Add a new option -run-slp-after-loop-vectorization.

This swaps the order of the loop vectorizer and the SLP/BB vectorizers. It is disabled by default so we can do performance testing - ideally we want to change to having the loop vectorizer running first, and the SLP vectorizer using its leftovers instead of the other way around.

llvm-svn: 214963

diff --git a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
index 3d846b0..e765577 100644 (file)
--- a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -57,6 +57,13 @@ static cl::opt<bool> RunLoadCombine("combine-loads", cl::init(false),
                                     cl::Hidden,
                                     cl::desc("Run the load combining pass"));
 
+static cl::opt<bool>
+RunSLPAfterLoopVectorization("run-slp-after-loop-vectorization",
+  cl::init(false), cl::Hidden,
+  cl::desc("Run the SLP vectorizer (and BB vectorizer) after the Loop "
+           "vectorizer instead of before"));
+
+
 PassManagerBuilder::PassManagerBuilder() {
     OptLevel = 2;
     SizeLevel = 0;
@@ -227,21 +234,23 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &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());
+  if (!RunSLPAfterLoopVectorization) {
+    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());
+    }
   }
 
   if (LoadCombine)
@@ -263,6 +272,26 @@ 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 (RunSLPAfterLoopVectorization) {
+    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());
+    }
+  }
+
   addExtensionsToPM(EP_Peephole, MPM);
   MPM.add(createCFGSimplificationPass());