Revert r230921, "Revert some changes that were made to fix PR20680.", for now.

It caused a failure on clang/test/Misc/backend-optimization-failure.cpp .

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@230929 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Scalar/IndVarSimplify.cpp b/lib/Transforms/Scalar/IndVarSimplify.cpp
index 462c2b6f90d636cf5904855a1d951c17d1089192..f99ebbc453f55bc2a472c46605d778c19259d876 100644 (file)
--- a/lib/Transforms/Scalar/IndVarSimplify.cpp
+++ b/lib/Transforms/Scalar/IndVarSimplify.cpp
@@ -1705,15 +1705,51 @@ LinearFunctionTestReplace(Loop *L,
   // compare against the post-incremented value, otherwise we must compare
   // against the preincremented value.
   if (L->getExitingBlock() == L->getLoopLatch()) {
   // compare against the post-incremented value, otherwise we must compare
   // against the preincremented value.
   if (L->getExitingBlock() == L->getLoopLatch()) {

-    // 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,
-                             SE->getConstant(BackedgeTakenCount->getType(), 1));

     // 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.
     // 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());
+    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,
+                         SE->getConstant(BackedgeTakenCount->getType(), 1));
+      CmpIndVar = IncrementedIndvar;
+    }

   }
 
   Value *ExitCnt = genLoopLimit(IndVar, IVCount, L, Rewriter, SE);
   }
 
   Value *ExitCnt = genLoopLimit(IndVar, IVCount, L, Rewriter, SE);

diff --git a/test/Transforms/IndVarSimplify/2011-10-27-lftrnull.ll b/test/Transforms/IndVarSimplify/2011-10-27-lftrnull.ll
index f1d1139aef80240d8785f174f19846f01817b196..75eaf918bcf37f0a8e6ce56d17ffd28604442757 100644 (file)
--- a/test/Transforms/IndVarSimplify/2011-10-27-lftrnull.ll
+++ b/test/Transforms/IndVarSimplify/2011-10-27-lftrnull.ll
@@ -6,7 +6,7 @@ target triple = "thumbv7-apple-darwin"
 
 ; CHECK-LABEL: @test(
 ; CHECK: if.end.i126:
 
 ; CHECK-LABEL: @test(
 ; CHECK: if.end.i126:

-; CHECK: %exitcond = icmp ne i8* %incdec.ptr.i, getelementptr (i8* null, i32 undef)
+; CHECK: %exitcond = icmp ne i8* %destYPixelPtr.010.i, getelementptr (i8* null, i32 undef)

 define void @test() nounwind {
 entry:
   br label %while.cond
 define void @test() nounwind {
 entry:
   br label %while.cond

diff --git a/test/Transforms/IndVarSimplify/lftr-address-space-pointers.ll b/test/Transforms/IndVarSimplify/lftr-address-space-pointers.ll
index feb4b35a20a7226cff2aae10e8d92c6c0a2d535c..b23e08dfad7b991f8d2bf1fc15809d2001f8827c 100644 (file)
--- a/test/Transforms/IndVarSimplify/lftr-address-space-pointers.ll
+++ b/test/Transforms/IndVarSimplify/lftr-address-space-pointers.ll
@@ -11,7 +11,7 @@ entry:
   br i1 %cmp1, label %for.body, label %for.end
 
 ; Make sure the added GEP has the right index type
   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 %0
+; CHECK: %lftr.limit = getelementptr i8, i8 addrspace(2)* %base, i8

 
 ; CHECK: for.body:
 ; CHECK: phi i8 addrspace(2)*
 
 ; CHECK: for.body:
 ; CHECK: phi i8 addrspace(2)*


@@ -43,7 +43,7 @@ entry:
   br i1 %cmp1, label %for.body, label %for.end
 
 ; Make sure the added GEP has the right index type
   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 %0
+; CHECK: %lftr.limit = getelementptr i8, i8 addrspace(3)* %base, i16

 
 ; CHECK: for.body:
 ; CHECK: phi i8 addrspace(3)*
 
 ; CHECK: for.body:
 ; CHECK: phi i8 addrspace(3)*

diff --git a/test/Transforms/IndVarSimplify/lftr-reuse.ll b/test/Transforms/IndVarSimplify/lftr-reuse.ll
index b4e1fdef48857f1f4aa65d845320d87760e7d6fa..befbb9e3f15c0632667fcdc25555bccde32dc38d 100644 (file)
--- a/test/Transforms/IndVarSimplify/lftr-reuse.ll
+++ b/test/Transforms/IndVarSimplify/lftr-reuse.ll
@@ -82,15 +82,23 @@ exit:
 ; Perform LFTR without generating extra preheader code.
 define void @guardedloop([0 x double]* %matrix, [0 x double]* %vector,
                          i32 %irow, i32 %ilead) nounwind {
 ; Perform LFTR without generating extra preheader code.
 define void @guardedloop([0 x double]* %matrix, [0 x double]* %vector,
                          i32 %irow, i32 %ilead) nounwind {

-; CHECK: entry:
-; CHECK-NOT: zext
-; CHECK-NOT: add
-; CHECK: loop:
-; CHECK: phi i64
-; CHECK: phi i64
+; 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-NOT: phi
 ; CHECK-NOT: phi

-; CHECK: icmp ne
-; CHECK: br i1
+; 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

 entry:
   %cmp = icmp slt i32 1, %irow
   br i1 %cmp, label %loop, label %return
 entry:
   %cmp = icmp slt i32 1, %irow
   br i1 %cmp, label %loop, label %return