diff --git a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPULowerModuleLDSPass.cpp
@@ -73,8 +73,6 @@
 // The "module" lowering implemented here finds LDS variables which are used by
 // non-kernel functions and creates a new struct with a field for each of those
 // LDS variables. Variables that are only used from kernels are excluded.
-// Kernels that do not use this struct are annoteated with the attribute
-// amdgpu-elide-module-lds which allows the back end to elide the allocation.
 //
 // The "table" lowering implemented here has three components.
 // First kernels are assigned a unique integer identifier which is available in
@@ -906,9 +904,6 @@
             });
 
         markUsedByKernel(Builder, &Func, ModuleScopeReplacement.SGV);
-
-      } else {
-        markElideModuleLDS(Func);
       }
     }
 
@@ -1106,16 +1101,6 @@
     return KernelToCreatedDynamicLDS;
   }
 
-  // This attribute is no longer used by the backend. TODO: Delete it in favour
-  // of pass-local state and update the tests to remove the string.
-  static bool canElideModuleLDS(const Function &F) {
-    return F.hasFnAttribute("amdgpu-elide-module-lds");
-  }
-
-  static void markElideModuleLDS(Function &F) {
-    F.addFnAttr("amdgpu-elide-module-lds");
-  }
-
   bool runOnModule(Module &M) override {
     CallGraph CG = CallGraph(M);
     bool Changed = superAlignLDSGlobals(M);
@@ -1232,7 +1217,8 @@
         //}
 
         const bool AllocateModuleScopeStruct =
-            MaybeModuleScopeStruct && !canElideModuleLDS(Func);
+            MaybeModuleScopeStruct &&
+            KernelsThatAllocateModuleLDS.contains(&Func);
 
         auto Replacement = KernelToReplacement.find(&Func);
         const bool AllocateKernelScopeStruct =
diff --git a/llvm/test/CodeGen/AMDGPU/lds-frame-extern.ll b/llvm/test/CodeGen/AMDGPU/lds-frame-extern.ll
--- a/llvm/test/CodeGen/AMDGPU/lds-frame-extern.ll
+++ b/llvm/test/CodeGen/AMDGPU/lds-frame-extern.ll
@@ -90,7 +90,7 @@
 ; kernel variable normal/overaligned
 ; extern variable normal/overaligned
 
-define amdgpu_kernel void @module_0_kernel_normal_extern_normal(i32 %idx) #1 {
+define amdgpu_kernel void @module_0_kernel_normal_extern_normal(i32 %idx) {
 ; CHECK-LABEL: module_0_kernel_normal_extern_normal:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    s_load_dword s0, s[4:5], 0x0
@@ -148,7 +148,7 @@
   ret void
 }
 
-define amdgpu_kernel void @module_0_kernel_overalign_extern_normal(i32 %idx) #1 {
+define amdgpu_kernel void @module_0_kernel_overalign_extern_normal(i32 %idx) {
 ; CHECK-LABEL: module_0_kernel_overalign_extern_normal:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    s_load_dword s0, s[4:5], 0x0
@@ -206,7 +206,7 @@
   ret void
 }
 
-define amdgpu_kernel void @module_0_kernel_normal_extern_overalign(i32 %idx) #1 {
+define amdgpu_kernel void @module_0_kernel_normal_extern_overalign(i32 %idx) {
 ; CHECK-LABEL: module_0_kernel_normal_extern_overalign:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    s_load_dword s0, s[4:5], 0x0
@@ -264,7 +264,7 @@
   ret void
 }
 
-define amdgpu_kernel void @module_0_kernel_overalign_extern_overalign(i32 %idx) #1 {
+define amdgpu_kernel void @module_0_kernel_overalign_extern_overalign(i32 %idx) {
 ; CHECK-LABEL: module_0_kernel_overalign_extern_overalign:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    s_load_dword s0, s[4:5], 0x0
@@ -329,7 +329,7 @@
 ; kernel variable normal/overaligned
 ; extern variable normal/overaligned
 
-define amdgpu_kernel void @module_0_kernel_normal_indirect_extern_normal(i32 %idx) #1 {
+define amdgpu_kernel void @module_0_kernel_normal_indirect_extern_normal(i32 %idx) {
 ; CHECK-LABEL: module_0_kernel_normal_indirect_extern_normal:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    s_add_u32 s8, s8, s11
@@ -396,7 +396,7 @@
   ret void
 }
 
-define amdgpu_kernel void @module_0_kernel_overalign_indirect_extern_normal(i32 %idx) #1 {
+define amdgpu_kernel void @module_0_kernel_overalign_indirect_extern_normal(i32 %idx) {
 ; CHECK-LABEL: module_0_kernel_overalign_indirect_extern_normal:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    s_add_u32 s8, s8, s11
@@ -463,7 +463,7 @@
   ret void
 }
 
-define amdgpu_kernel void @module_0_kernel_normal_indirect_extern_overalign(i32 %idx) #1 {
+define amdgpu_kernel void @module_0_kernel_normal_indirect_extern_overalign(i32 %idx) {
 ; CHECK-LABEL: module_0_kernel_normal_indirect_extern_overalign:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    s_add_u32 s8, s8, s11
@@ -530,7 +530,7 @@
   ret void
 }
 
-define amdgpu_kernel void @module_0_kernel_overalign_indirect_extern_overalign(i32 %idx) #1 {
+define amdgpu_kernel void @module_0_kernel_overalign_indirect_extern_overalign(i32 %idx) {
 ; CHECK-LABEL: module_0_kernel_overalign_indirect_extern_overalign:
 ; CHECK:       ; %bb.0:
 ; CHECK-NEXT:    s_add_u32 s8, s8, s11
@@ -599,4 +599,3 @@
 
 
 attributes #0 = { noinline }
-attributes #1 = { "amdgpu-elide-module-lds" }
diff --git a/llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll b/llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-kernel-and-module-lds.ll
@@ -93,10 +93,10 @@
   ret void
 }
 
-; CHECK: attributes #0 = { "amdgpu-elide-module-lds" "amdgpu-lds-size"="23" }
-; CHECK: attributes #1 = { "amdgpu-elide-module-lds" "amdgpu-lds-size"="22" }
-; CHECK: attributes #2 = { "amdgpu-elide-module-lds" "amdgpu-lds-size"="2" }
-; CHECK: attributes #3 = { "amdgpu-elide-module-lds" "amdgpu-lds-size"="4" }
+; CHECK: attributes #0 = { "amdgpu-lds-size"="23" }
+; CHECK: attributes #1 = { "amdgpu-lds-size"="22" }
+; CHECK: attributes #2 = { "amdgpu-lds-size"="2" }
+; CHECK: attributes #3 = { "amdgpu-lds-size"="4" }
 ; CHECK: attributes #4 = { "amdgpu-lds-size"="9" }
 
 ; CHECK: !0 = !{i64 0, i64 1}
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-constantexpr.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-constantexpr.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-constantexpr.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-constantexpr.ll
@@ -42,13 +42,13 @@
 ; CHECK:      %5 = inttoptr i64 %4 to ptr
 ; CHECK:      store i32 %x, ptr %5, align 4
 ; CHECK:      ret void
-define void @set_func(i32 %x) local_unnamed_addr #1 {
+define void @set_func(i32 %x) {
 entry:
   store i32 %x, ptr inttoptr (i64 add (i64 ptrtoint (ptr addrspacecast (ptr addrspace(3) @b_both to ptr) to i64), i64 ptrtoint (ptr addrspacecast (ptr addrspace(3) @b_both to ptr) to i64)) to ptr), align 4
   ret void
 }
 
-; CHECK-LABEL: @timestwo() #1
+; CHECK-LABEL: @timestwo() #0
 ; CHECK-NOT: call void @llvm.donothing()
 
 ; CHECK:      %1 = addrspacecast ptr addrspace(3) @llvm.amdgcn.kernel.timestwo.lds to ptr
@@ -67,14 +67,14 @@
 ; CHECK:      %12 = inttoptr i64 %11 to ptr
 ; CHECK:      store i32 %mul, ptr %12, align 4
 ; CHECK:      ret void
-define amdgpu_kernel void @timestwo() #1 {
+define amdgpu_kernel void @timestwo() {
   %ld = load i32, ptr inttoptr (i64 add (i64 ptrtoint (ptr addrspacecast (ptr addrspace(3) @b_both to ptr) to i64), i64 ptrtoint (ptr addrspacecast (ptr addrspace(3) @kern to ptr) to i64)) to ptr), align 4
   %mul = mul i32 %ld, 2
   store i32 %mul, ptr inttoptr (i64 add (i64 ptrtoint (ptr addrspacecast (ptr addrspace(3) @kern to ptr) to i64), i64 ptrtoint (ptr addrspacecast (ptr addrspace(3) @b_both to ptr) to i64)) to ptr), align 4
   ret void
 }
 
-; CHECK-LABEL: @through_functions() #2
+; CHECK-LABEL: @through_functions() #0
 define amdgpu_kernel void @through_functions() {
   %ld = call i32 @get_func()
   %mul = mul i32 %ld, 4
@@ -82,7 +82,4 @@
   ret void
 }
 
-attributes #0 = { "amdgpu-elide-module-lds" }
-; CHECK: attributes #0 = { "amdgpu-elide-module-lds" }
-; CHECK: attributes #1 = { "amdgpu-elide-module-lds" "amdgpu-lds-size"="8" }
-; CHECK: attributes #2 = { "amdgpu-lds-size"="8" }
+; CHECK: attributes #0 = { "amdgpu-lds-size"="8" }
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
--- 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
@@ -1,7 +1,6 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s | FileCheck %s
 
-
 ; Not reached by a non-kernel function and therefore not changed by this pass
 @dynamic_kernel_only = external addrspace(3) global [0 x double]
 
@@ -34,7 +33,7 @@
 
 
 define amdgpu_kernel void @kernel_only() {
-; CHECK-LABEL: @kernel_only() #0 {
+; CHECK-LABEL: @kernel_only() {
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds [0 x double], ptr addrspace(3) @dynamic_kernel_only, i32 0, i32 0
 ; CHECK-NEXT:    store double 3.140000e+00, ptr addrspace(3) [[ARRAYIDX]], align 8
 ; CHECK-NEXT:    ret void
@@ -45,8 +44,8 @@
 }
 
 ; The accesses from functions are rewritten to go through the llvm.amdgcn.dynlds.offset.table
-define void @use_shared1() #0 {
-; CHECK-LABEL: @use_shared1() #1 {
+define void @use_shared1() {
+; CHECK-LABEL: @use_shared1() {
 ; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
 ; CHECK-NEXT:    [[DYNAMIC_SHARED1:%.*]] = getelementptr inbounds [5 x i32], ptr addrspace(4) @llvm.amdgcn.dynlds.offset.table, i32 0, i32 [[TMP1]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr addrspace(4) [[DYNAMIC_SHARED1]], align 4
@@ -61,7 +60,7 @@
 }
 
 define void @use_shared2() #0 {
-; CHECK-LABEL: @use_shared2() #1 {
+; CHECK-LABEL: @use_shared2() #0 {
 ; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
 ; CHECK-NEXT:    [[DYNAMIC_SHARED2:%.*]] = getelementptr inbounds [5 x i32], ptr addrspace(4) @llvm.amdgcn.dynlds.offset.table, i32 0, i32 [[TMP1]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr addrspace(4) [[DYNAMIC_SHARED2]], align 4
@@ -78,7 +77,7 @@
 ; Include a normal variable so that the new variables aren't all at the same absolute_symbol
 @static_shared = addrspace(3) global i32 undef
 define void @use_shared4() #0 {
-; CHECK-LABEL: @use_shared4() #1 {
+; CHECK-LABEL: @use_shared4() #0 {
 ; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
 ; CHECK-NEXT:    store i32 4, ptr addrspace(3) @llvm.amdgcn.module.lds, align 4
 ; CHECK-NEXT:    [[DYNAMIC_SHARED4:%.*]] = getelementptr inbounds [5 x i32], ptr addrspace(4) @llvm.amdgcn.dynlds.offset.table, i32 0, i32 [[TMP1]]
@@ -95,7 +94,7 @@
 }
 
 define void @use_shared8() #0 {
-; CHECK-LABEL: @use_shared8() #1 {
+; CHECK-LABEL: @use_shared8() #0 {
 ; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
 ; CHECK-NEXT:    [[DYNAMIC_SHARED8:%.*]] = getelementptr inbounds [5 x i32], ptr addrspace(4) @llvm.amdgcn.dynlds.offset.table, i32 0, i32 [[TMP1]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr addrspace(4) [[DYNAMIC_SHARED8]], align 4
@@ -111,7 +110,7 @@
 
 ; The kernels are annotated with kernel.id and llvm.donothing use of the corresponding variable
 define amdgpu_kernel void @expect_align1() {
-; CHECK-LABEL: @expect_align1() #0 !llvm.amdgcn.lds.kernel.id !2
+; CHECK-LABEL: @expect_align1() !llvm.amdgcn.lds.kernel.id !2
 ; 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
@@ -121,7 +120,7 @@
 }
 
 define amdgpu_kernel void @expect_align2() {
-; CHECK-LABEL: @expect_align2() #0 !llvm.amdgcn.lds.kernel.id !3
+; CHECK-LABEL: @expect_align2() !llvm.amdgcn.lds.kernel.id !3
 ; 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
@@ -131,7 +130,7 @@
 }
 
 define amdgpu_kernel void @expect_align4() {
-; CHECK-LABEL: @expect_align4() #2 !llvm.amdgcn.lds.kernel.id !4 {
+; CHECK-LABEL: @expect_align4() #1 !llvm.amdgcn.lds.kernel.id !4 {
 ; 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()
@@ -141,9 +140,9 @@
   ret void
 }
 
-; Use dynamic_shared directly too. Can elide module lds (#0) 
+; Use dynamic_shared directly too.
 define amdgpu_kernel void @expect_align8() {
-; CHECK-LABEL: @expect_align8() #0 !llvm.amdgcn.lds.kernel.id !5 {
+; CHECK-LABEL: @expect_align8() !llvm.amdgcn.lds.kernel.id !5 {
 ; 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 4
@@ -158,7 +157,7 @@
 
 ; 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: @expect_max_of_2_and_4() #2 !llvm.amdgcn.lds.kernel.id !6 {
+; CHECK-LABEL: @expect_max_of_2_and_4() #1 !llvm.amdgcn.lds.kernel.id !6 {
 ; 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()
@@ -174,16 +173,15 @@
 attributes #0 = { noinline }
 
 ; Function Attrs: nocallback nofree nosync nounwind willreturn memory(none)
-; CHECK: declare void @llvm.donothing() #3
+; CHECK: declare void @llvm.donothing() #2
 
 ; Function Attrs: nocallback nofree nosync nounwind speculatable willreturn memory(none)
-; CHECK: declare i32 @llvm.amdgcn.lds.kernel.id() #4
+; CHECK: declare i32 @llvm.amdgcn.lds.kernel.id() #3
 
-; CHECK: attributes #0 = { "amdgpu-elide-module-lds" }
-; CHECK: attributes #1 = { noinline }
-; CHECK: attributes #2 = { "amdgpu-lds-size"="4" }
-; CHECK: attributes #3 = { nocallback nofree nosync nounwind willreturn memory(none) }
-; CHECK: attributes #4 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
+; CHECK: attributes #0 = { noinline }
+; CHECK: attributes #1 = { "amdgpu-lds-size"="4" }
+; CHECK: attributes #2 = { nocallback nofree nosync nounwind willreturn memory(none) }
+; CHECK: attributes #3 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
 
 ; CHECK: !0 = !{i64 0, i64 1}
 ; CHECK: !1 = !{i64 4, i64 5}
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-offsets.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-offsets.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-offsets.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-offsets.ll
@@ -42,6 +42,3 @@
   store i8 3, ptr addrspace(3) @lds.size.1.align.1, align 1
   ret void
 }
-
-attributes #0 = { "amdgpu-elide-module-lds" }
-; CHECK: attributes #0 = { "amdgpu-elide-module-lds" }
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-hybrid.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-hybrid.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-hybrid.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-hybrid.ll
@@ -284,12 +284,11 @@
 !2 = !{i32 1}
 
 
-; OPT: attributes #0 = { "amdgpu-elide-module-lds" "amdgpu-lds-size"="8" }
-; OPT: attributes #1 = { "amdgpu-lds-size"="8" }
-; OPT: attributes #2 = { "amdgpu-elide-module-lds" "amdgpu-lds-size"="12" }
-; OPT: attributes #3 = { "amdgpu-lds-size"="20" }
-; OPT: attributes #4 = { nocallback nofree nosync nounwind willreturn memory(none) }
-; OPT: attributes #5 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
+; OPT: attributes #0 = { "amdgpu-lds-size"="8" }
+; OPT: attributes #1 = { "amdgpu-lds-size"="12" }
+; OPT: attributes #2 = { "amdgpu-lds-size"="20" }
+; OPT: attributes #3 = { nocallback nofree nosync nounwind willreturn memory(none) }
+; OPT: attributes #4 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
 
 ; OPT: !0 = !{i64 0, i64 1}
 ; OPT: !1 = !{i64 4, i64 5}
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds.ll
@@ -51,9 +51,9 @@
 }
 
 ; This kernel does alloc the LDS block as it makes no calls
-; CHECK-LABEL: @kern_empty() #1
+; CHECK-LABEL: @kern_empty()
 ; CHECK-NOT: call void @llvm.donothing()
-define spir_kernel void @kern_empty() #0{
+define spir_kernel void @kern_empty() {
   ret void
 }
 
@@ -61,7 +61,4 @@
 ; declaration.
 declare amdgpu_kernel void @kernel_declaration()
 
-attributes #0 = { "amdgpu-elide-module-lds" }
-
 ; CHECK: attributes #0 = { "amdgpu-lds-size"="12" }
-; CHECK: attributes #1 = { "amdgpu-elide-module-lds" }