Index: llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
===================================================================
--- llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
+++ llvm/trunk/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp
@@ -252,6 +252,7 @@
           return !GV.use_empty();
         }));
         PM.add(createGlobalDCEPass());
+        PM.add(createAMDGPUAlwaysInlinePass());
       }
   });
 }
Index: llvm/trunk/test/CodeGen/AMDGPU/early-inline-alias.ll
===================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/early-inline-alias.ll
+++ llvm/trunk/test/CodeGen/AMDGPU/early-inline-alias.ll
@@ -0,0 +1,12 @@
+; RUN: opt -mtriple=amdgcn-- -O1 -S -inline-threshold=1 %s | FileCheck %s
+
+; CHECK: @add1alias = alias i32 (i32), i32 (i32)* @add1
+; CHECK: @add1alias2 = alias i32 (i32), i32 (i32)* @add1
+
+@add1alias = alias i32 (i32), i32 (i32)* @add1
+@add1alias2 = alias i32 (i32), i32 (i32)* @add1
+
+define i32 @add1(i32) {
+  %2 = add nsw i32 %0, 1
+  ret i32 %2
+}
Index: llvm/trunk/test/CodeGen/AMDGPU/early-inline.ll
===================================================================
--- llvm/trunk/test/CodeGen/AMDGPU/early-inline.ll
+++ llvm/trunk/test/CodeGen/AMDGPU/early-inline.ll
@@ -0,0 +1,21 @@
+; RUN: opt -mtriple=amdgcn-- -O1 -S -inline-threshold=1 -amdgpu-internalize-symbols %s | FileCheck %s
+
+define i32 @callee(i32 %x) {
+entry:
+  %mul1 = mul i32 %x, %x
+  %mul2 = mul i32 %mul1, %x
+  %mul3 = mul i32 %mul1, %mul2
+  %mul4 = mul i32 %mul3, %mul2
+  %mul5 = mul i32 %mul4, %mul3
+  ret i32 %mul5
+}
+
+; CHECK-LABEL: @caller
+; CHECK: mul i32
+; CHECK-NOT: call i32
+
+define amdgpu_kernel i32 @caller(i32 %x) {
+entry:
+  %res = call i32 @callee(i32 %x)
+  ret i32 %res
+}