[SimpleLoopUnswitch] Canonicalize conditions for injection of invariant condition

[mkazantsev]

Summary

When loop condition isn't immediately in the form supported by invariant injection
unswitching, try to canonicalize it to this form.

[skatkov]

The patch itself seems straightforward. LGTM.

llvm/test/Transforms/SimpleLoopUnswitch/inject-invariant-conditions.ll

193

This seems unlikely profitable... Why not max from -2147483648 and [[LEN]]?

Or do I miss anything?

[skatkov]

llvm/test/Transforms/SimpleLoopUnswitch/inject-invariant-conditions.ll

193

min I meant.

[mkazantsev]

llvm/test/Transforms/SimpleLoopUnswitch/inject-invariant-conditions.ll

193

It's just a confusing name, I'll rename it. In fact, it is profitable when len <s 0. If you look at test_04 which is the aim of this whole thing, it should make it more clear.

llvm/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp

if (auto Info = hasPartialIVCondition(L, MSSAThreshold, *MSSA, AA)) {
       llvm::append_range(ValsToDuplicate, Info->InstToDuplicate);
       UnswitchCandidates.push_back(
           {L.getHeader()->getTerminator(), std::move(ValsToDuplicate)});
     }
   }
   return !UnswitchCandidates.empty();
 }
 
+/// Tries to canonicalize condition described by:
+///
+///   br (LHS pred RHS), label IfTrue, label IfFalse
+///
+/// into its equivalent where `Pred` is something that we support for injected
+/// invariants (so far it is limited to ult), LHS in canonicalized form is
+/// non-invariant and RHS is an invariant.
+static void canonicalizeForInvariantConditionInjection(
+    ICmpInst::Predicate &Pred, Value *&LHS, Value *&RHS, BasicBlock *&IfTrue,
+    BasicBlock *&IfFalse, const Loop &L) {
+  if (!L.contains(IfTrue)) {
+    Pred = ICmpInst::getInversePredicate(Pred);
+    std::swap(IfTrue, IfFalse);
+  }
+
+  // Move loop-invariant argument to RHS position.
+  if (L.isLoopInvariant(LHS)) {
+    Pred = ICmpInst::getSwappedPredicate(Pred);
+    std::swap(LHS, RHS);
+  }
+
+  if (Pred == ICmpInst::ICMP_SGE && match(RHS, m_Zero())) {
+    // Turn "x >=s 0" into "x <u UMIN_INT"
+    Pred = ICmpInst::ICMP_ULT;
+    RHS = ConstantInt::get(
+        RHS->getContext(),
+        APInt::getSignedMinValue(RHS->getType()->getIntegerBitWidth()));
+  }
+}
+
 /// Returns true, if predicate described by ( \p Pred, \p LHS, \p RHS )
 /// succeeding into blocks ( \p IfTrue, \p IfFalse) can be optimized by
 /// injecting a loop-invariant condition.
 static bool shouldInjectInvariantCondition(const ICmpInst::Predicate Pred,
                                            const Value *LHS, const Value *RHS,
                                            const BasicBlock *IfTrue,
                                            const BasicBlock *IfFalse,
                                            const Loop &L) {
for (auto *DTN = DT.getNode(Latch); L.contains(DTN->getBlock());
     ICmpInst::Predicate Pred;
     Value *LHS = nullptr, *RHS = nullptr;
     BasicBlock *IfTrue = nullptr, *IfFalse = nullptr;
     auto *BB = DTN->getBlock();
     auto *Term = BB->getTerminator();
     if (!match(Term, m_Br(m_ICmp(Pred, m_Value(LHS), m_Value(RHS)),
                           m_BasicBlock(IfTrue), m_BasicBlock(IfFalse))))
       continue;
+    canonicalizeForInvariantConditionInjection(Pred, LHS, RHS, IfTrue, IfFalse,
+                                               L);
     if (!shouldInjectInvariantCondition(Pred, LHS, RHS, IfTrue, IfFalse, L))
       continue;
     if (!shouldInjectBasingOnMetadata(cast<BranchInst>(Term), IfTrue))
       continue;
     CompareDesc Desc(cast<BranchInst>(Term), RHS, IfTrue);
     CandidatesULT[LHS].push_back(Desc);
   }
 

llvm/test/Transforms/SimpleLoopUnswitch/inject-invariant-conditions.ll

 range_check_failed:                               ; preds = %guarded
   ret i32 -2
 }
 
 define i32 @test_02(ptr noundef %p, i32 noundef %n, i32 noundef %limit, ptr noundef %arr, ptr noundef %len_p) {
 ; CHECK-LABEL: @test_02(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[LEN:%.*]] = load i32, ptr [[LEN_P:%.*]], align 4, !noundef !0
-; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK-NEXT:    [[INJECTED_COND:%.*]] = icmp ule i32 -2147483648, [[LEN]]
+; CHECK-NEXT:    br i1 [[INJECTED_COND]], label [[LOOP_US:%.*]], label [[LOOP:%.*]]
+; CHECK:       loop.us:
+; CHECK-NEXT:    [[IV_US:%.*]] = phi i32 [ [[IV_NEXT_US:%.*]], [[GUARDED_US:%.*]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[EL_PTR_US:%.*]] = getelementptr i32, ptr [[P:%.*]], i32 [[IV_US]]
+; CHECK-NEXT:    [[EL_US:%.*]] = load i32, ptr [[EL_PTR_US]], align 4
+; CHECK-NEXT:    [[BOUND_CHECK_US:%.*]] = icmp sge i32 [[EL_US]], 0
+; CHECK-NEXT:    br i1 [[BOUND_CHECK_US]], label [[GUARDED_US]], label [[COMMON_RET:%.*]], !prof [[PROF1]]
+; CHECK:       guarded.us:
+; CHECK-NEXT:    [[RANGE_CHECK_US:%.*]] = icmp ult i32 [[EL_US]], [[LEN]]
+; CHECK-NEXT:    [[ARR_PTR_US:%.*]] = getelementptr i32, ptr [[ARR:%.*]], i32 [[EL_US]]
+; CHECK-NEXT:    store i32 [[IV_US]], ptr [[ARR_PTR_US]], align 4
+; CHECK-NEXT:    [[IV_NEXT_US]] = add i32 [[IV_US]], 1
+; CHECK-NEXT:    [[LOOP_COND_US:%.*]] = icmp slt i32 [[IV_NEXT_US]], [[N:%.*]]
+; CHECK-NEXT:    br i1 [[LOOP_COND_US]], label [[LOOP_US]], label [[COMMON_RET]]
 ; CHECK:       loop:
-; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[BACKEDGE:%.*]] ]
-; CHECK-NEXT:    [[EL_PTR:%.*]] = getelementptr i32, ptr [[P:%.*]], i32 [[IV]]
+; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[IV_NEXT:%.*]], [[BACKEDGE:%.*]] ], [ 0, [[ENTRY]] ]
+; CHECK-NEXT:    [[EL_PTR:%.*]] = getelementptr i32, ptr [[P]], i32 [[IV]]
 ; CHECK-NEXT:    [[EL:%.*]] = load i32, ptr [[EL_PTR]], align 4
 ; CHECK-NEXT:    [[BOUND_CHECK:%.*]] = icmp sge i32 [[EL]], 0
-; CHECK-NEXT:    br i1 [[BOUND_CHECK]], label [[GUARDED:%.*]], label [[COMMON_RET:%.*]], !prof [[PROF1]]
+; CHECK-NEXT:    br i1 [[BOUND_CHECK]], label [[GUARDED:%.*]], label [[COMMON_RET]], !prof [[PROF1]]
 ; CHECK:       guarded:
 ; CHECK-NEXT:    [[RANGE_CHECK:%.*]] = icmp ult i32 [[EL]], [[LEN]]
-; CHECK-NEXT:    br i1 [[RANGE_CHECK]], label [[BACKEDGE]], label [[COMMON_RET]], !prof [[PROF1]]
+; CHECK-NEXT:    br i1 [[RANGE_CHECK]], label [[BACKEDGE]], label [[COMMON_RET]], !llvm.invariant.condition.injection.disabled !0
 ; CHECK:       backedge:
-; CHECK-NEXT:    [[ARR_PTR:%.*]] = getelementptr i32, ptr [[ARR:%.*]], i32 [[EL]]
+; CHECK-NEXT:    [[ARR_PTR:%.*]] = getelementptr i32, ptr [[ARR]], i32 [[EL]]
 ; CHECK-NEXT:    store i32 [[IV]], ptr [[ARR_PTR]], align 4
 ; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1
-; CHECK-NEXT:    [[LOOP_COND:%.*]] = icmp slt i32 [[IV_NEXT]], [[N:%.*]]
+; CHECK-NEXT:    [[LOOP_COND:%.*]] = icmp slt i32 [[IV_NEXT]], [[N]]
 ; CHECK-NEXT:    br i1 [[LOOP_COND]], label [[LOOP]], label [[COMMON_RET]]
 ; CHECK:       common.ret:
-; CHECK-NEXT:    [[COMMON_RET_OP:%.*]] = phi i32 [ 0, [[BACKEDGE]] ], [ -1, [[LOOP]] ], [ -2, [[GUARDED]] ]
+; CHECK-NEXT:    [[COMMON_RET_OP:%.*]] = phi i32 [ 0, [[BACKEDGE]] ], [ 0, [[GUARDED_US]] ], [ -1, [[LOOP]] ], [ -1, [[LOOP_US]] ], [ -2, [[GUARDED]] ]
 ; CHECK-NEXT:    ret i32 [[COMMON_RET_OP]]
 ;
 entry:
   %len = load i32, ptr %len_p, align 4, !noundef !{}
   br label %loop
 
 loop:                                             ; preds = %backedge, %entry
   %iv = phi i32 [ 0, %entry ], [ %iv.next, %backedge ]

 range_check_failed:                               ; preds = %guarded
   ret i32 -2
 }
 
 define i32 @test_03(ptr noundef %p, i32 noundef %n, i32 noundef %limit, ptr noundef %arr, ptr noundef %len_p) {
 ; CHECK-LABEL: @test_03(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[LEN:%.*]] = load i32, ptr [[LEN_P:%.*]], align 4, !noundef !0
-; CHECK-NEXT:    br label [[LOOP:%.*]]
+; CHECK-NEXT:    [[INJECTED_COND:%.*]] = icmp ule i32 -2147483648, [[LEN]]
+; CHECK-NEXT:    br i1 [[INJECTED_COND]], label [[LOOP_US:%.*]], label [[LOOP:%.*]]
+; CHECK:       loop.us:
+; CHECK-NEXT:    [[IV_US:%.*]] = phi i32 [ [[IV_NEXT_US:%.*]], [[GUARDED_US:%.*]] ], [ 0, [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[EL_PTR_US:%.*]] = getelementptr i32, ptr [[P:%.*]], i32 [[IV_US]]
+; CHECK-NEXT:    [[EL_US:%.*]] = load i32, ptr [[EL_PTR_US]], align 4
+; CHECK-NEXT:    [[BOUND_CHECK_US:%.*]] = icmp slt i32 [[EL_US]], 0
+; CHECK-NEXT:    br i1 [[BOUND_CHECK_US]], label [[COMMON_RET:%.*]], label [[GUARDED_US]], !prof [[PROF3:![0-9]+]]
+; CHECK:       guarded.us:
+; CHECK-NEXT:    [[RANGE_CHECK_US:%.*]] = icmp ult i32 [[EL_US]], [[LEN]]
+; CHECK-NEXT:    [[ARR_PTR_US:%.*]] = getelementptr i32, ptr [[ARR:%.*]], i32 [[EL_US]]
+; CHECK-NEXT:    store i32 [[IV_US]], ptr [[ARR_PTR_US]], align 4
+; CHECK-NEXT:    [[IV_NEXT_US]] = add i32 [[IV_US]], 1
+; CHECK-NEXT:    [[LOOP_COND_US:%.*]] = icmp slt i32 [[IV_NEXT_US]], [[N:%.*]]
+; CHECK-NEXT:    br i1 [[LOOP_COND_US]], label [[LOOP_US]], label [[COMMON_RET]]
 ; CHECK:       loop:
-; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[BACKEDGE:%.*]] ]
-; CHECK-NEXT:    [[EL_PTR:%.*]] = getelementptr i32, ptr [[P:%.*]], i32 [[IV]]
+; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[IV_NEXT:%.*]], [[BACKEDGE:%.*]] ], [ 0, [[ENTRY]] ]
+; CHECK-NEXT:    [[EL_PTR:%.*]] = getelementptr i32, ptr [[P]], i32 [[IV]]
 ; CHECK-NEXT:    [[EL:%.*]] = load i32, ptr [[EL_PTR]], align 4
 ; CHECK-NEXT:    [[BOUND_CHECK:%.*]] = icmp slt i32 [[EL]], 0
-; CHECK-NEXT:    br i1 [[BOUND_CHECK]], label [[COMMON_RET:%.*]], label [[GUARDED:%.*]], !prof [[PROF3:![0-9]+]]
+; CHECK-NEXT:    br i1 [[BOUND_CHECK]], label [[COMMON_RET]], label [[GUARDED:%.*]], !prof [[PROF3]]
 ; CHECK:       guarded:
 ; CHECK-NEXT:    [[RANGE_CHECK:%.*]] = icmp ult i32 [[EL]], [[LEN]]
-; CHECK-NEXT:    br i1 [[RANGE_CHECK]], label [[BACKEDGE]], label [[COMMON_RET]], !prof [[PROF1]]
+; CHECK-NEXT:    br i1 [[RANGE_CHECK]], label [[BACKEDGE]], label [[COMMON_RET]], !llvm.invariant.condition.injection.disabled !0
 ; CHECK:       backedge:
-; CHECK-NEXT:    [[ARR_PTR:%.*]] = getelementptr i32, ptr [[ARR:%.*]], i32 [[EL]]
+; CHECK-NEXT:    [[ARR_PTR:%.*]] = getelementptr i32, ptr [[ARR]], i32 [[EL]]
 ; CHECK-NEXT:    store i32 [[IV]], ptr [[ARR_PTR]], align 4
 ; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], 1
-; CHECK-NEXT:    [[LOOP_COND:%.*]] = icmp slt i32 [[IV_NEXT]], [[N:%.*]]
+; CHECK-NEXT:    [[LOOP_COND:%.*]] = icmp slt i32 [[IV_NEXT]], [[N]]
 ; CHECK-NEXT:    br i1 [[LOOP_COND]], label [[LOOP]], label [[COMMON_RET]]
 ; CHECK:       common.ret:
-; CHECK-NEXT:    [[COMMON_RET_OP:%.*]] = phi i32 [ 0, [[BACKEDGE]] ], [ -1, [[LOOP]] ], [ -2, [[GUARDED]] ]
+; CHECK-NEXT:    [[COMMON_RET_OP:%.*]] = phi i32 [ 0, [[BACKEDGE]] ], [ 0, [[GUARDED_US]] ], [ -1, [[LOOP]] ], [ -1, [[LOOP_US]] ], [ -2, [[GUARDED]] ]
 ; CHECK-NEXT:    ret i32 [[COMMON_RET_OP]]
 ;
 entry:
   %len = load i32, ptr %len_p, align 4, !noundef !{}
   br label %loop
 
 loop:                                             ; preds = %backedge, %entry
   %iv = phi i32 [ 0, %entry ], [ %iv.next, %backedge ]