From e5ff7055beb116f103f030d992fadea49c994511 Mon Sep 17 00:00:00 2001
From: Florian Hahn <flo@fhahn.com>
Date: Tue, 10 Jun 2025 08:29:42 +0100
Subject: [PATCH] [LoopPeel] Use loop guards when checking if last iter can be
 peeled. (#142605)

Apply loop guards to BTC before checking if the last iteration should be
peeled off. This also adds an assert to make sure applying the guards
does not pessimize the results. I checked on a large test set and it did
not trigger there, but it adds an additional guard to catch potential
cases where loop-guards pessimize results.

Peels ~15% more loops.

PR: https://github.com/llvm/llvm-project/pull/142605
---
 llvm/lib/Transforms/Utils/LoopPeel.cpp        |  3 ++
 .../peel-last-iteration-with-guards.ll        | 28 ++++++++++++++++---
 2 files changed, 27 insertions(+), 4 deletions(-)

diff --git a/llvm/lib/Transforms/Utils/LoopPeel.cpp b/llvm/lib/Transforms/Utils/LoopPeel.cpp
index 9149f71941db..f34396254825 100644
--- a/llvm/lib/Transforms/Utils/LoopPeel.cpp
+++ b/llvm/lib/Transforms/Utils/LoopPeel.cpp
@@ -374,6 +374,9 @@ static bool shouldPeelLastIteration(Loop &L, CmpPredicate Pred,
                                    L.getLoopPredecessor()->getTerminator()))
     return false;
 
+  auto Guards = ScalarEvolution::LoopGuards::collect(&L, SE);
+  BTC = SE.applyLoopGuards(BTC, Guards);
+  RightSCEV = SE.applyLoopGuards(RightSCEV, Guards);
   const SCEV *ValAtLastIter = LeftAR->evaluateAtIteration(BTC, SE);
   const SCEV *ValAtSecondToLastIter = LeftAR->evaluateAtIteration(
       SE.getMinusSCEV(BTC, SE.getOne(BTC->getType())), SE);
diff --git a/llvm/test/Transforms/LoopUnroll/peel-last-iteration-with-guards.ll b/llvm/test/Transforms/LoopUnroll/peel-last-iteration-with-guards.ll
index af07a9713132..824e23fcf3e6 100644
--- a/llvm/test/Transforms/LoopUnroll/peel-last-iteration-with-guards.ll
+++ b/llvm/test/Transforms/LoopUnroll/peel-last-iteration-with-guards.ll
@@ -13,14 +13,33 @@ define void @peel_with_guard_known_nonnegative_1(i32 %n) {
 ; CHECK-NEXT:    [[N_EXT:%.*]] = zext i32 [[N]] to i64
 ; CHECK-NEXT:    [[N_1:%.*]] = add i32 [[N]], 1
 ; CHECK-NEXT:    [[WIDE_TRIP_COUNT:%.*]] = zext i32 [[N_1]] to i64
+; CHECK-NEXT:    [[TMP0:%.*]] = add nsw i64 [[WIDE_TRIP_COUNT]], -1
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ne i64 [[TMP0]], 0
+; CHECK-NEXT:    br i1 [[TMP1]], label %[[PH_SPLIT:.*]], label %[[EXIT_LOOPEXIT_PEEL_BEGIN:.*]]
+; CHECK:       [[PH_SPLIT]]:
 ; CHECK-NEXT:    br label %[[LOOP:.*]]
 ; CHECK:       [[LOOP]]:
-; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, %[[PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[IV1:%.*]] = phi i64 [ 0, %[[PH_SPLIT]] ], [ [[IV_NEXT1:%.*]], %[[LOOP]] ]
+; CHECK-NEXT:    [[IV_NEXT1]] = add nuw nsw i64 [[IV1]], 1
+; CHECK-NEXT:    [[TMP2:%.*]] = sub i64 [[WIDE_TRIP_COUNT]], 1
+; CHECK-NEXT:    [[EC1:%.*]] = icmp eq i64 [[IV_NEXT1]], [[TMP2]]
+; CHECK-NEXT:    br i1 [[EC1]], label %[[EXIT_LOOPEXIT_PEEL_BEGIN_LOOPEXIT:.*]], label %[[LOOP]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK:       [[EXIT_LOOPEXIT_PEEL_BEGIN_LOOPEXIT]]:
+; CHECK-NEXT:    [[DOTPH:%.*]] = phi i64 [ [[IV_NEXT1]], %[[LOOP]] ]
+; CHECK-NEXT:    br label %[[EXIT_LOOPEXIT_PEEL_BEGIN]]
+; CHECK:       [[EXIT_LOOPEXIT_PEEL_BEGIN]]:
+; CHECK-NEXT:    [[IV:%.*]] = phi i64 [ 0, %[[PH]] ], [ [[DOTPH]], %[[EXIT_LOOPEXIT_PEEL_BEGIN_LOOPEXIT]] ]
+; CHECK-NEXT:    br label %[[LOOP_PEEL:.*]]
+; CHECK:       [[LOOP_PEEL]]:
 ; CHECK-NEXT:    [[C:%.*]] = icmp eq i64 [[IV]], [[N_EXT]]
 ; CHECK-NEXT:    [[SPEC_SELECT:%.*]] = select i1 [[C]], i32 10, i32 20
-; CHECK-NEXT:    [[IV_NEXT]] = add i64 [[IV]], 1
+; CHECK-NEXT:    [[IV_NEXT:%.*]] = add i64 [[IV]], 1
 ; CHECK-NEXT:    [[EC:%.*]] = icmp eq i64 [[IV_NEXT]], [[WIDE_TRIP_COUNT]]
-; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT_LOOPEXIT:.*]], label %[[LOOP]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT_LOOPEXIT_PEEL_NEXT:.*]], label %[[EXIT_LOOPEXIT_PEEL_NEXT]]
+; CHECK:       [[EXIT_LOOPEXIT_PEEL_NEXT]]:
+; CHECK-NEXT:    br label %[[LOOP_PEEL_NEXT:.*]]
+; CHECK:       [[LOOP_PEEL_NEXT]]:
+; CHECK-NEXT:    br label %[[EXIT_LOOPEXIT:.*]]
 ; CHECK:       [[EXIT_LOOPEXIT]]:
 ; CHECK-NEXT:    br label %[[EXIT]]
 ; CHECK:       [[EXIT]]:
@@ -137,7 +156,7 @@ define void @peel_with_guard2(i32 %n) {
 ; CHECK-NEXT:    [[IV_NEXT]] = add nuw i32 [[IV]], 1
 ; CHECK-NEXT:    [[TMP2:%.*]] = sub i32 [[N]], 1
 ; CHECK-NEXT:    [[EC:%.*]] = icmp eq i32 [[IV_NEXT]], [[TMP2]]
-; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT_LOOPEXIT_PEEL_BEGIN_LOOPEXIT:.*]], label %[[LOOP_HEADER]], !llvm.loop [[LOOP0:![0-9]+]]
+; CHECK-NEXT:    br i1 [[EC]], label %[[EXIT_LOOPEXIT_PEEL_BEGIN_LOOPEXIT:.*]], label %[[LOOP_HEADER]], !llvm.loop [[LOOP2:![0-9]+]]
 ; CHECK:       [[EXIT_LOOPEXIT_PEEL_BEGIN_LOOPEXIT]]:
 ; CHECK-NEXT:    [[DOTPH:%.*]] = phi i32 [ [[IV_NEXT]], %[[LOOP_LATCH]] ]
 ; CHECK-NEXT:    br label %[[EXIT_LOOPEXIT_PEEL_BEGIN]]
@@ -188,4 +207,5 @@ exit:
 ;.
 ; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]]}
 ; CHECK: [[META1]] = !{!"llvm.loop.peeled.count", i32 1}
+; CHECK: [[LOOP2]] = distinct !{[[LOOP2]], [[META1]]}
 ;.