Index: lib/Target/X86/X86.td
===================================================================
--- lib/Target/X86/X86.td
+++ lib/Target/X86/X86.td
@@ -108,6 +108,10 @@
 def FeatureSlowUAMem32 : SubtargetFeature<"slow-unaligned-mem-32",
                                 "IsUAMem32Slow", "true",
                                 "Slow unaligned 32-byte memory access">;
+// TODO: This should be replaced with cost function per processor later
+def FeatureFastAVX2Gather : SubtargetFeature<"fast-avx2-gathers", 
+                                "HasFastAVX2Gather", "true",
+                                "Has Fast AVX2 Gathers Support">;
 def FeatureSSE4A   : SubtargetFeature<"sse4a", "HasSSE4A", "true",
                                       "Support SSE 4a instructions",
                                       [FeatureSSE3]>;
@@ -568,6 +572,7 @@
 def : BroadwellProc<"broadwell">;
 
 def SKLFeatures : ProcessorFeatures<BDWFeatures.Value, [
+  FeatureFastAVX2Gather,
   FeatureMPX,
   FeatureRTM,
   FeatureXSAVEC,
Index: lib/Target/X86/X86Subtarget.h
===================================================================
--- lib/Target/X86/X86Subtarget.h
+++ lib/Target/X86/X86Subtarget.h
@@ -197,6 +197,9 @@
   /// True if unaligned memory accesses of 32-bytes are slow.
   bool IsUAMem32Slow;
 
+  ///  TODO: This should be replaced with cost function per processor later 
+  bool HasFastAVX2Gather;
+
   /// True if SSE operations can have unaligned memory operands.
   /// This may require setting a configuration bit in the processor.
   bool HasSSEUnalignedMem;
@@ -477,6 +480,7 @@
   bool isPMULLDSlow() const { return IsPMULLDSlow; }
   bool isUnalignedMem16Slow() const { return IsUAMem16Slow; }
   bool isUnalignedMem32Slow() const { return IsUAMem32Slow; }
+  bool hasFastAVX2Gather() const { return HasFastAVX2Gather; }
   bool hasSSEUnalignedMem() const { return HasSSEUnalignedMem; }
   bool hasCmpxchg16b() const { return HasCmpxchg16b; }
   bool useLeaForSP() const { return UseLeaForSP; }
Index: lib/Target/X86/X86Subtarget.cpp
===================================================================
--- lib/Target/X86/X86Subtarget.cpp
+++ lib/Target/X86/X86Subtarget.cpp
@@ -319,6 +319,7 @@
   IsSHLDSlow = false;
   IsUAMem16Slow = false;
   IsUAMem32Slow = false;
+  HasFastAVX2Gather = false;
   HasSSEUnalignedMem = false;
   HasCmpxchg16b = false;
   UseLeaForSP = false;