias [[META2]]
 ; CHECK-NEXT:    [[CMP_I_I19:%.*]] = icmp eq i8 [[TMP1]], 2
 ; CHECK-NEXT:    [[TMP2:%.*]] = and i1 [[CMP_I_I19]], [[CMP_I_I]]
 ; CHECK-NEXT:    [[FROMBOOL8:%.*]] = zext i1 [[TMP2]] to i8
 ; CHECK-NEXT:    store i8 [[FROMBOOL8]], ptr addrspace(1) [[PTR_COERCE]], align 1
 ; CHECK-NEXT:    ret void
+;
 entry:
   store i8 3, ptr addrspace(3) @_f1, align 1
   tail call void @llvm.memcpy.p3.p3.i64(ptr addrspace(3) noundef align 1 dereferenceable(3) @_f2, ptr addrspace(3) noundef align 1 dereferenceable(3) @_f1, i64 3, i1 false)
@@ -63,17 +64,15 @@ entry:
 }
 
 declare void @llvm.memcpy.p3.p3.i64(ptr addrspace(3) noalias nocapture writeonly, ptr addrspace(3) noalias nocapture readonly, i64, i1 immarg) #1
-
 ;.
 ; CHECK: attributes #[[ATTR0]] = { "amdgpu-lds-size"="7" }
 ; CHECK: attributes #[[ATTR1:[0-9]+]] = { nocallback nofree nounwind willreturn memory(argmem: readwrite) }
 ;.
-; CHECK: [[META0:![0-9]+]] = !{i32 0, i32 1}
-; CHECK: [[META1:![0-9]+]] = !{!2}
-; CHECK: [[META2:![0-9]+]] = distinct !{!2, !3}
-; CHECK: [[META3:![0-9]+]] = distinct !{!3}
-; CHECK: [[META4:![0-9]+]] = !{!5}
-; CHECK: [[META5:![0-9]+]] = distinct !{!5, !3}
-; CHECK: [[META6:![0-9]+]] = !{!5, !2}
-; CHECK: [[META7:![0-9]+]] = !{}
+; CHECK: [[META2]] = !{[[META3:![0-9]+]]}
+; CHECK: [[META3]] = distinct !{[[META3]], [[META4:![0-9]+]]}
+; CHECK: [[META4]] = distinct !{[[META4]]}
+; CHECK: [[META5]] = !{[[META6:![0-9]+]]}
+; CHECK: [[META6]] = distinct !{[[META6]], [[META4]]}
+; CHECK: [[META7]] = !{[[META6]], [[META3]]}
+; CHECK: [[META8]] = !{}
 ;.
diff --git a/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-merge.ll b/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-merge.ll
index 154c798a44f93..7437ce347d1a5 100644
--- a/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-merge.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa-merge.ll
@@ -9,12 +9,12 @@ define amdgpu_kernel void @no_clobber_ds_load_stores_x2_preexisting_aa(ptr addrs
 ; CHECK-LABEL: define amdgpu_kernel void @no_clobber_ds_load_stores_x2_preexisting_aa(
 ; CHECK-SAME: ptr addrspace(1) [[ARG:%.*]], i32 [[I:%.*]]) #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:  bb:
-; CHECK-NEXT:    store i32 1, ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2_preexisting_aa.lds, align 16, !tbaa [[TBAA1:![0-9]+]], !noalias !6
+; CHECK-NEXT:    store i32 1, ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2_preexisting_aa.lds, align 16, !tbaa [[TBAA2:![0-9]+]], !noalias [[META7:![0-9]+]]
 ; CHECK-NEXT:    [[GEP_A:%.*]] = getelementptr inbounds [64 x i32], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2_preexisting_aa.lds, i32 0, i32 [[I]]
-; CHECK-NEXT:    [[VAL_A:%.*]] = load i32, ptr addrspace(3) [[GEP_A]], align 4, !tbaa [[TBAA1]], !noalias !6
-; CHECK-NEXT:    store i32 2, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X2_PREEXISTING_AA_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2_preexisting_aa.lds, i32 0, i32 1), align 16, !tbaa [[TBAA1]], !noalias !11
+; CHECK-NEXT:    [[VAL_A:%.*]] = load i32, ptr addrspace(3) [[GEP_A]], align 4, !tbaa [[TBAA2]], !noalias [[META7]]
+; CHECK-NEXT:    store i32 2, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X2_PREEXISTING_AA_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2_preexisting_aa.lds, i32 0, i32 1), align 16, !tbaa [[TBAA2]], !noalias [[META12:![0-9]+]]
 ; CHECK-NEXT:    [[GEP_B:%.*]] = getelementptr inbounds [64 x i32], ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X2_PREEXISTING_AA_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2_preexisting_aa.lds, i32 0, i32 1), i32 0, i32 [[I]]
-; CHECK-NEXT:    [[VAL_B:%.*]] = load i32, ptr addrspace(3) [[GEP_B]], align 4, !tbaa [[TBAA1]], !noalias !11
+; CHECK-NEXT:    [[VAL_B:%.*]] = load i32, ptr addrspace(3) [[GEP_B]], align 4, !tbaa [[TBAA2]], !noalias [[META12]]
 ; CHECK-NEXT:    [[VAL:%.*]] = add i32 [[VAL_A]], [[VAL_B]]
 ; CHECK-NEXT:    store i32 [[VAL]], ptr addrspace(1) [[ARG]], align 4
 ; CHECK-NEXT:    ret void
@@ -42,17 +42,18 @@ bb:
 !8 = !{!"omnipotent char", !9, i64 0}
 !9 = !{!"Simple C++ TBAA"}
 
-; CHECK:!0 = !{i32 0, i32 1}
-; CHECK:!1 = !{!2, !3, i64 0}
-; CHECK:!2 = !{!"no_clobber_ds_load_stores_x2_preexisting_aa", !3, i64 0}
-; CHECK:!3 = !{!"int", !4, i64 0}
-; CHECK:!4 = !{!"omnipotent char", !5, i64 0}
-; CHECK:!5 = !{!"Simple C++ TBAA"}
-; CHECK:!6 = !{!7, !9}
-; CHECK:!7 = distinct !{!7, !8}
-; CHECK:!8 = distinct !{!8}
-; CHECK:!9 = distinct !{!9, !10}
-; CHECK:!10 = distinct !{!10}
-; CHECK:!11 = !{!12, !13}
-; CHECK:!12 = distinct !{!12, !8}
-; CHECK:!13 = distinct !{!13, !10}
+; CHECK: !0 = !{i32 0, i32 1}
+; CHECK: !1 = !{i32 1, !"amdgpu.lowered_lds", i32 1}
+; CHECK: !2 = !{!3, !4, i64 0}
+; CHECK: !3 = !{!"no_clobber_ds_load_stores_x2_preexisting_aa", !4, i64 0}
+; CHECK: !4 = !{!"int", !5, i64 0}
+; CHECK: !5 = !{!"omnipotent char", !6, i64 0}
+; CHECK: !6 = !{!"Simple C++ TBAA"}
+; CHECK: !7 = !{!8, !10}
+; CHECK: !8 = distinct !{!8, !9}
+; CHECK: !9 = distinct !{!9}
+; CHECK: !10 = distinct !{!10, !11}
+; CHECK: !11 = distinct !{!11}
+; CHECK: !12 = !{!13, !14}
+; CHECK: !13 = distinct !{!13, !9}
+; CHECK: !14 = distinct !{!14, !11}
diff --git a/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa.ll b/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa.ll
index 24c1bfb8d50f0..927ef687bc8d9 100644
--- a/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-lds-struct-aa.ll
@@ -14,12 +14,12 @@ define amdgpu_kernel void @no_clobber_ds_load_stores_x2(ptr addrspace(1) %arg, i
 ; CHECK-LABEL: define amdgpu_kernel void @no_clobber_ds_load_stores_x2(
 ; CHECK-SAME: ptr addrspace(1) [[ARG:%.*]], i32 [[I:%.*]]) #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:  bb:
-; CHECK-NEXT:    store i32 1, ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2.lds, align 16, !alias.scope !1, !noalias !4
+; CHECK-NEXT:    store i32 1, ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2.lds, align 16, !alias.scope !2, !noalias !5
 ; CHECK-NEXT:    [[GEP_A:%.*]] = getelementptr inbounds [64 x i32], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2.lds, i32 0, i32 [[I]]
-; CHECK-NEXT:    [[VAL_A:%.*]] = load i32, ptr addrspace(3) [[GEP_A]], align 4, !alias.scope !1, !noalias !4
-; CHECK-NEXT:    store i32 2, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X2_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2.lds, i32 0, i32 1), align 16, !alias.scope !4, !noalias !1
+; CHECK-NEXT:    [[VAL_A:%.*]] = load i32, ptr addrspace(3) [[GEP_A]], align 4, !alias.scope !2, !noalias !5
+; CHECK-NEXT:    store i32 2, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X2_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2.lds, i32 0, i32 1), align 16, !alias.scope !5, !noalias !2
 ; CHECK-NEXT:    [[GEP_B:%.*]] = getelementptr inbounds [64 x i32], ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X2_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x2.lds, i32 0, i32 1), i32 0, i32 [[I]]
-; CHECK-NEXT:    [[VAL_B:%.*]] = load i32, ptr addrspace(3) [[GEP_B]], align 4, !alias.scope !4, !noalias !1
+; CHECK-NEXT:    [[VAL_B:%.*]] = load i32, ptr addrspace(3) [[GEP_B]], align 4, !alias.scope !5, !noalias !2
 ; CHECK-NEXT:    [[VAL:%.*]] = add i32 [[VAL_A]], [[VAL_B]]
 ; CHECK-NEXT:    store i32 [[VAL]], ptr addrspace(1) [[ARG]], align 4
 ; CHECK-NEXT:    ret void
@@ -58,15 +58,15 @@ define amdgpu_kernel void @no_clobber_ds_load_stores_x3(ptr addrspace(1) %arg, i
 ; CHECK-LABEL: define amdgpu_kernel void @no_clobber_ds_load_stores_x3(
 ; CHECK-SAME: ptr addrspace(1) [[ARG:%.*]], i32 [[I:%.*]]) #[[ATTR1:[0-9]+]] {
 ; CHECK-NEXT:  bb:
-; CHECK-NEXT:    store i32 1, ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x3.lds, align 16, !alias.scope !6, !noalias !9
+; CHECK-NEXT:    store i32 1, ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x3.lds, align 16, !alias.scope !7, !noalias !10
 ; CHECK-NEXT:    [[GEP_A:%.*]] = getelementptr inbounds [64 x i32], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x3.lds, i32 0, i32 [[I]]
-; CHECK-NEXT:    [[VAL_A:%.*]] = load i32, ptr addrspace(3) [[GEP_A]], align 4, !alias.scope !6, !noalias !9
-; CHECK-NEXT:    store i32 2, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X3_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x3.lds, i32 0, i32 1), align 16, !alias.scope !12, !noalias !13
+; CHECK-NEXT:    [[VAL_A:%.*]] = load i32, ptr addrspace(3) [[GEP_A]], align 4, !alias.scope !7, !noalias !10
+; CHECK-NEXT:    store i32 2, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X3_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x3.lds, i32 0, i32 1), align 16, !alias.scope !13, !noalias !14
 ; CHECK-NEXT:    [[GEP_B:%.*]] = getelementptr inbounds [64 x i32], ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X3_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x3.lds, i32 0, i32 1), i32 0, i32 [[I]]
-; CHECK-NEXT:    [[VAL_B:%.*]] = load i32, ptr addrspace(3) [[GEP_B]], align 4, !alias.scope !12, !noalias !13
-; CHECK-NEXT:    store i32 3, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X3_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x3.lds, i32 0, i32 2), align 16, !alias.scope !14, !noalias !15
+; CHECK-NEXT:    [[VAL_B:%.*]] = load i32, ptr addrspace(3) [[GEP_B]], align 4, !alias.scope !13, !noalias !14
+; CHECK-NEXT:    store i32 3, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X3_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x3.lds, i32 0, i32 2), align 16, !alias.scope !15, !noalias !16
 ; CHECK-NEXT:    [[GEP_C:%.*]] = getelementptr inbounds [64 x i32], ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_NO_CLOBBER_DS_LOAD_STORES_X3_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.no_clobber_ds_load_stores_x3.lds, i32 0, i32 2), i32 0, i32 [[I]]
-; CHECK-NEXT:    [[VAL_C:%.*]] = load i32, ptr addrspace(3) [[GEP_C]], align 4, !alias.scope !14, !noalias !15
+; CHECK-NEXT:    [[VAL_C:%.*]] = load i32, ptr addrspace(3) [[GEP_C]], align 4, !alias.scope !15, !noalias !16
 ; CHECK-NEXT:    [[VAL_1:%.*]] = add i32 [[VAL_A]], [[VAL_B]]
 ; CHECK-NEXT:    [[VAL:%.*]] = add i32 [[VAL_1]], [[VAL_C]]
 ; CHECK-NEXT:    store i32 [[VAL]], ptr addrspace(1) [[ARG]], align 4
@@ -111,18 +111,19 @@ bb:
 }
 
 ; CHECK: !0 = !{i32 0, i32 1}
-; CHECK: !1 = !{!2}
-; CHECK: !2 = distinct !{!2, !3}
-; CHECK: !3 = distinct !{!3}
-; CHECK: !4 = !{!5}
-; CHECK: !5 = distinct !{!5, !3}
-; CHECK: !6 = !{!7}
-; CHECK: !7 = distinct !{!7, !8}
-; CHECK: !8 = distinct !{!8}
-; CHECK: !9 = !{!10, !11}
-; CHECK: !10 = distinct !{!10, !8}
-; CHECK: !11 = distinct !{!11, !8}
-; CHECK: !12 = !{!10}
-; CHECK: !13 = !{!7, !11}
-; CHECK: !14 = !{!11}
-; CHECK: !15 = !{!7, !10}
+; CHECK: !1 = !{i32 1, !"amdgpu.lowered_lds", i32 1}
+; CHECK: !2 = !{!3}
+; CHECK: !3 = distinct !{!3, !4}
+; CHECK: !4 = distinct !{!4}
+; CHECK: !5 = !{!6}
+; CHECK: !6 = distinct !{!6, !4}
+; CHECK: !7 = !{!8}
+; CHECK: !8 = distinct !{!8, !9}
+; CHECK: !9 = distinct !{!9}
+; CHECK: !10 = !{!11, !12}
+; CHECK: !11 = distinct !{!11, !9}
+; CHECK: !12 = distinct !{!12, !9}
+; CHECK: !13 = !{!11}
+; CHECK: !14 = !{!8, !12}
+; CHECK: !15 = !{!12}
+; CHECK: !16 = !{!8, !11}
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-all-indirect-accesses.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-all-indirect-accesses.ll
index 4fcad258d4a74..9edaa72fa55bb 100644
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-all-indirect-accesses.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-all-indirect-accesses.ll
@@ -9,7 +9,8 @@
 @B = external addrspace(3) global [0 x i32]
 
 define amdgpu_kernel void @kernel_0() {
-; CHECK-LABEL: define amdgpu_kernel void @kernel_0() #0 !llvm.amdgcn.lds.kernel.id !1 {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_0
+; CHECK-SAME: () #[[ATTR0:[0-9]+]] {{.*}}.amdgcn.lds.kernel.id [[META2:![0-9]+]] {
 ; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.kernel_0.lds) ]
 ; CHECK-NEXT:    call void @call_store_A()
 ; CHECK-NEXT:    ret void
@@ -19,7 +20,8 @@ define amdgpu_kernel void @kernel_0() {
 }
 
 define amdgpu_kernel void @kernel_1() {
-; CHECK-LABEL: define amdgpu_kernel void @kernel_1() !llvm.amdgcn.lds.kernel.id !2 {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_1
+; CHECK-SAME: () {{.*}}.amdgcn.lds.kernel.id [[META3:![0-9]+]] {
 ; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel_1.dynlds) ]
 ; CHECK-NEXT:    [[PTR:%.*]] = call ptr @get_B_ptr()
 ; CHECK-NEXT:    ret void
@@ -29,7 +31,8 @@ define amdgpu_kernel void @kernel_1() {
 }
 
 define amdgpu_kernel void @kernel_2() {
-; CHECK-LABEL: define amdgpu_kernel void @kernel_2() #0 !llvm.amdgcn.lds.kernel.id !3 {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_2
+; CHECK-SAME: () #[[ATTR0]] {{.*}}.amdgcn.lds.kernel.id [[META4:![0-9]+]] {
 ; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.kernel_2.lds) ]
 ; CHECK-NEXT:    call void @store_A()
 ; CHECK-NEXT:    ret void
@@ -39,7 +42,8 @@ define amdgpu_kernel void @kernel_2() {
 }
 
 define amdgpu_kernel void @kernel_3() {
-; CHECK-LABEL: define amdgpu_kernel void @kernel_3() !llvm.amdgcn.lds.kernel.id !4 {
+; CHECK-LABEL: define amdgpu_kernel void @kernel_3
+; CHECK-SAME: () {{.*}}.amdgcn.lds.kernel.id [[META5:![0-9]+]] {
 ; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel_3.dynlds) ]
 ; CHECK-NEXT:    [[PTR:%.*]] = call ptr @get_B_ptr()
 ; CHECK-NEXT:    ret void
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-indirect-extern-uses-max-reachable-alignment.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-indirect-extern-uses-max-reachable-alignment.ll
index a553375cb51e0..a98e170a68b8a 100644
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-indirect-extern-uses-max-reachable-alignment.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-indirect-extern-uses-max-reachable-alignment.ll
@@ -13,22 +13,12 @@
 @dynamic_shared8 = external addrspace(3) global [0 x i64], align 8
 
 ; CHECK: %llvm.amdgcn.module.lds.t = type { i32 }
-; CHECK: @dynamic_kernel_only = external addrspace(3) global [0 x double]
-; CHECK: @dynamic_shared8 = external addrspace(3) global [0 x i64], align 8
-; CHECK: @llvm.amdgcn.module.lds = internal addrspace(3) global %llvm.amdgcn.module.lds.t poison, align 4, !absolute_symbol !0
-; CHECK: @llvm.compiler.used = appending addrspace(1) global [1 x ptr] [ptr addrspacecast (ptr addrspace(3) @llvm.amdgcn.module.lds to ptr)], section "llvm.metadata"
 
 ; Alignment of these must be the maximum of the alignment of the reachable symbols
-; CHECK: @llvm.amdgcn.expect_align1.dynlds = external addrspace(3) global [0 x i8], align 1, !absolute_symbol !0
-; CHECK: @llvm.amdgcn.expect_align2.dynlds = external addrspace(3) global [0 x i8], align 2, !absolute_symbol !0
-; CHECK: @llvm.amdgcn.expect_align4.dynlds = external addrspace(3) global [0 x i8], align 4, !absolute_symbol !1
-; CHECK: @llvm.amdgcn.expect_align8.dynlds = external addrspace(3) global [0 x i8], align 8, !absolute_symbol !0
 
 ; Align 4 and symbol at address [4 5) as module.lds is reachable
-; CHECK: @llvm.amdgcn.expect_max_of_2_and_4.dynlds = external addrspace(3) global [0 x i8], align 4, !absolute_symbol !1
 
 ; Builds a lookup table out of the newly created (suffixed .dynlds) variables in kernel.id order
-; CHECK: @llvm.amdgcn.dynlds.offset.table = internal addrspace(4) constant [5 x i32] [i32 ptrtoint (ptr addrspace(3) @llvm.amdgcn.expect_align1.dynlds to i32), i32 ptrtoint (ptr addrspace(3) @llvm.amdgcn.expect_align2.dynlds to i32), i32 ptrtoint (ptr addrspace(3) @llvm.amdgcn.expect_align4.dynlds to i32), i32 ptrtoint (ptr addrspace(3) @llvm.amdgcn.expect_align8.dynlds to i32), i32 ptrtoint (ptr addrspace(3) @llvm.amdgcn.expect_max_of_2_and_4.dynlds to i32)]
 
 
 
@@ -113,7 +103,8 @@ define void @use_shared8() #0 {
 
 ; The kernels are annotated with kernel.id and llvm.donothing use of the corresponding variable
 define amdgpu_kernel void @expect_align1() {
-; CHECK-LABEL: define amdgpu_kernel void @expect_align1() !llvm.amdgcn.lds.kernel.id !2 {
+; CHECK-LABEL: define amdgpu_kernel void @expect_align1(
+; CHECK-SAME: ) {{.*}}.amdgcn.lds.kernel.id [[META3:![0-9]+]] {
 ; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.expect_align1.dynlds) ]
 ; CHECK-NEXT:    call void @use_shared1()
 ; CHECK-NEXT:    ret void
@@ -123,7 +114,8 @@ define amdgpu_kernel void @expect_align1() {
 }
 
 define amdgpu_kernel void @expect_align2() {
-; CHECK-LABEL: define amdgpu_kernel void @expect_align2() !llvm.amdgcn.lds.kernel.id !3 {
+; CHECK-LABEL: define amdgpu_kernel void @expect_align2(
+; CHECK-SAME: ) {{.*}}.amdgcn.lds.kernel.id [[META4:![0-9]+]] {
 ; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.expect_align2.dynlds) ]
 ; CHECK-NEXT:    call void @use_shared2()
 ; CHECK-NEXT:    ret void
@@ -134,7 +126,7 @@ define amdgpu_kernel void @expect_align2() {
 
 define amdgpu_kernel void @expect_align4() {
 ; CHECK-LABEL: define amdgpu_kernel void @expect_align4(
-; CHECK-SAME: ) #[[ATTR1:[0-9]+]] !llvm.amdgcn.lds.kernel.id !4 {
+; CHECK-SAME: ) #[[ATTR1:[0-9]+]] {{.*}}.amdgcn.lds.kernel.id [[META5:![0-9]+]] {
 ; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.expect_align4.dynlds) ]
 ; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
 ; CHECK-NEXT:    call void @use_shared4()
@@ -146,7 +138,8 @@ define amdgpu_kernel void @expect_align4() {
 
 ; Use dynamic_shared directly too.
 define amdgpu_kernel void @expect_align8() {
-; CHECK-LABEL: define amdgpu_kernel void @expect_align8() !llvm.amdgcn.lds.kernel.id !5 {
+; CHECK-LABEL: define amdgpu_kernel void @expect_align8(
+; CHECK-SAME: ) {{.*}}.amdgcn.lds.kernel.id [[META6:![0-9]+]] {
 ; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.expect_align8.dynlds) ]
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [0 x i64], ptr addrspace(3) @dynamic_shared8, i32 0, i32 9
 ; CHECK-NEXT:    store i64 3, ptr addrspace(3) [[ARRAYIDX]], align 8
@@ -162,7 +155,7 @@ define amdgpu_kernel void @expect_align8() {
 ; Note: use_shared4 uses module.lds so this will allocate at offset 4
 define amdgpu_kernel void @expect_max_of_2_and_4() {
 ; CHECK-LABEL: define amdgpu_kernel void @expect_max_of_2_and_4(
-; CHECK-SAME: ) #[[ATTR1]] !llvm.amdgcn.lds.kernel.id !6 {
+; CHECK-SAME: ) #[[ATTR1]] {{.*}}.amdgcn.lds.kernel.id [[META7:![0-9]+]] {
 ; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.expect_max_of_2_and_4.dynlds) ]
 ; CHECK-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
 ; CHECK-NEXT:    call void @use_shared2()
@@ -178,10 +171,8 @@ define amdgpu_kernel void @expect_max_of_2_and_4() {
 attributes #0 = { noinline }
 
 ; Function Attrs: nocallback nofree nosync nounwind willreturn memory(none)
-; CHECK: declare void @llvm.donothing() #2
 
 ; Function Attrs: nocallback nofree nosync nounwind speculatable willreturn memory(none)
-; CHECK: declare noundef i32 @llvm.amdgcn.lds.kernel.id() #3
 
 ; CHECK: attributes #0 = { noinline }
 ; CHECK: attributes #1 = { "amdgpu-lds-size"="4,4" }
@@ -190,8 +181,8 @@ attributes #0 = { noinline }
 
 ; CHECK: !0 = !{i32 0, i32 1}
 ; CHECK: !1 = !{i32 4, i32 5}
-; CHECK: !2 = !{i32 0}
-; CHECK: !3 = !{i32 1}
-; CHECK: !4 = !{i32 2}
-; CHECK: !5 = !{i32 3}
-; CHECK: !6 = !{i32 4}
+; CHECK: !3 = !{i32 0}
+; CHECK: !4 = !{i32 1}
+; CHECK: !5 = !{i32 2}
+; CHECK: !6 = !{i32 3}
+; CHECK: !7 = !{i32 4}
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-hybrid.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-hybrid.ll
index 2a7553ae5d92b..4aa92ce85adef 100644
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-hybrid.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-hybrid.ll
@@ -195,7 +195,7 @@ define amdgpu_kernel void @k01() {
 
 define amdgpu_kernel void @k23() {
 ; OPT-LABEL: @k23(
-; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k23.lds) ], !alias.scope [[META5:![0-9]+]], !noalias [[META8:![0-9]+]]
+; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k23.lds) ], !alias.scope [[META6:![0-9]+]], !noalias [[META9:![0-9]+]]
 ; OPT-NEXT:    call void @f2()
 ; OPT-NEXT:    call void @f3()
 ; OPT-NEXT:    ret void
@@ -245,12 +245,12 @@ define amdgpu_kernel void @k23() {
 ; Access and allocate three variables
 define amdgpu_kernel void @k123() {
 ; OPT-LABEL: @k123(
-; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k123.lds) ], !alias.scope [[META11:![0-9]+]], !noalias [[META14:![0-9]+]]
+; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k123.lds) ], !alias.scope [[META12:![0-9]+]], !noalias [[META15:![0-9]+]]
 ; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
 ; OPT-NEXT:    call void @f1()
-; OPT-NEXT:    [[LD:%.*]] = load i8, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_K123_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.kernel.k123.lds, i32 0, i32 1), align 8, !alias.scope [[META14]], !noalias [[META11]]
+; OPT-NEXT:    [[LD:%.*]] = load i8, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_K123_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.kernel.k123.lds, i32 0, i32 1), align 8, !alias.scope [[META15]], !noalias [[META12]]
 ; OPT-NEXT:    [[MUL:%.*]] = mul i8 [[LD]], 8
-; OPT-NEXT:    store i8 [[MUL]], ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_K123_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.k123.lds, i32 0, i32 1), align 8, !alias.scope [[META14]], !noalias [[META11]]
+; OPT-NEXT:    store i8 [[MUL]], ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_KERNEL_K123_LDS_T]], ptr addrspace(3) @llvm.amdgcn.kernel.k123.lds, i32 0, i32 1), align 8, !alias.scope [[META15]], !noalias [[META12]]
 ; OPT-NEXT:    call void @f2()
 ; OPT-NEXT:    ret void
 ;
@@ -312,18 +312,19 @@ define amdgpu_kernel void @k123() {
 ; OPT: !1 = !{i32 4, i32 5}
 ; OPT: !2 = !{i32 8, i32 9}
 ; OPT: !3 = !{i32 1, !"amdhsa_code_object_version", i32 500}
-; OPT: !4 = !{i32 1}
-; OPT: !5 = !{!6}
-; OPT: !6 = distinct !{!6, !7}
-; OPT: !7 = distinct !{!7}
-; OPT: !8 = !{!9}
-; OPT: !9 = distinct !{!9, !7}
-; OPT: !10 = !{i32 0}
-; OPT: !11 = !{!12}
-; OPT: !12 = distinct !{!12, !13}
-; OPT: !13 = distinct !{!13}
-; OPT: !14 = !{!15}
-; OPT: !15 = distinct !{!15, !13}
+; OPT: !4 = !{i32 1, !"amdgpu.lowered_lds", i32 1}
+; OPT: !5 = !{i32 1}
+; OPT: !6 = !{!7}
+; OPT: !7 = distinct !{!7, !8}
+; OPT: !8 = distinct !{!8}
+; OPT: !9 = !{!10}
+; OPT: !10 = distinct !{!10, !8}
+; OPT: !11 = !{i32 0}
+; OPT: !12 = !{!13}
+; OPT: !13 = distinct !{!13, !14}
+; OPT: !14 = distinct !{!14}
+; OPT: !15 = !{!16}
+; OPT: !16 = distinct !{!16, !14}
 
 attributes #0 = { "amdgpu-lds-size"="8" }
 attributes #1 = { "amdgpu-lds-size"="16" }
diff --git a/llvm/test/CodeGen/AMDGPU/mmra.ll b/llvm/test/CodeGen/AMDGPU/mmra.ll
index 444997858bf7a..3e88b93125101 100644
--- a/llvm/test/CodeGen/AMDGPU/mmra.ll
+++ b/llvm/test/CodeGen/AMDGPU/mmra.ll
@@ -14,12 +14,12 @@ define void @fence_loads(ptr %ptr) {
   ; CHECK-NEXT:   [[DEF:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
   ; CHECK-NEXT:   [[DEF1:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
   ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY]], %subreg.sub1
-  ; CHECK-NEXT:   ATOMIC_FENCE 5, 1, mmra !0
-  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]], mmra !1
-  ; CHECK-NEXT:   [[FLAT_LOAD_UBYTE:%[0-9]+]]:vgpr_32 = FLAT_LOAD_UBYTE [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr, mmra !1 :: (load acquire (s8) from %ir.ptr, align 4)
+  ; CHECK-NEXT:   ATOMIC_FENCE 5, 1, mmra !1
+  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]], mmra !2
+  ; CHECK-NEXT:   [[FLAT_LOAD_UBYTE:%[0-9]+]]:vgpr_32 = FLAT_LOAD_UBYTE [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr, mmra !2 :: (load acquire (s8) from %ir.ptr, align 4)
   ; CHECK-NEXT:   [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 1, implicit $exec
-  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]], mmra !2
-  ; CHECK-NEXT:   FLAT_STORE_BYTE [[COPY3]], killed [[V_MOV_B32_e32_]], 0, 0, implicit $exec, implicit $flat_scr, mmra !2 :: (store release (s8) into %ir.ptr, align 4)
+  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]], mmra !3
+  ; CHECK-NEXT:   FLAT_STORE_BYTE [[COPY3]], killed [[V_MOV_B32_e32_]], 0, 0, implicit $exec, implicit $flat_scr, mmra !3 :: (store release (s8) into %ir.ptr, align 4)
   ; CHECK-NEXT:   SI_RETURN
   fence release,                                        !mmra !0
   %ld = load atomic i8, ptr %ptr acquire, align 4,      !mmra !2
@@ -37,8 +37,8 @@ define void @atomicrmw_acq(ptr %ptr) {
   ; CHECK-NEXT:   [[DEF:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
   ; CHECK-NEXT:   [[DEF1:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
   ; CHECK-NEXT:   [[REG_SEQUENCE:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY]], %subreg.sub1
-  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]], mmra !1
-  ; CHECK-NEXT:   [[FLAT_LOAD_UBYTE:%[0-9]+]]:vgpr_32 = FLAT_LOAD_UBYTE killed [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr, mmra !1 :: (load acquire (s8) from %ir.ptr)
+  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]], mmra !2
+  ; CHECK-NEXT:   [[FLAT_LOAD_UBYTE:%[0-9]+]]:vgpr_32 = FLAT_LOAD_UBYTE killed [[COPY2]], 0, 0, implicit $exec, implicit $flat_scr, mmra !2 :: (load acquire (s8) from %ir.ptr)
   ; CHECK-NEXT:   SI_RETURN
   %old.2 = atomicrmw add ptr %ptr, i8 0 acquire,        !mmra !2
   ret void
@@ -69,8 +69,8 @@ define void @atomicrmw_rel(ptr %ptr) {
   ; CHECK-NEXT:   [[S_MOV_B32_2:%[0-9]+]]:sreg_32 = S_MOV_B32 255
   ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 killed [[V_LSHLREV_B32_e64_]], killed [[S_MOV_B32_2]], implicit $exec
   ; CHECK-NEXT:   [[V_NOT_B32_e32_:%[0-9]+]]:vgpr_32 = V_NOT_B32_e32 [[V_LSHLREV_B32_e64_1]], implicit $exec
-  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE1]], mmra !2
-  ; CHECK-NEXT:   [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[COPY5]], 0, 0, implicit $exec, implicit $flat_scr, mmra !2 :: (load (s32) from %ir.AlignedAddr)
+  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE1]], mmra !3
+  ; CHECK-NEXT:   [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[COPY5]], 0, 0, implicit $exec, implicit $flat_scr, mmra !3 :: (load (s32) from %ir.AlignedAddr)
   ; CHECK-NEXT:   [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 0
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT: bb.1.atomicrmw.start:
@@ -83,9 +83,9 @@ define void @atomicrmw_rel(ptr %ptr) {
   ; CHECK-NEXT:   [[DEF4:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
   ; CHECK-NEXT:   [[DEF5:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
   ; CHECK-NEXT:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_AND_B32_e64_2]], %subreg.sub0, [[PHI1]], %subreg.sub1
-  ; CHECK-NEXT:   [[COPY6:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE2]], mmra !2
-  ; CHECK-NEXT:   [[FLAT_ATOMIC_CMPSWAP_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_CMPSWAP_RTN [[COPY4]], killed [[COPY6]], 0, 1, implicit $exec, implicit $flat_scr, mmra !2 :: (load store release monotonic (s32) on %ir.AlignedAddr)
-  ; CHECK-NEXT:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_EQ_U32_e64 [[FLAT_ATOMIC_CMPSWAP_RTN]], [[PHI1]], implicit $exec, mmra !2
+  ; CHECK-NEXT:   [[COPY6:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE2]], mmra !3
+  ; CHECK-NEXT:   [[FLAT_ATOMIC_CMPSWAP_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_CMPSWAP_RTN [[COPY4]], killed [[COPY6]], 0, 1, implicit $exec, implicit $flat_scr, mmra !3 :: (load store release monotonic (s32) on %ir.AlignedAddr)
+  ; CHECK-NEXT:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_EQ_U32_e64 [[FLAT_ATOMIC_CMPSWAP_RTN]], [[PHI1]], implicit $exec, mmra !3
   ; CHECK-NEXT:   [[SI_IF_BREAK:%[0-9]+]]:sreg_64 = SI_IF_BREAK killed [[V_CMP_EQ_U32_e64_]], [[PHI]], implicit-def dead $scc
   ; CHECK-NEXT:   SI_LOOP [[SI_IF_BREAK]], %bb.1, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
   ; CHECK-NEXT:   S_BRANCH %bb.2
@@ -125,8 +125,8 @@ define void @cmpxchg(ptr %ptr) {
   ; CHECK-NEXT:   [[V_NOT_B32_e32_:%[0-9]+]]:vgpr_32 = V_NOT_B32_e32 killed [[V_LSHLREV_B32_e64_1]], implicit $exec
   ; CHECK-NEXT:   [[S_MOV_B32_3:%[0-9]+]]:sreg_32 = S_MOV_B32 1
   ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_2:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 [[V_LSHLREV_B32_e64_]], killed [[S_MOV_B32_3]], implicit $exec
-  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE1]], mmra !1
-  ; CHECK-NEXT:   [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[COPY5]], 0, 0, implicit $exec, implicit $flat_scr, mmra !1 :: (load (s32) from %ir.AlignedAddr)
+  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE1]], mmra !2
+  ; CHECK-NEXT:   [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[COPY5]], 0, 0, implicit $exec, implicit $flat_scr, mmra !2 :: (load (s32) from %ir.AlignedAddr)
   ; CHECK-NEXT:   [[V_AND_B32_e64_2:%[0-9]+]]:vgpr_32 = V_AND_B32_e64 killed [[FLAT_LOAD_DWORD]], [[V_NOT_B32_e32_]], implicit $exec
   ; CHECK-NEXT:   [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 0
   ; CHECK-NEXT:   [[DEF4:%[0-9]+]]:sreg_64 = IMPLICIT_DEF
@@ -141,8 +141,8 @@ define void @cmpxchg(ptr %ptr) {
   ; CHECK-NEXT:   [[DEF5:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
   ; CHECK-NEXT:   [[DEF6:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
   ; CHECK-NEXT:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_OR_B32_e64_]], %subreg.sub0, [[PHI2]], %subreg.sub1
-  ; CHECK-NEXT:   [[COPY6:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE2]], mmra !1
-  ; CHECK-NEXT:   [[FLAT_ATOMIC_CMPSWAP_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_CMPSWAP_RTN [[COPY4]], killed [[COPY6]], 0, 1, implicit $exec, implicit $flat_scr, mmra !1 :: (load store acquire acquire (s32) on %ir.AlignedAddr)
+  ; CHECK-NEXT:   [[COPY6:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE2]], mmra !2
+  ; CHECK-NEXT:   [[FLAT_ATOMIC_CMPSWAP_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_CMPSWAP_RTN [[COPY4]], killed [[COPY6]], 0, 1, implicit $exec, implicit $flat_scr, mmra !2 :: (load store acquire acquire (s32) on %ir.AlignedAddr)
   ; CHECK-NEXT:   [[V_CMP_NE_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_NE_U32_e64 [[FLAT_ATOMIC_CMPSWAP_RTN]], [[PHI2]], implicit $exec
   ; CHECK-NEXT:   [[S_MOV_B64_1:%[0-9]+]]:sreg_64 = S_MOV_B64 -1
   ; CHECK-NEXT:   [[DEF7:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
@@ -248,8 +248,8 @@ define void @atomicrmw_rel_deepcopy(ptr %ptr) {
   ; CHECK-NEXT:   [[S_MOV_B32_2:%[0-9]+]]:sreg_32 = S_MOV_B32 255
   ; CHECK-NEXT:   [[V_LSHLREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHLREV_B32_e64 killed [[V_LSHLREV_B32_e64_]], killed [[S_MOV_B32_2]], implicit $exec
   ; CHECK-NEXT:   [[V_NOT_B32_e32_:%[0-9]+]]:vgpr_32 = V_NOT_B32_e32 [[V_LSHLREV_B32_e64_1]], implicit $exec
-  ; CHECK-NEXT:   [[COPY31:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE1]], mmra !0
-  ; CHECK-NEXT:   [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[COPY31]], 0, 0, implicit $exec, implicit $flat_scr, mmra !0 :: (load (s32) from %ir.AlignedAddr)
+  ; CHECK-NEXT:   [[COPY31:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE1]], mmra !1
+  ; CHECK-NEXT:   [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[COPY31]], 0, 0, implicit $exec, implicit $flat_scr, mmra !1 :: (load (s32) from %ir.AlignedAddr)
   ; CHECK-NEXT:   [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 0
   ; CHECK-NEXT: {{  $}}
   ; CHECK-NEXT: bb.1.atomicrmw.start:
@@ -262,9 +262,9 @@ define void @atomicrmw_rel_deepcopy(ptr %ptr) {
   ; CHECK-NEXT:   [[DEF4:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
   ; CHECK-NEXT:   [[DEF5:%[0-9]+]]:sgpr_32 = IMPLICIT_DEF
   ; CHECK-NEXT:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[V_AND_B32_e64_2]], %subreg.sub0, [[PHI1]], %subreg.sub1
-  ; CHECK-NEXT:   [[COPY32:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE2]], mmra !0
-  ; CHECK-NEXT:   [[FLAT_ATOMIC_CMPSWAP_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_CMPSWAP_RTN [[COPY30]], killed [[COPY32]], 0, 1, implicit $exec, implicit $flat_scr, mmra !0 :: (load store release monotonic (s32) on %ir.AlignedAddr)
-  ; CHECK-NEXT:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_EQ_U32_e64 [[FLAT_ATOMIC_CMPSWAP_RTN]], [[PHI1]], implicit $exec, mmra !0
+  ; CHECK-NEXT:   [[COPY32:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE2]], mmra !1
+  ; CHECK-NEXT:   [[FLAT_ATOMIC_CMPSWAP_RTN:%[0-9]+]]:vgpr_32 = FLAT_ATOMIC_CMPSWAP_RTN [[COPY30]], killed [[COPY32]], 0, 1, implicit $exec, implicit $flat_scr, mmra !1 :: (load store release monotonic (s32) on %ir.AlignedAddr)
+  ; CHECK-NEXT:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64 = V_CMP_EQ_U32_e64 [[FLAT_ATOMIC_CMPSWAP_RTN]], [[PHI1]], implicit $exec, mmra !1
   ; CHECK-NEXT:   [[SI_IF_BREAK:%[0-9]+]]:sreg_64 = SI_IF_BREAK killed [[V_CMP_EQ_U32_e64_]], [[PHI]], implicit-def dead $scc
   ; CHECK-NEXT:   SI_LOOP [[SI_IF_BREAK]], %bb.1, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
   ; CHECK-NEXT:   S_BRANCH %bb.2