diff --git a/clang/lib/Driver/ToolChains/AMDGPU.cpp b/clang/lib/Driver/ToolChains/AMDGPU.cpp
--- a/clang/lib/Driver/ToolChains/AMDGPU.cpp
+++ b/clang/lib/Driver/ToolChains/AMDGPU.cpp
@@ -540,6 +540,9 @@
   ArgStringList CmdArgs;
   addLinkerCompressDebugSectionsOption(getToolChain(), Args, CmdArgs);
   AddLinkerInputs(getToolChain(), Inputs, Args, CmdArgs, JA);
+  if (C.getDriver().isUsingLTO())
+    addLTOOptions(getToolChain(), Args, CmdArgs, Output, Inputs[0],
+                  C.getDriver().getLTOMode() == LTOK_Thin);
   CmdArgs.push_back("-shared");
   CmdArgs.push_back("-o");
   CmdArgs.push_back(Output.getFilename());
diff --git a/clang/test/Driver/amdgpu-toolchain.c b/clang/test/Driver/amdgpu-toolchain.c
--- a/clang/test/Driver/amdgpu-toolchain.c
+++ b/clang/test/Driver/amdgpu-toolchain.c
@@ -13,4 +13,4 @@
 // RUN: %clang -### --target=amdgcn-amd-amdhsa -mcpu=gfx906 -nogpulib \
 // RUN:   -flto %s 2>&1 | FileCheck -check-prefix=LTO %s
 // LTO: clang{{.*}} "-flto=full"
-// LTO: ld.lld{{.*}}
+// LTO: ld.lld{{.*}}-plugin-opt=mcpu=gfx906