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
@@ -162,7 +162,15 @@
     return 128;
 
   const GCNSubtarget &ST = TM.getSubtarget<GCNSubtarget>(F);
-  return ST.getMaxNumVGPRs(ST.getWavesPerEU(F).first);
+  unsigned MaxVGPRs = ST.getMaxNumVGPRs(ST.getWavesPerEU(F).first);
+
+  // A non-entry function has only 32 caller preserved registers.
+  // Do not promote alloca which will force spilling unless we know the function
+  // will be inlined.
+  if (!F.hasFnAttribute(Attribute::AlwaysInline) &&
+      !AMDGPU::isEntryFunctionCC(F.getCallingConv()))
+    MaxVGPRs = std::min(MaxVGPRs, 32u);
+  return MaxVGPRs;
 }
 
 } // end anonymous namespace
diff --git a/llvm/test/CodeGen/AMDGPU/vector-alloca-limits.ll b/llvm/test/CodeGen/AMDGPU/vector-alloca-limits.ll
--- a/llvm/test/CodeGen/AMDGPU/vector-alloca-limits.ll
+++ b/llvm/test/CodeGen/AMDGPU/vector-alloca-limits.ll
@@ -139,11 +139,26 @@
 }
 
 ; OPT-LABEL: @func_alloca_9xi64_max256(
+; OPT: alloca
+; OPT-NOT: <9 x i64>
+; LIMIT32: alloca
+; LIMIT32-NOT: <9 x i64>
+define void @func_alloca_9xi64_max256(ptr addrspace(1) %out, i32 %index) #2 {
+entry:
+  %tmp = alloca [9 x i64], addrspace(5)
+  store i64 0, ptr addrspace(5) %tmp
+  %tmp1 = getelementptr [9 x i64], ptr addrspace(5) %tmp, i32 0, i32 %index
+  %tmp2 = load i64, ptr addrspace(5) %tmp1
+  store i64 %tmp2, ptr addrspace(1) %out
+  ret void
+}
+
+; OPT-LABEL: @alwaysinlined_func_alloca_9xi64_max256(
 ; OPT-NOT: alloca
 ; OPT: <9 x i64>
 ; LIMIT32: alloca
 ; LIMIT32-NOT: <9 x i64>
-define void @func_alloca_9xi64_max256(ptr addrspace(1) %out, i32 %index) #2 {
+define void @alwaysinlined_func_alloca_9xi64_max256(ptr addrspace(1) %out, i32 %index) #3 {
 entry:
   %tmp = alloca [9 x i64], addrspace(5)
   store i64 0, ptr addrspace(5) %tmp
@@ -156,3 +171,4 @@
 attributes #0 = { "amdgpu-flat-work-group-size"="1,1024" }
 attributes #1 = { "amdgpu-flat-work-group-size"="1,512" }
 attributes #2 = { "amdgpu-flat-work-group-size"="1,256" }
+attributes #3 = { alwaysinline "amdgpu-flat-work-group-size"="1,256" }