Optimize the memory usage of MC bundling, by creating a new type of fragment

into which we can emit single instructions without fixups (which is most
instructions). This is an optimization required because MCDataFragment
is prety large (240 bytes on x64), with no change in functionality.

For large programs, this reduces memory usage overhead required for bundling
by 40%.

To make the code as palatable as possible, the MCEncodedFragment interface was
further fragmented (no pun intended) and MCEncodedFragmentWithFixups is used
as the interface to work against when the user expects fixups. MCDataFragment
and MCRelaxableFragment implement this interface, while the new
MCCompactEncodedInstFragment implements MCEncodeFragment.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172572 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/MC/MCAssembler.h b/include/llvm/MC/MCAssembler.h
index 57aa08a2d0f914bb8ee56590d3ba2a3c94f497b6..8269f08c4495bda0db7715a97e88e601567416b6 100644 (file)
--- a/include/llvm/MC/MCAssembler.h
+++ b/include/llvm/MC/MCAssembler.h
@@ -47,6 +47,7 @@ public:
   enum FragmentType {
     FT_Align,
     FT_Data,
+    FT_CompactEncodedInst,
     FT_Fill,
     FT_Relaxable,
     FT_Org,
@@ -105,6 +106,7 @@ public:
 
   /// \brief Should this fragment be placed at the end of an aligned bundle?
   virtual bool alignToBundleEnd() const { return false; }
+  virtual void setAlignToBundleEnd(bool V) { }
 
   /// \brief Get the padding size that must be inserted before this fragment.
   /// Used for bundling. By default, no padding is inserted.
@@ -120,9 +122,16 @@ public:
   virtual void setBundlePadding(uint8_t N) {
   }
 
+  virtual bool hasFixups() const {
+    return false;
+  }
+
   void dump();
 };
 
+/// Interface implemented by fragments that contain encoded instructions and/or
+/// data.
+///
 class MCEncodedFragment : public MCFragment {
   virtual void anchor();
 
@@ -134,20 +143,9 @@ public:
   }
   virtual ~MCEncodedFragment();
 
-  typedef SmallVectorImpl<MCFixup>::const_iterator const_fixup_iterator;
-  typedef SmallVectorImpl<MCFixup>::iterator fixup_iterator;
-
   virtual SmallVectorImpl<char> &getContents() = 0;
   virtual const SmallVectorImpl<char> &getContents() const = 0;
 
-  virtual SmallVectorImpl<MCFixup> &getFixups() = 0;
-  virtual const SmallVectorImpl<MCFixup> &getFixups() const = 0;
-
-  virtual fixup_iterator fixup_begin() = 0;
-  virtual const_fixup_iterator fixup_begin() const  = 0;
-  virtual fixup_iterator fixup_end() = 0;
-  virtual const_fixup_iterator fixup_end() const = 0;
-
   virtual uint8_t getBundlePadding() const {
     return BundlePadding;
   }
@@ -158,13 +156,55 @@ public:
 
   static bool classof(const MCFragment *F) {
     MCFragment::FragmentType Kind = F->getKind();
-    return Kind == MCFragment::FT_Relaxable || Kind == MCFragment::FT_Data;
+    switch (Kind) {
+      default:
+        return false;
+      case MCFragment::FT_Relaxable:
+      case MCFragment::FT_CompactEncodedInst:
+      case MCFragment::FT_Data:
+        return true;
+    }
+  }
+};
+
+/// Interface implemented by fragments that contain encoded instructions and/or
+/// data and also have fixups registered.
+///
+class MCEncodedFragmentWithFixups : public MCEncodedFragment {
+  virtual void anchor();
+
+public:
+  MCEncodedFragmentWithFixups(MCFragment::FragmentType FType,
+                              MCSectionData *SD = 0)
+    : MCEncodedFragment(FType, SD)
+  {
+  }
+
+  virtual ~MCEncodedFragmentWithFixups();
+
+  virtual bool hasFixups() const {
+    return true;
+  }
+
+  typedef SmallVectorImpl<MCFixup>::const_iterator const_fixup_iterator;
+  typedef SmallVectorImpl<MCFixup>::iterator fixup_iterator;
+
+  virtual SmallVectorImpl<MCFixup> &getFixups() = 0;
+  virtual const SmallVectorImpl<MCFixup> &getFixups() const = 0;
+
+  virtual fixup_iterator fixup_begin() = 0;
+  virtual const_fixup_iterator fixup_begin() const  = 0;
+  virtual fixup_iterator fixup_end() = 0;
+  virtual const_fixup_iterator fixup_end() const = 0;
+
+  static bool classof(const MCFragment *F) {
+    return isa<MCEncodedFragment>(F) && F->hasFixups();
   }
 };
 
 /// Fragment for data and encoded instructions.
 ///
-class MCDataFragment : public MCEncodedFragment {
+class MCDataFragment : public MCEncodedFragmentWithFixups {
   virtual void anchor();
 
   /// \brief Does this fragment contain encoded instructions anywhere in it?
@@ -179,7 +219,7 @@ class MCDataFragment : public MCEncodedFragment {
   SmallVector<MCFixup, 4> Fixups;
 public:
   MCDataFragment(MCSectionData *SD = 0)
-    : MCEncodedFragment(FT_Data, SD),
+    : MCEncodedFragmentWithFixups(FT_Data, SD),
       HasInstructions(false), AlignToBundleEnd(false)
   {
   }
@@ -212,10 +252,43 @@ public:
   }
 };
 
+/// This is a compact (memory-size-wise) fragment for holding an encoded
+/// instruction (non-relaxable) that has no fixups registered. When applicable,
+/// it can be used instead of MCDataFragment and lead to lower memory
+/// consumption.
+///
+class MCCompactEncodedInstFragment : public MCEncodedFragment {
+  virtual void anchor();
+
+  /// \brief Should this fragment be aligned to the end of a bundle?
+  bool AlignToBundleEnd;
+
+  SmallVector<char, 4> Contents;
+public:
+  MCCompactEncodedInstFragment(MCSectionData *SD = 0)
+    : MCEncodedFragment(FT_CompactEncodedInst, SD), AlignToBundleEnd(false)
+  {
+  }
+
+  virtual bool hasInstructions() const {
+    return true;
+  }
+
+  virtual SmallVectorImpl<char> &getContents() { return Contents; }
+  virtual const SmallVectorImpl<char> &getContents() const { return Contents; }
+
+  virtual bool alignToBundleEnd() const { return AlignToBundleEnd; }
+  virtual void setAlignToBundleEnd(bool V) { AlignToBundleEnd = V; }
+
+  static bool classof(const MCFragment *F) {
+    return F->getKind() == MCFragment::FT_CompactEncodedInst;
+  }
+};
+
 /// A relaxable fragment holds on to its MCInst, since it may need to be
 /// relaxed during the assembler layout and relaxation stage.
 ///
-class MCRelaxableFragment : public MCEncodedFragment {
+class MCRelaxableFragment : public MCEncodedFragmentWithFixups {
   virtual void anchor();
 
   /// Inst - The instruction this is a fragment for.
@@ -229,7 +302,7 @@ class MCRelaxableFragment : public MCEncodedFragment {
 
 public:
   MCRelaxableFragment(const MCInst &_Inst, MCSectionData *SD = 0)
-    : MCEncodedFragment(FT_Relaxable, SD), Inst(_Inst) {
+    : MCEncodedFragmentWithFixups(FT_Relaxable, SD), Inst(_Inst) {
   }
 
   virtual SmallVectorImpl<char> &getContents() { return Contents; }

diff --git a/lib/MC/MCAssembler.cpp b/lib/MC/MCAssembler.cpp
index 5fdc57ad30953b7ea89c6eae2e1705babb398788..c51ddc800e259adeaadca5d805b47e1bbc626b3a 100644 (file)
--- a/lib/MC/MCAssembler.cpp
+++ b/lib/MC/MCAssembler.cpp
@@ -38,6 +38,8 @@ STATISTIC(EmittedRelaxableFragments,
           "Number of emitted assembler fragments - relaxable");
 STATISTIC(EmittedDataFragments,
           "Number of emitted assembler fragments - data");
+STATISTIC(EmittedCompactEncodedInstFragments,
+          "Number of emitted assembler fragments - compact encoded inst");
 STATISTIC(EmittedAlignFragments,
           "Number of emitted assembler fragments - align");
 STATISTIC(EmittedFillFragments,
@@ -222,6 +224,11 @@ MCEncodedFragment::~MCEncodedFragment() {
 
 /* *** */
 
+MCEncodedFragmentWithFixups::~MCEncodedFragmentWithFixups() {
+}
+
+/* *** */
+
 MCSectionData::MCSectionData() : Section(0) {}
 
 MCSectionData::MCSectionData(const MCSection &_Section, MCAssembler *A)
@@ -388,6 +395,7 @@ uint64_t MCAssembler::computeFragmentSize(const MCAsmLayout &Layout,
   switch (F.getKind()) {
   case MCFragment::FT_Data:
   case MCFragment::FT_Relaxable:
+  case MCFragment::FT_CompactEncodedInst:
     return cast<MCEncodedFragment>(F).getContents().size();
   case MCFragment::FT_Fill:
     return cast<MCFillFragment>(F).getSize();
@@ -570,6 +578,11 @@ static void writeFragment(const MCAssembler &Asm, const MCAsmLayout &Layout,
     writeFragmentContents(F, OW);
     break;
 
+  case MCFragment::FT_CompactEncodedInst:
+    ++stats::EmittedCompactEncodedInstFragments;
+    writeFragmentContents(F, OW);
+    break;
+
   case MCFragment::FT_Fill: {
     ++stats::EmittedFillFragments;
     MCFillFragment &FF = cast<MCFillFragment>(F);
@@ -742,9 +755,10 @@ void MCAssembler::Finish() {
   for (MCAssembler::iterator it = begin(), ie = end(); it != ie; ++it) {
     for (MCSectionData::iterator it2 = it->begin(),
            ie2 = it->end(); it2 != ie2; ++it2) {
-      MCEncodedFragment *F = dyn_cast<MCEncodedFragment>(it2);
+      MCEncodedFragmentWithFixups *F =
+        dyn_cast<MCEncodedFragmentWithFixups>(it2);
       if (F) {
-        for (MCEncodedFragment::fixup_iterator it3 = F->fixup_begin(),
+        for (MCEncodedFragmentWithFixups::fixup_iterator it3 = F->fixup_begin(),
              ie3 = F->fixup_end(); it3 != ie3; ++it3) {
           MCFixup &Fixup = *it3;
           uint64_t FixedValue = handleFixup(Layout, *F, Fixup);
@@ -954,6 +968,8 @@ void MCFragment::dump() {
   switch (getKind()) {
   case MCFragment::FT_Align: OS << "MCAlignFragment"; break;
   case MCFragment::FT_Data:  OS << "MCDataFragment"; break;
+  case MCFragment::FT_CompactEncodedInst:
+    OS << "MCCompactEncodedInstFragment"; break;
   case MCFragment::FT_Fill:  OS << "MCFillFragment"; break;
   case MCFragment::FT_Relaxable:  OS << "MCRelaxableFragment"; break;
   case MCFragment::FT_Org:   OS << "MCOrgFragment"; break;
@@ -1001,6 +1017,19 @@ void MCFragment::dump() {
     }
     break;
   }
+  case MCFragment::FT_CompactEncodedInst: {
+    const MCCompactEncodedInstFragment *CEIF =
+      cast<MCCompactEncodedInstFragment>(this);
+    OS << "\n       ";
+    OS << " Contents:[";
+    const SmallVectorImpl<char> &Contents = CEIF->getContents();
+    for (unsigned i = 0, e = Contents.size(); i != e; ++i) {
+      if (i) OS << ",";
+      OS << hexdigit((Contents[i] >> 4) & 0xF) << hexdigit(Contents[i] & 0xF);
+    }
+    OS << "] (" << Contents.size() << " bytes)";
+    break;
+  }
   case MCFragment::FT_Fill:  {
     const MCFillFragment *FF = cast<MCFillFragment>(this);
     OS << " Value:" << FF->getValue() << " ValueSize:" << FF->getValueSize()
@@ -1094,7 +1123,9 @@ void MCAssembler::dump() {
 
 // anchors for MC*Fragment vtables
 void MCEncodedFragment::anchor() { }
+void MCEncodedFragmentWithFixups::anchor() { }
 void MCDataFragment::anchor() { }
+void MCCompactEncodedInstFragment::anchor() { }
 void MCRelaxableFragment::anchor() { }
 void MCAlignFragment::anchor() { }
 void MCFillFragment::anchor() { }
@@ -1102,3 +1133,4 @@ void MCOrgFragment::anchor() { }
 void MCLEBFragment::anchor() { }
 void MCDwarfLineAddrFragment::anchor() { }
 void MCDwarfCallFrameFragment::anchor() { }
+

diff --git a/lib/MC/MCELFStreamer.cpp b/lib/MC/MCELFStreamer.cpp
index cae73be2988078e6549c3443cb774fca1849a55a..e5b749e28b9b5066028958f9113245dc13834ae0 100644 (file)
--- a/lib/MC/MCELFStreamer.cpp
+++ b/lib/MC/MCELFStreamer.cpp
@@ -371,8 +371,10 @@ void MCELFStreamer::EmitInstToData(const MCInst &Inst) {
   // data fragment).
   //
   // If bundling is enabled:
-  // - If we're not in a bundle-locked group, emit the instruction into a data
-  //   fragment of its own.
+  // - If we're not in a bundle-locked group, emit the instruction into a
+  //   fragment of its own. If there are no fixups registered for the
+  //   instruction, emit a MCCompactEncodedInstFragment. Otherwise, emit a
+  //   MCDataFragment.
   // - If we're in a bundle-locked group, append the instruction to the current
   //   data fragment because we want all the instructions in a group to get into
   //   the same fragment. Be careful not to do that for the first instruction in
@@ -383,6 +385,14 @@ void MCELFStreamer::EmitInstToData(const MCInst &Inst) {
     MCSectionData *SD = getCurrentSectionData();
     if (SD->isBundleLocked() && !SD->isBundleGroupBeforeFirstInst())
       DF = getOrCreateDataFragment();
+    else if (!SD->isBundleLocked() && Fixups.size() == 0) {
+      // Optimize memory usage by emitting the instruction to a
+      // MCCompactEncodedInstFragment when not in a bundle-locked group and
+      // there are no fixups registered.
+      MCCompactEncodedInstFragment *CEIF = new MCCompactEncodedInstFragment(SD);
+      CEIF->getContents().append(Code.begin(), Code.end());
+      return;
+    }
     else {
       DF = new MCDataFragment(SD);
       if (SD->getBundleLockState() == MCSectionData::BundleLockedAlignToEnd) {