From a998735def5f04459fa6cbeaaffbb42f1a1dec5c Mon Sep 17 00:00:00 2001
From: Kevin Qin <Kevin.Qin@arm.com>
Date: Mon, 9 Mar 2015 06:14:07 +0000
Subject: [PATCH] Run LICM pass after loop unrolling pass.

Runtime unrollng will introduce a runtime check in loop prologue.
If the unrolled loop is a inner loop, then the proglogue will be inside
the outer loop. LICM pass can help to promote the runtime check out if
the checked value is loop invariant.

llvm-svn: 231630
---
 llvm/lib/Transforms/IPO/PassManagerBuilder.cpp   |  8 ++++-
 llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp  |  9 ++---
 llvm/test/Transforms/LoopUnroll/runtime-loop4.ll | 43 ++++++++++++++++++++++++
 3 files changed, 53 insertions(+), 7 deletions(-)
 create mode 100644 llvm/test/Transforms/LoopUnroll/runtime-loop4.ll

diff --git a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
index 21fa34d..7ff55a7 100644
--- a/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
+++ b/llvm/lib/Transforms/IPO/PassManagerBuilder.cpp
@@ -364,8 +364,14 @@ void PassManagerBuilder::populateModulePassManager(
   MPM.add(createCFGSimplificationPass());
   MPM.add(createInstructionCombiningPass());
 
-  if (!DisableUnrollLoops)
+  if (!DisableUnrollLoops) {
     MPM.add(createLoopUnrollPass());    // Unroll small loops
+    // Runtime unrollng will introduce runtime check in loop prologue. If the
+    // unrolled loop is a inner loop, then the prologue will be inside the
+    // outer loop. LICM pass can help to promote the runtime check out if the
+    // checked value is loop invariant.
+    MPM.add(createLICMPass());
+  }
 
   // After vectorization and unrolling, assume intrinsics may tell us more
   // about pointer alignments.
diff --git a/llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp b/llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp
index 91b688c..9e2d8c9 100644
--- a/llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp
+++ b/llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp
@@ -142,7 +142,7 @@ static void CloneLoopBlocks(Loop *L, Value *NewIter, const bool UnrollProlog,
                             BasicBlock *InsertTop, BasicBlock *InsertBot,
                             std::vector<BasicBlock *> &NewBlocks,
                             LoopBlocksDFS &LoopBlocks, ValueToValueMapTy &VMap,
-                            LoopInfo *LI) {
+                            LoopInfo *LI, LPPassManager *LPM) {
   BasicBlock *Preheader = L->getLoopPreheader();
   BasicBlock *Header = L->getHeader();
   BasicBlock *Latch = L->getLoopLatch();
@@ -153,10 +153,7 @@ static void CloneLoopBlocks(Loop *L, Value *NewIter, const bool UnrollProlog,
   Loop *ParentLoop = L->getParentLoop();
   if (!UnrollProlog) {
     NewLoop = new Loop();
-    if (ParentLoop)
-      ParentLoop->addChildLoop(NewLoop);
-    else
-      LI->addTopLevelLoop(NewLoop);
+    LPM->insertLoop(NewLoop, ParentLoop);
   }
 
   // For each block in the original loop, create a new copy,
@@ -390,7 +387,7 @@ bool llvm::UnrollRuntimeLoopProlog(Loop *L, unsigned Count, LoopInfo *LI,
   // the loop, otherwise we create a cloned loop to execute the extra
   // iterations. This function adds the appropriate CFG connections.
   CloneLoopBlocks(L, ModVal, UnrollPrologue, PH, PEnd, NewBlocks, LoopBlocks,
-                  VMap, LI);
+                  VMap, LI, LPM);
 
   // Insert the cloned blocks into function just before the original loop
   F->getBasicBlockList().splice(PEnd, F->getBasicBlockList(), NewBlocks[0],
diff --git a/llvm/test/Transforms/LoopUnroll/runtime-loop4.ll b/llvm/test/Transforms/LoopUnroll/runtime-loop4.ll
new file mode 100644
index 0000000..9be0ffd
--- /dev/null
+++ b/llvm/test/Transforms/LoopUnroll/runtime-loop4.ll
@@ -0,0 +1,43 @@
+; RUN: opt < %s -S -O2 -unroll-runtime=true | FileCheck %s
+
+; Check runtime unrolling prologue can be promoted by LICM pass.
+
+; CHECK: entry:
+; CHECK: %xtraiter
+; CHECK: %lcmp.mod
+; CHECK: loop1:
+; CHECK: br i1 %lcmp.mod
+; CHECK: loop2.prol:
+
+define void @unroll(i32 %iter, i32* %addr1, i32* %addr2) nounwind {
+entry:
+  br label %loop1
+
+loop1:
+  %iv1 = phi i32 [ 0, %entry ], [ %inc1, %loop1.latch ]
+  %offset1 = getelementptr i32, i32* %addr1, i32 %iv1
+  store i32 %iv1, i32* %offset1, align 4
+  br label %loop2.header
+
+loop2.header:
+  br label %loop2
+
+loop2:
+  %iv2 = phi i32 [ 0, %loop2.header ], [ %inc2, %loop2 ]
+  %offset2 = getelementptr i32, i32* %addr2, i32 %iv2
+  store i32 %iv2, i32* %offset2, align 4
+  %inc2 = add i32 %iv2, 1
+  %exitcnd2 = icmp uge i32 %inc2, %iter
+  br i1 %exitcnd2, label %exit2, label %loop2
+
+exit2:
+  br label %loop1.latch
+
+loop1.latch:
+  %inc1 = add i32 %iv1, 1
+  %exitcnd1 = icmp uge i32 %inc1, 1024
+  br i1 %exitcnd1, label %exit, label %loop1
+
+exit:
+  ret void
+}
-- 
2.7.4