From: Chris Lattner <sabre@nondot.org>
Date: Sat, 19 May 2007 01:22:21 +0000 (+0000)
Subject: Handle negative strides much more optimally.  This compiles X86/lsr-negative-stride.ll
X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=fb3e1190fc33c93a7185695051d5aeeaddbae0ad;p=oota-llvm.git

Handle negative strides much more optimally.  This compiles X86/lsr-negative-stride.ll
into:

_t:
        movl 8(%esp), %ecx
        movl 4(%esp), %eax
        cmpl %ecx, %eax
        je LBB1_3       #bb17
LBB1_1: #bb
        cmpl %ecx, %eax
        jg LBB1_4       #cond_true
LBB1_2: #cond_false
        subl %eax, %ecx
        cmpl %ecx, %eax
        jne LBB1_1      #bb
LBB1_3: #bb17
        ret
LBB1_4: #cond_true
        subl %ecx, %eax
        cmpl %ecx, %eax
        jne LBB1_1      #bb
        jmp LBB1_3      #bb17

instead of:

_t:
        subl $4, %esp
        movl %esi, (%esp)
        movl 12(%esp), %ecx
        movl 8(%esp), %eax
        cmpl %ecx, %eax
        je LBB1_4       #bb17
LBB1_1: #bb.outer
        movl %ecx, %edx
        negl %edx
LBB1_2: #bb
        cmpl %ecx, %eax
        jle LBB1_5      #cond_false
LBB1_3: #cond_true
        addl %edx, %eax
        cmpl %ecx, %eax
        jne LBB1_2      #bb
LBB1_4: #bb17
        movl (%esp), %esi
        addl $4, %esp
        ret
LBB1_5: #cond_false
        movl %ecx, %edx
        subl %eax, %edx
        movl %eax, %esi
        addl %esi, %esi
        cmpl %ecx, %esi
        je LBB1_4       #bb17
LBB1_6: #cond_false.bb.outer_crit_edge
        movl %edx, %ecx
        jmp LBB1_1      #bb.outer


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@37252 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/lib/Transforms/Scalar/LoopStrengthReduce.cpp b/lib/Transforms/Scalar/LoopStrengthReduce.cpp
index 1a9b9881d70..449cee3bda2 100644
--- a/lib/Transforms/Scalar/LoopStrengthReduce.cpp
+++ b/lib/Transforms/Scalar/LoopStrengthReduce.cpp
@@ -987,6 +987,20 @@ static bool PartitionByIsUseOfPostIncrementedValue(const BasedUser &Val) {
   return Val.isUseOfPostIncrementedValue;
 }
 
+/// isNonConstantNegative - REturn true if the specified scev is negated, but
+/// not a constant.
+static bool isNonConstantNegative(const SCEVHandle &Expr) {
+  SCEVMulExpr *Mul = dyn_cast<SCEVMulExpr>(Expr);
+  if (!Mul) return false;
+  
+  // If there is a constant factor, it will be first.
+  SCEVConstant *SC = dyn_cast<SCEVConstant>(Mul->getOperand(0));
+  if (!SC) return false;
+  
+  // Return true if the value is negative, this matches things like (-42 * V).
+  return SC->getValue()->getValue().isNegative();
+}
+
 /// StrengthReduceStridedIVUsers - Strength reduce all of the users of a single
 /// stride of IV.  All of the users may have different starting values, and this
 /// may not be the only stride (we know it is if isOnlyStride is true).
@@ -1104,15 +1118,24 @@ void LoopStrengthReduce::StrengthReduceStridedIVUsers(const SCEVHandle &Stride,
     // Add common base to the new Phi node.
     NewPHI->addIncoming(CommonBaseV, Preheader);
 
+    // If the stride is negative, insert a sub instead of an add for the
+    // increment.
+    bool isNegative = isNonConstantNegative(Stride);
+    SCEVHandle IncAmount = Stride;
+    if (isNegative)
+      IncAmount = SCEV::getNegativeSCEV(Stride);
+    
     // Insert the stride into the preheader.
-    Value *StrideV = PreheaderRewriter.expandCodeFor(Stride, PreInsertPt,
+    Value *StrideV = PreheaderRewriter.expandCodeFor(IncAmount, PreInsertPt,
                                                      ReplacedTy);
     if (!isa<ConstantInt>(StrideV)) ++NumVariable;
 
     // Emit the increment of the base value before the terminator of the loop
     // latch block, and add it to the Phi node.
-    SCEVHandle IncExp = SCEVAddExpr::get(SCEVUnknown::get(NewPHI),
-                                         SCEVUnknown::get(StrideV));
+    SCEVHandle IncExp = SCEVUnknown::get(StrideV);
+    if (isNegative)
+      IncExp = SCEV::getNegativeSCEV(IncExp);
+    IncExp = SCEVAddExpr::get(SCEVUnknown::get(NewPHI), IncExp);
   
     IncV = Rewriter.expandCodeFor(IncExp, LatchBlock->getTerminator(),
                                   ReplacedTy);