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
@@ -244,6 +244,10 @@
       }
     }
 
+    for (auto &GV : make_early_inc_range(M.globals()))
+      if (AMDGPU::isLDSVariableToLower(GV) && GV.use_empty())
+        GV.eraseFromParent();
+    
     return Changed;
   }
 
diff --git a/llvm/test/CodeGen/AMDGPU/lower-kernel-lds-super-align.ll b/llvm/test/CodeGen/AMDGPU/lower-kernel-lds-super-align.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-kernel-lds-super-align.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-kernel-lds-super-align.ll
@@ -12,6 +12,8 @@
 ; SUPER-ALIGN_OFF: @lds.unused = addrspace(3) global i32 undef, align 2
 @lds.unused = addrspace(3) global i32 undef, align 2
 
+@llvm.used = appending global [1 x i8*] [i8* addrspacecast (i32 addrspace(3)* @lds.unused to i8*)], section "llvm.metadata"
+
 ; CHECK-NOT: @lds.1
 @lds.1 = internal unnamed_addr addrspace(3) global [32 x i8] undef, align 1
 
diff --git a/llvm/test/CodeGen/AMDGPU/lower-kernel-lds.ll b/llvm/test/CodeGen/AMDGPU/lower-kernel-lds.ll
--- a/llvm/test/CodeGen/AMDGPU/lower-kernel-lds.ll
+++ b/llvm/test/CodeGen/AMDGPU/lower-kernel-lds.ll
@@ -4,14 +4,12 @@
 @lds.size.1.align.1 = internal unnamed_addr addrspace(3) global [1 x i8] undef, align 1
 @lds.size.2.align.2 = internal unnamed_addr addrspace(3) global [2 x i8] undef, align 2
 @lds.size.4.align.4 = internal unnamed_addr addrspace(3) global [4 x i8] undef, align 4
-@lds.size.8.align.8 = internal unnamed_addr addrspace(3) global [8 x i8] undef, align 8
 @lds.size.16.align.16 = internal unnamed_addr addrspace(3) global [16 x i8] undef, align 16
 
 ; CHECK: %llvm.amdgcn.kernel.k0.lds.t = type { [16 x i8], [4 x i8], [2 x i8], [1 x i8] }
 ; CHECK: %llvm.amdgcn.kernel.k1.lds.t = type { [16 x i8], [4 x i8], [2 x i8] }
 
 ;.
-; CHECK: @lds.size.8.align.8 = internal unnamed_addr addrspace(3) global [8 x i8] undef, align 8
 ; CHECK: @lds.k2 = addrspace(3) global [1 x i8] undef, align 1
 ; CHECK: @llvm.amdgcn.kernel.k0.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k0.lds.t undef, align 16
 ; CHECK: @llvm.amdgcn.kernel.k1.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k1.lds.t undef, align 16