target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
-; TODO: Make sure the loop is vectorized under -Os without folding its tail based on
+; Make sure the loop is vectorized under -Os without folding its tail based on
; its trip-count's lower bits assumed to be zero.
define dso_local void @assumeAlignedTC(i32* noalias nocapture %A, i32* %p) optsize {
; CHECK-NEXT: [[AND:%.*]] = and i32 [[N]], 3
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i32 [[AND]], 0
; CHECK-NEXT: tail call void @llvm.assume(i1 [[CMP]])
-; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
+; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
+; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
-; CHECK-NEXT: [[N_RND_UP:%.*]] = add i32 [[N]], 3
-; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], 4
-; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]]
-; CHECK-NEXT: [[TRIP_COUNT_MINUS_1:%.*]] = sub i32 [[N]], 1
-; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[TRIP_COUNT_MINUS_1]], i32 0
-; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[N]], 4
+; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
-; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[PRED_STORE_CONTINUE6:%.*]] ]
-; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[PRED_STORE_CONTINUE6]] ]
-; CHECK-NEXT: [[TMP0:%.*]] = icmp ule <4 x i32> [[VEC_IND]], [[BROADCAST_SPLAT]]
-; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i32 0
-; CHECK-NEXT: br i1 [[TMP1]], label [[PRED_STORE_IF:%.*]], label [[PRED_STORE_CONTINUE:%.*]]
-; CHECK: pred.store.if:
-; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[INDEX]], 0
-; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[TMP2]]
-; CHECK-NEXT: store i32 13, i32* [[TMP3]], align 1
-; CHECK-NEXT: br label [[PRED_STORE_CONTINUE]]
-; CHECK: pred.store.continue:
-; CHECK-NEXT: [[TMP4:%.*]] = extractelement <4 x i1> [[TMP0]], i32 1
-; CHECK-NEXT: br i1 [[TMP4]], label [[PRED_STORE_IF1:%.*]], label [[PRED_STORE_CONTINUE2:%.*]]
-; CHECK: pred.store.if1:
-; CHECK-NEXT: [[TMP5:%.*]] = add i32 [[INDEX]], 1
-; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[TMP5]]
-; CHECK-NEXT: store i32 13, i32* [[TMP6]], align 1
-; CHECK-NEXT: br label [[PRED_STORE_CONTINUE2]]
-; CHECK: pred.store.continue2:
-; CHECK-NEXT: [[TMP7:%.*]] = extractelement <4 x i1> [[TMP0]], i32 2
-; CHECK-NEXT: br i1 [[TMP7]], label [[PRED_STORE_IF3:%.*]], label [[PRED_STORE_CONTINUE4:%.*]]
-; CHECK: pred.store.if3:
-; CHECK-NEXT: [[TMP8:%.*]] = add i32 [[INDEX]], 2
-; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[TMP8]]
-; CHECK-NEXT: store i32 13, i32* [[TMP9]], align 1
-; CHECK-NEXT: br label [[PRED_STORE_CONTINUE4]]
-; CHECK: pred.store.continue4:
-; CHECK-NEXT: [[TMP10:%.*]] = extractelement <4 x i1> [[TMP0]], i32 3
-; CHECK-NEXT: br i1 [[TMP10]], label [[PRED_STORE_IF5:%.*]], label [[PRED_STORE_CONTINUE6]]
-; CHECK: pred.store.if5:
-; CHECK-NEXT: [[TMP11:%.*]] = add i32 [[INDEX]], 3
-; CHECK-NEXT: [[TMP12:%.*]] = getelementptr inbounds i32, i32* [[A]], i32 [[TMP11]]
-; CHECK-NEXT: store i32 13, i32* [[TMP12]], align 1
-; CHECK-NEXT: br label [[PRED_STORE_CONTINUE6]]
-; CHECK: pred.store.continue6:
+; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[INDEX]], i32 0
+; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
+; CHECK-NEXT: [[INDUCTION:%.*]] = add <4 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
+; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[TMP0]]
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i32 0
+; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32* [[TMP2]] to <4 x i32>*
+; CHECK-NEXT: store <4 x i32> <i32 13, i32 13, i32 13, i32 13>, <4 x i32>* [[TMP3]], align 1
; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4
-; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], <i32 4, i32 4, i32 4, i32 4>
-; CHECK-NEXT: [[TMP13:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
-; CHECK-NEXT: br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
+; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], [[LOOP0:!llvm.loop !.*]]
; CHECK: middle.block:
-; CHECK-NEXT: br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
+; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
+; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]