[LSR] Use simplest constant threshold for the moment

Author: preames

llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp

@@ -6813,15 +6813,6 @@ canFoldTermCondOfLoop(Loop *L, ScalarEvolution &SE, DominatorTree &DT,
   if (!isAlmostDeadIV(ToFold, LoopLatch, TermCond))
     return std::nullopt;
 
-  // Inserting instructions in the preheader has a runtime cost, scale
-  // the allowed cost with the loops trip count as best we can.
-  const unsigned ExpansionBudget = [&]() {
-    if (std::optional<unsigned> SmallTC = getLoopEstimatedTripCount(L))
-      return std::min(2*SCEVCheapExpansionBudget, *SmallTC);
-    // Unknown trip count, assume long running by default.
-    return 2*SCEVCheapExpansionBudget;
-  }();
-
   const SCEV *BECount = SE.getBackedgeTakenCount(L);
   const DataLayout &DL = L->getHeader()->getModule()->getDataLayout();
   SCEVExpander Expander(SE, DL, "lsr_fold_term_cond");
@@ -6871,7 +6862,8 @@ canFoldTermCondOfLoop(Loop *L, ScalarEvolution &SE, DominatorTree &DT,
       continue;
     }
 
-    if (Expander.isHighCostExpansion(TermValueSLocal, L, ExpansionBudget,
+    if (Expander.isHighCostExpansion(TermValueSLocal, L,
+                                     2*SCEVCheapExpansionBudget,
                                      &TTI, InsertPt)) {
       LLVM_DEBUG(
           dbgs() << "Is too expensive to expand terminating value for phi node"

llvm/test/Transforms/LoopStrengthReduce/lsr-term-fold.ll

@@ -599,26 +599,15 @@ define void @expensive_expand_unknown_tc2(ptr %a, i32 %offset, i32 %n, i32 %step
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[OFFSET_NONZERO:%.*]] = or i32 [[OFFSET:%.*]], 1
 ; CHECK-NEXT:    [[UGLYGEP:%.*]] = getelementptr i8, ptr [[A:%.*]], i64 84
-; CHECK-NEXT:    [[SMAX:%.*]] = call i32 @llvm.smax.i32(i32 [[STEP:%.*]], i32 [[N:%.*]])
-; CHECK-NEXT:    [[TMP0:%.*]] = sub i32 [[SMAX]], [[STEP]]
-; CHECK-NEXT:    [[UMIN:%.*]] = call i32 @llvm.umin.i32(i32 [[TMP0]], i32 1)
-; CHECK-NEXT:    [[TMP1:%.*]] = sub i32 [[TMP0]], [[UMIN]]
-; CHECK-NEXT:    [[UMAX:%.*]] = call i32 @llvm.umax.i32(i32 [[STEP]], i32 1)
-; CHECK-NEXT:    [[TMP2:%.*]] = udiv i32 [[TMP1]], [[UMAX]]
-; CHECK-NEXT:    [[TMP3:%.*]] = add i32 [[UMIN]], [[TMP2]]
-; CHECK-NEXT:    [[TMP4:%.*]] = zext i32 [[TMP3]] to i64
-; CHECK-NEXT:    [[TMP5:%.*]] = add nuw nsw i64 [[TMP4]], 1
-; CHECK-NEXT:    [[TMP6:%.*]] = sext i32 [[OFFSET_NONZERO]] to i64
-; CHECK-NEXT:    [[TMP7:%.*]] = mul i64 [[TMP5]], [[TMP6]]
-; CHECK-NEXT:    [[TMP8:%.*]] = add nsw i64 [[TMP7]], 84
-; CHECK-NEXT:    [[SCEVGEP:%.*]] = getelementptr i8, ptr [[A]], i64 [[TMP8]]
 ; CHECK-NEXT:    br label [[FOR_BODY:%.*]]
 ; CHECK:       for.body:
 ; CHECK-NEXT:    [[LSR_IV1:%.*]] = phi ptr [ [[UGLYGEP2:%.*]], [[FOR_BODY]] ], [ [[UGLYGEP]], [[ENTRY:%.*]] ]
+; CHECK-NEXT:    [[LSR_IV:%.*]] = phi i32 [ [[LSR_IV_NEXT:%.*]], [[FOR_BODY]] ], [ 0, [[ENTRY]] ]
 ; CHECK-NEXT:    store i32 1, ptr [[LSR_IV1]], align 4
+; CHECK-NEXT:    [[LSR_IV_NEXT]] = add nsw i32 [[LSR_IV]], [[STEP:%.*]]
 ; CHECK-NEXT:    [[UGLYGEP2]] = getelementptr i8, ptr [[LSR_IV1]], i32 [[OFFSET_NONZERO]]
-; CHECK-NEXT:    [[LSR_FOLD_TERM_COND_REPLACED_TERM_COND:%.*]] = icmp eq ptr [[UGLYGEP2]], [[SCEVGEP]]
-; CHECK-NEXT:    br i1 [[LSR_FOLD_TERM_COND_REPLACED_TERM_COND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
+; CHECK-NEXT:    [[EXITCOND_NOT:%.*]] = icmp sge i32 [[LSR_IV_NEXT]], [[N:%.*]]
+; CHECK-NEXT:    br i1 [[EXITCOND_NOT]], label [[FOR_END:%.*]], label [[FOR_BODY]]
 ; CHECK:       for.end:
 ; CHECK-NEXT:    ret void
 ;