This patch reverts some changes that were made to fix PR20680.

[sanjoy]

Summary

As far as I can tell, the real bug causing the issue was fixed in r230533.

SCEVExpander should mark an increment operation as nuw or nsw only if
it can *prove* that the operation does not overflow. There shouldn't
be any situation where we have to do something different because of
no-wrap flags generated by SCEVExpander.

Revert "IndVarSimplify: Allow LFTR to fire more often"

This reverts commit 1ade0f0faa98877b688e0b9da58e876052c1e04e.

Revert "IndVarSimplify: Don't let LFTR compare against a poison value"

This reverts commit c0f2b8b528d8a37b0a1522aae90af649d6357eb5.

[atrick]

Great!

llvm/trunk/lib/Transforms/Scalar/IndVarSimplify.cpp

LinearFunctionTestReplace(Loop *L,
   // Initialize CmpIndVar and IVCount to their preincremented values.
   Value *CmpIndVar = IndVar;
   const SCEV *IVCount = BackedgeTakenCount;
 
   // If the exiting block is the same as the backedge block, we prefer to
   // compare against the post-incremented value, otherwise we must compare
   // against the preincremented value.
   if (L->getExitingBlock() == L->getLoopLatch()) {
-    // The BackedgeTaken expression contains the number of times that the
-    // backedge branches to the loop header.  This is one less than the
-    // number of times the loop executes, so use the incremented indvar.
-    llvm::Value *IncrementedIndvar =
-        IndVar->getIncomingValueForBlock(L->getExitingBlock());
-    const auto *IncrementedIndvarSCEV =
-        cast<SCEVAddRecExpr>(SE->getSCEV(IncrementedIndvar));
-    // It is unsafe to use the incremented indvar if it has a wrapping flag, we
-    // don't want to compare against a poison value.  Check the SCEV that
-    // corresponds to the incremented indvar, the SCEVExpander will only insert
-    // flags in the IR if the SCEV originally had wrapping flags.
-    // FIXME: In theory, SCEV could drop flags even though they exist in IR.
-    // A more robust solution would involve getting a new expression for
-    // CmpIndVar by applying non-NSW/NUW AddExprs.
-    auto WrappingFlags =
-        ScalarEvolution::setFlags(SCEV::FlagNUW, SCEV::FlagNSW);
-    const SCEV *IVInit = IncrementedIndvarSCEV->getStart();
-    if (SE->getTypeSizeInBits(IVInit->getType()) >
-        SE->getTypeSizeInBits(IVCount->getType()))
-      IVInit = SE->getTruncateExpr(IVInit, IVCount->getType());
-    unsigned BitWidth = SE->getTypeSizeInBits(IVCount->getType());
-    Type *WideTy = IntegerType::get(SE->getContext(), BitWidth + 1);
-    // Check if InitIV + BECount+1 requires sign/zero extension.
-    // If not, clear the corresponding flag from WrappingFlags because it is not
-    // necessary for those flags in the IncrementedIndvarSCEV expression.
-    if (SE->getSignExtendExpr(SE->getAddExpr(IVInit, BackedgeTakenCount),
-                              WideTy) ==
-        SE->getAddExpr(SE->getSignExtendExpr(IVInit, WideTy),
-                       SE->getSignExtendExpr(BackedgeTakenCount, WideTy)))
-      WrappingFlags = ScalarEvolution::clearFlags(WrappingFlags, SCEV::FlagNSW);
-    if (SE->getZeroExtendExpr(SE->getAddExpr(IVInit, BackedgeTakenCount),
-                              WideTy) ==
-        SE->getAddExpr(SE->getZeroExtendExpr(IVInit, WideTy),
-                       SE->getZeroExtendExpr(BackedgeTakenCount, WideTy)))
-      WrappingFlags = ScalarEvolution::clearFlags(WrappingFlags, SCEV::FlagNUW);
-    if (!ScalarEvolution::maskFlags(IncrementedIndvarSCEV->getNoWrapFlags(),
-                                    WrappingFlags)) {
-      // Add one to the "backedge-taken" count to get the trip count.
-      // This addition may overflow, which is valid as long as the comparison is
-      // truncated to BackedgeTakenCount->getType().
-      IVCount =
-          SE->getAddExpr(BackedgeTakenCount,
+    IVCount = SE->getAddExpr(BackedgeTakenCount,
                              SE->getConstant(BackedgeTakenCount->getType(), 1));
-      CmpIndVar = IncrementedIndvar;
-    }
+    // The BackedgeTaken expression contains the number of times that the
+    // backedge branches to the loop header.  This is one less than the
+    // number of times the loop executes, so use the incremented indvar.
+    CmpIndVar = IndVar->getIncomingValueForBlock(L->getExitingBlock());
   }
 
   Value *ExitCnt = genLoopLimit(IndVar, IVCount, L, Rewriter, SE);
   assert(ExitCnt->getType()->isPointerTy() == IndVar->getType()->isPointerTy()
          && "genLoopLimit missed a cast");
 
   // Insert a new icmp_ne or icmp_eq instruction before the branch.
   BranchInst *BI = cast<BranchInst>(L->getExitingBlock()->getTerminator());

llvm/trunk/test/Transforms/IndVarSimplify/2011-10-27-lftrnull.ll

 ; RUN: opt < %s -indvars -S | FileCheck %s
 ; rdar://10359193: assert "IndVar type must match IVInit type"
 
 target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
 target triple = "thumbv7-apple-darwin"
 
 ; CHECK-LABEL: @test(
 ; CHECK: if.end.i126:
-; CHECK: %exitcond = icmp ne i8* %destYPixelPtr.010.i, getelementptr (i8* null, i32 undef)
+; CHECK: %exitcond = icmp ne i8* %incdec.ptr.i, getelementptr (i8* null, i32 undef)
 define void @test() nounwind {
 entry:
   br label %while.cond
 
 while.cond:
   br i1 undef, label %while.end, label %while.body
 
 while.body:                                       ; preds = %while.cond

llvm/trunk/test/Transforms/IndVarSimplify/lftr-address-space-pointers.ll

 ; RUN: opt -S -indvars -o - %s | FileCheck %s
 target datalayout = "e-p:32:32:32-p1:64:64:64-p2:8:8:8-p3:16:16:16-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:32-n8:16:32:64"
 
 ; Derived from ptriv in lftr-reuse.ll
 define void @ptriv_as2(i8 addrspace(2)* %base, i32 %n) nounwind {
 ; CHECK-LABEL: @ptriv_as2(
 entry:
   %idx.trunc = trunc i32 %n to i8
   %add.ptr = getelementptr inbounds i8, i8 addrspace(2)* %base, i8 %idx.trunc
   %cmp1 = icmp ult i8 addrspace(2)* %base, %add.ptr
   br i1 %cmp1, label %for.body, label %for.end
 
 ; Make sure the added GEP has the right index type
-; CHECK: %lftr.limit = getelementptr i8, i8 addrspace(2)* %base, i8
+; CHECK: %lftr.limit = getelementptr i8, i8 addrspace(2)* %base, i8 %0
 
 ; CHECK: for.body:
 ; CHECK: phi i8 addrspace(2)*
 ; CHECK-NOT: phi
 ; CHECK-NOT: add{{^rspace}}
 ; CHECK: icmp ne i8 addrspace(2)*
 ; CHECK: br i1
 for.body:

 ; CHECK-LABEL: @ptriv_as3(
 entry:
   %idx.trunc = trunc i32 %n to i16
   %add.ptr = getelementptr inbounds i8, i8 addrspace(3)* %base, i16 %idx.trunc
   %cmp1 = icmp ult i8 addrspace(3)* %base, %add.ptr
   br i1 %cmp1, label %for.body, label %for.end
 
 ; Make sure the added GEP has the right index type
-; CHECK: %lftr.limit = getelementptr i8, i8 addrspace(3)* %base, i16
+; CHECK: %lftr.limit = getelementptr i8, i8 addrspace(3)* %base, i16 %0
 
 ; CHECK: for.body:
 ; CHECK: phi i8 addrspace(3)*
 ; CHECK-NOT: phi
 ; CHECK-NOT: add{{^rspace}}
 ; CHECK: icmp ne i8 addrspace(3)*
 ; CHECK: br i1
 for.body:

llvm/trunk/test/Transforms/IndVarSimplify/lftr-reuse.ll

 exit:
   ret void
 }
 
 ; Force SCEVExpander to look for an existing well-formed phi.
 ; Perform LFTR without generating extra preheader code.
 define void @guardedloop([0 x double]* %matrix, [0 x double]* %vector,
                          i32 %irow, i32 %ilead) nounwind {
-; CHECK-LABEL: @guardedloop(
-; CHECK-LABEL: entry:
-; CHECK-NEXT: %[[cmp:.*]] = icmp slt i32 1, %irow
-; CHECK-NEXT: br i1 %[[cmp]], label %[[loop_preheader:.*]], label %[[return:.*]]
-
-; CHECK: [[loop_preheader]]:
-; CHECK-NEXT: %[[sext:.*]] = sext i32 %ilead to i64
-; CHECK-NEXT: %[[add:.*]] = add i32 %irow, -1
-; CHECK-NEXT: br label %[[loop:.*]]
-
-; CHECK: [[loop]]:
-; CHECK-NEXT: %[[indvars_iv2:.*]] = phi i64
-; CHECK-NEXT: phi i64
+; CHECK: entry:
+; CHECK-NOT: zext
+; CHECK-NOT: add
+; CHECK: loop:
+; CHECK: phi i64
+; CHECK: phi i64
 ; CHECK-NOT: phi
-; CHECK: %[[lftr_wideiv:.*]] = trunc i64 %[[indvars_iv2]] to i32
-; CHECK-NEXT: %[[exitcond:.*]] = icmp ne i32 %[[lftr_wideiv]], %[[add]]
-; CHECK-NEXT: br i1 %[[exitcond]], label %[[loop]], label
+; CHECK: icmp ne
+; CHECK: br i1
 entry:
   %cmp = icmp slt i32 1, %irow
   br i1 %cmp, label %loop, label %return
 
 loop:
   %rowidx = phi i32 [ 0, %entry ], [ %row.inc, %loop ]
   %i = phi i32 [ 0, %entry ], [ %i.inc, %loop ]
   %diagidx = add nsw i32 %rowidx, %i