rebase

Author: hassnaaHamdi

llvm/test/Transforms/LoopVectorize/AArch64/low_trip_count_predicates.ll

@@ -90,7 +90,7 @@ define void @low_vf_ic_is_better(ptr nocapture noundef %p, i32 %tc, i16 noundef
 ; CHECK-VS1-NEXT:    [[IND_END4:%.*]] = add i64 [[TMP0]], [[N_VEC]]
 ; CHECK-VS1-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 [[TMP3]], [[N_VEC]]
 ; CHECK-VS1-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8
-; CHECK-VS1-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]]
+; CHECK-VS1-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]], !prof [[PROF3:![0-9]+]]
 ; CHECK-VS1:       [[VEC_EPILOG_PH]]:
 ; CHECK-VS1-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
 ; CHECK-VS1-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 [[TMP3]], 8
@@ -184,7 +184,7 @@ define void @low_vf_ic_is_better(ptr nocapture noundef %p, i32 %tc, i16 noundef
 ; CHECK-VS2-NEXT:    [[IND_END4:%.*]] = add i64 [[TMP0]], [[N_VEC]]
 ; CHECK-VS2-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 [[TMP3]], [[N_VEC]]
 ; CHECK-VS2-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8
-; CHECK-VS2-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]]
+; CHECK-VS2-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label %[[VEC_EPILOG_SCALAR_PH]], label %[[VEC_EPILOG_PH]], !prof [[PROF3:![0-9]+]]
 ; CHECK-VS2:       [[VEC_EPILOG_PH]]:
 ; CHECK-VS2-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[VEC_EPILOG_ITER_CHECK]] ], [ 0, %[[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
 ; CHECK-VS2-NEXT:    [[N_MOD_VF2:%.*]] = urem i64 [[TMP3]], 8

llvm/test/Transforms/LoopVectorize/AArch64/store-costs-sve.ll

@@ -38,7 +38,7 @@ define void @cost_store_i8(ptr %dst) #0 {
 ; DEFAULT:       vec.epilog.iter.check:
 ; DEFAULT-NEXT:    [[N_VEC_REMAINING:%.*]] = sub i64 101, [[N_VEC]]
 ; DEFAULT-NEXT:    [[MIN_EPILOG_ITERS_CHECK:%.*]] = icmp ult i64 [[N_VEC_REMAINING]], 8
-; DEFAULT-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]]
+; DEFAULT-NEXT:    br i1 [[MIN_EPILOG_ITERS_CHECK]], label [[VEC_EPILOG_SCALAR_PH]], label [[VEC_EPILOG_PH]], !prof [[PROF3:![0-9]+]]
 ; DEFAULT:       vec.epilog.ph:
 ; DEFAULT-NEXT:    [[VEC_EPILOG_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[VEC_EPILOG_ITER_CHECK]] ], [ 0, [[VECTOR_MAIN_LOOP_ITER_CHECK]] ]
 ; DEFAULT-NEXT:    br label [[VEC_EPILOG_VECTOR_BODY:%.*]]
@@ -48,7 +48,7 @@ define void @cost_store_i8(ptr %dst) #0 {
 ; DEFAULT-NEXT:    store <8 x i8> zeroinitializer, ptr [[TMP19]], align 1
 ; DEFAULT-NEXT:    [[INDEX_NEXT6]] = add nuw i64 [[INDEX5]], 8
 ; DEFAULT-NEXT:    [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT6]], 96
-; DEFAULT-NEXT:    br i1 [[TMP10]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
+; DEFAULT-NEXT:    br i1 [[TMP10]], label [[VEC_EPILOG_MIDDLE_BLOCK:%.*]], label [[VEC_EPILOG_VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
 ; DEFAULT:       vec.epilog.middle.block:
 ; DEFAULT-NEXT:    br i1 false, label [[EXIT]], label [[VEC_EPILOG_SCALAR_PH]]
 ; DEFAULT:       vec.epilog.scalar.ph: