llvm/test/Transforms/LoopVectorize/AArch64/pr151664-cost-hoisted-vector-scalable.ll

; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "^scalar.ph" --version 5
; RUN: opt -passes=loop-vectorize -mtriple=aarch64 -mattr=+sve -S %s | FileCheck %s

define void @cost_hoisted_vector_code(ptr %p, float %arg) {
; CHECK-LABEL: define void @cost_hoisted_vector_code(
; CHECK-SAME: ptr [[P:%.*]], float [[ARG:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT:  [[ENTRY:.*:]]
; CHECK-NEXT:    br i1 false, label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK:       [[VECTOR_PH]]:
; CHECK-NEXT:    [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x float> poison, float [[ARG]], i64 0
; CHECK-NEXT:    [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x float> [[BROADCAST_SPLATINSERT]], <4 x float> poison, <4 x i32> zeroinitializer
; CHECK-NEXT:    [[TMP0:%.*]] = call <4 x float> @llvm.minimumnum.v4f32(<4 x float> [[BROADCAST_SPLAT]], <4 x float> zeroinitializer)
; CHECK-NEXT:    br label %[[VECTOR_BODY:.*]]
; CHECK:       [[VECTOR_BODY]]:
; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i64 1, [[INDEX]]
; CHECK-NEXT:    [[TMP1:%.*]] = getelementptr float, ptr [[P]], i64 [[OFFSET_IDX]]
; CHECK-NEXT:    [[TMP2:%.*]] = getelementptr float, ptr [[TMP1]], i32 4
; CHECK-NEXT:    store <4 x float> [[TMP0]], ptr [[TMP1]], align 4
; CHECK-NEXT:    store <4 x float> [[TMP0]], ptr [[TMP2]], align 4
; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 8
; CHECK-NEXT:    [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], -8
; CHECK-NEXT:    br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK:       [[MIDDLE_BLOCK]]:
; CHECK-NEXT:    br label %[[SCALAR_PH]]
; CHECK:       [[SCALAR_PH]]:
;
entry:
  br label %loop

loop:                                              ; preds = %loop, %entry
  %iv = phi i64 [ 1, %entry ], [ %iv.next, %loop ]
  %res = tail call float @llvm.minimumnum.f32(float %arg, float 0.0)
  %gep.p.red = getelementptr float, ptr %p, i64 %iv
  store float %res, ptr %gep.p.red, align 4
  %iv.next = add i64 %iv, 1
  %exit.cond = icmp eq i64 %iv.next, 0
  br i1 %exit.cond, label %exit, label %loop

exit:                                              ; preds = %loop
  ret void
}

declare float @llvm.minimumnum.f32(float, float)