; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -mtriple=aarch64--linux-gnu -mattr=+sve  < %s | FileCheck %s

; Check getIntrinsicInstrCost in BasicTTIImpl.h for vector.reverse

target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"

define void @vector_reverse() #0 {
; CHECK-LABEL: 'vector_reverse'
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %1 = call <16 x i8> @llvm.vector.reverse.v16i8(<16 x i8> undef)
; CHECK-NEXT:  Cost Model: Found costs of 4 for: %2 = call <32 x i8> @llvm.vector.reverse.v32i8(<32 x i8> undef)
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %3 = call <8 x i16> @llvm.vector.reverse.v8i16(<8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found costs of 4 for: %4 = call <16 x i16> @llvm.vector.reverse.v16i16(<16 x i16> undef)
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %5 = call <4 x i32> @llvm.vector.reverse.v4i32(<4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found costs of 4 for: %6 = call <8 x i32> @llvm.vector.reverse.v8i32(<8 x i32> undef)
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %7 = call <2 x i64> @llvm.vector.reverse.v2i64(<2 x i64> undef)
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %8 = call <4 x i64> @llvm.vector.reverse.v4i64(<4 x i64> undef)
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %9 = call <8 x half> @llvm.vector.reverse.v8f16(<8 x half> undef)
; CHECK-NEXT:  Cost Model: Found costs of 4 for: %10 = call <16 x half> @llvm.vector.reverse.v16f16(<16 x half> undef)
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %11 = call <4 x float> @llvm.vector.reverse.v4f32(<4 x float> undef)
; CHECK-NEXT:  Cost Model: Found costs of 4 for: %12 = call <8 x float> @llvm.vector.reverse.v8f32(<8 x float> undef)
; CHECK-NEXT:  Cost Model: Found costs of 1 for: %13 = call <2 x double> @llvm.vector.reverse.v2f64(<2 x double> undef)
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %14 = call <4 x double> @llvm.vector.reverse.v4f64(<4 x double> undef)
; CHECK-NEXT:  Cost Model: Found costs of 2 for: %15 = call <8 x bfloat> @llvm.vector.reverse.v8bf16(<8 x bfloat> undef)
; CHECK-NEXT:  Cost Model: Found costs of 4 for: %16 = call <16 x bfloat> @llvm.vector.reverse.v16bf16(<16 x bfloat> undef)
; CHECK-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;

  call <16 x i8> @llvm.vector.reverse.v16i8(<16 x i8> undef)
  call <32 x i8> @llvm.vector.reverse.v32i8(<32 x i8> undef)
  call <8 x i16> @llvm.vector.reverse.v8i16(<8 x i16> undef)
  call <16 x i16> @llvm.vector.reverse.v16i16(<16 x i16> undef)
  call <4 x i32> @llvm.vector.reverse.v4i32(<4 x i32> undef)
  call <8 x i32> @llvm.vector.reverse.v8i32(<8 x i32> undef)
  call <2 x i64> @llvm.vector.reverse.v2i64(<2 x i64> undef)
  call <4 x i64> @llvm.vector.reverse.v4i64(<4 x i64> undef)
  call <8 x half> @llvm.vector.reverse.v8f16(<8 x half> undef)
  call <16 x half> @llvm.vector.reverse.v16f16(<16 x half> undef)
  call <4 x float> @llvm.vector.reverse.v4f32(<4 x float> undef)
  call <8 x float> @llvm.vector.reverse.v8f32(<8 x float> undef)
  call <2 x double> @llvm.vector.reverse.v2f64(<2 x double> undef)
  call <4 x double> @llvm.vector.reverse.v4f64(<4 x double> undef)
  call <8 x bfloat> @llvm.vector.reverse.v8bf16(<8 x bfloat> undef)
  call <16 x bfloat> @llvm.vector.reverse.v16bf16(<16 x bfloat> undef)
  ret void
}

attributes #0 = { "target-features"="+sve,+bf16" }
declare <16 x i8> @llvm.vector.reverse.v16i8(<16 x i8>)
declare <32 x i8> @llvm.vector.reverse.v32i8(<32 x i8>)
declare <8 x i16> @llvm.vector.reverse.v8i16(<8 x i16>)
declare <16 x i16> @llvm.vector.reverse.v16i16(<16 x i16>)
declare <4 x i32> @llvm.vector.reverse.v4i32(<4 x i32>)
declare <8 x i32> @llvm.vector.reverse.v8i32(<8 x i32>)
declare <2 x i64> @llvm.vector.reverse.v2i64(<2 x i64>)
declare <4 x i64> @llvm.vector.reverse.v4i64(<4 x i64>)
declare <8 x half> @llvm.vector.reverse.v8f16(<8 x half>)
declare <16 x half> @llvm.vector.reverse.v16f16(<16 x half>)
declare <4 x float> @llvm.vector.reverse.v4f32(<4 x float>)
declare <8 x float> @llvm.vector.reverse.v8f32(<8 x float>)
declare <2 x double> @llvm.vector.reverse.v2f64(<2 x double>)
declare <4 x double> @llvm.vector.reverse.v4f64(<4 x double>)
declare <8 x bfloat> @llvm.vector.reverse.v8bf16(<8 x bfloat>)
declare <16 x bfloat> @llvm.vector.reverse.v16bf16(<16 x bfloat>)