; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 4
; RUN: opt -p loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S %s | FileCheck %s
; TODO: Preserve disjoint flag on OR instruction.
define void @generate_disjoint_flags(i64 %n, ptr noalias %x) {
; CHECK-LABEL: define void @generate_disjoint_flags(
; CHECK-SAME: i64 [[N:%.*]], ptr noalias [[X:%.*]]) {
; CHECK-NEXT: entry:
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[N]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N]], 4
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds i32, ptr [[X]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i32, ptr [[TMP1]], i32 0
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x i32>, ptr [[TMP2]], align 4
; CHECK-NEXT: [[TMP3:%.*]] = or disjoint <4 x i32> [[WIDE_LOAD]], <i32 1, i32 1, i32 1, i32 1>
; CHECK-NEXT: [[TMP4:%.*]] = or <4 x i32> [[WIDE_LOAD]], <i32 3, i32 3, i32 3, i32 3>
; CHECK-NEXT: [[TMP5:%.*]] = add nuw nsw <4 x i32> [[TMP3]], [[TMP4]]
; CHECK-NEXT: store <4 x i32> [[TMP5]], ptr [[TMP2]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP6]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[N]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[GEP_X:%.*]] = getelementptr inbounds i32, ptr [[X]], i64 [[IV]]
; CHECK-NEXT: [[LV:%.*]] = load i32, ptr [[GEP_X]], align 4
; CHECK-NEXT: [[OR_1:%.*]] = or disjoint i32 [[LV]], 1
; CHECK-NEXT: [[OR_2:%.*]] = or i32 [[LV]], 3
; CHECK-NEXT: [[ADD:%.*]] = add nuw nsw i32 [[OR_1]], [[OR_2]]
; CHECK-NEXT: store i32 [[ADD]], ptr [[GEP_X]], align 4
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[IV_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[EXITCOND]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%gep.x = getelementptr inbounds i32, ptr %x, i64 %iv
%lv = load i32, ptr %gep.x, align 4
%or.1 = or disjoint i32 %lv, 1
%or.2 = or i32 %lv, 3
%add = add nsw nuw i32 %or.1, %or.2
store i32 %add, ptr %gep.x, align 4
%iv.next = add i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, %n
br i1 %exitcond, label %exit, label %loop
exit:
ret void
}
;.
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
; CHECK: [[LOOP3]] = distinct !{[[LOOP3]], [[META2]], [[META1]]}
;.