TheRock/compiler/amd-llvm/llvm/test/Transforms/LoopVectorize/tail-folding-alloca-in-loop.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -S --passes=loop-vectorize -tail-folding-policy=must-fold-tail -force-vector-width=4  < %s | FileCheck %s

define i32 @test(ptr %vf1, i64 %n) {
; CHECK-LABEL: define i32 @test(
; CHECK-SAME: ptr [[VF1:%.*]], i64 [[N:%.*]]) {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    br label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[PRED_STORE_CONTINUE6:.*]] ]
; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i8> [ <i8 0, i8 1, i8 2, i8 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[PRED_STORE_CONTINUE6]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = icmp ule <4 x i8> [[VEC_IND]], splat (i8 -56)
; CHECK-NEXT:    [[TMP18:%.*]] = alloca i8, i64 [[N]], align 16
; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i1> [[TMP0]], i64 0
; CHECK-NEXT:    br i1 [[TMP1]], label %[[PRED_STORE_IF:.*]], label %[[PRED_STORE_CONTINUE:.*]]
; CHECK:       [[PRED_STORE_IF]]:
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds ptr, ptr [[VF1]], i64 [[INDEX]]
; CHECK-NEXT:    store ptr [[TMP18]], ptr [[TMP3]], align 8
; CHECK-NEXT:    br label %[[PRED_STORE_CONTINUE]]
; CHECK:       [[PRED_STORE_CONTINUE]]:
; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x i1> [[TMP0]], i64 1
; CHECK-NEXT:    br i1 [[TMP5]], label %[[PRED_STORE_IF1:.*]], label %[[PRED_STORE_CONTINUE2:.*]]
; CHECK:       [[PRED_STORE_IF1]]:
; CHECK-NEXT:    [[TMP6:%.*]] = add i64 [[INDEX]], 1
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds ptr, ptr [[VF1]], i64 [[TMP6]]
; CHECK-NEXT:    store ptr [[TMP18]], ptr [[TMP7]], align 8
; CHECK-NEXT:    br label %[[PRED_STORE_CONTINUE2]]
; CHECK:       [[PRED_STORE_CONTINUE2]]:
; CHECK-NEXT:    [[TMP9:%.*]] = extractelement <4 x i1> [[TMP0]], i64 2
; CHECK-NEXT:    br i1 [[TMP9]], label %[[PRED_STORE_IF3:.*]], label %[[PRED_STORE_CONTINUE4:.*]]
; CHECK:       [[PRED_STORE_IF3]]:
; CHECK-NEXT:    [[TMP10:%.*]] = add i64 [[INDEX]], 2
; CHECK-NEXT:    [[TMP11:%.*]] = getelementptr inbounds ptr, ptr [[VF1]], i64 [[TMP10]]
; CHECK-NEXT:    store ptr [[TMP18]], ptr [[TMP11]], align 8
; CHECK-NEXT:    br label %[[PRED_STORE_CONTINUE4]]
; CHECK:       [[PRED_STORE_CONTINUE4]]:
; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <4 x i1> [[TMP0]], i64 3
; CHECK-NEXT:    br i1 [[TMP13]], label %[[PRED_STORE_IF5:.*]], label %[[PRED_STORE_CONTINUE6]]
; CHECK:       [[PRED_STORE_IF5]]:
; CHECK-NEXT:    [[TMP14:%.*]] = add i64 [[INDEX]], 3
; CHECK-NEXT:    [[TMP15:%.*]] = getelementptr inbounds ptr, ptr [[VF1]], i64 [[TMP14]]
; CHECK-NEXT:    store ptr [[TMP18]], ptr [[TMP15]], align 8
; CHECK-NEXT:    br label %[[PRED_STORE_CONTINUE6]]
; CHECK:       [[PRED_STORE_CONTINUE6]]:
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT:    [[VEC_IND_NEXT]] = add nuw <4 x i8> [[VEC_IND]], splat (i8 4)
; CHECK-NEXT:    [[TMP17:%.*]] = icmp eq i64 [[INDEX_NEXT]], 204
; CHECK-NEXT:    br i1 [[TMP17]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    br label %[[EXIT:.*]]
; CHECK:       [[EXIT]]:
; CHECK-NEXT:    ret i32 0
;
entry:
  br label %for.body

for.body:
  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
  %0 = alloca i8, i64 %n, align 16
  %arrayidx = getelementptr inbounds ptr, ptr %vf1, i64 %indvars.iv
  store ptr %0, ptr %arrayidx, align 8
  %indvars.iv.next = add i64 %indvars.iv, 1
  %exitcond.not = icmp eq i64 %indvars.iv, 200
  br i1 %exitcond.not, label %exit, label %for.body

exit:
  ret i32 0
}
;.
; CHECK: [[LOOP0]] = distinct !{[[LOOP0]], [[META1:![0-9]+]], [[META2:![0-9]+]]}
; CHECK: [[META1]] = !{!"llvm.loop.isvectorized", i32 1}
; CHECK: [[META2]] = !{!"llvm.loop.unroll.runtime.disable"}
;.