1 ; RUN: opt < %s -S -passes='print<scalar-evolution>,loop-unroll<peeling;full-unroll-max=0>,print<scalar-evolution>' 2>&1 | FileCheck %s
3 ; This test ensures that (extractvalue 0 (with-overflow-inst op0, op1))
4 ; is invalidated by LoopPeel when the operands of with-overflow-inst
7 ; In the following case, LoopPeel modifies the CFG into another one
8 ; with %bb7 not dominating %bb2 and %bb3 although %extractvalue is
9 ; still the step for the %bb3 loop. %call has been modified and uses
10 ; different operands but the SCEV value for %extractvalue has not been
11 ; invalidated and still refers to %load in its SCEV operands
12 ; (SCEV(%extractvalue) := -2 + -2 * %load).
14 ; When LoopUnroll tries to compute the SCEV for the %bb3 Phi, the
15 ; stale data for %extractvalue is used whereas %load is not available
16 ; in %bb3 which is wrong.
18 ; for more details and nice pictures: https://github.com/llvm/llvm-project/issues/97586
20 ; Although the reason for the bug was in forgetValue, it is still relevant to
21 ; test if LoopPeel invalidates %extractvalue after changing %call.
23 ; forgetValue only walks the users, so calling it on the IV Phis does not
24 ; invalidate %extractvalue (thus forgetLoop does not invalidate it too).
25 ; It has to be done by LoopPeel itself.
28 define void @loop_peeling_smul_with_overflow() {
30 ; CHECK: Classifying expressions for: @loop_peeling_smul_with_overflow
31 ; CHECK: %extractvalue = extractvalue { i32, i1 } %call, 0
32 ; CHECK-NEXT: --> (-2 + (-2 * %load))
33 ; CHECK: %phi4 = phi i32 [ %add, %bb3 ], [ 0, %bb2 ]
34 ; CHECK-NEXT: --> {0,+,(-2 + (-2 * %load))}<nuw><nsw><%bb3>
36 ; CHECK: Classifying expressions for: @loop_peeling_smul_with_overflow
37 ; CHECK: %extractvalue = extractvalue { i32, i1 } %call, 0
38 ; CHECK-NEXT: --> (-2 * %add8.lcssa)
39 ; CHECK: %phi4 = phi i32 [ %add, %bb3 ], [ 0, %bb2 ]
40 ; CHECK-NEXT: --> {0,+,(-2 * %add8.lcssa)}<nuw><nsw><%bb3>
45 bb1: ; preds = %bb3, %bb
46 %phi = phi i32 [ 0, %bb ], [ %phi4, %bb3 ]
50 %call = call { i32, i1 } @llvm.smul.with.overflow.i32(i32 %add8, i32 -2)
51 %extractvalue = extractvalue { i32, i1 } %call, 0
54 bb3: ; preds = %bb3, %bb2
55 %phi4 = phi i32 [ %add, %bb3 ], [ 0, %bb2 ]
56 %add = add i32 %extractvalue, %phi4
57 br i1 false, label %bb3, label %bb1
59 bb5: ; preds = %bb7, %bb1
60 %phi6 = phi i32 [ 1, %bb1 ], [ 0, %bb7 ]
61 %icmp = icmp eq i32 %phi, 0
62 br i1 %icmp, label %bb9, label %bb7
65 %load = load i32, ptr addrspace(1) null, align 4
66 %add8 = add i32 %load, 1
67 br i1 false, label %bb2, label %bb5