; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sve | FileCheck %s --check-prefix=CHECK-VSCALE-1
; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -mcpu=neoverse-v1 -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sve | FileCheck %s --check-prefixes=CHECK-VSCALE-2,CHECK-SVE
; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -mcpu=neoverse-v1 -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sve2p1 | FileCheck %s --check-prefixes=CHECK-VSCALE-2,CHECK-SVE2p1-OR-SME2
; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -mcpu=neoverse-v1 -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sme2 | FileCheck %s --check-prefixes=CHECK-VSCALE-2,CHECK-SVE2p1-OR-SME2
; RUN: opt < %s -passes="print<cost-model>" -cost-kind=all 2>&1 -intrinsic-cost-strategy=type-based-intrinsic-cost -disable-output -S -mtriple=aarch64--linux-gnu -mattr=+sve | FileCheck %s --check-prefix=TYPE_BASED_ONLY

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

define void @vector_insert_extract(<vscale x 4 x i32> %v0, <vscale x 16 x i32> %v1, <16 x i32> %v2) {
; CHECK-VSCALE-1-LABEL: 'vector_insert_extract'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:64 CodeSize:32 Lat:64 SizeLat:64 for: %extract_fixed_from_scalable = call <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:64 CodeSize:32 Lat:64 SizeLat:64 for: %insert_fixed_into_scalable = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> %v0, <16 x i32> %v2, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %extract_scalable_from_scalable = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> %v1, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %insert_scalable_into_scalable = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> %v1, <vscale x 4 x i32> %v0, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'vector_insert_extract'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:64 CodeSize:32 Lat:64 SizeLat:64 for: %extract_fixed_from_scalable = call <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:64 CodeSize:32 Lat:64 SizeLat:64 for: %insert_fixed_into_scalable = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> %v0, <16 x i32> %v2, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %extract_scalable_from_scalable = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> %v1, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %insert_scalable_into_scalable = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> %v1, <vscale x 4 x i32> %v0, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'vector_insert_extract'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_fixed_from_scalable = call <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %insert_fixed_into_scalable = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> %v0, <16 x i32> %v2, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_scalable_from_scalable = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> %v1, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %insert_scalable_into_scalable = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> %v1, <vscale x 4 x i32> %v0, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %extract_fixed_from_scalable = call <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32> %v0, i64 0)
  %insert_fixed_into_scalable = call <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32> %v0, <16 x i32> %v2, i64 0)
  %extract_scalable_from_scalable = call <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32> %v1, i64 0)
  %insert_scalable_into_scalable = call <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32> %v1, <vscale x 4 x i32> %v0, i64 0)
  ret void
}
declare <16 x i32> @llvm.vector.extract.v16i32.nxv4i32(<vscale x 4 x i32>, i64)
declare <vscale x 4 x i32> @llvm.vector.insert.nxv4i32.v16i32(<vscale x 4 x i32>, <16 x i32>, i64)
declare <vscale x 4 x i32> @llvm.vector.extract.nxv4i32.nxv16i32(<vscale x 16 x i32>, i64)
declare <vscale x 16 x i32> @llvm.vector.insert.nxv16i32.nxv4i32(<vscale x 16 x i32>, <vscale x 4 x i32>, i64)

define void @vector_insert_extract_idxzero_128b() #1 {
; CHECK-VSCALE-1-LABEL: 'vector_insert_extract_idxzero_128b'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> poison, <4 x float> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'vector_insert_extract_idxzero_128b'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> poison, <4 x float> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'vector_insert_extract_idxzero_128b'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> poison, <4 x float> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %insert_legal_fixed_into_scalable = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float> poison, <4 x float> poison, i64 0)
  %extract_legal_fixed_from_scalable = call <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double> poison, i64 0)
  %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.v2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0)
  %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0)
  %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0)
  %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0)
  %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0)
  %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0)
  %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0)
  ret void
}
declare <vscale x 4 x float> @llvm.vector.insert.nxv4f32.v4f32(<vscale x 4 x float>, <4 x float>, i64)
declare <2 x double> @llvm.vector.extract.v2f64.nxv2f64(<vscale x 2 x double>, i64)
declare <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.v2i1(<vscale x 16 x i1>, <vscale x 2 x i1>, i64)
declare <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1>, i64)
declare <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float>, <2 x float>, i64)
declare <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half>, i64)
declare <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float>, <vscale x 2 x float>, i64)
declare <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float>, i64)

define void @vector_insert_extract_idxzero_256b() #2 {
; CHECK-VSCALE-1-LABEL: 'vector_insert_extract_idxzero_256b'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> poison, <16 x i16> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'vector_insert_extract_idxzero_256b'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 0 for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> poison, <16 x i16> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 0 for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:48 CodeSize:32 Lat:48 SizeLat:48 for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:2 Lat:4 SizeLat:4 for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:12 CodeSize:6 Lat:12 SizeLat:12 for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'vector_insert_extract_idxzero_256b'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> poison, <16 x i16> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.nxv2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %insert_legal_fixed_into_scalable = call <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16> poison, <16 x i16> poison, i64 0)
  %extract_legal_fixed_from_scalable = call <8 x float> @llvm.vector.extract.v8f32.nx4f32(<vscale x 4 x float> poison, i64 0)
  %insert_nxv16i1_nxv2i1 = call <vscale x 16 x i1> @llvm.vector.insert.nxv16i1.v2i1(<vscale x 16 x i1> poison, <vscale x 2 x i1> poison, i64 0)
  %extract_nxv4i1_nxv16i1 = call <vscale x 4 x i1> @llvm.vector.extract.nxv4i1.nxv16i1(<vscale x 16 x i1> poison, i64 0)
  %extract_v8i1_nxv8i1 = call <8 x i1> @llvm.vector.extract.v8i1.nxv8i1(<vscale x 8 x i1> poison, i64 0)
  %insert_v2f32_nxv2f32 = call <vscale x 2 x float> @llvm.vector.insert.nxv2f32.v2f32(<vscale x 2 x float> poison, <2 x float> poison, i64 0)
  %extract_v4f16_nxv4f16 = call <4 x half> @llvm.vector.extract.v4f16.nxv4f16(<vscale x 4 x half> poison, i64 0)
  %insert_nxv2f32_nxv4f32 = call <vscale x 4 x float> @llvm.vector.insert.nxv4f32.nxv2f32(<vscale x 4 x float> poison, <vscale x 2 x float> poison, i64 0)
  %extract_nxv4f32_nxv8f32 = call <vscale x 4 x float> @llvm.vector.extract.nxv4f32.nxv8f32(<vscale x 8 x float> poison, i64 0)
  ret void
}
declare <vscale x 8 x i16> @llvm.vector.insert.nxv8i16.v16i16(<vscale x 8 x i16>, <16 x i16>, i64)
declare <8 x float> @llvm.vector.extract.v8f32.nxv4f32(<vscale x 4 x float>, i64)

define void @reductions(<vscale x 4 x i32> %v0, <vscale x 4 x i64> %v1, <vscale x 4 x float> %v2, <vscale x 4 x double> %v3) {
; CHECK-VSCALE-1-LABEL: 'reductions'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:3 Lat:5 SizeLat:3 for: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'reductions'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:3 Lat:5 SizeLat:3 for: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'reductions'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 3 for: %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 3 for: %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 3 for: %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 3 for: %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 3 for: %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 3 for: %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 3 for: %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 3 for: %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.000000e+00, <vscale x 1 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v2)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:3 CodeSize:3 Lat:5 SizeLat:3 for: %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v3)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 3 for: %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 3 for: %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %add_nxv1i32 = call i32 @llvm.vector.reduce.add.nxv1i32(<vscale x 1 x i32> poison)
  %add_nxv4i32 = call i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32> %v0)
  %add_nxv4i64 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> %v1)
  %mul_nxv1i32 = call i32 @llvm.vector.reduce.mul.nxv1i32(<vscale x 1 x i32> poison)
  %mul_nxv4i32 = call i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32> %v0)
  %mul_nxv4i64 = call i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64> %v1)
  %and_nxv1i32 = call i32 @llvm.vector.reduce.and.nxv1i32(<vscale x 1 x i32> poison)
  %and_nxv4i32 = call i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32> %v0)
  %and_nxv4i64 = call i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64> %v1)
  %or_nxv1i32 = call i32 @llvm.vector.reduce.or.nxv1i32(<vscale x 1 x i32> poison)
  %or_nxv4i32 = call i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32> %v0)
  %or_nxv4i64 = call i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64> %v1)
  %xor_nxv1i32 = call i32 @llvm.vector.reduce.xor.nxv1i32(<vscale x 1 x i32> poison)
  %xor_nxv4i32 = call i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32> %v0)
  %xor_nxv4i64 = call i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64> %v1)
  %umin_nxv1i64 = call i64 @llvm.vector.reduce.umin.nxv1i64(<vscale x 1 x i64> poison)
  %umin_nxv4i32 = call i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32> %v0)
  %umin_nxv4i64 = call i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64> %v1)
  %smin_nxv1i64 = call i64 @llvm.vector.reduce.smin.nxv1i64(<vscale x 1 x i64> poison)
  %smin_nxv4i32 = call i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32> %v0)
  %smin_nxv4i64 = call i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64> %v1)
  %umax_nxv1i64 = call i64 @llvm.vector.reduce.umax.nxv1i64(<vscale x 1 x i64> poison)
  %umax_nxv4i32 = call i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32> %v0)
  %umax_nxv4i64 = call i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64> %v1)
  %smax_nxv1i64 = call i64 @llvm.vector.reduce.smax.nxv1i64(<vscale x 1 x i64> poison)
  %smax_nxv4i32 = call i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32> %v0)
  %smax_nxv4i64 = call i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64> %v1)

  %fadd_nxv1f32 = call fast float @llvm.vector.reduce.fadd.nxv1f32(float 0.0, <vscale x 1 x float> poison)
  %fadd_nxv4f32 = call fast float @llvm.vector.reduce.fadd.nxv4f32(float 0.0, <vscale x 4 x float> %v2)
  %fadd_nxv4f64 = call fast double @llvm.vector.reduce.fadd.nxv4f64(double 0.0, <vscale x 4 x double> %v3)
  %fmin_nxv1f32 = call fast float @llvm.vector.reduce.fmin.nxv1f32(<vscale x 1 x float> poison)
  %fmin_nxv4f32 = call fast float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float> %v2)
  %fmin_nxv4f64 = call fast double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double> %v3)
  %fmax_nxv1f32 = call fast float @llvm.vector.reduce.fmax.nxv1f32(<vscale x 1 x float> poison)
  %fmax_nxv4f32 = call fast float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float> %v2)
  %fmax_nxv4f64 = call fast double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double> %v3)

  ret void
}

define void @strict_fp_reductions(<vscale x 4 x float> %v0, <vscale x 4 x double> %v1) {
; CHECK-VSCALE-1-LABEL: 'strict_fp_reductions'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:4 Lat:12 SizeLat:4 for: %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:4 Lat:12 SizeLat:4 for: %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %fmul_nxv4f32 = call float @llvm.vector.reduce.fmul.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %fmul_nxv4f64 = call double @llvm.vector.reduce.fmul.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'strict_fp_reductions'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:8 Lat:24 SizeLat:8 for: %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:8 Lat:24 SizeLat:8 for: %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %fmul_nxv4f32 = call float @llvm.vector.reduce.fmul.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %fmul_nxv4f64 = call double @llvm.vector.reduce.fmul.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'strict_fp_reductions'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:4 Lat:12 SizeLat:4 for: %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:4 CodeSize:4 Lat:12 SizeLat:4 for: %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %fmul_nxv4f32 = call float @llvm.vector.reduce.fmul.nxv4f32(float 0.000000e+00, <vscale x 4 x float> %v0)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %fmul_nxv4f64 = call double @llvm.vector.reduce.fmul.nxv4f64(double 0.000000e+00, <vscale x 4 x double> %v1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %fadd_nxv4f32 = call float @llvm.vector.reduce.fadd.nxv4f32(float 0.0, <vscale x 4 x float> %v0)
  %fadd_nxv4f64 = call double @llvm.vector.reduce.fadd.nxv4f64(double 0.0, <vscale x 4 x double> %v1)
  %fmul_nxv4f32 = call float @llvm.vector.reduce.fmul.nxv4f32(float 0.0, <vscale x 4 x float> %v0)
  %fmul_nxv4f64 = call double @llvm.vector.reduce.fmul.nxv4f64(double 0.0, <vscale x 4 x double> %v1)

  ret void
}

declare i32 @llvm.vector.reduce.add.nxv4i32(<vscale x 4 x i32>)
declare i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64>)
declare i32 @llvm.vector.reduce.mul.nxv4i32(<vscale x 4 x i32>)
declare i64 @llvm.vector.reduce.mul.nxv4i64(<vscale x 4 x i64>)
declare i32 @llvm.vector.reduce.and.nxv4i32(<vscale x 4 x i32>)
declare i64 @llvm.vector.reduce.and.nxv4i64(<vscale x 4 x i64>)
declare i32 @llvm.vector.reduce.or.nxv4i32(<vscale x 4 x i32>)
declare i64 @llvm.vector.reduce.or.nxv4i64(<vscale x 4 x i64>)
declare i32 @llvm.vector.reduce.xor.nxv4i32(<vscale x 4 x i32>)
declare i64 @llvm.vector.reduce.xor.nxv4i64(<vscale x 4 x i64>)
declare i32 @llvm.vector.reduce.umin.nxv4i32(<vscale x 4 x i32>)
declare i64 @llvm.vector.reduce.umin.nxv4i64(<vscale x 4 x i64>)
declare i32 @llvm.vector.reduce.smin.nxv4i32(<vscale x 4 x i32>)
declare i64 @llvm.vector.reduce.smin.nxv4i64(<vscale x 4 x i64>)
declare i32 @llvm.vector.reduce.umax.nxv4i32(<vscale x 4 x i32>)
declare i64 @llvm.vector.reduce.umax.nxv4i64(<vscale x 4 x i64>)
declare i32 @llvm.vector.reduce.smax.nxv4i32(<vscale x 4 x i32>)
declare i64 @llvm.vector.reduce.smax.nxv4i64(<vscale x 4 x i64>)
declare float @llvm.vector.reduce.fadd.nxv4f32(float, <vscale x 4 x float>)
declare double @llvm.vector.reduce.fadd.nxv4f64(double, <vscale x 4 x double>)
declare float @llvm.vector.reduce.fmul.nxv4f32(float, <vscale x 4 x float>)
declare double @llvm.vector.reduce.fmul.nxv4f64(double, <vscale x 4 x double>)
declare float @llvm.vector.reduce.fmin.nxv4f32(<vscale x 4 x float>)
declare double @llvm.vector.reduce.fmin.nxv4f64(<vscale x 4 x double>)
declare float @llvm.vector.reduce.fmax.nxv4f32(<vscale x 4 x float>)
declare double @llvm.vector.reduce.fmax.nxv4f64(<vscale x 4 x double>)


define void  @count_zeroes(<vscale x 4 x i32> %A) {
; CHECK-VSCALE-1-LABEL: 'count_zeroes'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %ctlz = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %cttz = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'count_zeroes'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %ctlz = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %cttz = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'count_zeroes'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %ctlz = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %cttz = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %ctlz = call <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
  %cttz = call <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32> %A, i1 true)
  ret void
}
declare <vscale x 4 x i32> @llvm.ctlz.nxv4i32(<vscale x 4 x i32>, i1)
declare <vscale x 4 x i32> @llvm.cttz.nxv4i32(<vscale x 4 x i32>, i1)


define void @vector_reverse() #0 {
; CHECK-VSCALE-1-LABEL: 'vector_reverse'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'vector_reverse'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'vector_reverse'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv8i1 = call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;

  %reverse_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8> poison)
  %reverse_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8> poison)
  %reverse_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16> poison)
  %reverse_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16> poison)
  %reverse_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16> poison)
  %reverse_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16> poison)
  %reverse_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32> poison)
  %reverse_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32> poison)
  %reverse_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64> poison)
  %reverse_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64> poison)
  %reverse_nxv2f16 = call <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half> poison)
  %reverse_nxv4f16 = call <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half> poison)
  %reverse_nxv8f16 = call <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half> poison)
  %reverse_nxv16f16 = call <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half> poison)
  %reverse_nxv2f32 = call <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float> poison)
  %reverse_nxv4f32 = call <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float> poison)
  %reverse_nxv8f32 = call <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float> poison)
  %reverse_nxv2f64 = call <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double> poison)
  %reverse_nxv4f64 = call <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double> poison)
  %reverse_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat> poison)
  %reverse_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat> poison)
  %reverse_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat> poison)
  %reverse_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat> poison)
  %reverse_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1> poison)
  %reverse_nxv8i1 =  call <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1> poison)
  %reverse_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1> poison)
  %reverse_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1> poison)
  ret void
}
declare <vscale x 16 x i8> @llvm.vector.reverse.nxv16i8(<vscale x 16 x i8>)
declare <vscale x 32 x i8> @llvm.vector.reverse.nxv32i8(<vscale x 32 x i8>)
declare <vscale x 2 x i16> @llvm.vector.reverse.nxv2i16(<vscale x 2 x i16>)
declare <vscale x 4 x i16> @llvm.vector.reverse.nxv4i16(<vscale x 4 x i16>)
declare <vscale x 8 x i16> @llvm.vector.reverse.nxv8i16(<vscale x 8 x i16>)
declare <vscale x 16 x i16> @llvm.vector.reverse.nxv16i16(<vscale x 16 x i16>)
declare <vscale x 4 x i32> @llvm.vector.reverse.nxv4i32(<vscale x 4 x i32>)
declare <vscale x 8 x i32> @llvm.vector.reverse.nxv8i32(<vscale x 8 x i32>)
declare <vscale x 2 x i64> @llvm.vector.reverse.nxv2i64(<vscale x 2 x i64>)
declare <vscale x 4 x i64> @llvm.vector.reverse.nxv4i64(<vscale x 4 x i64>)
declare <vscale x 2 x half> @llvm.vector.reverse.nxv2f16(<vscale x 2 x half>)
declare <vscale x 4 x half> @llvm.vector.reverse.nxv4f16(<vscale x 4 x half>)
declare <vscale x 8 x half> @llvm.vector.reverse.nxv8f16(<vscale x 8 x half>)
declare <vscale x 16 x half> @llvm.vector.reverse.nxv16f16(<vscale x 16 x half>)
declare <vscale x 2 x float> @llvm.vector.reverse.nxv2f32(<vscale x 2 x float>)
declare <vscale x 4 x float> @llvm.vector.reverse.nxv4f32(<vscale x 4 x float>)
declare <vscale x 8 x float> @llvm.vector.reverse.nxv8f32(<vscale x 8 x float>)
declare <vscale x 2 x double> @llvm.vector.reverse.nxv2f64(<vscale x 2 x double>)
declare <vscale x 4 x double> @llvm.vector.reverse.nxv4f64(<vscale x 4 x double>)
declare <vscale x 2 x bfloat> @llvm.vector.reverse.nxv2bf16(<vscale x 2 x bfloat>)
declare <vscale x 4 x bfloat> @llvm.vector.reverse.nxv4bf16(<vscale x 4 x bfloat>)
declare <vscale x 8 x bfloat> @llvm.vector.reverse.nxv8bf16(<vscale x 8 x bfloat>)
declare <vscale x 16 x bfloat> @llvm.vector.reverse.nxv16bf16(<vscale x 16 x bfloat>)
declare <vscale x 16 x i1> @llvm.vector.reverse.nxv16i1(<vscale x 16 x i1>)
declare <vscale x 8 x i1> @llvm.vector.reverse.nxv8i1(<vscale x 8 x i1>)
declare <vscale x 4 x i1> @llvm.vector.reverse.nxv4i1(<vscale x 4 x i1>)
declare <vscale x 2 x i1> @llvm.vector.reverse.nxv2i1(<vscale x 2 x i1>)

define void @unsupported_fp_ops(<vscale x 4 x float> %vec, i32 %extraarg) {
; CHECK-VSCALE-1-LABEL: 'unsupported_fp_ops'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 %extraarg)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'unsupported_fp_ops'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 %extraarg)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'unsupported_fp_ops'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 %extraarg)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;

  %sin = call <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float> %vec)
  %cos = call <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float> %vec)
  %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
  %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 %extraarg)
  %exp = call <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float> %vec)
  %exp2 = call <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float> %vec)
  %log = call <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float> %vec)
  %log2 = call <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float> %vec)
  %log10 = call <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float> %vec)
  ret void
}

define void @powi(<vscale x 4 x float> %vec) {
; CHECK-VSCALE-1-LABEL: 'powi'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:14 CodeSize:7 Lat:21 SizeLat:7 for: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'powi'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:14 CodeSize:7 Lat:21 SizeLat:7 for: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'powi'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
  ret void
}

declare <vscale x 4 x float> @llvm.sin.nxv4f32(<vscale x 4 x float>)
declare <vscale x 4 x float> @llvm.cos.nxv4f32(<vscale x 4 x float>)
declare <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float>, i32)
declare <vscale x 4 x float> @llvm.exp.nxv4f32(<vscale x 4 x float>)
declare <vscale x 4 x float> @llvm.exp2.nxv4f32(<vscale x 4 x float>)
declare <vscale x 4 x float> @llvm.log.nxv4f32(<vscale x 4 x float>)
declare <vscale x 4 x float> @llvm.log2.nxv4f32(<vscale x 4 x float>)
declare <vscale x 4 x float> @llvm.log10.nxv4f32(<vscale x 4 x float>)

define void @vector_splice(i32 %offset) #0 {
; CHECK-VSCALE-1-LABEL: 'vector_splice'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %1 = call <vscale x 16 x i8> @llvm.vector.splice.left.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %2 = call <vscale x 32 x i8> @llvm.vector.splice.left.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %3 = call <vscale x 2 x i16> @llvm.vector.splice.left.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %4 = call <vscale x 4 x i16> @llvm.vector.splice.left.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %5 = call <vscale x 8 x i16> @llvm.vector.splice.left.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %6 = call <vscale x 16 x i16> @llvm.vector.splice.left.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %7 = call <vscale x 4 x i32> @llvm.vector.splice.left.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %8 = call <vscale x 8 x i32> @llvm.vector.splice.left.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %9 = call <vscale x 2 x i64> @llvm.vector.splice.left.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %10 = call <vscale x 4 x i64> @llvm.vector.splice.left.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %11 = call <vscale x 2 x half> @llvm.vector.splice.left.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %12 = call <vscale x 4 x half> @llvm.vector.splice.left.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %13 = call <vscale x 8 x half> @llvm.vector.splice.left.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %14 = call <vscale x 16 x half> @llvm.vector.splice.left.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %15 = call <vscale x 2 x float> @llvm.vector.splice.left.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %16 = call <vscale x 4 x float> @llvm.vector.splice.left.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %17 = call <vscale x 8 x float> @llvm.vector.splice.left.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %18 = call <vscale x 2 x double> @llvm.vector.splice.left.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %19 = call <vscale x 4 x double> @llvm.vector.splice.left.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %20 = call <vscale x 2 x bfloat> @llvm.vector.splice.left.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %21 = call <vscale x 4 x bfloat> @llvm.vector.splice.left.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %22 = call <vscale x 8 x bfloat> @llvm.vector.splice.left.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %23 = call <vscale x 16 x bfloat> @llvm.vector.splice.left.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %24 = call <vscale x 16 x i1> @llvm.vector.splice.left.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %25 = call <vscale x 8 x i1> @llvm.vector.splice.left.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %26 = call <vscale x 4 x i1> @llvm.vector.splice.left.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %27 = call <vscale x 2 x i1> @llvm.vector.splice.left.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %28 = call <vscale x 16 x i8> @llvm.vector.splice.right.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %29 = call <vscale x 32 x i8> @llvm.vector.splice.right.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %30 = call <vscale x 1 x i16> @llvm.vector.splice.right.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %31 = call <vscale x 2 x i16> @llvm.vector.splice.right.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %32 = call <vscale x 4 x i16> @llvm.vector.splice.right.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %33 = call <vscale x 8 x i16> @llvm.vector.splice.right.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %34 = call <vscale x 16 x i16> @llvm.vector.splice.right.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %35 = call <vscale x 4 x i32> @llvm.vector.splice.right.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %36 = call <vscale x 8 x i32> @llvm.vector.splice.right.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %37 = call <vscale x 1 x i64> @llvm.vector.splice.right.nxv1i64(<vscale x 1 x i64> zeroinitializer, <vscale x 1 x i64> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %38 = call <vscale x 2 x i64> @llvm.vector.splice.right.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %39 = call <vscale x 4 x i64> @llvm.vector.splice.right.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %40 = call <vscale x 1 x half> @llvm.vector.splice.right.nxv1f16(<vscale x 1 x half> zeroinitializer, <vscale x 1 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %41 = call <vscale x 2 x half> @llvm.vector.splice.right.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %42 = call <vscale x 4 x half> @llvm.vector.splice.right.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %43 = call <vscale x 8 x half> @llvm.vector.splice.right.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %44 = call <vscale x 16 x half> @llvm.vector.splice.right.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %45 = call <vscale x 1 x float> @llvm.vector.splice.right.nxv1f32(<vscale x 1 x float> zeroinitializer, <vscale x 1 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %46 = call <vscale x 2 x float> @llvm.vector.splice.right.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %47 = call <vscale x 4 x float> @llvm.vector.splice.right.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %48 = call <vscale x 8 x float> @llvm.vector.splice.right.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %49 = call <vscale x 1 x double> @llvm.vector.splice.right.nxv1f64(<vscale x 1 x double> zeroinitializer, <vscale x 1 x double> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %50 = call <vscale x 2 x double> @llvm.vector.splice.right.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %51 = call <vscale x 4 x double> @llvm.vector.splice.right.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %52 = call <vscale x 1 x bfloat> @llvm.vector.splice.right.nxv1bf16(<vscale x 1 x bfloat> zeroinitializer, <vscale x 1 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %53 = call <vscale x 2 x bfloat> @llvm.vector.splice.right.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %54 = call <vscale x 4 x bfloat> @llvm.vector.splice.right.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 3 for: %55 = call <vscale x 8 x bfloat> @llvm.vector.splice.right.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %56 = call <vscale x 16 x bfloat> @llvm.vector.splice.right.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %57 = call <vscale x 16 x i1> @llvm.vector.splice.right.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %58 = call <vscale x 8 x i1> @llvm.vector.splice.right.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %59 = call <vscale x 4 x i1> @llvm.vector.splice.right.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %60 = call <vscale x 2 x i1> @llvm.vector.splice.right.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %61 = call <vscale x 1 x i1> @llvm.vector.splice.right.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %left.variable = call <vscale x 4 x i32> @llvm.vector.splice.left.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 %offset)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of Invalid for: %right.variable = call <vscale x 4 x i32> @llvm.vector.splice.right.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 %offset)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'vector_splice'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %1 = call <vscale x 16 x i8> @llvm.vector.splice.left.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %2 = call <vscale x 32 x i8> @llvm.vector.splice.left.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %3 = call <vscale x 2 x i16> @llvm.vector.splice.left.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %4 = call <vscale x 4 x i16> @llvm.vector.splice.left.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %5 = call <vscale x 8 x i16> @llvm.vector.splice.left.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %6 = call <vscale x 16 x i16> @llvm.vector.splice.left.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %7 = call <vscale x 4 x i32> @llvm.vector.splice.left.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %8 = call <vscale x 8 x i32> @llvm.vector.splice.left.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %9 = call <vscale x 2 x i64> @llvm.vector.splice.left.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %10 = call <vscale x 4 x i64> @llvm.vector.splice.left.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %11 = call <vscale x 2 x half> @llvm.vector.splice.left.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %12 = call <vscale x 4 x half> @llvm.vector.splice.left.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %13 = call <vscale x 8 x half> @llvm.vector.splice.left.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %14 = call <vscale x 16 x half> @llvm.vector.splice.left.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %15 = call <vscale x 2 x float> @llvm.vector.splice.left.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %16 = call <vscale x 4 x float> @llvm.vector.splice.left.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %17 = call <vscale x 8 x float> @llvm.vector.splice.left.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %18 = call <vscale x 2 x double> @llvm.vector.splice.left.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %19 = call <vscale x 4 x double> @llvm.vector.splice.left.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %20 = call <vscale x 2 x bfloat> @llvm.vector.splice.left.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %21 = call <vscale x 4 x bfloat> @llvm.vector.splice.left.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %22 = call <vscale x 8 x bfloat> @llvm.vector.splice.left.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %23 = call <vscale x 16 x bfloat> @llvm.vector.splice.left.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 4 for: %24 = call <vscale x 16 x i1> @llvm.vector.splice.left.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 4 for: %25 = call <vscale x 8 x i1> @llvm.vector.splice.left.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 4 for: %26 = call <vscale x 4 x i1> @llvm.vector.splice.left.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 4 for: %27 = call <vscale x 2 x i1> @llvm.vector.splice.left.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %28 = call <vscale x 16 x i8> @llvm.vector.splice.right.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %29 = call <vscale x 32 x i8> @llvm.vector.splice.right.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %30 = call <vscale x 1 x i16> @llvm.vector.splice.right.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %31 = call <vscale x 2 x i16> @llvm.vector.splice.right.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %32 = call <vscale x 4 x i16> @llvm.vector.splice.right.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %33 = call <vscale x 8 x i16> @llvm.vector.splice.right.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %34 = call <vscale x 16 x i16> @llvm.vector.splice.right.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %35 = call <vscale x 4 x i32> @llvm.vector.splice.right.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %36 = call <vscale x 8 x i32> @llvm.vector.splice.right.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %37 = call <vscale x 1 x i64> @llvm.vector.splice.right.nxv1i64(<vscale x 1 x i64> zeroinitializer, <vscale x 1 x i64> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %38 = call <vscale x 2 x i64> @llvm.vector.splice.right.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %39 = call <vscale x 4 x i64> @llvm.vector.splice.right.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %40 = call <vscale x 1 x half> @llvm.vector.splice.right.nxv1f16(<vscale x 1 x half> zeroinitializer, <vscale x 1 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %41 = call <vscale x 2 x half> @llvm.vector.splice.right.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %42 = call <vscale x 4 x half> @llvm.vector.splice.right.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %43 = call <vscale x 8 x half> @llvm.vector.splice.right.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %44 = call <vscale x 16 x half> @llvm.vector.splice.right.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %45 = call <vscale x 1 x float> @llvm.vector.splice.right.nxv1f32(<vscale x 1 x float> zeroinitializer, <vscale x 1 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %46 = call <vscale x 2 x float> @llvm.vector.splice.right.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %47 = call <vscale x 4 x float> @llvm.vector.splice.right.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %48 = call <vscale x 8 x float> @llvm.vector.splice.right.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %49 = call <vscale x 1 x double> @llvm.vector.splice.right.nxv1f64(<vscale x 1 x double> zeroinitializer, <vscale x 1 x double> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %50 = call <vscale x 2 x double> @llvm.vector.splice.right.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %51 = call <vscale x 4 x double> @llvm.vector.splice.right.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %52 = call <vscale x 1 x bfloat> @llvm.vector.splice.right.nxv1bf16(<vscale x 1 x bfloat> zeroinitializer, <vscale x 1 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %53 = call <vscale x 2 x bfloat> @llvm.vector.splice.right.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %54 = call <vscale x 4 x bfloat> @llvm.vector.splice.right.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 3 for: %55 = call <vscale x 8 x bfloat> @llvm.vector.splice.right.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %56 = call <vscale x 16 x bfloat> @llvm.vector.splice.right.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %57 = call <vscale x 16 x i1> @llvm.vector.splice.right.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %58 = call <vscale x 8 x i1> @llvm.vector.splice.right.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %59 = call <vscale x 4 x i1> @llvm.vector.splice.right.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 6 for: %60 = call <vscale x 2 x i1> @llvm.vector.splice.right.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %61 = call <vscale x 1 x i1> @llvm.vector.splice.right.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 1)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %left.variable = call <vscale x 4 x i32> @llvm.vector.splice.left.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 %offset)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of Invalid for: %right.variable = call <vscale x 4 x i32> @llvm.vector.splice.right.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 %offset)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'vector_splice'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %1 = call <vscale x 16 x i8> @llvm.vector.splice.left.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %2 = call <vscale x 32 x i8> @llvm.vector.splice.left.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %3 = call <vscale x 2 x i16> @llvm.vector.splice.left.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %4 = call <vscale x 4 x i16> @llvm.vector.splice.left.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %5 = call <vscale x 8 x i16> @llvm.vector.splice.left.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %6 = call <vscale x 16 x i16> @llvm.vector.splice.left.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %7 = call <vscale x 4 x i32> @llvm.vector.splice.left.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %8 = call <vscale x 8 x i32> @llvm.vector.splice.left.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %9 = call <vscale x 2 x i64> @llvm.vector.splice.left.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %10 = call <vscale x 4 x i64> @llvm.vector.splice.left.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %11 = call <vscale x 2 x half> @llvm.vector.splice.left.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %12 = call <vscale x 4 x half> @llvm.vector.splice.left.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %13 = call <vscale x 8 x half> @llvm.vector.splice.left.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %14 = call <vscale x 16 x half> @llvm.vector.splice.left.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %15 = call <vscale x 2 x float> @llvm.vector.splice.left.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %16 = call <vscale x 4 x float> @llvm.vector.splice.left.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %17 = call <vscale x 8 x float> @llvm.vector.splice.left.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %18 = call <vscale x 2 x double> @llvm.vector.splice.left.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %19 = call <vscale x 4 x double> @llvm.vector.splice.left.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %20 = call <vscale x 2 x bfloat> @llvm.vector.splice.left.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %21 = call <vscale x 4 x bfloat> @llvm.vector.splice.left.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %22 = call <vscale x 8 x bfloat> @llvm.vector.splice.left.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %23 = call <vscale x 16 x bfloat> @llvm.vector.splice.left.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %24 = call <vscale x 16 x i1> @llvm.vector.splice.left.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %25 = call <vscale x 8 x i1> @llvm.vector.splice.left.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %26 = call <vscale x 4 x i1> @llvm.vector.splice.left.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %27 = call <vscale x 2 x i1> @llvm.vector.splice.left.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %28 = call <vscale x 16 x i8> @llvm.vector.splice.right.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %29 = call <vscale x 32 x i8> @llvm.vector.splice.right.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %30 = call <vscale x 1 x i16> @llvm.vector.splice.right.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %31 = call <vscale x 2 x i16> @llvm.vector.splice.right.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %32 = call <vscale x 4 x i16> @llvm.vector.splice.right.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %33 = call <vscale x 8 x i16> @llvm.vector.splice.right.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %34 = call <vscale x 16 x i16> @llvm.vector.splice.right.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %35 = call <vscale x 4 x i32> @llvm.vector.splice.right.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %36 = call <vscale x 8 x i32> @llvm.vector.splice.right.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %37 = call <vscale x 1 x i64> @llvm.vector.splice.right.nxv1i64(<vscale x 1 x i64> zeroinitializer, <vscale x 1 x i64> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %38 = call <vscale x 2 x i64> @llvm.vector.splice.right.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %39 = call <vscale x 4 x i64> @llvm.vector.splice.right.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %40 = call <vscale x 1 x half> @llvm.vector.splice.right.nxv1f16(<vscale x 1 x half> zeroinitializer, <vscale x 1 x half> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %41 = call <vscale x 2 x half> @llvm.vector.splice.right.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %42 = call <vscale x 4 x half> @llvm.vector.splice.right.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %43 = call <vscale x 8 x half> @llvm.vector.splice.right.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %44 = call <vscale x 16 x half> @llvm.vector.splice.right.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %45 = call <vscale x 1 x float> @llvm.vector.splice.right.nxv1f32(<vscale x 1 x float> zeroinitializer, <vscale x 1 x float> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %46 = call <vscale x 2 x float> @llvm.vector.splice.right.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %47 = call <vscale x 4 x float> @llvm.vector.splice.right.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %48 = call <vscale x 8 x float> @llvm.vector.splice.right.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %49 = call <vscale x 1 x double> @llvm.vector.splice.right.nxv1f64(<vscale x 1 x double> zeroinitializer, <vscale x 1 x double> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %50 = call <vscale x 2 x double> @llvm.vector.splice.right.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %51 = call <vscale x 4 x double> @llvm.vector.splice.right.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %52 = call <vscale x 1 x bfloat> @llvm.vector.splice.right.nxv1bf16(<vscale x 1 x bfloat> zeroinitializer, <vscale x 1 x bfloat> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %53 = call <vscale x 2 x bfloat> @llvm.vector.splice.right.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %54 = call <vscale x 4 x bfloat> @llvm.vector.splice.right.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %55 = call <vscale x 8 x bfloat> @llvm.vector.splice.right.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %56 = call <vscale x 16 x bfloat> @llvm.vector.splice.right.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %57 = call <vscale x 16 x i1> @llvm.vector.splice.right.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %58 = call <vscale x 8 x i1> @llvm.vector.splice.right.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %59 = call <vscale x 4 x i1> @llvm.vector.splice.right.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %60 = call <vscale x 2 x i1> @llvm.vector.splice.right.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %61 = call <vscale x 1 x i1> @llvm.vector.splice.right.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 1)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %left.variable = call <vscale x 4 x i32> @llvm.vector.splice.left.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 %offset)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %right.variable = call <vscale x 4 x i32> @llvm.vector.splice.right.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 %offset)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;

  %splice_nxv16i8 = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 1)
  %splice_nxv32i8 = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 1)
  %splice_nxv2i16 = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 1)
  %splice_nxv4i16 = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 1)
  %splice_nxv8i16 = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 1)
  %splice_nxv16i16 = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 1)
  %splice_nxv4i32 = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 1)
  %splice_nxv8i32 = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 1)
  %splice_nxv2i64 = call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 1)
  %splice_nxv4i64 = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 1)
  %splice_nxv2f16 = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 1)
  %splice_nxv4f16 = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 1)
  %splice_nxv8f16 = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 1)
  %splice_nxv16f16 = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 1)
  %splice_nxv2f32 = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 1)
  %splice_nxv4f32 = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 1)
  %splice_nxv8f32 = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 1)
  %splice_nxv2f64 = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 1)
  %splice_nxv4f64 = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 1)
  %splice_nxv2bf16 = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 1)
  %splice_nxv4bf16 = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 1)
  %splice_nxv8bf16 = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 1)
  %splice_nxv16bf16 = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 1)
  %splice_nxv16i1 = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 1)
  %splice_nxv8i1 =  call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 1)
  %splice_nxv4i1 = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 1)
  %splice_nxv2i1 = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 1)
;; negative Index
  %splice_nxv16i8_neg = call <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i8> zeroinitializer, i32 -1)
  %splice_nxv32i8_neg = call <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8> zeroinitializer, <vscale x 32 x i8> zeroinitializer, i32 -1)
  %splice_nxv1i16_neg = call <vscale x 1 x i16> @llvm.vector.splice.nxv1i16(<vscale x 1 x i16> zeroinitializer, <vscale x 1 x i16> zeroinitializer, i32 -1)
  %splice_nxv2i16_neg = call <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16> zeroinitializer, <vscale x 2 x i16> zeroinitializer, i32 -1)
  %splice_nxv4i16_neg = call <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16> zeroinitializer, <vscale x 4 x i16> zeroinitializer, i32 -1)
  %splice_nxv8i16_neg = call <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i16> zeroinitializer, i32 -1)
  %splice_nxv16i16_neg = call <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16> zeroinitializer, <vscale x 16 x i16> zeroinitializer, i32 -1)
  %splice_nxv4i32_neg = call <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 -1)
  %splice_nxv8i32_neg = call <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32> zeroinitializer, <vscale x 8 x i32> zeroinitializer, i32 -1)
  %splice_nxv1i64_neg= call <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64> zeroinitializer, <vscale x 1 x i64> zeroinitializer, i32 -1)
  %splice_nxv2i64_neg= call <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i64> zeroinitializer, i32 -1)
  %splice_nxv4i64_neg = call <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64> zeroinitializer, <vscale x 4 x i64> zeroinitializer, i32 -1)
  %splice_nxv1f16_neg = call <vscale x 1 x half> @llvm.vector.splice.nxv1f16(<vscale x 1 x half> zeroinitializer, <vscale x 1 x half> zeroinitializer, i32 -1)
  %splice_nxv2f16_neg = call <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half> zeroinitializer, <vscale x 2 x half> zeroinitializer, i32 -1)
  %splice_nxv4f16_neg = call <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half> zeroinitializer, <vscale x 4 x half> zeroinitializer, i32 -1)
  %splice_nxv8f16_neg = call <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half> zeroinitializer, <vscale x 8 x half> zeroinitializer, i32 -1)
  %splice_nxv16f16_neg = call <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half> zeroinitializer, <vscale x 16 x half> zeroinitializer, i32 -1)
  %splice_nxv1f32_neg = call <vscale x 1 x float> @llvm.vector.splice.nxv1f32(<vscale x 1 x float> zeroinitializer, <vscale x 1 x float> zeroinitializer, i32 -1)
  %splice_nxv2f32_neg = call <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float> zeroinitializer, <vscale x 2 x float> zeroinitializer, i32 -1)
  %splice_nxv4f32_neg = call <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float> zeroinitializer, <vscale x 4 x float> zeroinitializer, i32 -1)
  %splice_nxv8f32_neg = call <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float> zeroinitializer, <vscale x 8 x float> zeroinitializer, i32 -1)
  %splice_nxv1f64_neg = call <vscale x 1 x double> @llvm.vector.splice.nxv1f64(<vscale x 1 x double> zeroinitializer, <vscale x 1 x double> zeroinitializer, i32 -1)
  %splice_nxv2f64_neg = call <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double> zeroinitializer, <vscale x 2 x double> zeroinitializer, i32 -1)
  %splice_nxv4f64_neg = call <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double> zeroinitializer, <vscale x 4 x double> zeroinitializer, i32 -1)
  %splice_nxv1bf16_neg = call <vscale x 1 x bfloat> @llvm.vector.splice.nxv1bf16(<vscale x 1 x bfloat> zeroinitializer, <vscale x 1 x bfloat> zeroinitializer, i32 -1)
  %splice_nxv2bf16_neg = call <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat> zeroinitializer, <vscale x 2 x bfloat> zeroinitializer, i32 -1)
  %splice_nxv4bf16_neg = call <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat> zeroinitializer, <vscale x 4 x bfloat> zeroinitializer, i32 -1)
  %splice_nxv8bf16_neg = call <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat> zeroinitializer, <vscale x 8 x bfloat> zeroinitializer, i32 -1)
  %splice_nxv16bf16_neg = call <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat> zeroinitializer, <vscale x 16 x bfloat> zeroinitializer, i32 -1)
  %splice_nxv16i1_neg = call <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1> zeroinitializer, <vscale x 16 x i1> zeroinitializer, i32 -1)
  %splice_nxv8i1_neg =  call <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1> zeroinitializer, <vscale x 8 x i1> zeroinitializer, i32 -1)
  %splice_nxv4i1_neg = call <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1> zeroinitializer, <vscale x 4 x i1> zeroinitializer, i32 -1)
  %splice_nxv2i1_neg = call <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1> zeroinitializer, <vscale x 2 x i1> zeroinitializer, i32 -1)
  %splice_nxv1i1_neg = call <vscale x 1 x i1> @llvm.vector.splice.nxv1i1(<vscale x 1 x i1> zeroinitializer, <vscale x 1 x i1> zeroinitializer, i32 -1)

  %left.variable = call <vscale x 4 x i32> @llvm.vector.splice.left(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 %offset)
  %right.variable = call <vscale x 4 x i32> @llvm.vector.splice.right(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i32> zeroinitializer, i32 %offset)
  ret void
}

declare <vscale x 1 x i1> @llvm.vector.splice.nxv1i1(<vscale x 1 x i1>, <vscale x 1 x i1>, i32)
declare <vscale x 2 x i1> @llvm.vector.splice.nxv2i1(<vscale x 2 x i1>, <vscale x 2 x i1>, i32)
declare <vscale x 4 x i1> @llvm.vector.splice.nxv4i1(<vscale x 4 x i1>, <vscale x 4 x i1>, i32)
declare <vscale x 8 x i1> @llvm.vector.splice.nxv8i1(<vscale x 8 x i1>, <vscale x 8 x i1>, i32)
declare <vscale x 16 x i1> @llvm.vector.splice.nxv16i1(<vscale x 16 x i1>, <vscale x 16 x i1>, i32)
declare <vscale x 1 x i8> @llvm.vector.splice.nxv1i8(<vscale x 1 x i8>, <vscale x 1 x i8>, i32)
declare <vscale x 2 x i8> @llvm.vector.splice.nxv2i8(<vscale x 2 x i8>, <vscale x 2 x i8>, i32)
declare <vscale x 16 x i8> @llvm.vector.splice.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, i32)
declare <vscale x 32 x i8> @llvm.vector.splice.nxv32i8(<vscale x 32 x i8>, <vscale x 32 x i8>, i32)
declare <vscale x 1 x i16> @llvm.vector.splice.nxv1i16(<vscale x 1 x i16>, <vscale x 1 x i16>, i32)
declare <vscale x 2 x i16> @llvm.vector.splice.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i16>, i32)
declare <vscale x 4 x i16> @llvm.vector.splice.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i16>, i32)
declare <vscale x 8 x i16> @llvm.vector.splice.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, i32)
declare <vscale x 16 x i16> @llvm.vector.splice.nxv16i16(<vscale x 16 x i16>, <vscale x 16 x i16>, i32)
declare <vscale x 4 x i32> @llvm.vector.splice.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, i32)
declare <vscale x 8 x i32> @llvm.vector.splice.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32>, i32)
declare <vscale x 1 x i64> @llvm.vector.splice.nxv1i64(<vscale x 1 x i64>, <vscale x 1 x i64>, i32)
declare <vscale x 2 x i64> @llvm.vector.splice.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, i32)
declare <vscale x 4 x i64> @llvm.vector.splice.nxv4i64(<vscale x 4 x i64>, <vscale x 4 x i64>, i32)
declare <vscale x 1 x half> @llvm.vector.splice.nxv1f16(<vscale x 1 x half>, <vscale x 1 x half>, i32)
declare <vscale x 2 x half> @llvm.vector.splice.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>, i32)
declare <vscale x 4 x half> @llvm.vector.splice.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>, i32)
declare <vscale x 8 x half> @llvm.vector.splice.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, i32)
declare <vscale x 16 x half> @llvm.vector.splice.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>, i32)
declare <vscale x 1 x bfloat> @llvm.vector.splice.nxv1bf16(<vscale x 1 x bfloat>, <vscale x 1 x bfloat>, i32)
declare <vscale x 2 x bfloat> @llvm.vector.splice.nxv2bf16(<vscale x 2 x bfloat>, <vscale x 2 x bfloat>, i32)
declare <vscale x 4 x bfloat> @llvm.vector.splice.nxv4bf16(<vscale x 4 x bfloat>, <vscale x 4 x bfloat>, i32)
declare <vscale x 8 x bfloat> @llvm.vector.splice.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>, i32)
declare <vscale x 16 x bfloat> @llvm.vector.splice.nxv16bf16(<vscale x 16 x bfloat>, <vscale x 16 x bfloat>, i32)
declare <vscale x 1 x float> @llvm.vector.splice.nxv1f32(<vscale x 1 x float>, <vscale x 1 x float>, i32)
declare <vscale x 2 x float> @llvm.vector.splice.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>, i32)
declare <vscale x 4 x float> @llvm.vector.splice.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, i32)
declare <vscale x 8 x float> @llvm.vector.splice.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>, i32)
declare <vscale x 16 x float> @llvm.vector.splice.nxv16f32(<vscale x 16 x float>, <vscale x 16 x float>, i32)
declare <vscale x 1 x double> @llvm.vector.splice.nxv1f64(<vscale x 1 x double>, <vscale x 1 x double>, i32)
declare <vscale x 2 x double> @llvm.vector.splice.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, i32)
declare <vscale x 4 x double> @llvm.vector.splice.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>, i32)

define void @get_lane_mask() #0 {
; CHECK-VSCALE-1-LABEL: 'get_lane_mask'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 poison, i64 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 poison, i64 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 poison, i64 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 poison, i64 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 poison, i32 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 poison, i32 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 poison, i32 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 poison, i32 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 13 for: %mask_nxv64i1_i64 = call <vscale x 64 x i1> @llvm.get.active.lane.mask.nxv64i1.i64(i64 poison, i64 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 5 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 poison, i64 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 poison, i16 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 poison, i64 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 poison, i64 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 poison, i64 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 poison, i64 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 poison, i32 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 poison, i32 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 poison, i32 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 poison, i32 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 48 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 poison, i64 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 6 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 poison, i16 poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-SVE-LABEL: 'get_lane_mask'
; CHECK-SVE-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 poison, i64 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 poison, i64 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 poison, i64 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 poison, i64 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 poison, i32 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 poison, i32 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 poison, i32 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 poison, i32 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 13 for: %mask_nxv64i1_i64 = call <vscale x 64 x i1> @llvm.get.active.lane.mask.nxv64i1.i64(i64 poison, i64 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 5 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 poison, i64 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 poison, i16 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 poison, i64 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 poison, i64 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 poison, i64 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 poison, i64 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 poison, i32 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 poison, i32 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 poison, i32 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 poison, i32 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 48 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 poison, i64 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of 6 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 poison, i16 poison)
; CHECK-SVE-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-SVE2p1-OR-SME2-LABEL: 'get_lane_mask'
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 poison, i64 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 poison, i64 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 poison, i64 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 poison, i64 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 poison, i32 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 poison, i32 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 poison, i32 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 poison, i32 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 5 for: %mask_nxv64i1_i64 = call <vscale x 64 x i1> @llvm.get.active.lane.mask.nxv64i1.i64(i64 poison, i64 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 poison, i64 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 poison, i16 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 poison, i64 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 poison, i64 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 poison, i64 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 poison, i64 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 poison, i32 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 poison, i32 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 poison, i32 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 poison, i32 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 48 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 poison, i64 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of 6 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 poison, i16 poison)
; CHECK-SVE2p1-OR-SME2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'get_lane_mask'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 poison, i64 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 poison, i64 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 poison, i64 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 poison, i64 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 poison, i32 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 poison, i32 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 poison, i32 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 poison, i32 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 13 for: %mask_nxv64i1_i64 = call <vscale x 64 x i1> @llvm.get.active.lane.mask.nxv64i1.i64(i64 poison, i64 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 5 for: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 poison, i64 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 poison, i16 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 32 for: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 poison, i64 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 16 for: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 poison, i64 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 8 for: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 poison, i64 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 4 for: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 poison, i64 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 32 for: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 poison, i32 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 16 for: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 poison, i32 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 8 for: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 poison, i32 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 4 for: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 poison, i32 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 48 for: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 poison, i64 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 6 for: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 poison, i16 poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 poison, i64 poison)
  %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 poison, i64 poison)
  %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 poison, i64 poison)
  %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 poison, i64 poison)

  %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 poison, i32 poison)
  %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 poison, i32 poison)
  %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 poison, i32 poison)
  %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 poison, i32 poison)

  %mask_nxv64i1_i64 = call <vscale x 64 x i1> @llvm.get.active.lane.mask.nxv64i1.i64(i64 poison, i64 poison)
  %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 poison, i64 poison)
  %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 poison, i16 poison)

  %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 poison, i64 poison)
  %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 poison, i64 poison)
  %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 poison, i64 poison)
  %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 poison, i64 poison)

  %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 poison, i32 poison)
  %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 poison, i32 poison)
  %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 poison, i32 poison)
  %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 poison, i32 poison)

  %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 poison, i64 poison)
  %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 poison, i16 poison)

  ret void
}

define void @fshr() #0 {
; CHECK-VSCALE-1-LABEL: 'fshr'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'fshr'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'fshr'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 7 for: %1 = call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 7 for: %2 = call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 7 for: %3 = call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 7 for: %4 = call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  call <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison)
  call <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison)
  call <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison)
  call <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison)
  ret void
}

define void @fshl() #0 {
; CHECK-VSCALE-1-LABEL: 'fshl'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'fshl'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 5 for: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 5 for: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 5 for: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 5 for: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'fshl'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 7 for: %1 = call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 7 for: %2 = call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 7 for: %3 = call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 7 for: %4 = call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  call <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8> poison, <vscale x 16 x i8> poison, <vscale x 16 x i8> poison)
  call <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16> poison, <vscale x 8 x i16> poison, <vscale x 8 x i16> poison)
  call <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32> poison, <vscale x 4 x i32> poison, <vscale x 4 x i32> poison)
  call <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64> poison, <vscale x 2 x i64> poison, <vscale x 2 x i64> poison)
  ret void
}

define <vscale x 4 x i32> @masked_gather_nxv4i32(<vscale x 4 x ptr> %ld, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru) {
; CHECK-VSCALE-1-LABEL: 'masked_gather_nxv4i32'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:40 CodeSize:40 Lat:160 SizeLat:40 for: %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> align 4 %ld, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <vscale x 4 x i32> %res
;
; CHECK-VSCALE-2-LABEL: 'masked_gather_nxv4i32'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:80 CodeSize:80 Lat:320 SizeLat:80 for: %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> align 4 %ld, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <vscale x 4 x i32> %res
;
; TYPE_BASED_ONLY-LABEL: 'masked_gather_nxv4i32'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32.nxv4p0(<vscale x 4 x ptr> align 4 %ld, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <vscale x 4 x i32> %res
;
  %res = call <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x ptr> %ld, i32 0, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
  ret <vscale x 4 x i32> %res
}

define <vscale x 8 x i32> @masked_gather_nxv8i32(<vscale x 8 x ptr> %ld, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru) {
; CHECK-VSCALE-1-LABEL: 'masked_gather_nxv8i32'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:80 CodeSize:80 Lat:320 SizeLat:80 for: %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0(<vscale x 8 x ptr> align 4 %ld, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <vscale x 8 x i32> %res
;
; CHECK-VSCALE-2-LABEL: 'masked_gather_nxv8i32'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:160 CodeSize:160 Lat:640 SizeLat:160 for: %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0(<vscale x 8 x ptr> align 4 %ld, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <vscale x 8 x i32> %res
;
; TYPE_BASED_ONLY-LABEL: 'masked_gather_nxv8i32'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32.nxv8p0(<vscale x 8 x ptr> align 4 %ld, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <vscale x 8 x i32> %res
;
  %res = call <vscale x 8 x i32> @llvm.masked.gather.nxv8i32(<vscale x 8 x ptr> %ld, i32 0, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
  ret <vscale x 8 x i32> %res
}

define <4 x i32> @masked_gather_v4i32(<4 x ptr> %ld, <4 x i1> %masks, <4 x i32> %passthru) {
; CHECK-VSCALE-1-LABEL: 'masked_gather_v4i32'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:28 CodeSize:20 Lat:44 SizeLat:32 for: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0(<4 x ptr> align 4 %ld, <4 x i1> %masks, <4 x i32> %passthru)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x i32> %res
;
; CHECK-VSCALE-2-LABEL: 'masked_gather_v4i32'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:28 CodeSize:20 Lat:44 SizeLat:32 for: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0(<4 x ptr> align 4 %ld, <4 x i1> %masks, <4 x i32> %passthru)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x i32> %res
;
; TYPE_BASED_ONLY-LABEL: 'masked_gather_v4i32'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:36 CodeSize:20 Lat:36 SizeLat:36 for: %res = call <4 x i32> @llvm.masked.gather.v4i32.v4p0(<4 x ptr> align 4 %ld, <4 x i1> %masks, <4 x i32> %passthru)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <4 x i32> %res
;
  %res = call <4 x i32> @llvm.masked.gather.v4i32(<4 x ptr> %ld, i32 0, <4 x i1> %masks, <4 x i32> %passthru)
  ret <4 x i32> %res
}

define <1 x i128> @masked_gather_v1i128(<1 x ptr> %ld, <1 x i1> %masks, <1 x i128> %passthru) {
; CHECK-VSCALE-1-LABEL: 'masked_gather_v1i128'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:6 Lat:11 SizeLat:9 for: %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0(<1 x ptr> align 16 %ld, <1 x i1> %masks, <1 x i128> %passthru)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <1 x i128> %res
;
; CHECK-VSCALE-2-LABEL: 'masked_gather_v1i128'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:6 Lat:11 SizeLat:9 for: %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0(<1 x ptr> align 16 %ld, <1 x i1> %masks, <1 x i128> %passthru)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <1 x i128> %res
;
; TYPE_BASED_ONLY-LABEL: 'masked_gather_v1i128'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0(<1 x ptr> align 16 %ld, <1 x i1> %masks, <1 x i128> %passthru)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret <1 x i128> %res
;
  %res = call <1 x i128> @llvm.masked.gather.v1i128.v1p0(<1 x ptr> %ld, i32 0, <1 x i1> %masks, <1 x i128> %passthru)
  ret <1 x i128> %res
}

define void @masked_scatter_nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x ptr> %ptrs, <vscale x 4 x i1> %masks) {
; CHECK-VSCALE-1-LABEL: 'masked_scatter_nxv4i32'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 40 for: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> %data, <vscale x 4 x ptr> align 4 %ptrs, <vscale x 4 x i1> %masks)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatter_nxv4i32'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 80 for: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> %data, <vscale x 4 x ptr> align 4 %ptrs, <vscale x 4 x i1> %masks)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'masked_scatter_nxv4i32'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> %data, <vscale x 4 x ptr> align 4 %ptrs, <vscale x 4 x i1> %masks)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;

  call void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x ptr> %ptrs, i32 0, <vscale x 4 x i1> %masks)
  ret void
}

define void @masked_scatter_nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x ptr> %ptrs, <vscale x 8 x i1> %masks) {
; CHECK-VSCALE-1-LABEL: 'masked_scatter_nxv8i32'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 80 for: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %data, <vscale x 8 x ptr> align 4 %ptrs, <vscale x 8 x i1> %masks)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatter_nxv8i32'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 160 for: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %data, <vscale x 8 x ptr> align 4 %ptrs, <vscale x 8 x i1> %masks)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'masked_scatter_nxv8i32'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of Invalid for: call void @llvm.masked.scatter.nxv8i32.nxv8p0(<vscale x 8 x i32> %data, <vscale x 8 x ptr> align 4 %ptrs, <vscale x 8 x i1> %masks)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;

  call void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x ptr> %ptrs, i32 0, <vscale x 8 x i1> %masks)
  ret void
}

define void @masked_scatter_v4i32(<4 x i32> %data, <4 x ptr> %ptrs, <4 x i1> %masks) {
; CHECK-VSCALE-1-LABEL: 'masked_scatter_v4i32'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:28 CodeSize:20 Lat:32 SizeLat:32 for: call void @llvm.masked.scatter.v4i32.v4p0(<4 x i32> %data, <4 x ptr> align 4 %ptrs, <4 x i1> %masks)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatter_v4i32'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:28 CodeSize:20 Lat:32 SizeLat:32 for: call void @llvm.masked.scatter.v4i32.v4p0(<4 x i32> %data, <4 x ptr> align 4 %ptrs, <4 x i1> %masks)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'masked_scatter_v4i32'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:28 CodeSize:16 Lat:28 SizeLat:28 for: call void @llvm.masked.scatter.v4i32.v4p0(<4 x i32> %data, <4 x ptr> align 4 %ptrs, <4 x i1> %masks)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;

  call void @llvm.masked.scatter.v4i32(<4 x i32> %data, <4 x ptr> %ptrs, i32 0, <4 x i1> %masks)
  ret void
}

define void @masked_scatter_v1i128(<1 x i128> %data, <1 x ptr> %ptrs, <1 x i1> %masks) {
; CHECK-VSCALE-1-LABEL: 'masked_scatter_v1i128'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:6 Lat:8 SizeLat:9 for: call void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> align 16 %ptrs, <1 x i1> %masks)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'masked_scatter_v1i128'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:8 CodeSize:6 Lat:8 SizeLat:9 for: call void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> align 16 %ptrs, <1 x i1> %masks)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'masked_scatter_v1i128'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: call void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> align 16 %ptrs, <1 x i1> %masks)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;

  call void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> %ptrs, i32 0, <1 x i1> %masks)
  ret void
}

define void @histogram_nxv2i64(<vscale x 2 x ptr> %buckets, <vscale x 2 x i1> %mask) #3 {
; CHECK-VSCALE-1-LABEL: 'histogram_nxv2i64'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %buckets, i64 1, <vscale x 2 x i1> %mask)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_nxv2i64'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %buckets, i64 1, <vscale x 2 x i1> %mask)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv2i64'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %buckets, i64 1, <vscale x 2 x i1> %mask)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  call void @llvm.experimental.vector.histogram.add.nxv2p0.i64(<vscale x 2 x ptr> %buckets, i64 1, <vscale x 2 x i1> %mask)
  ret void
}

define void @histogram_nxv4i32(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %mask) #3 {
; CHECK-VSCALE-1-LABEL: 'histogram_nxv4i32'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> %buckets, i32 1, <vscale x 4 x i1> %mask)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_nxv4i32'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> %buckets, i32 1, <vscale x 4 x i1> %mask)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv4i32'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 8 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> %buckets, i32 1, <vscale x 4 x i1> %mask)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  call void @llvm.experimental.vector.histogram.add.nxv4p0.i32(<vscale x 4 x ptr> %buckets, i32 1, <vscale x 4 x i1> %mask)
  ret void
}

define void @histogram_nxv8i16(<vscale x 8 x ptr> %buckets, <vscale x 8 x i1> %mask) #3 {
; CHECK-VSCALE-1-LABEL: 'histogram_nxv8i16'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_nxv8i16'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv8i16'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  call void @llvm.experimental.vector.histogram.add.nxv8p0.i16(<vscale x 8 x ptr> %buckets, i16 1, <vscale x 8 x i1> %mask)
  ret void
}

define void @histogram_nxv16i8(<vscale x 16 x ptr> %buckets, <vscale x 16 x i1> %mask) #3 {
; CHECK-VSCALE-1-LABEL: 'histogram_nxv16i8'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 32 for: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_nxv16i8'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 32 for: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv16i8'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 32 for: call void @llvm.experimental.vector.histogram.add.nxv16p0.i8(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  call void @llvm.experimental.vector.histogram.add.nxv16p0.i64(<vscale x 16 x ptr> %buckets, i8 1, <vscale x 16 x i1> %mask)
  ret void
}

define void @histogram_v2i64(<2 x ptr> %buckets, <2 x i1> %mask) {
; CHECK-VSCALE-1-LABEL: 'histogram_v2i64'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:10 CodeSize:8 Lat:16 SizeLat:10 for: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> %buckets, i64 1, <2 x i1> %mask)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_v2i64'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:10 CodeSize:8 Lat:16 SizeLat:10 for: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> %buckets, i64 1, <2 x i1> %mask)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_v2i64'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:10 CodeSize:8 Lat:16 SizeLat:10 for: call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> %buckets, i64 1, <2 x i1> %mask)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  call void @llvm.experimental.vector.histogram.add.v2p0.i64(<2 x ptr> %buckets, i64 1, <2 x i1> %mask)
  ret void
}

define void @histogram_v4i32(<4 x ptr> %buckets, <4 x i1> %mask) {
; CHECK-VSCALE-1-LABEL: 'histogram_v4i32'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:20 CodeSize:16 Lat:32 SizeLat:20 for: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_v4i32'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:20 CodeSize:16 Lat:32 SizeLat:20 for: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_v4i32'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:20 CodeSize:16 Lat:32 SizeLat:20 for: call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  call void @llvm.experimental.vector.histogram.add.v4p0.i32(<4 x ptr> %buckets, i32 1, <4 x i1> %mask)
  ret void
}

define void @histogram_v8i16(<8 x ptr> %buckets, <8 x i1> %mask) {
; CHECK-VSCALE-1-LABEL: 'histogram_v8i16'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:40 CodeSize:32 Lat:64 SizeLat:40 for: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> %buckets, i16 1, <8 x i1> %mask)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_v8i16'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:40 CodeSize:32 Lat:64 SizeLat:40 for: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> %buckets, i16 1, <8 x i1> %mask)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_v8i16'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:40 CodeSize:32 Lat:64 SizeLat:40 for: call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> %buckets, i16 1, <8 x i1> %mask)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  call void @llvm.experimental.vector.histogram.add.v8p0.i16(<8 x ptr> %buckets, i16 1, <8 x i1> %mask)
  ret void
}

define void @histogram_v16i8(<16 x ptr> %buckets, <16 x i1> %mask) {
; CHECK-VSCALE-1-LABEL: 'histogram_v16i8'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:80 CodeSize:64 Lat:128 SizeLat:80 for: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> %buckets, i8 1, <16 x i1> %mask)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_v16i8'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:80 CodeSize:64 Lat:128 SizeLat:80 for: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> %buckets, i8 1, <16 x i1> %mask)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_v16i8'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:80 CodeSize:64 Lat:128 SizeLat:80 for: call void @llvm.experimental.vector.histogram.add.v16p0.i8(<16 x ptr> %buckets, i8 1, <16 x i1> %mask)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  call void @llvm.experimental.vector.histogram.add.v16p0.i64(<16 x ptr> %buckets, i8 1, <16 x i1> %mask)
  ret void
}

define void @histogram_nxv4i64(<vscale x 4 x ptr> %buckets, <vscale x 4 x i1> %mask) #3 {
; CHECK-VSCALE-1-LABEL: 'histogram_nxv4i64'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'histogram_nxv4i64'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'histogram_nxv4i64'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 16 for: call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  call void @llvm.experimental.vector.histogram.add.nxv4p0.i64(<vscale x 4 x ptr> %buckets, i64 1, <vscale x 4 x i1> %mask)
  ret void
}

define void @match() #3 {
; CHECK-VSCALE-1-LABEL: 'match'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> poison, <vscale x 16 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> poison, <vscale x 8 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> poison, <vscale x 4 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> poison, <vscale x 2 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> poison, <16 x i8> poison, <16 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> poison, <8 x i16> poison, <8 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> poison, <4 x i32> poison, <4 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> poison, <2 x i64> poison, <2 x i1> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'match'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> poison, <vscale x 16 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> poison, <vscale x 8 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> poison, <vscale x 4 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> poison, <vscale x 2 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> poison, <16 x i8> poison, <16 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> poison, <8 x i16> poison, <8 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> poison, <4 x i32> poison, <4 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> poison, <2 x i64> poison, <2 x i1> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'match'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 4 for: %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> poison, <vscale x 16 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 4 for: %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> poison, <vscale x 8 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> poison, <vscale x 4 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> poison, <vscale x 2 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 14 for: %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> poison, <16 x i8> poison, <16 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 14 for: %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> poison, <8 x i16> poison, <8 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:29 CodeSize:21 Lat:29 SizeLat:29 for: %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> poison, <4 x i32> poison, <4 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:15 CodeSize:11 Lat:15 SizeLat:15 for: %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> poison, <2 x i64> poison, <2 x i1> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;

  %match_nxv16i8_v16i8 = call <vscale x 16 x i1> @llvm.experimental.vector.match.nxv16i8.v16i8(<vscale x 16 x i8> poison, <16 x i8> poison, <vscale x 16 x i1> poison)
  %match_nxv8i16_v8i16 = call <vscale x 8 x i1> @llvm.experimental.vector.match.nxv8i16.v8i16(<vscale x 8 x i16> poison, <8 x i16> poison, <vscale x 8 x i1> poison)
  %match_nxv4i32_v4i32 = call <vscale x 4 x i1> @llvm.experimental.vector.match.nxv4i32.v4i32(<vscale x 4 x i32> poison, <4 x i32> poison, <vscale x 4 x i1> poison)
  %match_nxv2i64_v2i64 = call <vscale x 2 x i1> @llvm.experimental.vector.match.nxv2i64.v2i64(<vscale x 2 x i64> poison, <2 x i64> poison, <vscale x 2 x i1> poison)

  %match_v16i8_v16i8 = call <16 x i1> @llvm.experimental.vector.match.v16i8.v16i8(<16 x i8> poison, <16 x i8> poison, <16 x i1> poison)
  %match_v8i16_v8i16 = call <8 x i1> @llvm.experimental.vector.match.v8i16.v8i16(<8 x i16> poison, <8 x i16> poison, <8 x i1> poison)
  %match_v4i32_v4i32 = call <4 x i1> @llvm.experimental.vector.match.v4i32.v4i32(<4 x i32> poison, <4 x i32> poison, <4 x i1> poison)
  %match_v2i64_v2i64 = call <2 x i1> @llvm.experimental.vector.match.v2i64.v2i64(<2 x i64> poison, <2 x i64> poison, <2 x i1> poison)

  ret void
}

define void @sqrt() #1 {
; CHECK-VSCALE-1-LABEL: 'sqrt'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %sqrt.nxv8f16 = call <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %sqrt.nxv4f32 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %sqrt.nxv2f64 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %sqrt.nxv4f64 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'sqrt'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %sqrt.nxv8f16 = call <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %sqrt.nxv4f32 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %sqrt.nxv2f64 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %sqrt.nxv4f64 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'sqrt'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %sqrt.nxv8f16 = call <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %sqrt.nxv4f32 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %sqrt.nxv2f64 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %sqrt.nxv4f64 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %sqrt.nxv8f16 = call <vscale x 8 x half> @llvm.sqrt.nxv8f16(<vscale x 8 x half> poison)
  %sqrt.nxv4f32 = call <vscale x 4 x float> @llvm.sqrt.nxv4f32(<vscale x 4 x float> poison)
  %sqrt.nxv2f64 = call <vscale x 2 x double> @llvm.sqrt.nxv2f64(<vscale x 2 x double> poison)
  %sqrt.nxv4f64 = call <vscale x 4 x double> @llvm.sqrt.nxv4f64(<vscale x 4 x double> poison)

  ret void
}

define void @fabs() #1 {
; CHECK-VSCALE-1-LABEL: 'fabs'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %fabs.nxv8f16 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %fabs.nxv4f32 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %fabs.nxv2f64 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %fabs.nxv4f64 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'fabs'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %fabs.nxv8f16 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %fabs.nxv4f32 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %fabs.nxv2f64 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %fabs.nxv4f64 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'fabs'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %fabs.nxv8f16 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %fabs.nxv4f32 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %fabs.nxv2f64 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %fabs.nxv4f64 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %fabs.nxv8f16 = call <vscale x 8 x half> @llvm.fabs.nxv8f16(<vscale x 8 x half> poison)
  %fabs.nxv4f32 = call <vscale x 4 x float> @llvm.fabs.nxv4f32(<vscale x 4 x float> poison)
  %fabs.nxv2f64 = call <vscale x 2 x double> @llvm.fabs.nxv2f64(<vscale x 2 x double> poison)
  %fabs.nxv4f64 = call <vscale x 4 x double> @llvm.fabs.nxv4f64(<vscale x 4 x double> poison)

  ret void
}

define void @ceil() #1 {
; CHECK-VSCALE-1-LABEL: 'ceil'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %ceil.nxv8f16 = call <vscale x 8 x half> @llvm.ceil.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %ceil.nxv4f32 = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %ceil.nxv2f64 = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %ceil.nxv4f64 = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'ceil'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %ceil.nxv8f16 = call <vscale x 8 x half> @llvm.ceil.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %ceil.nxv4f32 = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %ceil.nxv2f64 = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %ceil.nxv4f64 = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'ceil'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %ceil.nxv8f16 = call <vscale x 8 x half> @llvm.ceil.nxv8f16(<vscale x 8 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %ceil.nxv4f32 = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %ceil.nxv2f64 = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %ceil.nxv4f64 = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %ceil.nxv8f16 = call <vscale x 8 x half> @llvm.ceil.nxv8f16(<vscale x 8 x half> poison)
  %ceil.nxv4f32 = call <vscale x 4 x float> @llvm.ceil.nxv4f32(<vscale x 4 x float> poison)
  %ceil.nxv2f64 = call <vscale x 2 x double> @llvm.ceil.nxv2f64(<vscale x 2 x double> poison)
  %ceil.nxv4f64 = call <vscale x 4 x double> @llvm.ceil.nxv4f64(<vscale x 4 x double> poison)

  ret void
}

define void @floor() #1 {
; CHECK-VSCALE-1-LABEL: 'floor'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %floor.nxv8f16 = call <vscale x 8 x half> @llvm.floor.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %floor.nxv4f32 = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %floor.nxv2f64 = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %floor.nxv4f64 = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'floor'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %floor.nxv8f16 = call <vscale x 8 x half> @llvm.floor.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %floor.nxv4f32 = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %floor.nxv2f64 = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %floor.nxv4f64 = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'floor'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %floor.nxv8f16 = call <vscale x 8 x half> @llvm.floor.nxv8f16(<vscale x 8 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %floor.nxv4f32 = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %floor.nxv2f64 = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %floor.nxv4f64 = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %floor.nxv8f16 = call <vscale x 8 x half> @llvm.floor.nxv8f16(<vscale x 8 x half> poison)
  %floor.nxv4f32 = call <vscale x 4 x float> @llvm.floor.nxv4f32(<vscale x 4 x float> poison)
  %floor.nxv2f64 = call <vscale x 2 x double> @llvm.floor.nxv2f64(<vscale x 2 x double> poison)
  %floor.nxv4f64 = call <vscale x 4 x double> @llvm.floor.nxv4f64(<vscale x 4 x double> poison)

  ret void
}

define void @nearbyint() #1 {
; CHECK-VSCALE-1-LABEL: 'nearbyint'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %nearbyint.nxv8f16 = call <vscale x 8 x half> @llvm.nearbyint.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %nearbyint.nxv4f32 = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %nearbyint.nxv2f64 = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %nearbyint.nxv4f64 = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'nearbyint'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %nearbyint.nxv8f16 = call <vscale x 8 x half> @llvm.nearbyint.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %nearbyint.nxv4f32 = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %nearbyint.nxv2f64 = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %nearbyint.nxv4f64 = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'nearbyint'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %nearbyint.nxv8f16 = call <vscale x 8 x half> @llvm.nearbyint.nxv8f16(<vscale x 8 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %nearbyint.nxv4f32 = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %nearbyint.nxv2f64 = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %nearbyint.nxv4f64 = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %nearbyint.nxv8f16 = call <vscale x 8 x half> @llvm.nearbyint.nxv8f16(<vscale x 8 x half> poison)
  %nearbyint.nxv4f32 = call <vscale x 4 x float> @llvm.nearbyint.nxv4f32(<vscale x 4 x float> poison)
  %nearbyint.nxv2f64 = call <vscale x 2 x double> @llvm.nearbyint.nxv2f64(<vscale x 2 x double> poison)
  %nearbyint.nxv4f64 = call <vscale x 4 x double> @llvm.nearbyint.nxv4f64(<vscale x 4 x double> poison)

  ret void
}

define void @round() #1 {
; CHECK-VSCALE-1-LABEL: 'round'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %round.nxv8f16 = call <vscale x 8 x half> @llvm.round.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %round.nxv4f32 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %round.nxv2f64 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %round.nxv4f64 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'round'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %round.nxv8f16 = call <vscale x 8 x half> @llvm.round.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %round.nxv4f32 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %round.nxv2f64 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %round.nxv4f64 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'round'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %round.nxv8f16 = call <vscale x 8 x half> @llvm.round.nxv8f16(<vscale x 8 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %round.nxv4f32 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %round.nxv2f64 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %round.nxv4f64 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %round.nxv8f16 = call <vscale x 8 x half> @llvm.round.nxv8f16(<vscale x 8 x half> poison)
  %round.nxv4f32 = call <vscale x 4 x float> @llvm.round.nxv4f32(<vscale x 4 x float> poison)
  %round.nxv2f64 = call <vscale x 2 x double> @llvm.round.nxv2f64(<vscale x 2 x double> poison)
  %round.nxv4f64 = call <vscale x 4 x double> @llvm.round.nxv4f64(<vscale x 4 x double> poison)

  ret void
}

define void @rint() #1 {
; CHECK-VSCALE-1-LABEL: 'rint'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %rint.nxv8f16 = call <vscale x 8 x half> @llvm.rint.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %rint.nxv4f32 = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %rint.nxv2f64 = call <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %rint.nxv4f64 = call <vscale x 4 x double> @llvm.rint.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'rint'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %rint.nxv8f16 = call <vscale x 8 x half> @llvm.rint.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %rint.nxv4f32 = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %rint.nxv2f64 = call <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %rint.nxv4f64 = call <vscale x 4 x double> @llvm.rint.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'rint'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %rint.nxv8f16 = call <vscale x 8 x half> @llvm.rint.nxv8f16(<vscale x 8 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %rint.nxv4f32 = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %rint.nxv2f64 = call <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %rint.nxv4f64 = call <vscale x 4 x double> @llvm.rint.nxv4f64(<vscale x 4 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %rint.nxv8f16 = call <vscale x 8 x half> @llvm.rint.nxv8f16(<vscale x 8 x half> poison)
  %rint.nxv4f32 = call <vscale x 4 x float> @llvm.rint.nxv4f32(<vscale x 4 x float> poison)
  %rint.nxv2f64 = call <vscale x 2 x double> @llvm.rint.nxv2f64(<vscale x 2 x double> poison)
  %rint.nxv4f64 = call <vscale x 4 x double> @llvm.rint.nxv4f64(<vscale x 4 x double> poison)

  ret void
}

define void @roundeven() #1 {
; CHECK-VSCALE-1-LABEL: 'roundeven'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %roundeven.nxv8f16 = call <vscale x 8 x half> @llvm.roundeven.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %roundeven.nxv4f32 = call <vscale x 4 x float> @llvm.roundeven.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %roundeven.nxv2f64 = call <vscale x 2 x double> @llvm.roundeven.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %roundeven.nxv4f64 = call <vscale x 4 x double> @llvm.roundeven.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'roundeven'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %roundeven.nxv8f16 = call <vscale x 8 x half> @llvm.roundeven.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %roundeven.nxv4f32 = call <vscale x 4 x float> @llvm.roundeven.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %roundeven.nxv2f64 = call <vscale x 2 x double> @llvm.roundeven.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %roundeven.nxv4f64 = call <vscale x 4 x double> @llvm.roundeven.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'roundeven'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %roundeven.nxv8f16 = call <vscale x 8 x half> @llvm.roundeven.nxv8f16(<vscale x 8 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %roundeven.nxv4f32 = call <vscale x 4 x float> @llvm.roundeven.nxv4f32(<vscale x 4 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %roundeven.nxv2f64 = call <vscale x 2 x double> @llvm.roundeven.nxv2f64(<vscale x 2 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %roundeven.nxv4f64 = call <vscale x 4 x double> @llvm.roundeven.nxv4f64(<vscale x 4 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %roundeven.nxv8f16 = call <vscale x 8 x half> @llvm.roundeven.nxv8f16(<vscale x 8 x half> poison)
  %roundeven.nxv4f32 = call <vscale x 4 x float> @llvm.roundeven.nxv4f32(<vscale x 4 x float> poison)
  %roundeven.nxv2f64 = call <vscale x 2 x double> @llvm.roundeven.nxv2f64(<vscale x 2 x double> poison)
  %roundeven.nxv4f64 = call <vscale x 4 x double> @llvm.roundeven.nxv4f64(<vscale x 4 x double> poison)

  ret void
}

define void @trunc() #1 {
; CHECK-VSCALE-1-LABEL: 'trunc'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %trunc.nxv8f16 = call <vscale x 8 x half> @llvm.trunc.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %trunc.nxv4f32 = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %trunc.nxv2f64 = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %trunc.nxv4f64 = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'trunc'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %trunc.nxv8f16 = call <vscale x 8 x half> @llvm.trunc.nxv8f16(<vscale x 8 x half> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %trunc.nxv4f32 = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %trunc.nxv2f64 = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %trunc.nxv4f64 = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> poison)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'trunc'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %trunc.nxv8f16 = call <vscale x 8 x half> @llvm.trunc.nxv8f16(<vscale x 8 x half> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %trunc.nxv4f32 = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %trunc.nxv2f64 = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %trunc.nxv4f64 = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> poison)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %trunc.nxv8f16 = call <vscale x 8 x half> @llvm.trunc.nxv8f16(<vscale x 8 x half> poison)
  %trunc.nxv4f32 = call <vscale x 4 x float> @llvm.trunc.nxv4f32(<vscale x 4 x float> poison)
  %trunc.nxv2f64 = call <vscale x 2 x double> @llvm.trunc.nxv2f64(<vscale x 2 x double> poison)
  %trunc.nxv4f64 = call <vscale x 4 x double> @llvm.trunc.nxv4f64(<vscale x 4 x double> poison)

  ret void
}

define void @abs() #1 {
; CHECK-VSCALE-1-LABEL: 'abs'
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv16i8 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> poison, i1 true)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv8i16 = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> poison, i1 true)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv4i32 = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> poison, i1 true)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv2i64 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> poison, i1 true)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of 2 for: %abs.nxv4i64 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> poison, i1 true)
; CHECK-VSCALE-1-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; CHECK-VSCALE-2-LABEL: 'abs'
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv16i8 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> poison, i1 true)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv8i16 = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> poison, i1 true)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv4i32 = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> poison, i1 true)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv2i64 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> poison, i1 true)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of 2 for: %abs.nxv4i64 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> poison, i1 true)
; CHECK-VSCALE-2-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
; TYPE_BASED_ONLY-LABEL: 'abs'
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv16i8 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> poison, i1 true)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv8i16 = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> poison, i1 true)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv4i32 = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> poison, i1 true)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 1 for: %abs.nxv2i64 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> poison, i1 true)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of 2 for: %abs.nxv4i64 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> poison, i1 true)
; TYPE_BASED_ONLY-NEXT:  Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
;
  %abs.nxv16i8 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> poison, i1 true)
  %abs.nxv8i16 = call <vscale x 8 x i16> @llvm.abs.nxv8i16(<vscale x 8 x i16> poison, i1 true)
  %abs.nxv4i32 = call <vscale x 4 x i32> @llvm.abs.nxv4i32(<vscale x 4 x i32> poison, i1 true)
  %abs.nxv2i64 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> poison, i1 true)
  %abs.nxv4i64 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> poison, i1 true)

  ret void
}


declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64, i64)
declare <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64, i64)
declare <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64, i64)
declare <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64, i64)
declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32, i32)
declare <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32, i32)
declare <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32, i32)
declare <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32, i32)
declare <vscale x 64 x i1> @llvm.get.active.lane.mask.nxv64i1.i64(i64, i64)
declare <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64, i64)
declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16, i16)
declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64, i64)
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64, i64)
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64, i64)
declare <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64, i64)
declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32, i32)
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32, i32)
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
declare <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32, i32)
declare <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64, i64)
declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16, i16)
declare <vscale x 16 x i8> @llvm.fshr.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.fshr.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.fshr.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.fshr.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 16 x i8> @llvm.fshl.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, <vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.fshl.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.fshl.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.fshl.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x i32> @llvm.masked.gather.nxv4i32(<vscale x 4 x ptr> %ptrs, i32 %align, <vscale x 4 x i1> %masks, <vscale x 4 x i32> %passthru)
declare <vscale x 8 x i32> @llvm.masked.gather.nxv8i32(<vscale x 8 x ptr> %ptrs, i32 %align, <vscale x 8 x i1> %masks, <vscale x 8 x i32> %passthru)
declare <4 x i32> @llvm.masked.gather.v4i32(<4 x ptr> %ptrs, i32 %align, <4 x i1> %masks, <4 x i32> %passthru)
declare <1 x i128> @llvm.masked.gather.v1i128.v1p0(<1 x ptr>, i32, <1 x i1>, <1 x i128>)
declare void @llvm.masked.scatter.nxv4i32(<vscale x 4 x i32> %data, <vscale x 4 x ptr> %ptrs, i32 %align, <vscale x 4 x i1> %masks)
declare void @llvm.masked.scatter.nxv8i32(<vscale x 8 x i32> %data, <vscale x 8 x ptr> %ptrs, i32 %align, <vscale x 8 x i1> %masks)
declare void @llvm.masked.scatter.v4i32(<4 x i32> %data, <4 x ptr> %ptrs, i32 %align, <4 x i1> %masks)
declare void @llvm.masked.scatter.v1i128.v1p0(<1 x i128> %data, <1 x ptr> %ptrs, i32 %align, <1 x i1> %masks)

attributes #0 = { "target-features"="+sve,+bf16" }
attributes #1 = { "target-features"="+sve" vscale_range(1,16) }
attributes #2 = { "target-features"="+sve" vscale_range(2, 16) }
attributes #3 = { "target-features"="+sve,+sve2" vscale_range(1,16) }