[llvm] 1e686d2 - [X86] Add FeatureFast7ByteNOP flag

[Simon Pilgrim via llvm-commits]

Author: Simon Pilgrim
Date: 2020-03-12T13:06:43Z
New Revision: 1e686d268980c7167f12c71e8b1bb66bdc3fd51c

URL: https://github.com/llvm/llvm-project/commit/1e686d268980c7167f12c71e8b1bb66bdc3fd51c
DIFF: https://github.com/llvm/llvm-project/commit/1e686d268980c7167f12c71e8b1bb66bdc3fd51c.diff

LOG: [X86] Add FeatureFast7ByteNOP flag

Lets us remove another SLM proc family flag usage.

This is NFC, but we should probably check whether atom/glm/knl? should be using this flag as well...

Added: 
    

Modified: 
    llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
    llvm/lib/Target/X86/X86.td
    llvm/lib/Target/X86/X86Subtarget.h

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
index 2f84d23d6db5..0498f3f2473a 100644
--- a/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
+++ b/llvm/lib/Target/X86/MCTargetDesc/X86AsmBackend.cpp
@@ -924,7 +924,7 @@ bool X86AsmBackend::writeNopData(raw_ostream &OS, uint64_t Count) const {
   // 15-bytes is the longest single NOP instruction, but 10-bytes is
   // commonly the longest that can be efficiently decoded.
   uint64_t MaxNopLength = 10;
-  if (STI.getFeatureBits()[X86::ProcIntelSLM])
+  if (STI.getFeatureBits()[X86::FeatureFast7ByteNOP])
     MaxNopLength = 7;
   else if (STI.getFeatureBits()[X86::FeatureFast15ByteNOP])
     MaxNopLength = 15;

diff  --git a/llvm/lib/Target/X86/X86.td b/llvm/lib/Target/X86/X86.td
index a2b11d55f650..931367ce4de5 100644
--- a/llvm/lib/Target/X86/X86.td
+++ b/llvm/lib/Target/X86/X86.td
@@ -329,6 +329,11 @@ def FeatureFastLZCNT
     : SubtargetFeature<
           "fast-lzcnt", "HasFastLZCNT", "true",
           "LZCNT instructions are as fast as most simple integer ops">;
+// If the target can efficiently decode NOPs upto 7-bytes in length.
+def FeatureFast7ByteNOP
+    : SubtargetFeature<
+          "fast-7bytenop", "HasFast7ByteNOP", "true",
+          "Target can quickly decode up to 7 byte NOPs">;
 // If the target can efficiently decode NOPs upto 11-bytes in length.
 def FeatureFast11ByteNOP
     : SubtargetFeature<
@@ -728,6 +733,7 @@ def ProcessorFeatures {
   list<SubtargetFeature> SLMSpecificFeatures = [ProcIntelSLM,
                                                 FeatureSlowDivide64,
                                                 FeatureSlowPMULLD,
+                                                FeatureFast7ByteNOP,
                                                 FeaturePOPCNTFalseDeps];
   list<SubtargetFeature> SLMInheritableFeatures =
     !listconcat(AtomInheritableFeatures, SLMAdditionalFeatures);

diff  --git a/llvm/lib/Target/X86/X86Subtarget.h b/llvm/lib/Target/X86/X86Subtarget.h
index f4e8d30328ca..93801455254c 100644
--- a/llvm/lib/Target/X86/X86Subtarget.h
+++ b/llvm/lib/Target/X86/X86Subtarget.h
@@ -257,6 +257,10 @@ class X86Subtarget final : public X86GenSubtargetInfo {
   /// ymm or zmm registers.
   bool InsertVZEROUPPER = false;
 
+  /// True if there is no performance penalty for writing NOPs with up to
+  /// 7 bytes.
+  bool HasFast7ByteNOP = false;
+
   /// True if there is no performance penalty for writing NOPs with up to
   /// 11 bytes.
   bool HasFast11ByteNOP = false;