1 files changed, 32 insertions, 1 deletions

diff --git a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
index d02e6975a19..877fc712ec7 100644
--- a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -48,6 +48,10 @@ UseGVNAfterVectorization("use-gvn-after-vectorization",
   cl::init(false), cl::Hidden,
   cl::desc("Run GVN instead of Early CSE after vectorization passes"));
 
+static cl::opt<bool> ExtraVectorizerPasses(
+    "extra-vectorizer-passes", cl::init(false), cl::Hidden,
+    cl::desc("Run cleanup optimization passes after vectorization."));
+
 static cl::opt<bool> UseNewSROA("use-new-sroa",
   cl::init(true), cl::Hidden,
   cl::desc("Enable the new, experimental SROA pass"));
@@ -283,6 +287,13 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   // 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());
+
+  // Re-rotate loops in all our loop nests. These may have fallout out of
+  // rotated form due to GVN or other transformations, and the vectorizer relies
+  // on the rotated form.
+  if (ExtraVectorizerPasses)
+    MPM.add(createLoopRotatePass());
+
   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
@@ -290,10 +301,29 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   // as function calls, so that we can only pass them when the vectorizer
   // changed the code.
   MPM.add(createInstructionCombiningPass());
+  if (OptLevel > 1 && ExtraVectorizerPasses) {
+    // At higher optimization levels, try to clean up any runtime overlap and
+    // alignment checks inserted by the vectorizer. We want to track correllated
+    // runtime checks for two inner loops in the same outer loop, fold any
+    // common computations, hoist loop-invariant aspects out of any outer loop,
+    // and unswitch the runtime checks if possible. Once hoisted, we may have
+    // dead (or speculatable) control flows or more combining opportunities.
+    MPM.add(createEarlyCSEPass());
+    MPM.add(createCorrelatedValuePropagationPass());
+    MPM.add(createInstructionCombiningPass());
+    MPM.add(createLICMPass());
+    MPM.add(createLoopUnswitchPass(SizeLevel || OptLevel < 3));
+    MPM.add(createCFGSimplificationPass());
+    MPM.add(createInstructionCombiningPass());
+  }
 
   if (RunSLPAfterLoopVectorization) {
-    if (SLPVectorize)
+    if (SLPVectorize) {
       MPM.add(createSLPVectorizerPass());   // Vectorize parallel scalar chains.
+      if (OptLevel > 1 && ExtraVectorizerPasses) {
+        MPM.add(createEarlyCSEPass());
+      }
+    }
 
     if (BBVectorize) {
       MPM.add(createBBVectorizePass());
@@ -312,6 +342,7 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
 
   addExtensionsToPM(EP_Peephole, MPM);
   MPM.add(createCFGSimplificationPass());
+  MPM.add(createInstructionCombiningPass());
 
   if (!DisableUnrollLoops)
     MPM.add(createLoopUnrollPass());    // Unroll small loops