Align function starts to target-specific bundle alignment.

src/IceCfg.cpp

 //===- subzero/src/IceCfg.cpp - Control flow graph implementation ---------===//
 //
 //                        The Subzero Code Generator
 //
 // This file is distributed under the University of Illinois Open Source
 // License. See LICENSE.TXT for details.
 //
 //===----------------------------------------------------------------------===//
 //
 // This file implements the Cfg class, including constant pool
@@ skipping 296 matching lines @@
         << "\n\n";
   }
   Str << "\t.text\n";
   IceString MangledName = getContext()->mangleName(getFunctionName());
   if (Ctx->getFlags().FunctionSections)
     Str << "\t.section\t.text." << MangledName << ",\"ax\",@progbits\n";
   if (!getInternal()) {
     Str << "\t.globl\t" << MangledName << "\n";
     Str << "\t.type\t" << MangledName << ",@function\n";
   }
+  Str << "\t.p2align " << getTarget()->getBundleP2Align() << "\n";

[Jim Stichnoth, 2014/08/28 20:26:12]

Should we consider padding with a halt sled, just for defense-in-depth?

[jvoung (off chromium), 2014/08/28 21:02:22]

We could do that. Added a hook for now.

I'm not sure if there's a performance difference, if the processor does
speculative execution, or what not.

E.g., one study showed that different choices of non-executed nops could make a
difference. The guess was if it touched different processor units. Section 5.4
of
http://static.googleusercontent.com/media/research.google.com/en/us/pubs/arch...

[Jim Stichnoth, 2014/08/28 21:22:21]

I'd kind of hope that if this performance difference really is real, it's due to
speculative execution of the never-actually-executed instructions that's
clogging up the functional units, and that speculatively executing a halt
instruction would hopefully not have that effect.

   for (NodeList::const_iterator I = Nodes.begin(), E = Nodes.end(); I != E;
        ++I) {
     (*I)->emit(this);
   }
   Str << "\n";
   T_emit.printElapsedUs(Ctx, "emit()");
 }
 
 // Dumps the IR with an optional introductory message.
 void Cfg::dump(const IceString &Message) {
@@ skipping 41 matching lines @@
   for (NodeList::const_iterator I = Nodes.begin(), E = Nodes.end(); I != E;
        ++I) {
     (*I)->dump(this);
   }
   if (getContext()->isVerbose(IceV_Instructions)) {
     Str << "}\n";
   }
 }
 
 } // end of namespace Ice