1 files changed, 14 insertions, 0 deletions
diff --git a/llvm/lib/Target/X86/X86Subtarget.cpp b/llvm/lib/Target/X86/X86Subtarget.cpp
index 2a7733996c4..13062ca8cfe 100644
--- a/llvm/lib/Target/X86/X86Subtarget.cpp
+++ b/llvm/lib/Target/X86/X86Subtarget.cpp
@@ -283,6 +283,17 @@ void X86Subtarget::initSubtargetFeatures(StringRef CPU, StringRef FS) {
   else if (isTargetDarwin() || isTargetLinux() || isTargetSolaris() ||
            isTargetKFreeBSD() || In64BitMode)
     stackAlignment = 16;
+ 
+  // Gather is available since Haswell (AVX2 set). So technically, we can generate Gathers 
+  // on all AVX2 processors. But the overhead on HSW is high. Skylake Client processor has
+  // faster Gathers than HSW and performance is similar to Skylake Server (AVX-512). 
+  // The specified overhead is relative to the Load operation."2" is the number provided 
+  // by Intel architects, This parameter is used for cost estimation of Gather Op and 
+  // comparison with other alternatives.
+  if (X86ProcFamily == IntelSkylake || hasAVX512())
+    GatherOverhead = 2;
+  if (hasAVX512())
+    ScatterOverhead = 2;
 }
 
 void X86Subtarget::initializeEnvironment() {
@@ -361,6 +372,9 @@ void X86Subtarget::initializeEnvironment() {
   // FIXME: this is a known good value for Yonah. How about others?
   MaxInlineSizeThreshold = 128;
   UseSoftFloat = false;
+  X86ProcFamily = Others;
+  GatherOverhead = 1024;
+  ScatterOverhead = 1024;
 }
 
 X86Subtarget &X86Subtarget::initializeSubtargetDependencies(StringRef CPU,