[SCEV] Make isLoopEntryGuardedByCond a bit smarter

Sometimes `isLoopEntryGuardedByCond` cannot prove predicate `a > b` directly.
But it is a common situation when `a >= b` is known from ranges and `a != b` is
known from a dominating condition. Thia patch teaches SCEV to sum these facts
together and prove strict comparison via non-strict one.

Differential Revision: https://reviews.llvm.org/D42835

llvm-svn: 324453

include/llvm/IR/InstrTypes.h

@@ -973,6 +973,19 @@ public:
   /// @brief Return the predicate as if the operands were swapped.
   static Predicate getSwappedPredicate(Predicate pred);
 
+  /// For example, SGT -> SGE, SLT -> SLE, ULT -> ULE, UGT -> UGE.
+  /// @brief Returns the non-strict version of strict comparisons.
+  Predicate getNonStrictPredicate() const {
+    return getNonStrictPredicate(getPredicate());
+  }
+
+  /// This is a static version that you can use without an instruction
+  /// available.
+  /// @returns the non-strict version of comparison provided in \p pred.
+  /// If \p pred is not a strict comparison predicate, returns \p pred.
+  /// @brief Returns the non-strict version of strict comparisons.
+  static Predicate getNonStrictPredicate(Predicate pred);
+
   /// @brief Provide more efficient getOperand methods.
   DECLARE_TRANSPARENT_OPERAND_ACCESSORS(Value);
 

lib/Analysis/ScalarEvolution.cpp

@@ -9073,6 +9073,59 @@ ScalarEvolution::isLoopEntryGuardedByCond(const Loop *L,
   if (isKnownPredicateViaConstantRanges(Pred, LHS, RHS))
     return true;
 
+  // If we cannot prove strict comparison (e.g. a > b), maybe we can prove
+  // the facts (a >= b && a != b) separately. A typical situation is when the
+  // non-strict comparison is known from ranges and non-equality is known from
+  // dominating predicates. If we are proving strict comparison, we always try
+  // to prove non-equality and non-strict comparison separately.
+  auto NonStrictPredicate = ICmpInst::getNonStrictPredicate(Pred);
+  const bool ProvingStrictComparison = (Pred != NonStrictPredicate);
+  bool ProvedNonStrictComparison = false;
+  bool ProvedNonEquality = false;
+
+  if (ProvingStrictComparison) {
+    ProvedNonStrictComparison =
+        isKnownPredicateViaConstantRanges(NonStrictPredicate, LHS, RHS);
+    ProvedNonEquality =
+        isKnownPredicateViaConstantRanges(ICmpInst::ICMP_NE, LHS, RHS);
+    assert((!ProvedNonStrictComparison || !ProvedNonEquality) &&
+           "Why we were unable to prove (Pred, LHS, RHS) via constant ranges?");
+  }
+
+  // Try to prove (Pred, LHS, RHS) using isImpliedViaGuard.
+  auto ProveViaGuard = [&](BasicBlock *Block) {
+    if (isImpliedViaGuard(Block, Pred, LHS, RHS))
+      return true;
+    if (ProvingStrictComparison) {
+      if (!ProvedNonStrictComparison)
+        ProvedNonStrictComparison =
+            isImpliedViaGuard(Block, NonStrictPredicate, LHS, RHS);
+      if (!ProvedNonEquality)
+        ProvedNonEquality =
+            isImpliedViaGuard(Block, ICmpInst::ICMP_NE, LHS, RHS);
+      if (ProvedNonStrictComparison && ProvedNonEquality)
+        return true;
+    }
+    return false;
+  };
+
+  // Try to prove (Pred, LHS, RHS) using isImpliedCond.
+  auto ProveViaCond = [&](Value *Condition, bool Inverse) {
+    if (isImpliedCond(Pred, LHS, RHS, Condition, Inverse))
+      return true;
+    if (ProvingStrictComparison) {
+      if (!ProvedNonStrictComparison)
+        ProvedNonStrictComparison =
+            isImpliedCond(NonStrictPredicate, LHS, RHS, Condition, Inverse);
+      if (!ProvedNonEquality)
+        ProvedNonEquality =
+            isImpliedCond(ICmpInst::ICMP_NE, LHS, RHS, Condition, Inverse);
+      if (ProvedNonStrictComparison && ProvedNonEquality)
+        return true;
+    }
+    return false;
+  };
+
   // Starting at the loop predecessor, climb up the predecessor chain, as long
   // as there are predecessors that can be found that have unique successors
   // leading to the original header.
@@ -9081,7 +9134,7 @@ ScalarEvolution::isLoopEntryGuardedByCond(const Loop *L,
        Pair.first;
        Pair = getPredecessorWithUniqueSuccessorForBB(Pair.first)) {
 
-    if (isImpliedViaGuard(Pair.first, Pred, LHS, RHS))
+    if (ProveViaGuard(Pair.first))
       return true;
 
     BranchInst *LoopEntryPredicate =
@@ -9090,9 +9143,8 @@ ScalarEvolution::isLoopEntryGuardedByCond(const Loop *L,
         LoopEntryPredicate->isUnconditional())
       continue;
 
-    if (isImpliedCond(Pred, LHS, RHS,
+    if (ProveViaCond(LoopEntryPredicate->getCondition(),
-                      LoopEntryPredicate->getCondition(),
+                     LoopEntryPredicate->getSuccessor(0) != Pair.second))
-                      LoopEntryPredicate->getSuccessor(0) != Pair.second))
       return true;
   }
 
@@ -9104,7 +9156,7 @@ ScalarEvolution::isLoopEntryGuardedByCond(const Loop *L,
     if (!DT.dominates(CI, L->getHeader()))
       continue;
 
-    if (isImpliedCond(Pred, LHS, RHS, CI->getArgOperand(0), false))
+    if (ProveViaCond(CI->getArgOperand(0), false))
       return true;
   }
 

lib/IR/Instructions.cpp

@@ -3467,6 +3467,20 @@ CmpInst::Predicate CmpInst::getSwappedPredicate(Predicate pred) {
   }
 }
 
+CmpInst::Predicate CmpInst::getNonStrictPredicate(Predicate pred) {
+  switch (pred) {
+  case ICMP_SGT: return ICMP_SGE;
+  case ICMP_SLT: return ICMP_SLE;
+  case ICMP_UGT: return ICMP_UGE;
+  case ICMP_ULT: return ICMP_ULE;
+  case FCMP_OGT: return FCMP_OGE;
+  case FCMP_OLT: return FCMP_OLE;
+  case FCMP_UGT: return FCMP_UGE;
+  case FCMP_ULT: return FCMP_ULE;
+  default: return pred;
+  }
+}
+
 CmpInst::Predicate CmpInst::getSignedPredicate(Predicate pred) {
   assert(CmpInst::isUnsigned(pred) && "Call only with signed predicates!");
 

test/Transforms/IRCE/conjunctive-checks.ll

@@ -4,10 +4,10 @@ define void @f_0(i32 *%arr, i32 *%a_len_ptr, i32 %n, i1* %cond_buf) {
 ; CHECK-LABEL: @f_0(
 
 ; CHECK: loop.preheader:
-; CHECK: [[not_n:[^ ]+]] = sub i32 -1, %n
 ; CHECK: [[not_safe_range_end:[^ ]+]] = sub i32 3, %len
-; CHECK: [[not_exit_main_loop_at_hiclamp_cmp:[^ ]+]] = icmp sgt i32 [[not_n]], [[not_safe_range_end]]
+; CHECK: [[not_n:[^ ]+]] = sub i32 -1, %n
-; CHECK: [[not_exit_main_loop_at_hiclamp:[^ ]+]] = select i1 [[not_exit_main_loop_at_hiclamp_cmp]], i32 [[not_n]], i32 [[not_safe_range_end]]
+; CHECK: [[not_exit_main_loop_at_hiclamp_cmp:[^ ]+]] = icmp sgt i32 [[not_safe_range_end]], [[not_n]]
+; CHECK: [[not_exit_main_loop_at_hiclamp:[^ ]+]] = select i1 [[not_exit_main_loop_at_hiclamp_cmp]], i32 [[not_safe_range_end]], i32 [[not_n]]
 ; CHECK: [[exit_main_loop_at_hiclamp:[^ ]+]] = sub i32 -1, [[not_exit_main_loop_at_hiclamp]]
 ; CHECK: [[exit_main_loop_at_loclamp_cmp:[^ ]+]] = icmp sgt i32 [[exit_main_loop_at_hiclamp]], 0
 ; CHECK: [[exit_main_loop_at_loclamp:[^ ]+]] = select i1 [[exit_main_loop_at_loclamp_cmp]], i32 [[exit_main_loop_at_hiclamp]], i32 0

test/Transforms/IRCE/decrementing-loop.ll

@@ -1,4 +1,8 @@
-; RUN: opt -verify-loop-info -irce -S < %s | FileCheck %s
+; RUN: opt -verify-loop-info -irce -debug-only=irce -S < %s 2>&1 | FileCheck %s
+
+; CHECK-LABEL: irce: in function decrementing_loop: constrained Loop at depth 1
+; CHECK-LABEL: irce: in function test_01: constrained Loop at depth 1
+; CHECK-LABEL: irce: in function test_02: constrained Loop at depth 1
 
 define void @decrementing_loop(i32 *%arr, i32 *%a_len_ptr, i32 %n) {
  entry:
@@ -38,5 +42,85 @@ define void @decrementing_loop(i32 *%arr, i32 *%a_len_ptr, i32 %n) {
 ; CHECK:   %exit.preloop.at = add i32 [[not_exit_preloop_at]], -1
 }
 
+; Make sure that we can eliminate the range check when the loop looks like:
+; for (i = len.a - 1; i >= 0; --i)
+;   b[i] = a[i];
+define void @test_01(i32* %a, i32* %b, i32* %a_len_ptr, i32* %b_len_ptr) {
+
+; CHECK-LABEL: test_01
+; CHECK:       mainloop:
+; CHECK-NEXT:    br label %loop
+; CHECK:       loop:
+; CHECK:         %rc = and i1 true, true
+; CHECK:       loop.preloop:
+
+ entry:
+  %len.a = load i32, i32* %a_len_ptr, !range !0
+  %len.b = load i32, i32* %b_len_ptr, !range !0
+  %first.itr.check = icmp ne i32 %len.a, 0
+  br i1 %first.itr.check, label %loop, label %exit
+
+ loop:
+  %idx = phi i32 [ %len.a, %entry ] , [ %idx.next, %in.bounds ]
+  %idx.next = sub i32 %idx, 1
+  %rca = icmp ult i32 %idx.next, %len.a
+  %rcb = icmp ult i32 %idx.next, %len.b
+  %rc = and i1 %rca, %rcb
+  br i1 %rc, label %in.bounds, label %out.of.bounds, !prof !1
+
+ in.bounds:
+  %el.a = getelementptr i32, i32* %a, i32 %idx.next
+  %el.b = getelementptr i32, i32* %b, i32 %idx.next
+  %v = load i32, i32* %el.a
+  store i32 %v, i32* %el.b
+  %loop.cond = icmp slt i32 %idx, 2
+  br i1 %loop.cond, label %exit, label %loop
+
+ out.of.bounds:
+  ret void
+
+ exit:
+  ret void
+}
+
+; Same as test_01, but the latch condition is unsigned
+define void @test_02(i32* %a, i32* %b, i32* %a_len_ptr, i32* %b_len_ptr) {
+
+; CHECK-LABEL: test_02
+; CHECK:       mainloop:
+; CHECK-NEXT:    br label %loop
+; CHECK:       loop:
+; CHECK:         %rc = and i1 true, true
+; CHECK:       loop.preloop:
+
+ entry:
+  %len.a = load i32, i32* %a_len_ptr, !range !0
+  %len.b = load i32, i32* %b_len_ptr, !range !0
+  %first.itr.check = icmp ne i32 %len.a, 0
+  br i1 %first.itr.check, label %loop, label %exit
+
+ loop:
+  %idx = phi i32 [ %len.a, %entry ] , [ %idx.next, %in.bounds ]
+  %idx.next = sub i32 %idx, 1
+  %rca = icmp ult i32 %idx.next, %len.a
+  %rcb = icmp ult i32 %idx.next, %len.b
+  %rc = and i1 %rca, %rcb
+  br i1 %rc, label %in.bounds, label %out.of.bounds, !prof !1
+
+ in.bounds:
+  %el.a = getelementptr i32, i32* %a, i32 %idx.next
+  %el.b = getelementptr i32, i32* %b, i32 %idx.next
+  %v = load i32, i32* %el.a
+  store i32 %v, i32* %el.b
+  %loop.cond = icmp ult i32 %idx, 2
+  br i1 %loop.cond, label %exit, label %loop
+
+ out.of.bounds:
+  ret void
+
+ exit:
+  ret void
+}
+
 !0 = !{i32 0, i32 2147483647}
 !1 = !{!"branch_weights", i32 64, i32 4}

test/Transforms/IRCE/single-access-no-preloop.ll

@@ -85,10 +85,10 @@ define void @single_access_no_preloop_with_offset(i32 *%arr, i32 *%a_len_ptr, i3
 ; CHECK-LABEL: @single_access_no_preloop_with_offset(
 
 ; CHECK: loop.preheader:
-; CHECK: [[not_n:[^ ]+]] = sub i32 -1, %n
 ; CHECK: [[not_safe_range_end:[^ ]+]] = sub i32 3, %len
-; CHECK: [[not_exit_main_loop_at_hiclamp_cmp:[^ ]+]] = icmp sgt i32 [[not_n]], [[not_safe_range_end]]
+; CHECK: [[not_n:[^ ]+]] = sub i32 -1, %n
-; CHECK: [[not_exit_main_loop_at_hiclamp:[^ ]+]] = select i1 [[not_exit_main_loop_at_hiclamp_cmp]], i32 [[not_n]], i32 [[not_safe_range_end]]
+; CHECK: [[not_exit_main_loop_at_hiclamp_cmp:[^ ]+]] = icmp sgt i32 [[not_safe_range_end]], [[not_n]]
+; CHECK: [[not_exit_main_loop_at_hiclamp:[^ ]+]] = select i1 [[not_exit_main_loop_at_hiclamp_cmp]], i32 [[not_safe_range_end]], i32 [[not_n]]
 ; CHECK: [[exit_main_loop_at_hiclamp:[^ ]+]] = sub i32 -1, [[not_exit_main_loop_at_hiclamp]]
 ; CHECK: [[exit_main_loop_at_loclamp_cmp:[^ ]+]] = icmp sgt i32 [[exit_main_loop_at_hiclamp]], 0
 ; CHECK: [[exit_main_loop_at_loclamp:[^ ]+]] = select i1 [[exit_main_loop_at_loclamp_cmp]], i32 [[exit_main_loop_at_hiclamp]], i32 0

test/Transforms/IndVarSimplify/loop-invariant-conditions.ll

@@ -325,6 +325,36 @@ exit:
   ret void
 }
 
+; check that we can figure out that iv.next > 1 from the facts that iv >= 0 and
+; iv.start != 0.
+define void @test11(i64* %inc_ptr) {
+; CHECK-LABEL: @test11
+entry:
+  %inc = load i64, i64* %inc_ptr, !range !0
+  %ne.cond = icmp ne i64 %inc, 0
+  br i1 %ne.cond, label %loop, label %exit
+
+loop:
+  %iv = phi i64 [ %inc, %entry ], [ %iv.next, %backedge ]
+  %iv.next = add i64 %iv, 1
+  %brcond = icmp sgt i64 %iv.next, 1
+  ; CHECK: br i1 true, label %if.true, label %if.false
+  br i1 %brcond, label %if.true, label %if.false
+
+if.true:
+  br label %backedge
+
+if.false:
+  br label %backedge
+
+backedge:
+  %loopcond = icmp slt i64 %iv, 200
+  br i1 %loopcond, label %loop, label %exit
+
+exit:
+  ret void
+}
+
 !1 = !{i64 -1, i64 100}