diff --git a/llvm/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp b/llvm/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp --- a/llvm/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp +++ b/llvm/lib/Transforms/Scalar/SimpleLoopUnswitch.cpp @@ -796,6 +796,13 @@ if (!ExitL || ExitL->contains(OuterL)) OuterL = ExitL; } + for (unsigned Index : ExitCaseIndices) { + auto CaseI = SI.case_begin() + Index; + // Compute the outer loop from this exit. + Loop *ExitL = LI.getLoopFor(CaseI->getCaseSuccessor()); + if (!ExitL || ExitL->contains(OuterL)) + OuterL = ExitL; + } if (SE) { if (OuterL) @@ -821,10 +828,6 @@ // and don't disrupt the earlier indices. for (unsigned Index : reverse(ExitCaseIndices)) { auto CaseI = SI.case_begin() + Index; - // Compute the outer loop from this exit. - Loop *ExitL = LI.getLoopFor(CaseI->getCaseSuccessor()); - if (!ExitL || ExitL->contains(OuterL)) - OuterL = ExitL; // Save the value of this case. auto W = SIW.getSuccessorWeight(CaseI->getSuccessorIndex()); ExitCases.emplace_back(CaseI->getCaseValue(), CaseI->getCaseSuccessor(), W); diff --git a/llvm/test/Transforms/SimpleLoopUnswitch/update-scev-2.ll b/llvm/test/Transforms/SimpleLoopUnswitch/update-scev-2.ll new file mode 100644 --- /dev/null +++ b/llvm/test/Transforms/SimpleLoopUnswitch/update-scev-2.ll @@ -0,0 +1,75 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2 +; RUN: opt < %s -passes='print,simple-loop-unswitch,print' -disable-output 2>&1 | FileCheck -check-prefix CHECK-SCEV %s +; RUN: opt < %s -passes='function(loop-deletion,simple-loop-unswitch),verify' -S | FileCheck -check-prefix CHECK-IR %s + +; These tests used to hit an assertion failure in llvm::ScalarEvolution::BackedgeTakenInfo::getExact: +; "We should only have known counts for exiting blocks that dominate latch!"' failed. +; +; Verify that we no longer hit that assert, while we expect to have forgotten SCEV for the outer loop. +; Also added checks to show and verify the IR transformation. + + +; Before the unswitch: +; +; CHECK-SCEV: Classifying expressions for: @f4 +; CHECK-SCEV-NEXT: %j.0 = phi i16 [ 0, %entry ], [ %0, %sw.bb2 ] +; CHECK-SCEV-NEXT: --> {0,+,1}<%lbl1> U: [0,3) S: [0,3) Exits: 2 LoopDispositions: { %lbl1: Computable, %lbl2: Invariant } +; CHECK-SCEV-NEXT: %0 = add i16 %j.0, 1 +; CHECK-SCEV-NEXT: --> {1,+,1}<%lbl1> U: [1,4) S: [1,4) Exits: 3 LoopDispositions: { %lbl1: Computable, %lbl2: Invariant } +; CHECK-SCEV-DAG: Loop %lbl2: Unpredictable backedge-taken count. +; CHECK-SCEV-DAG: Loop %lbl1: backedge-taken count is 2 +; +; After the unswitch: +; +; CHECK-SCEV: Classifying expressions for: @f4 +; CHECK-SCEV-NEXT: %j.0 = phi i16 [ 0, %entry ], [ %0, %sw.bb2 ] +; CHECK-SCEV-NEXT: --> {0,+,1}<%lbl1> U: [0,-32768) S: [0,-32768) Exits: <> LoopDispositions: { %lbl1: Computable } +; CHECK-SCEV-NEXT: %0 = add i16 %j.0, 1 +; CHECK-SCEV-NEXT: --> {1,+,1}<%lbl1> U: [1,-32768) S: [1,-32768) Exits: <> LoopDispositions: { %lbl1: Computable } +; CHECK-SCEV-DAG: Loop %lbl1: Unpredictable backedge-taken count. +; CHECK-SCEV-DAG: Loop %lbl2: Unpredictable backedge-taken count. + + +define i16 @f4() { +; CHECK-IR-LABEL: define i16 @f4() { +; CHECK-IR-NEXT: entry: +; CHECK-IR-NEXT: br label [[LBL1:%.*]] +; CHECK-IR: lbl1: +; CHECK-IR-NEXT: [[J_0:%.*]] = phi i16 [ 0, [[ENTRY:%.*]] ], [ [[TMP0:%.*]], [[SW_BB2:%.*]] ] +; CHECK-IR-NEXT: switch i16 [[J_0]], label [[LBL1_SPLIT:%.*]] [ +; CHECK-IR-NEXT: i16 0, label [[SW_BB2]] +; CHECK-IR-NEXT: i16 1, label [[SW_BB2]] +; CHECK-IR-NEXT: i16 2, label [[LBL3:%.*]] +; CHECK-IR-NEXT: ] +; CHECK-IR: lbl1.split: +; CHECK-IR-NEXT: br label [[LBL2:%.*]] +; CHECK-IR: lbl2: +; CHECK-IR-NEXT: br label [[LBL2]] +; CHECK-IR: sw.bb2: +; CHECK-IR-NEXT: [[TMP0]] = add i16 [[J_0]], 1 +; CHECK-IR-NEXT: br label [[LBL1]] +; CHECK-IR: lbl3: +; CHECK-IR-NEXT: ret i16 0 +; +entry: + br label %lbl1 + +lbl1: ; preds = %sw.bb2, %entry + %j.0 = phi i16 [ 0, %entry ], [ %0, %sw.bb2 ] + br label %lbl2 + +lbl2: ; preds = %lbl2, %lbl1 + switch i16 %j.0, label %lbl2 [ + i16 0, label %sw.bb2 + i16 1, label %sw.bb2 + i16 2, label %lbl3 + ] + +sw.bb2: ; preds = %lbl2, %lbl2 + %0 = add i16 %j.0, 1 + br label %lbl1 + +lbl3: ; preds = %lbl2 + ret i16 0 +} +