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
@@ -902,8 +902,6 @@
               Function *F = I->getFunction();
               return F == &Func;
             });
-
-        markUsedByKernel(Builder, &Func, ModuleScopeReplacement.SGV);
       }
     }
 
@@ -972,14 +970,6 @@
       auto Replacement =
           createLDSVariableReplacement(M, VarName, KernelUsedVariables);
 
-      // If any indirect uses, create a direct use to ensure allocation
-      // TODO: Simpler to unconditionally mark used but that regresses
-      // codegen in test/CodeGen/AMDGPU/noclobber-barrier.ll
-      auto Accesses = LDSUsesInfo.indirect_access.find(&Func);
-      if ((Accesses != LDSUsesInfo.indirect_access.end()) &&
-          !Accesses->second.empty())
-        markUsedByKernel(Builder, &Func, Replacement.SGV);
-
       // remove preserves existing codegen
       removeLocalVarsFromUsedLists(M, KernelUsedVariables);
       KernelToReplacement[&Func] = Replacement;
@@ -1067,6 +1057,7 @@
 
           KernelToCreatedDynamicLDS[func] = N;
 
+          // Could replace this with a dynamic LDS alignment attribute
           markUsedByKernel(Builder, func, N);
 
           auto emptyCharArray = ArrayType::get(Type::getInt8Ty(Ctx), 0);
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPromoteAlloca.cpp
@@ -945,22 +945,28 @@
     AllocatedSizes.emplace_back(AllocSize, Alignment);
   }
 
-  // Sort to try to estimate the worst case alignment padding
-  //
-  // FIXME: We should really do something to fix the addresses to a more optimal
-  // value instead
-  llvm::sort(AllocatedSizes, llvm::less_second());
-
   // Check how much local memory is being used by global objects
   CurrentLocalMemUsage = 0;
 
-  // FIXME: Try to account for padding here. The real padding and address is
-  // currently determined from the inverse order of uses in the function when
-  // legalizing, which could also potentially change. We try to estimate the
-  // worst case here, but we probably should fix the addresses earlier.
-  for (auto Alloc : AllocatedSizes) {
-    CurrentLocalMemUsage = alignTo(CurrentLocalMemUsage, Alloc.second);
-    CurrentLocalMemUsage += Alloc.first;
+  // If the kernel has an amdgpu-lds-size attribute, use that value instead of
+  // estimating.
+  CurrentLocalMemUsage = F.getFnAttributeAsParsedInteger("amdgpu-lds-size", 0);
+
+  if (CurrentLocalMemUsage == 0) {
+    // Sort to try to estimate the worst case alignment padding
+    //
+    // FIXME: We should really do something to fix the addresses to a more optimal
+    // value instead
+    llvm::sort(AllocatedSizes, llvm::less_second());
+
+    // FIXME: Try to account for padding here. The real padding and address is
+    // currently determined from the inverse order of uses in the function when
+    // legalizing, which could also potentially change. We try to estimate the
+    // worst case here, but we probably should fix the addresses earlier.
+    for (auto Alloc : AllocatedSizes) {
+      CurrentLocalMemUsage = alignTo(CurrentLocalMemUsage, Alloc.second);
+      CurrentLocalMemUsage += Alloc.first;
+    }
   }
 
   unsigned MaxOccupancy =
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
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-all-indirect-accesses.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-all-indirect-accesses.ll
@@ -10,7 +10,6 @@
 
 define amdgpu_kernel void @kernel_0() {
 ; CHECK-LABEL: define amdgpu_kernel void @kernel_0() #0 !llvm.amdgcn.lds.kernel.id !1 {
-; 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
 ;
@@ -30,7 +29,6 @@
 
 define amdgpu_kernel void @kernel_2() {
 ; CHECK-LABEL: define amdgpu_kernel void @kernel_2() #0 !llvm.amdgcn.lds.kernel.id !3 {
-; 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
 ;
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
@@ -33,7 +33,7 @@
 
 
 define amdgpu_kernel void @kernel_only() {
-; CHECK-LABEL: @kernel_only() {
+; 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
@@ -44,8 +44,8 @@
 }
 
 ; The accesses from functions are rewritten to go through the llvm.amdgcn.dynlds.offset.table
-define void @use_shared1() {
-; CHECK-LABEL: @use_shared1() {
+define void @use_shared1() #0 {
+; CHECK-LABEL: @use_shared1() #0
 ; 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
@@ -60,7 +60,7 @@
 }
 
 define void @use_shared2() #0 {
-; CHECK-LABEL: @use_shared2() #0 {
+; 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
@@ -77,7 +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() #0 {
+; 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]]
@@ -94,7 +94,7 @@
 }
 
 define void @use_shared8() #0 {
-; CHECK-LABEL: @use_shared8() #0 {
+; 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
@@ -130,9 +130,8 @@
 }
 
 define amdgpu_kernel void @expect_align4() {
-; CHECK-LABEL: @expect_align4() #1 !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()
 ; CHECK-NEXT:    ret void
 ;
@@ -140,9 +139,9 @@
   ret void
 }
 
-; Use dynamic_shared directly too.
+; Use dynamic_shared directly too. Can elide module lds (#0)
 define amdgpu_kernel void @expect_align8() {
-; CHECK-LABEL: @expect_align8() !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
@@ -157,9 +156,8 @@
 
 ; 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() #1 !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()
 ; CHECK-NEXT:    call void @use_shared4()
 ; CHECK-NEXT:    ret void
@@ -181,7 +179,7 @@
 ; 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: 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
@@ -17,8 +17,6 @@
 ; GCN:     ds_write_b8 [[NULL]], [[TWO]] offset:16
 define amdgpu_kernel void @k0() {
 ; OPT-LABEL: @k0(
-; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds) ]
-; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
 ; OPT-NEXT:    store i8 1, ptr addrspace(3) @llvm.amdgcn.module.lds, align 1
 ; OPT-NEXT:    store i8 2, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, align 16
 ; OPT-NEXT:    call void @f0()
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-single-var-ambiguous.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-single-var-ambiguous.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-single-var-ambiguous.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-single-var-ambiguous.ll
@@ -68,12 +68,10 @@
 
 define amdgpu_kernel void @k0_f0() {
 ; M_OR_HY-LABEL: @k0_f0(
-; M_OR_HY-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
 ; M_OR_HY-NEXT:    call void @f0()
 ; M_OR_HY-NEXT:    ret void
 ;
 ; TABLE-LABEL: @k0_f0(
-; TABLE-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k0_f0.lds) ]
 ; TABLE-NEXT:    call void @f0()
 ; TABLE-NEXT:    ret void
 ;
@@ -83,12 +81,10 @@
 
 define amdgpu_kernel void @k1_f0() {
 ; M_OR_HY-LABEL: @k1_f0(
-; M_OR_HY-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
 ; M_OR_HY-NEXT:    call void @f0()
 ; M_OR_HY-NEXT:    ret void
 ;
 ; TABLE-LABEL: @k1_f0(
-; TABLE-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k1_f0.lds) ]
 ; TABLE-NEXT:    call void @f0()
 ; TABLE-NEXT:    ret void
 ;
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-single-var-unambiguous.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-single-var-unambiguous.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-single-var-unambiguous.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-single-var-unambiguous.ll
@@ -59,20 +59,9 @@
 }
 
 define amdgpu_kernel void @k_f0() {
-; MODULE-LABEL: @k_f0(
-; MODULE-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ], !alias.scope [[META5:![0-9]+]], !noalias [[META1]]
-; MODULE-NEXT:    call void @f0()
-; MODULE-NEXT:    ret void
-;
-; TABLE-LABEL: @k_f0(
-; TABLE-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k_f0.lds) ]
-; TABLE-NEXT:    call void @f0()
-; TABLE-NEXT:    ret void
-;
-; K_OR_HY-LABEL: @k_f0(
-; K_OR_HY-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k_f0.lds) ]
-; K_OR_HY-NEXT:    call void @f0()
-; K_OR_HY-NEXT:    ret void
+; CHECK-LABEL: @k_f0(
+; CHECK-NEXT:    call void @f0()
+; CHECK-NEXT:    ret void
 ;
   call void @f0()
   ret void
@@ -83,7 +72,7 @@
 @both.lds = addrspace(3) global i32 undef
 define void @f_both() {
 ; MODULE-LABEL: @f_both(
-; MODULE-NEXT:    [[LD:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !alias.scope [[META5]], !noalias [[META4]]
+; MODULE-NEXT:    [[LD:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !alias.scope [[META5:![0-9]+]], !noalias [[META4]]
 ; MODULE-NEXT:    [[MUL:%.*]] = mul i32 [[LD]], 4
 ; MODULE-NEXT:    store i32 [[MUL]], ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !alias.scope [[META5]], !noalias [[META4]]
 ; MODULE-NEXT:    ret void
@@ -115,7 +104,6 @@
 
 define amdgpu_kernel void @k0_both() {
 ; MODULE-LABEL: @k0_both(
-; MODULE-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
 ; MODULE-NEXT:    [[LD:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !alias.scope [[META5]], !noalias [[META1]]
 ; MODULE-NEXT:    [[MUL:%.*]] = mul i32 [[LD]], 5
 ; MODULE-NEXT:    store i32 [[MUL]], ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !alias.scope [[META5]], !noalias [[META1]]
@@ -123,7 +111,6 @@
 ; MODULE-NEXT:    ret void
 ;
 ; TABLE-LABEL: @k0_both(
-; TABLE-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds) ]
 ; TABLE-NEXT:    [[LD:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds, align 4
 ; TABLE-NEXT:    [[MUL:%.*]] = mul i32 [[LD]], 5
 ; TABLE-NEXT:    store i32 [[MUL]], ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds, align 4
@@ -131,7 +118,6 @@
 ; TABLE-NEXT:    ret void
 ;
 ; K_OR_HY-LABEL: @k0_both(
-; K_OR_HY-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds) ]
 ; K_OR_HY-NEXT:    [[LD:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds, align 4
 ; K_OR_HY-NEXT:    [[MUL:%.*]] = mul i32 [[LD]], 5
 ; K_OR_HY-NEXT:    store i32 [[MUL]], ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds, align 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
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-hybrid.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-hybrid.ll
@@ -1,4 +1,4 @@
-; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -S -mtriple=amdgcn--amdhsa -passes=amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=hybrid | FileCheck -check-prefix=OPT %s
 ; RUN: llc -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s --amdgpu-lower-module-lds-strategy=hybrid | FileCheck -check-prefix=GCN %s
 
@@ -158,8 +158,6 @@
 ; Access two variables, will allocate those two
 define amdgpu_kernel void @k01() {
 ; OPT-LABEL: @k01(
-; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k01.lds) ]
-; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
 ; OPT-NEXT:    call void @f0()
 ; OPT-NEXT:    call void @f1()
 ; OPT-NEXT:    ret void
@@ -193,7 +191,6 @@
 
 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 [[META4:![0-9]+]], !noalias [[META7:![0-9]+]]
 ; OPT-NEXT:    call void @f2()
 ; OPT-NEXT:    call void @f3()
 ; OPT-NEXT:    ret void
@@ -231,12 +228,10 @@
 ; 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 [[META10:![0-9]+]], !noalias [[META13:![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 [[META13]], !noalias [[META10]]
+; 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 [[META5:![0-9]+]], !noalias [[META8:![0-9]+]]
 ; 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 [[META13]], !noalias [[META10]]
+; 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 [[META5]], !noalias [[META8]]
 ; OPT-NEXT:    call void @f2()
 ; OPT-NEXT:    ret void
 ;
@@ -287,24 +282,18 @@
 ; 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: attributes #3 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }
 
 ; OPT: !0 = !{i64 0, i64 1}
 ; OPT: !1 = !{i64 4, i64 5}
 ; OPT: !2 = !{i64 8, i64 9}
 ; OPT: !3 = !{i32 1}
-; OPT: !4 = !{!5}
-; OPT: !5 = distinct !{!5, !6}
-; OPT: !6 = distinct !{!6}
-; OPT: !7 = !{!8}
-; OPT: !8 = distinct !{!8, !6}
-; OPT: !9 = !{i32 0}
-; OPT: !10 = !{!11}
-; OPT: !11 = distinct !{!11, !12}
-; OPT: !12 = distinct !{!12}
-; OPT: !13 = !{!14}
-; OPT: !14 = distinct !{!14, !12}
+; OPT: !4 = !{i32 0}
+; OPT: !5 = !{!6}
+; OPT: !6 = distinct !{!6, !7}
+; OPT: !7 = distinct !{!7}
+; OPT: !8 = !{!9}
+; OPT: !9 = distinct !{!9, !7}
 
 ; Table size length number-kernels * number-variables * sizeof(uint16_t)
 ; GCN:      .type	llvm.amdgcn.lds.offset.table,@object
diff --git a/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-table.ll b/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-table.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-table.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-module-lds-via-table.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -S -mtriple=amdgcn--amdhsa -passes=amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=table | FileCheck -check-prefix=OPT %s
 ; RUN: llc -mtriple=amdgcn--amdhsa -verify-machineinstrs < %s --amdgpu-lower-module-lds-strategy=table | FileCheck -check-prefix=GCN %s
 
@@ -219,7 +220,6 @@
 ; Access two variables, will allocate those two
 define amdgpu_kernel void @k01() {
 ; OPT-LABEL: @k01() #0 !llvm.amdgcn.lds.kernel.id !1 {
-; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k01.lds) ]
 ; OPT-NEXT:    call void @f0()
 ; OPT-NEXT:    call void @f1()
 ; OPT-NEXT:    ret void
@@ -256,8 +256,7 @@
 }
 
 define amdgpu_kernel void @k23() {
-; OPT-LABEL: @k23() #1 !llvm.amdgcn.lds.kernel.id !7 {
-; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k23.lds) ]
+; OPT-LABEL: @k23() #1 !llvm.amdgcn.lds.kernel.id !2 {
 ; OPT-NEXT:    call void @f2()
 ; OPT-NEXT:    call void @f3()
 ; OPT-NEXT:    ret void
@@ -295,12 +294,11 @@
 
 ; Access and allocate three variables
 define amdgpu_kernel void @k123() {
-; OPT-LABEL: @k123() #2 !llvm.amdgcn.lds.kernel.id !13 {
-; OPT-NEXT:    call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k123.lds) ]
+; OPT-LABEL: @k123() #2 !llvm.amdgcn.lds.kernel.id !3 {
 ; 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 2, !alias.scope !20, !noalias !21
+; 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 2, !alias.scope [[META4:![0-9]+]], !noalias [[META7:![0-9]+]]
 ; 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 2, !alias.scope !20, !noalias !21
+; 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 2, !alias.scope [[META4]], !noalias [[META7]]
 ; OPT-NEXT:    call void @f2()
 ; OPT-NEXT:    ret void
 ;
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
@@ -41,7 +41,6 @@
 
 ; This kernel calls a function that uses LDS so needs the block
 ; CHECK-LABEL: @kern_call() #0
-; CHECK: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
 ; CHECK: call void @func()
 ; CHECK: %dec = atomicrmw fsub ptr addrspace(3) @llvm.amdgcn.module.lds, float 2.000000e+00 monotonic, align 8
 define amdgpu_kernel void @kern_call() {
@@ -51,9 +50,8 @@
 }
 
 ; This kernel does alloc the LDS block as it makes no calls
-; CHECK-LABEL: @kern_empty()
-; CHECK-NOT: call void @llvm.donothing()
-define spir_kernel void @kern_empty() {
+; CHECK-LABEL: @kern_empty() #1
+define spir_kernel void @kern_empty() #0{
   ret void
 }
 
@@ -61,4 +59,7 @@
 ; 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" }