[LV] Use SCEV to check if minimum iteration check is known. (#111310)

fhahn · web-flow · commit c7496cebac04 · 2024-10-18T15:22:59.000-07:00
Use SCEV to check if the minimum iteration check (TC < Step) is known to be false. This is a first step towards addressing #111098. To catch the exact case from the issue, we need to do extra work to make sure the wrap flags on the shl are preserved and used by SCEV. Note that skeleton creation will be gradually moved to VPlan and this simplification should be done as VPlan transform eventually. The current plan is to move skeleton creation to VPlan starting from parts closest to the parts already created by VPlan, starting with induction resume value creation (started with #110577), then memory and SCEV checks and finally minimum iteration checks. PR: #111310
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -2447,12 +2447,26 @@ void InnerLoopVectorizer::emitIterationCountCheck(BasicBlock *Bypass) {
   };
 
   TailFoldingStyle Style = Cost->getTailFoldingStyle();
-  if (Style == TailFoldingStyle::None)
-    CheckMinIters =
-        Builder.CreateICmp(P, Count, CreateStep(), "min.iters.check");
-  else if (VF.isScalable() &&
-           !isIndvarOverflowCheckKnownFalse(Cost, VF, UF) &&
-           Style != TailFoldingStyle::DataAndControlFlowWithoutRuntimeCheck) {
+  if (Style == TailFoldingStyle::None) {
+    Value *Step = CreateStep();
+    ScalarEvolution &SE = *PSE.getSE();
+    // TODO: Emit unconditional branch to vector preheader instead of
+    // conditional branch with known condition.
+    const SCEV *TripCountSCEV = SE.applyLoopGuards(SE.getSCEV(Count), OrigLoop);
+    // Check if the trip count is < the step.
+    if (SE.isKnownPredicate(P, TripCountSCEV, SE.getSCEV(Step))) {
+      // TODO: Ensure step is at most the trip count when determining max VF and
+      // UF, w/o tail folding.
+      CheckMinIters = Builder.getTrue();
+    } else if (!SE.isKnownPredicate(CmpInst::getInversePredicate(P),
+                                    TripCountSCEV, SE.getSCEV(Step))) {
+      // Generate the minimum iteration check only if we cannot prove the
+      // check is known to be true, or known to be false.
+      CheckMinIters = Builder.CreateICmp(P, Count, Step, "min.iters.check");
+    } // else step known to be < trip count, use CheckMinIters preset to false.
+  } else if (VF.isScalable() &&
+             !isIndvarOverflowCheckKnownFalse(Cost, VF, UF) &&
+             Style != TailFoldingStyle::DataAndControlFlowWithoutRuntimeCheck) {
     // vscale is not necessarily a power-of-2, which means we cannot guarantee
     // an overflow to zero when updating induction variables and so an
     // additional overflow check is required before entering the vector loop.
@@ -2462,8 +2476,18 @@ void InnerLoopVectorizer::emitIterationCountCheck(BasicBlock *Bypass) {
         ConstantInt::get(CountTy, cast<IntegerType>(CountTy)->getMask());
     Value *LHS = Builder.CreateSub(MaxUIntTripCount, Count);
 
+    Value *Step = CreateStep();
+#ifndef NDEBUG
+    ScalarEvolution &SE = *PSE.getSE();
+    const SCEV *TC2OverflowSCEV = SE.applyLoopGuards(SE.getSCEV(LHS), OrigLoop);
+    assert(
+        !isIndvarOverflowCheckKnownFalse(Cost, VF * UF) &&
+        !SE.isKnownPredicate(CmpInst::getInversePredicate(ICmpInst::ICMP_ULT),
+                             TC2OverflowSCEV, SE.getSCEV(Step)) &&
+        "unexpectedly proved overflow check to be known");
+#endif
     // Don't execute the vector loop if (UMax - n) < (VF * UF).
-    CheckMinIters = Builder.CreateICmp(ICmpInst::ICMP_ULT, LHS, CreateStep());
+    CheckMinIters = Builder.CreateICmp(ICmpInst::ICMP_ULT, LHS, Step);
   }
 
   // Create new preheader for vector loop.
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/eliminate-tail-predication.ll b/llvm/test/Transforms/LoopVectorize/AArch64/eliminate-tail-predication.ll
@@ -11,8 +11,7 @@ define void @f1(ptr %A) #0 {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll b/llvm/test/Transforms/LoopVectorize/AArch64/masked-call.ll
@@ -11,10 +11,7 @@ target triple = "aarch64-unknown-linux-gnu"
 define void @test_widen(ptr noalias %a, ptr readnone %b) #4 {
 ; TFNONE-LABEL: @test_widen(
 ; TFNONE-NEXT:  entry:
-; TFNONE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFNONE-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFNONE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1025, [[TMP1]]
-; TFNONE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFNONE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; TFNONE:       vector.ph:
 ; TFNONE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; TFNONE-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
@@ -146,10 +143,7 @@ for.cond.cleanup:
 define void @test_if_then(ptr noalias %a, ptr readnone %b) #4 {
 ; TFNONE-LABEL: @test_if_then(
 ; TFNONE-NEXT:  entry:
-; TFNONE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFNONE-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFNONE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1025, [[TMP1]]
-; TFNONE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFNONE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; TFNONE:       vector.ph:
 ; TFNONE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; TFNONE-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
@@ -310,10 +304,7 @@ for.cond.cleanup:
 define void @test_widen_if_then_else(ptr noalias %a, ptr readnone %b) #4 {
 ; TFNONE-LABEL: @test_widen_if_then_else(
 ; TFNONE-NEXT:  entry:
-; TFNONE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFNONE-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFNONE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1025, [[TMP1]]
-; TFNONE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFNONE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; TFNONE:       vector.ph:
 ; TFNONE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; TFNONE-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
@@ -490,10 +481,7 @@ for.cond.cleanup:
 define void @test_widen_nomask(ptr noalias %a, ptr readnone %b) #4 {
 ; TFNONE-LABEL: @test_widen_nomask(
 ; TFNONE-NEXT:  entry:
-; TFNONE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFNONE-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFNONE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1025, [[TMP1]]
-; TFNONE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFNONE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; TFNONE:       vector.ph:
 ; TFNONE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; TFNONE-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
@@ -548,11 +536,6 @@ define void @test_widen_nomask(ptr noalias %a, ptr readnone %b) #4 {
 ;
 ; TFFALLBACK-LABEL: @test_widen_nomask(
 ; TFFALLBACK-NEXT:  entry:
-; TFFALLBACK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFFALLBACK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFFALLBACK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1025, [[TMP1]]
-; TFFALLBACK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
-; TFFALLBACK:       vector.ph:
 ; TFFALLBACK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; TFFALLBACK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
 ; TFFALLBACK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 1025, [[TMP3]]
@@ -561,20 +544,17 @@ define void @test_widen_nomask(ptr noalias %a, ptr readnone %b) #4 {
 ; TFFALLBACK-NEXT:    [[TMP5:%.*]] = mul i64 [[TMP4]], 2
 ; TFFALLBACK-NEXT:    br label [[VECTOR_BODY:%.*]]
 ; TFFALLBACK:       vector.body:
-; TFFALLBACK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; TFFALLBACK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
 ; TFFALLBACK-NEXT:    [[TMP6:%.*]] = getelementptr i64, ptr [[B:%.*]], i64 [[INDEX]]
 ; TFFALLBACK-NEXT:    [[WIDE_LOAD:%.*]] = load <vscale x 2 x i64>, ptr [[TMP6]], align 8
 ; TFFALLBACK-NEXT:    [[TMP7:%.*]] = call <vscale x 2 x i64> @foo_vector_nomask(<vscale x 2 x i64> [[WIDE_LOAD]])
 ; TFFALLBACK-NEXT:    [[TMP8:%.*]] = getelementptr inbounds i64, ptr [[A:%.*]], i64 [[INDEX]]
 ; TFFALLBACK-NEXT:    store <vscale x 2 x i64> [[TMP7]], ptr [[TMP8]], align 8
 ; TFFALLBACK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], [[TMP5]]
 ; TFFALLBACK-NEXT:    [[TMP9:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
-; TFFALLBACK-NEXT:    br i1 [[TMP9]], label [[SCALAR_PH]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
-; TFFALLBACK:       scalar.ph:
-; TFFALLBACK-NEXT:    [[BC_RESUME_VAL:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[N_VEC]], [[VECTOR_BODY]] ]
-; TFFALLBACK-NEXT:    br label [[FOR_BODY:%.*]]
+; TFFALLBACK-NEXT:    br i1 [[TMP9]], label [[FOR_BODY:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
 ; TFFALLBACK:       for.body:
-; TFFALLBACK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
+; TFFALLBACK-NEXT:    [[INDVARS_IV:%.*]] = phi i64 [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ], [ [[N_VEC]], [[VECTOR_BODY]] ]
 ; TFFALLBACK-NEXT:    [[GEP:%.*]] = getelementptr i64, ptr [[B]], i64 [[INDVARS_IV]]
 ; TFFALLBACK-NEXT:    [[LOAD:%.*]] = load i64, ptr [[GEP]], align 8
 ; TFFALLBACK-NEXT:    [[CALL:%.*]] = call i64 @foo(i64 [[LOAD]]) #[[ATTR5:[0-9]+]]
@@ -626,10 +606,7 @@ for.cond.cleanup:
 define void @test_widen_optmask(ptr noalias %a, ptr readnone %b) #4 {
 ; TFNONE-LABEL: @test_widen_optmask(
 ; TFNONE-NEXT:  entry:
-; TFNONE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFNONE-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFNONE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1025, [[TMP1]]
-; TFNONE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFNONE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; TFNONE:       vector.ph:
 ; TFNONE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; TFNONE-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
@@ -791,10 +768,7 @@ for.cond.cleanup:
 define double @test_widen_fmuladd_and_call(ptr noalias %a, ptr readnone %b, double %m) #4 {
 ; TFNONE-LABEL: @test_widen_fmuladd_and_call(
 ; TFNONE-NEXT:  entry:
-; TFNONE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; TFNONE-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 2
-; TFNONE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1025, [[TMP1]]
-; TFNONE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; TFNONE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; TFNONE:       vector.ph:
 ; TFNONE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; TFNONE-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 2
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/pr60831-sve-inv-store-crash.ll b/llvm/test/Transforms/LoopVectorize/AArch64/pr60831-sve-inv-store-crash.ll
@@ -10,8 +10,7 @@ define void @test_invar_gep(ptr %dst) #0 {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 100, [[TMP1]]
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll b/llvm/test/Transforms/LoopVectorize/AArch64/sve-tail-folding.ll
@@ -757,8 +757,7 @@ define void @simple_memset_trip1024(i32 %val, ptr %ptr, i64 %n) #0 {
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1024, [[TMP1]]
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; CHECK:       vector.ph:
 ; CHECK-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; CHECK-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/wider-VF-for-callinst.ll b/llvm/test/Transforms/LoopVectorize/AArch64/wider-VF-for-callinst.ll
@@ -7,10 +7,7 @@ target triple = "aarch64-unknown-linux-gnu"
 define void @test_widen(ptr noalias %a, ptr readnone %b) #1 {
 ; WIDE-LABEL: @test_widen(
 ; WIDE-NEXT:  entry:
-; WIDE-NEXT:    [[TMP0:%.*]] = call i64 @llvm.vscale.i64()
-; WIDE-NEXT:    [[TMP1:%.*]] = mul i64 [[TMP0]], 4
-; WIDE-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 1025, [[TMP1]]
-; WIDE-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; WIDE-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
 ; WIDE:       vector.ph:
 ; WIDE-NEXT:    [[TMP2:%.*]] = call i64 @llvm.vscale.i64()
 ; WIDE-NEXT:    [[TMP3:%.*]] = mul i64 [[TMP2]], 4
diff --git a/llvm/test/Transforms/LoopVectorize/if-reduction.ll b/llvm/test/Transforms/LoopVectorize/if-reduction.ll
@@ -1659,6 +1659,7 @@ for.end:                                          ; preds = %for.body, %entry
   ret i64 %1
 }
 
+; FIXME: %indvars.iv.next is poison on first iteration due to sub nuw 0, 1.
 define i32 @fcmp_0_sub_select1(ptr noalias %x, i32 %N) nounwind readonly {
 ; CHECK-LABEL: define i32 @fcmp_0_sub_select1(
 ; CHECK-SAME: ptr noalias [[X:%.*]], i32 [[N:%.*]]) #[[ATTR0]] {
@@ -1668,8 +1669,7 @@ define i32 @fcmp_0_sub_select1(ptr noalias %x, i32 %N) nounwind readonly {
 ; CHECK:       [[FOR_HEADER]]:
 ; CHECK-NEXT:    [[ZEXT:%.*]] = zext i32 [[N]] to i64
 ; CHECK-NEXT:    [[TMP0:%.*]] = sub i64 0, [[ZEXT]]
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP0]], 4
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
+; CHECK-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
 ; CHECK:       [[VECTOR_PH]]:
 ; CHECK-NEXT:    [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 4
 ; CHECK-NEXT:    [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
diff --git a/llvm/test/Transforms/LoopVectorize/version-stride-with-integer-casts.ll b/llvm/test/Transforms/LoopVectorize/version-stride-with-integer-casts.ll
@@ -415,6 +415,7 @@ exit:
 
 ; Test case to make sure that uses of versioned strides of type i1 are properly
 ; extended. From https://github.com/llvm/llvm-project/issues/91369.
+; TODO: Better check (udiv i64 15, %g.64) after checking if %g == 1.
 define void @zext_of_i1_stride(i1 %g, ptr %dst) mustprogress {
 ; CHECK-LABEL: define void @zext_of_i1_stride(
 ; CHECK-SAME: i1 [[G:%.*]], ptr [[DST:%.*]]) #[[ATTR0:[0-9]+]] {
@@ -423,8 +424,7 @@ define void @zext_of_i1_stride(i1 %g, ptr %dst) mustprogress {
 ; CHECK-NEXT:    [[G_64:%.*]] = zext i1 [[G]] to i64
 ; CHECK-NEXT:    [[TMP0:%.*]] = udiv i64 15, [[G_64]]
 ; CHECK-NEXT:    [[TMP1:%.*]] = add nuw nsw i64 [[TMP0]], 1
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP1]], 4
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
+; CHECK-NEXT:    br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
 ; CHECK:       vector.scevcheck:
 ; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i1 [[G]], true
 ; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
@@ -489,8 +489,7 @@ define void @sext_of_i1_stride(i1 %g, ptr %dst) mustprogress {
 ; CHECK-NEXT:    [[TMP0:%.*]] = add i64 [[UMAX]], -1
 ; CHECK-NEXT:    [[TMP1:%.*]] = udiv i64 [[TMP0]], [[G_64]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = add nuw nsw i64 [[TMP1]], 1
-; CHECK-NEXT:    [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[TMP2]], 4
-; CHECK-NEXT:    br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
+; CHECK-NEXT:    br i1 true, label [[SCALAR_PH:%.*]], label [[VECTOR_SCEVCHECK:%.*]]
 ; CHECK:       vector.scevcheck:
 ; CHECK-NEXT:    [[IDENT_CHECK:%.*]] = icmp ne i1 [[G]], true
 ; CHECK-NEXT:    br i1 [[IDENT_CHECK]], label [[SCALAR_PH]], label [[VECTOR_PH:%.*]]
