Add an extension point for peephole optimizers.

[pcc]

Summary

This extension point allows adding passes that perform peephole optimizations
similar to the instruction combiner. These passes will be inserted after
each instance of the instruction combiner pass.

[chandlerc]

This makes a lot of sense to me, and the patch LGTM. Please commit.

I wonder if we want to distinguish between an early, canonicalizing peephole and a late target-specific peephole? Certainly, this patch is fine, just food for thought if this ever comes up.

[pcc]

Closed by commit rL209595 (authored by @pcc).

llvm/trunk/include/llvm/Transforms/IPO/PassManagerBuilder.h

enum ExtensionPointTy {
 
     /// EP_OptimizerLast -- This extension point allows adding passes that
     /// run after everything else.
     EP_OptimizerLast,
 
     /// EP_EnabledOnOptLevel0 - This extension point allows adding passes that
     /// should not be disabled by O0 optimization level. The passes will be
     /// inserted after the inlining pass.
-    EP_EnabledOnOptLevel0
+    EP_EnabledOnOptLevel0,
+
+    /// EP_Peephole - This extension point allows adding passes that perform
+    /// peephole optimizations similar to the instruction combiner. These passes
+    /// will be inserted after each instance of the instruction combiner pass.
+    EP_Peephole,
   };
 
   /// The Optimization Level - Specify the basic optimization level.
   ///    0 = -O0, 1 = -O1, 2 = -O2, 3 = -O3
   unsigned OptLevel;
 
   /// SizeLevel - How much we're optimizing for size.
   ///    0 = none, 1 = -Os, 2 = -Oz

llvm/trunk/lib/Transforms/IPO/PassManagerBuilder.cpp

if (!DisableUnitAtATime) {
     addExtensionsToPM(EP_ModuleOptimizerEarly, MPM);
 
     MPM.add(createGlobalOptimizerPass());     // Optimize out global vars
 
     MPM.add(createIPSCCPPass());              // IP SCCP
     MPM.add(createDeadArgEliminationPass());  // Dead argument elimination
 
     MPM.add(createInstructionCombiningPass());// Clean up after IPCP & DAE
+    addExtensionsToPM(EP_Peephole, MPM);
     MPM.add(createCFGSimplificationPass());   // Clean up after IPCP & DAE
   }
 
   // Start of CallGraph SCC passes.
   if (!DisableUnitAtATime)
     MPM.add(createPruneEHPass());             // Remove dead EH info
   if (Inliner) {
     MPM.add(Inliner);
if (UseNewSROA)
     MPM.add(createSROAPass(/*RequiresDomTree*/ false));
   else
     MPM.add(createScalarReplAggregatesPass(-1, false));
   MPM.add(createEarlyCSEPass());              // Catch trivial redundancies
   MPM.add(createJumpThreadingPass());         // Thread jumps.
   MPM.add(createCorrelatedValuePropagationPass()); // Propagate conditionals
   MPM.add(createCFGSimplificationPass());     // Merge & remove BBs
   MPM.add(createInstructionCombiningPass());  // Combine silly seq's
+  addExtensionsToPM(EP_Peephole, MPM);
 
   if (!DisableTailCalls)
     MPM.add(createTailCallEliminationPass()); // Eliminate tail calls
   MPM.add(createCFGSimplificationPass());     // Merge & remove BBs
   MPM.add(createReassociatePass());           // Reassociate expressions
   MPM.add(createLoopRotatePass());            // Rotate Loop
   MPM.add(createLICMPass());                  // Hoist loop invariants
   MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3));
void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   if (OptLevel > 1)
     MPM.add(createGVNPass());                 // Remove redundancies
   MPM.add(createMemCpyOptPass());             // Remove memcpy / form memset
   MPM.add(createSCCPPass());                  // Constant prop with SCCP
 
   // Run instcombine after redundancy elimination to exploit opportunities
   // opened up by them.
   MPM.add(createInstructionCombiningPass());
+  addExtensionsToPM(EP_Peephole, MPM);
   MPM.add(createJumpThreadingPass());         // Thread jumps
   MPM.add(createCorrelatedValuePropagationPass());
   MPM.add(createDeadStoreEliminationPass());  // Delete dead stores
 
   addExtensionsToPM(EP_ScalarOptimizerLate, MPM);
 
   if (RerollLoops)
     MPM.add(createLoopRerollPass());
   if (SLPVectorize)
     MPM.add(createSLPVectorizerPass());   // Vectorize parallel scalar chains.
 
   if (BBVectorize) {
     MPM.add(createBBVectorizePass());
     MPM.add(createInstructionCombiningPass());
+    addExtensionsToPM(EP_Peephole, MPM);
     if (OptLevel > 1 && UseGVNAfterVectorization)
       MPM.add(createGVNPass());           // Remove redundancies
     else
       MPM.add(createEarlyCSEPass());      // Catch trivial redundancies
 
     // BBVectorize may have significantly shortened a loop body; unroll again.
     if (!DisableUnrollLoops)
       MPM.add(createLoopUnrollPass());
   }
 
   MPM.add(createAggressiveDCEPass());         // Delete dead instructions
   MPM.add(createCFGSimplificationPass()); // Merge & remove BBs
   MPM.add(createInstructionCombiningPass());  // Clean up after everything.
+  addExtensionsToPM(EP_Peephole, MPM);
 
   // FIXME: This is a HACK! The inliner pass above implicitly creates a CGSCC
   // pass manager that we are specifically trying to avoid. To prevent this
   // we must insert a no-op module pass to reset the pass manager.
   MPM.add(createBarrierNoopPass());
   MPM.add(createLoopVectorizePass(DisableUnrollLoops, LoopVectorize));
   // FIXME: Because of #pragma vectorize enable, the passes below are always
   // inserted in the pipeline, even when the vectorizer doesn't run (ex. when
   // on -O1 and no #pragma is found). Would be good to have these two passes
   // as function calls, so that we can only pass them when the vectorizer
   // changed the code.
   MPM.add(createInstructionCombiningPass());
+  addExtensionsToPM(EP_Peephole, MPM);
   MPM.add(createCFGSimplificationPass());
 
   if (!DisableUnrollLoops)
     MPM.add(createLoopUnrollPass());    // Unroll small loops
 
   if (!DisableUnitAtATime) {
     // FIXME: We shouldn't bother with this anymore.
     MPM.add(createStripDeadPrototypesPass()); // Get rid of dead prototypes
void PassManagerBuilder::populateLTOPassManager(PassManagerBase &PM,
   // Remove unused arguments from functions.
   PM.add(createDeadArgEliminationPass());
 
   // Reduce the code after globalopt and ipsccp.  Both can open up significant
   // simplification opportunities, and both can propagate functions through
   // function pointers.  When this happens, we often have to resolve varargs
   // calls, etc, so let instcombine do this.
   PM.add(createInstructionCombiningPass());
+  addExtensionsToPM(EP_Peephole, PM);
 
   // Inline small functions
   if (RunInliner)
     PM.add(createFunctionInliningPass());
 
   PM.add(createPruneEHPass());   // Remove dead EH info.
 
   // Optimize globals again if we ran the inliner.
   if (RunInliner)
     PM.add(createGlobalOptimizerPass());
   PM.add(createGlobalDCEPass()); // Remove dead functions.
 
   // If we didn't decide to inline a function, check to see if we can
   // transform it to pass arguments by value instead of by reference.
   PM.add(createArgumentPromotionPass());
 
   // The IPO passes may leave cruft around.  Clean up after them.
   PM.add(createInstructionCombiningPass());
+  addExtensionsToPM(EP_Peephole, PM);
   PM.add(createJumpThreadingPass());
 
   // Break up allocas
   if (UseNewSROA)
     PM.add(createSROAPass());
   else
     PM.add(createScalarReplAggregatesPass());
 
void PassManagerBuilder::populateLTOPassManager(PassManagerBase &PM,
   PM.add(createLoopDeletionPass());
   PM.add(createLoopVectorizePass(true, true));
 
   // More scalar chains could be vectorized due to more alias information
   PM.add(createSLPVectorizerPass()); // Vectorize parallel scalar chains.
 
   // Cleanup and simplify the code after the scalar optimizations.
   PM.add(createInstructionCombiningPass());
+  addExtensionsToPM(EP_Peephole, PM);
 
   PM.add(createJumpThreadingPass());
 
   // Delete basic blocks, which optimization passes may have killed.
   PM.add(createCFGSimplificationPass());
 
   // Now that we have optimized the program, discard unreachable functions.
   PM.add(createGlobalDCEPass());