Index: lib/Target/AMDGPU/AMDGPU.td
===================================================================
--- lib/Target/AMDGPU/AMDGPU.td
+++ lib/Target/AMDGPU/AMDGPU.td
@@ -267,15 +267,6 @@
 // Subtarget Features (options and debugging)
 //===------------------------------------------------------------===//
 
-// Some instructions do not support denormals despite this flag. Using
-// fp32 denormals also causes instructions to run at the double
-// precision rate for the device.
-def FeatureFP32Denormals : SubtargetFeature<"fp32-denormals",
-  "FP32Denormals",
-  "true",
-  "Enable single precision denormal handling"
->;
-
 // Denormal handling for fp64 and fp16 is controlled by the same
 // config register when fp16 supported.
 // TODO: Do we need a separate f16 setting when not legal?
Index: lib/Target/AMDGPU/AMDGPUFeatures.td
===================================================================
--- lib/Target/AMDGPU/AMDGPUFeatures.td
+++ lib/Target/AMDGPU/AMDGPUFeatures.td
@@ -19,6 +19,15 @@
   "Enable single precision FMA (not as fast as mul+add, but fused)"
 >;
 
+// Some instructions do not support denormals despite this flag. Using
+// fp32 denormals also causes instructions to run at the double
+// precision rate for the device.
+def FeatureFP32Denormals : SubtargetFeature<"fp32-denormals",
+  "FP32Denormals",
+  "true",
+  "Enable single precision denormal handling"
+>;
+
 class SubtargetFeatureLocalMemorySize <int Value> : SubtargetFeature<
   "localmemorysize"#Value,
   "LocalMemorySize",
Index: test/CodeGen/AMDGPU/target-features.ll
===================================================================
--- /dev/null
+++ test/CodeGen/AMDGPU/target-features.ll
@@ -0,0 +1,118 @@
+; RUN: llc -march=amdgcn -mattr=help 2>&1 | FileCheck %s --check-prefix=GCN
+; RUN: llc -march=r600 -mattr=help 2>&1 | FileCheck %s --check-prefix=R600
+
+
+GCN:   16-bit-insts
+GCN:   DumpCode
+GCN:   GFX9
+GCN:   SEA_ISLANDS
+GCN:   SOUTHERN_ISLANDS
+GCN:   VOLCANIC_ISLANDS
+GCN:   add-no-carry-insts
+GCN:   amdgpu-debugger-emit-prologue
+GCN:   amdgpu-debugger-insert-nops
+GCN:   aperture-regs
+GCN:   auto-waitcnt-before-barrier
+GCN:   ci-insts
+GCN:   code-object-v3
+GCN:   d16-preserves-unused-bits
+GCN:   dl-insts
+GCN:   dpp
+GCN:   dumpcode
+GCN:   dx10-clamp
+GCN:   enable-ds128
+GCN:   fast-fmaf
+GCN:   flat-address-space
+GCN:   flat-for-global
+GCN:   flat-global-insts
+GCN:   flat-inst-offsets
+GCN:   flat-scratch-insts
+GCN:   fma-mix-insts
+GCN:   fmaf
+GCN:   fp-exceptions
+GCN:   fp16-denormals
+GCN:   fp32-denormals
+GCN:   fp64
+GCN:   fp64-denormals
+GCN:   fp64-fp16-denormals
+GCN:   gcn
+GCN:   gcn3-encoding
+GCN:   gfx9-insts
+GCN:   half-rate-64-ops
+GCN:   huge-private-buffer
+GCN:   int-clamp-insts
+GCN:   inv-2pi-inline-imm
+GCN:   isaver6.0.0
+GCN:   isaver6.0.1
+GCN:   isaver7.0.0
+GCN:   isaver7.0.1
+GCN:   isaver7.0.2
+GCN:   isaver7.0.3
+GCN:   isaver7.0.4
+GCN:   isaver8.0.1
+GCN:   isaver8.0.2
+GCN:   isaver8.0.3
+GCN:   isaver8.1.0
+GCN:   isaver9.0.0
+GCN:   isaver9.0.2
+GCN:   isaver9.0.4
+GCN:   isaver9.0.6
+GCN:   ldsbankcount16
+GCN:   ldsbankcount32
+GCN:   load-store-opt
+GCN:   localmemorysize0
+GCN:   localmemorysize32768
+GCN:   localmemorysize65536
+GCN:   mad-mix-insts
+GCN:   max-private-element-size-16
+GCN:   max-private-element-size-4
+GCN:   max-private-element-size-8
+GCN:   mimg-r128
+GCN:   movrel
+GCN:   promote-alloca
+GCN:   s-memrealtime
+GCN:   scalar-atomics
+GCN:   scalar-stores
+GCN:   sdwa
+GCN:   sdwa-mav
+GCN:   sdwa-omod
+GCN:   sdwa-out-mods-vopc
+GCN:   sdwa-scalar
+GCN:   sdwa-sdst
+GCN:   sgpr-init-bug
+GCN:   si-scheduler
+GCN:   trap-handler
+GCN:   unaligned-buffer-access
+GCN:   unaligned-scratch-access
+GCN:   unpacked-d16-vmem
+GCN:   unsafe-ds-offset-folding
+GCN:   vgpr-index-mode
+GCN:   vgpr-spilling
+GCN:   vop3p
+GCN:   wavefrontsize16
+GCN:   wavefrontsize32
+GCN:   wavefrontsize64
+GCN:   xnack
+
+
+R600:   EVERGREEN
+R600:   HasVertexCache
+R600:   NORTHERN_ISLANDS
+R600:   R600
+R600:   R600ALUInst
+R600:   R700
+R600:   caymanISA
+R600:   cfalubug
+R600:   dx10-clamp
+R600:   fetch16
+R600:   fetch8
+R600:   fmaf
+R600:   fp32-denormals
+R600:   fp64
+R600:   localmemorysize0
+R600:   localmemorysize32768
+R600:   localmemorysize65536
+R600:   promote-alloca
+R600:   wavefrontsize16
+R600:   wavefrontsize32
+R600:   wavefrontsize64