Move partial/runtime unrolling late in the pipeline

The generic (concatenation) loop unroller is currently placed early in the
standard optimization pipeline. This is a good place to perform full unrolling,
but not the right place to perform partial/runtime unrolling. However, most
targets don't enable partial/runtime unrolling, so this never mattered.

However, even some x86 cores benefit from partial/runtime unrolling of very
small loops, and follow-up commits will enable this. First, we need to move
partial/runtime unrolling late in the optimization pipeline (importantly, this
is after SLP and loop vectorization, as vectorization can drastically change
the size of a loop), while keeping the full unrolling where it is now. This
change does just that.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205264 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/include/llvm/Transforms/Scalar.h b/include/llvm/Transforms/Scalar.h
index 5c57ea6db0cbf05d36eec8929129807a99f3c76a..726722270d09c8abfbb1eb535c8cb459663776b6 100644 (file)
--- a/include/llvm/Transforms/Scalar.h
+++ b/include/llvm/Transforms/Scalar.h
@@ -142,6 +142,8 @@ Pass *createLoopInstSimplifyPass();
 //
 Pass *createLoopUnrollPass(int Threshold = -1, int Count = -1,
                            int AllowPartial = -1, int Runtime = -1);
+// Create an unrolling pass for full unrolling only.
+Pass *createSimpleLoopUnrollPass();
 
 //===----------------------------------------------------------------------===//
 //

diff --git a/lib/Transforms/IPO/PassManagerBuilder.cpp b/lib/Transforms/IPO/PassManagerBuilder.cpp
index 21d8e58db7cda70f92b68b69236388f150d863f2..4a28b34468baa0a50e57e7f63d40fefdc549bff9 100644 (file)
--- a/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -195,7 +195,7 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   MPM.add(createLoopDeletionPass());          // Delete dead loops
 
   if (!DisableUnrollLoops)
-    MPM.add(createLoopUnrollPass());          // Unroll small loops
+    MPM.add(createSimpleLoopUnrollPass());    // Unroll small loops
   addExtensionsToPM(EP_LoopOptimizerEnd, MPM);
 
   if (OptLevel > 1)
@@ -247,6 +247,9 @@ void PassManagerBuilder::populateModulePassManager(PassManagerBase &MPM) {
   MPM.add(createInstructionCombiningPass());
   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

diff --git a/lib/Transforms/Scalar/LoopUnrollPass.cpp b/lib/Transforms/Scalar/LoopUnrollPass.cpp
index 583fdd4133010549742eff1dc467e5183fbc71fb..4420dc2d4add344fc0524ef056352e0dee9f2ea4 100644 (file)
--- a/lib/Transforms/Scalar/LoopUnrollPass.cpp
+++ b/lib/Transforms/Scalar/LoopUnrollPass.cpp
@@ -125,6 +125,10 @@ Pass *llvm::createLoopUnrollPass(int Threshold, int Count, int AllowPartial,
   return new LoopUnroll(Threshold, Count, AllowPartial, Runtime);
 }
 
+Pass *llvm::createSimpleLoopUnrollPass() {
+  return llvm::createLoopUnrollPass(-1, -1, 0, 0);
+}
+
 /// ApproximateLoopSize - Approximate the size of the loop.
 static unsigned ApproximateLoopSize(const Loop *L, unsigned &NumCalls,
                                     bool &NotDuplicatable,

diff --git a/test/Transforms/LoopVectorize/X86/already-vectorized.ll b/test/Transforms/LoopVectorize/X86/already-vectorized.ll
index 885418c0fdd9e1b571230a6739f35bdb51e71230..faed77d66dc73dd5dbd1b945b7722e6ef2611db9 100644 (file)
--- a/test/Transforms/LoopVectorize/X86/already-vectorized.ll
+++ b/test/Transforms/LoopVectorize/X86/already-vectorized.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -debug-only=loop-vectorize -O3 -S 2>&1 | FileCheck %s
+; RUN: opt < %s -disable-loop-unrolling -debug-only=loop-vectorize -O3 -S 2>&1 | FileCheck %s
 ; REQUIRES: asserts
 ; We want to make sure that we don't even try to vectorize loops again
 ; The vectorizer used to mark the un-vectorized loop only as already vectorized