From 7c5f9c35d1afd65c80369803dc5f65309dc361ce Mon Sep 17 00:00:00 2001
From: Chris Lattner <sabre@nondot.org>
Date: Sun, 26 Dec 2010 20:45:45 +0000
Subject: [PATCH] sketch more of this out.

llvm-svn: 122567
---
 .../Transforms/Scalar/LoopIdiomRecognize.cpp  | 84 ++++++++++++++-----
 1 file changed, 64 insertions(+), 20 deletions(-)

diff --git a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
index 270c4afcc1d5..eb7d4930edfa 100644
--- a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp
@@ -17,6 +17,8 @@
 #include "llvm/Transforms/Scalar.h"
 #include "llvm/Analysis/LoopPass.h"
 #include "llvm/Analysis/ScalarEvolutionExpressions.h"
+#include "llvm/Analysis/ValueTracking.h"
+#include "llvm/Target/TargetData.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/raw_ostream.h"
 using namespace llvm;
@@ -26,6 +28,9 @@ using namespace llvm;
 
 namespace {
   class LoopIdiomRecognize : public LoopPass {
+    Loop *CurLoop;
+    const TargetData *TD;
+    ScalarEvolution *SE;
   public:
     static char ID;
     explicit LoopIdiomRecognize() : LoopPass(ID) {
@@ -34,7 +39,7 @@ namespace {
 
     bool runOnLoop(Loop *L, LPPassManager &LPM);
 
-    bool scanBlock(BasicBlock *BB, Loop *L);
+    bool processLoopStore(StoreInst *SI, const SCEV *BECount);
     
     /// This transformation requires natural loop information & requires that
     /// loop preheaders be inserted into the CFG.
@@ -66,38 +71,77 @@ INITIALIZE_PASS_END(LoopIdiomRecognize, "loop-idiom", "Recognize loop idioms",
 Pass *llvm::createLoopIdiomPass() { return new LoopIdiomRecognize(); }
 
 bool LoopIdiomRecognize::runOnLoop(Loop *L, LPPassManager &LPM) {
+  CurLoop = L;
+  
   // We only look at trivial single basic block loops.
   // TODO: eventually support more complex loops, scanning the header.
   if (L->getBlocks().size() != 1)
     return false;
   
+  // The trip count of the loop must be analyzable.
+  SE = &getAnalysis<ScalarEvolution>();
+  if (!SE->hasLoopInvariantBackedgeTakenCount(L))
+    return false;
+  const SCEV *BECount = SE->getBackedgeTakenCount(L);
+  if (isa<SCEVCouldNotCompute>(BECount)) return false;
+  
+  // We require target data for now.
+  TD = getAnalysisIfAvailable<TargetData>();
+  if (TD == 0) return false;
+  
   BasicBlock *BB = L->getHeader();
-  DEBUG(dbgs() << "Loop Idiom Recognize: F[" << BB->getParent()->getName()
+  DEBUG(dbgs() << "loop-idiom Scanning: F[" << BB->getParent()->getName()
                << "] Loop %" << BB->getName() << "\n");
 
-  return scanBlock(BB, L);
+  bool MadeChange = false;
+  for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ) {
+    // Look for store instructions, which may be memsets.
+    if (StoreInst *SI = dyn_cast<StoreInst>(I++))
+      MadeChange |= processLoopStore(SI, BECount);
+  }
+  
+  return MadeChange;
 }
 
 /// scanBlock - Look over a block to see if we can promote anything out of it.
-bool LoopIdiomRecognize::scanBlock(BasicBlock *BB, Loop *L) {
-  ScalarEvolution &SE = getAnalysis<ScalarEvolution>();
+bool LoopIdiomRecognize::processLoopStore(StoreInst *SI, const SCEV *BECount) {
+  Value *StoredVal = SI->getValueOperand();
   
-  for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E; ) {
-    // Look for store instructions, which may be memsets.
-    StoreInst *SI = dyn_cast<StoreInst>(I++);
-    if (SI == 0) continue;
-    
-    // See if the pointer expression is an AddRec like {base,+,1} on the current
-    // loop, which indicates a strided store.  If we have something else, it's a
-    // random store we can't handle.
-    const SCEVAddRecExpr *Ev =
-      dyn_cast<SCEVAddRecExpr>(SE.getSCEV(SI->getPointerOperand()));
-    if (Ev == 0 || Ev->getLoop() != L)
-      continue;
-    
-    errs() << "Found strided store: " << *Ev << "\n";
-  }
+  // Check to see if the store updates all bits in memory.  We don't want to
+  // process things like a store of i3.  We also require that the store be a
+  // multiple of a byte.
+  uint64_t SizeInBits = TD->getTypeSizeInBits(StoredVal->getType());
+  if ((SizeInBits & 7) || (SizeInBits >> 32) != 0 ||
+      SizeInBits != TD->getTypeStoreSizeInBits(StoredVal->getType()))
+    return false;
   
+  // See if the pointer expression is an AddRec like {base,+,1} on the current
+  // loop, which indicates a strided store.  If we have something else, it's a
+  // random store we can't handle.
+  const SCEVAddRecExpr *Ev =
+    dyn_cast<SCEVAddRecExpr>(SE->getSCEV(SI->getPointerOperand()));
+  if (Ev == 0 || Ev->getLoop() != CurLoop || !Ev->isAffine())
+    return false;
+
+  // Check to see if the stride matches the size of the store.  If so, then we
+  // know that every byte is touched in the loop.
+  unsigned StoreSize = (unsigned)SizeInBits >> 3; 
+  const SCEVConstant *Stride = dyn_cast<SCEVConstant>(Ev->getOperand(1));
+  if (Stride == 0 || StoreSize != Stride->getValue()->getValue())
+    return false;
+  
+  errs() << "Found strided store: " << *Ev << "\n";
+  
+  // Check for memcpy here.
+  
+  
+  // If the stored value is a byte-wise value (like i32 -1), then it may be
+  // turned into a memset of i8 -1, assuming that all the consequtive bytes
+  // are stored.  A store of i32 0x01020304 can never be turned into a memset.
+  Value *SplatValue = isBytewiseValue(StoredVal);
+  if (SplatValue == 0) return false;
+  
+
   return false;
 }