[SCEV] Check whether the start is non-zero in ScalarEvolution::howFarToZero (#131522)

#94525 assumes that the loop
will be infinite when the stride is zero. However, it doesn't hold when
the start value of addrec is also zero.

Closes #131465.

Author: dtcxzyw

llvm/lib/Analysis/ScalarEvolution.cpp

@@ -10635,10 +10635,11 @@ ScalarEvolution::ExitLimit ScalarEvolution::howFarToZero(const SCEV *V,
   if (ControlsOnlyExit && AddRec->hasNoSelfWrap() &&
       loopHasNoAbnormalExits(AddRec->getLoop())) {
 
-    // If the stride is zero, the loop must be infinite.  In C++, most loops
-    // are finite by assumption, in which case the step being zero implies
-    // UB must execute if the loop is entered.
-    if (!loopIsFiniteByAssumption(L) && !isKnownNonZero(StepWLG))
+    // If the stride is zero and the start is non-zero, the loop must be
+    // infinite. In C++, most loops are finite by assumption, in which case the
+    // step being zero implies UB must execute if the loop is entered.
+    if (!(loopIsFiniteByAssumption(L) && isKnownNonZero(Start)) &&
+        !isKnownNonZero(StepWLG))
       return getCouldNotCompute();
 
     const SCEV *Exact =

llvm/test/Analysis/ScalarEvolution/trip-count-unknown-stride.ll

@@ -329,10 +329,9 @@ define void @ne_nsw_nonneg_step(ptr nocapture %A, i32 %n, i32 %s) mustprogress {
 ;
 ; CHECK-LABEL: 'ne_nsw_nonneg_step'
 ; CHECK-NEXT:  Determining loop execution counts for: @ne_nsw_nonneg_step
-; CHECK-NEXT:  Loop %for.body: backedge-taken count is (((-1 * %s) + %n) /u %s)
-; CHECK-NEXT:  Loop %for.body: constant max backedge-taken count is i32 -1
-; CHECK-NEXT:  Loop %for.body: symbolic max backedge-taken count is (((-1 * %s) + %n) /u %s)
-; CHECK-NEXT:  Loop %for.body: Trip multiple is 1
+; CHECK-NEXT:  Loop %for.body: Unpredictable backedge-taken count.
+; CHECK-NEXT:  Loop %for.body: Unpredictable constant max backedge-taken count.
+; CHECK-NEXT:  Loop %for.body: Unpredictable symbolic max backedge-taken count.
 ;
 entry:
   %nonneg_step = icmp sge i32 %s, 0
@@ -442,10 +441,9 @@ define void @ne_nuw_nonneg_step(ptr nocapture %A, i32 %n, i32 %s) mustprogress {
 ;
 ; CHECK-LABEL: 'ne_nuw_nonneg_step'
 ; CHECK-NEXT:  Determining loop execution counts for: @ne_nuw_nonneg_step
-; CHECK-NEXT:  Loop %for.body: backedge-taken count is (((-1 * %s) + %n) /u %s)
-; CHECK-NEXT:  Loop %for.body: constant max backedge-taken count is i32 -1
-; CHECK-NEXT:  Loop %for.body: symbolic max backedge-taken count is (((-1 * %s) + %n) /u %s)
-; CHECK-NEXT:  Loop %for.body: Trip multiple is 1
+; CHECK-NEXT:  Loop %for.body: Unpredictable backedge-taken count.
+; CHECK-NEXT:  Loop %for.body: Unpredictable constant max backedge-taken count.
+; CHECK-NEXT:  Loop %for.body: Unpredictable symbolic max backedge-taken count.
 ;
 entry:
   %nonneg_step = icmp sge i32 %s, 0
@@ -493,6 +491,26 @@ for.end:                                          ; preds = %for.body, %entry
   ret void
 }
 
+define i32 @pr131465(i1 %x) mustprogress {
+; CHECK-LABEL: 'pr131465'
+; CHECK-NEXT:  Determining loop execution counts for: @pr131465
+; CHECK-NEXT:  Loop %for.body: Unpredictable backedge-taken count.
+; CHECK-NEXT:  Loop %for.body: Unpredictable constant max backedge-taken count.
+; CHECK-NEXT:  Loop %for.body: Unpredictable symbolic max backedge-taken count.
+;
+entry:
+  %inc = zext i1 %x to i32
+  br label %for.body
+
+for.body:
+  %indvar = phi i32 [ 2, %entry ], [ %next, %for.body ]
+  %next = add nsw i32 %indvar, %inc
+  %exitcond = icmp eq i32 %next, 2
+  br i1 %exitcond, label %for.end, label %for.body
+
+for.end:
+  ret i32 0
+}
 
 declare void @llvm.assume(i1)
 

llvm/test/Transforms/LoopUnroll/pr131465.ll

@@ -0,0 +1,43 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S -passes=loop-unroll -unroll-runtime %s | FileCheck %s
+
+define i32 @pr131465(i1 %x) mustprogress {
+; CHECK-LABEL: define i32 @pr131465(
+; CHECK-SAME: i1 [[X:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    [[INC:%.*]] = zext i1 [[X]] to i32
+; CHECK-NEXT:    br label %[[FOR_BODY:.*]]
+; CHECK:       [[FOR_BODY]]:
+; CHECK-NEXT:    [[INDVAR:%.*]] = phi i32 [ 2, %[[ENTRY]] ], [ [[NEXT_1:%.*]], %[[FOR_BODY_1:.*]] ]
+; CHECK-NEXT:    [[NEXT:%.*]] = add nsw i32 [[INDVAR]], [[INC]]
+; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[NEXT]], 2
+; CHECK-NEXT:    br i1 [[EXITCOND]], label %[[FOR_END:.*]], label %[[FOR_BODY_1]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       [[FOR_BODY_1]]:
+; CHECK-NEXT:    [[NEXT_1]] = add nsw i32 [[NEXT]], [[INC]]
+; CHECK-NEXT:    [[EXITCOND_1:%.*]] = icmp eq i32 [[NEXT_1]], 2
+; CHECK-NEXT:    br i1 [[EXITCOND_1]], label %[[FOR_END]], label %[[FOR_BODY]], !llvm.loop [[LOOP2:![0-9]+]]
+; CHECK:       [[FOR_END]]:
+; CHECK-NEXT:    ret i32 0
+;
+entry:
+  %inc = zext i1 %x to i32
+  br label %for.body
+
+for.body:
+  %indvar = phi i32 [ 2, %entry ], [ %next, %for.body ]
+  %next = add nsw i32 %indvar, %inc
+  %exitcond = icmp eq i32 %next, 2
+  br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
+
+for.end:
+  ret i32 0
+}
+
+; Force runtime unrolling.
+!0 = !{!0, !{!"llvm.loop.unroll.count", i32 2}}
+;.
+; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]]}
+; CHECK: [[META1]] = !{!"llvm.loop.unroll.count", i32 2}
+; CHECK: [[LOOP2]] = distinct !{[[LOOP2]], [[META3:![0-9]+]]}
+; CHECK: [[META3]] = !{!"llvm.loop.unroll.disable"}
+;.