llvm/test/Transforms/LoopVectorize/early_exit_pseudo_probe.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
; RUN: opt -S < %s -p loop-vectorize -force-vector-width=4 | FileCheck %s

declare void @init_mem(ptr, i64);

;; llvm.pseudoprobe is modelled as accessing inaccessible memory, so it reports
;; may-read and may-write, but it carries no real memory dependence. A read-only
;; early exit loop must vectorize whether or not it has been instrumented for
;; sample profiling.
define i64 @early_exit_with_pseudo_probe() {
; CHECK-LABEL: define i64 @early_exit_with_pseudo_probe() {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    [[P1:%.*]] = alloca [1024 x i8], align 1
; CHECK-NEXT:    [[P2:%.*]] = alloca [1024 x i8], align 1
; CHECK-NEXT:    call void @init_mem(ptr [[P1]], i64 1024)
; CHECK-NEXT:    call void @init_mem(ptr [[P2]], i64 1024)
; CHECK-NEXT:    br label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX1:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT3:%.*]], %[[VECTOR_BODY_INTERIM:.*]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = add i64 3, [[INDEX1]]
; CHECK-NEXT:    call void @llvm.pseudoprobe(i64 5116412291814990879, i64 1, i32 0, i64 -1)
; CHECK-NEXT:    call void @llvm.pseudoprobe(i64 5116412291814990879, i64 1, i32 0, i64 -1)
; CHECK-NEXT:    call void @llvm.pseudoprobe(i64 5116412291814990879, i64 1, i32 0, i64 -1)
; CHECK-NEXT:    call void @llvm.pseudoprobe(i64 5116412291814990879, i64 1, i32 0, i64 -1)
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr inbounds i8, ptr [[P1]], i64 [[TMP0]]
; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <4 x i8>, ptr [[TMP1]], align 1
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[P2]], i64 [[TMP0]]
; CHECK-NEXT:    [[WIDE_LOAD2:%.*]] = load <4 x i8>, ptr [[TMP2]], align 1
; CHECK-NEXT:    [[TMP3:%.*]] = icmp ne <4 x i8> [[WIDE_LOAD]], [[WIDE_LOAD2]]
; CHECK-NEXT:    [[TMP4:%.*]] = freeze <4 x i1> [[TMP3]]
; CHECK-NEXT:    [[TMP5:%.*]] = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> [[TMP4]])
; CHECK-NEXT:    [[INDEX_NEXT3]] = add nuw i64 [[INDEX1]], 4
; CHECK-NEXT:    [[TMP6:%.*]] = icmp eq i64 [[INDEX_NEXT3]], 64
; CHECK-NEXT:    br i1 [[TMP5]], label %[[VECTOR_EARLY_EXIT:.*]], label %[[VECTOR_BODY_INTERIM]]
; CHECK:       [[VECTOR_BODY_INTERIM]]:
; CHECK-NEXT:    br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP1:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    br label %[[LOOP_END:.*]]
; CHECK:       [[VECTOR_EARLY_EXIT]]:
; CHECK-NEXT:    br label %[[LOOP_END]]
; CHECK:       [[LOOP_END]]:
; CHECK-NEXT:    [[RETVAL:%.*]] = phi i64 [ 0, %[[VECTOR_EARLY_EXIT]] ], [ 1, %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT:    ret i64 [[RETVAL]]
;
entry:
  %p1 = alloca [1024 x i8]
  %p2 = alloca [1024 x i8]
  call void @init_mem(ptr %p1, i64 1024)
  call void @init_mem(ptr %p2, i64 1024)
  br label %loop

loop:
  %index = phi i64 [ %index.next, %loop.inc ], [ 3, %entry ]
  call void @llvm.pseudoprobe(i64 5116412291814990879, i64 1, i32 0, i64 -1)
  %arrayidx = getelementptr inbounds i8, ptr %p1, i64 %index
  %ld1 = load i8, ptr %arrayidx, align 1
  %arrayidx1 = getelementptr inbounds i8, ptr %p2, i64 %index
  %ld2 = load i8, ptr %arrayidx1, align 1
  %cmp3 = icmp eq i8 %ld1, %ld2
  br i1 %cmp3, label %loop.inc, label %loop.end

loop.inc:
  %index.next = add i64 %index, 1
  %exitcond = icmp ne i64 %index.next, 67
  br i1 %exitcond, label %loop, label %loop.end

loop.end:
  %retval = phi i64 [ 0, %loop ], [ 1, %loop.inc ]
  ret i64 %retval
}

declare void @llvm.pseudoprobe(i64, i64, i32, i64)

!llvm.pseudo_probe_desc = !{!0}

!0 = !{i64 5116412291814990879, i64 52824598631, !"early_exit_with_pseudo_probe"}
;.
; CHECK: [[LOOP1]] = distinct !{[[LOOP1]], [[META2:![0-9]+]], [[META3:![0-9]+]]}
; CHECK: [[META2]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META3]] = !{!"llvm.loop.unroll.runtime.disable"}
;.