; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s

define void @masked_scatter_nxv2i8(<vscale x 2 x i8> %data, <vscale x 2 x i8*> %ptrs, <vscale x 2 x i1> %masks) nounwind {
; CHECK-LABEL: masked_scatter_nxv2i8:
; CHECK:       // %bb.0:
; CHECK-NEXT:    st1b { z0.d }, p0, [z1.d]
; CHECK-NEXT:    ret
  call void @llvm.masked.scatter.nxv2i8(<vscale x 2 x i8> %data, <vscale x 2 x i8*> %ptrs, i32 0, <vscale x 2 x i1> %masks)
  ret void
}

define void @masked_scatter_nxv2i16(<vscale x 2 x i16> %data, <vscale x 2 x i16*> %ptrs, <vscale x 2 x i1> %masks) nounwind {
; CHECK-LABEL: masked_scatter_nxv2i16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    st1h { z0.d }, p0, [z1.d]
; CHECK-NEXT:    ret
  call void @llvm.masked.scatter.nxv2i16(<vscale x 2 x i16> %data, <vscale x 2 x i16*> %ptrs, i32 0, <vscale x 2 x i1> %masks)
  ret void
}

define void @masked_scatter_nxv2i32(<vscale x 2 x i32> %data, <vscale x 2 x i32*> %ptrs, <vscale x 2 x i1> %masks) nounwind {
; CHECK-LABEL: masked_scatter_nxv2i32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    st1w { z0.d }, p0, [z1.d]
; CHECK-NEXT:    ret
  call void @llvm.masked.scatter.nxv2i32(<vscale x 2 x i32> %data, <vscale x 2 x i32*> %ptrs, i32 0, <vscale x 2 x i1> %masks)
  ret void
}

define void @masked_scatter_nxv2i64(<vscale x 2 x i64> %data, <vscale x 2 x i64*> %ptrs, <vscale x 2 x i1> %masks) nounwind {
; CHECK-LABEL: masked_scatter_nxv2i64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    st1d { z0.d }, p0, [z1.d]
; CHECK-NEXT:    ret
  call void @llvm.masked.scatter.nxv2i64(<vscale x 2 x i64> %data, <vscale x 2 x i64*> %ptrs, i32 0, <vscale x 2 x i1> %masks)
  ret void
}

define void @masked_scatter_nxv2f16(<vscale x 2 x half> %data, <vscale x 2 x half*> %ptrs, <vscale x 2 x i1> %masks) nounwind {
; CHECK-LABEL: masked_scatter_nxv2f16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    st1h { z0.d }, p0, [z1.d]
; CHECK-NEXT:    ret
  call void @llvm.masked.scatter.nxv2f16(<vscale x 2 x half> %data, <vscale x 2 x half*> %ptrs, i32 0, <vscale x 2 x i1> %masks)
  ret void
}

define void @masked_scatter_nxv2bf16(<vscale x 2 x bfloat> %data, <vscale x 2 x bfloat*> %ptrs, <vscale x 2 x i1> %masks) nounwind #0 {
; CHECK-LABEL: masked_scatter_nxv2bf16:
; CHECK:       // %bb.0:
; CHECK-NEXT:    st1h { z0.d }, p0, [z1.d]
; CHECK-NEXT:    ret
  call void @llvm.masked.scatter.nxv2bf16(<vscale x 2 x bfloat> %data, <vscale x 2 x bfloat*> %ptrs, i32 0, <vscale x 2 x i1> %masks)
  ret void
}

define void @masked_scatter_nxv2f32(<vscale x 2 x float> %data, <vscale x 2 x float*> %ptrs, <vscale x 2 x i1> %masks) nounwind {
; CHECK-LABEL: masked_scatter_nxv2f32:
; CHECK:       // %bb.0:
; CHECK-NEXT:    st1w { z0.d }, p0, [z1.d]
; CHECK-NEXT:    ret
  call void @llvm.masked.scatter.nxv2f32(<vscale x 2 x float> %data, <vscale x 2 x float*> %ptrs, i32 0, <vscale x 2 x i1> %masks)
  ret void
}

define void @masked_scatter_nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x double*> %ptrs, <vscale x 2 x i1> %masks) nounwind {
; CHECK-LABEL: masked_scatter_nxv2f64:
; CHECK:       // %bb.0:
; CHECK-NEXT:    st1d { z0.d }, p0, [z1.d]
; CHECK-NEXT:    ret
  call void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x double*> %ptrs, i32 0, <vscale x 2 x i1> %masks)
  ret void
}

define void @masked_scatter_splat_constant_pointer (<vscale x 4 x i1> %pg) {
; CHECK-LABEL: masked_scatter_splat_constant_pointer:
; CHECK:       // %bb.0: // %vector.body
; CHECK-NEXT:    punpklo p1.h, p0.b
; CHECK-NEXT:    mov z0.d, #0 // =0x0
; CHECK-NEXT:    punpkhi p0.h, p0.b
; CHECK-NEXT:    st1w { z0.d }, p1, [z0.d]
; CHECK-NEXT:    st1w { z0.d }, p0, [z0.d]
; CHECK-NEXT:    ret
vector.body:
  call void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32> undef,
    <vscale x 4 x i32*> shufflevector (<vscale x 4 x i32*> insertelement (<vscale x 4 x i32*> poison, i32* null, i32 0), <vscale x 4 x i32*> poison, <vscale x 4 x i32> zeroinitializer),
    i32 4,
    <vscale x 4 x i1> %pg)
  ret void
}

%i64_x3 = type { i64, i64, i64 }
define void @masked_scatter_non_power_of_two_based_scaling(<vscale x 2 x double> %data, ptr %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_scatter_non_power_of_two_based_scaling:
; CHECK:       // %bb.0:
; CHECK-NEXT:    mul z1.d, z1.d, #24
; CHECK-NEXT:    st1d { z0.d }, p0, [x0, z1.d]
; CHECK-NEXT:    ret
  %ptrs = getelementptr inbounds %i64_x3, ptr %base, <vscale x 2 x i64> %offsets
  call void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x ptr> %ptrs, i32 8, <vscale x 2 x i1> %mask)
  ret void
}

%i64_x4 = type { i64, i64, i64, i64}
define void @masked_scatter_non_element_type_based_scaling(<vscale x 2 x double> %data, ptr %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
; CHECK-LABEL: masked_scatter_non_element_type_based_scaling:
; CHECK:       // %bb.0:
; CHECK-NEXT:    lsl z1.d, z1.d, #5
; CHECK-NEXT:    st1d { z0.d }, p0, [x0, z1.d]
; CHECK-NEXT:    ret
  %ptrs = getelementptr inbounds %i64_x4, ptr %base, <vscale x 2 x i64> %offsets
  call void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x ptr> %ptrs, i32 8, <vscale x 2 x i1> %mask)
  ret void
}

declare void @llvm.masked.scatter.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half*>, i32, <vscale x 2 x i1>)
declare void @llvm.masked.scatter.nxv2bf16(<vscale x 2 x bfloat>, <vscale x 2 x bfloat*>, i32, <vscale x 2 x i1>)
declare void @llvm.masked.scatter.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float*>, i32, <vscale x 2 x i1>)
declare void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double*>, i32, <vscale x 2 x i1>)
declare void @llvm.masked.scatter.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i16*>, i32, <vscale x 2 x i1>)
declare void @llvm.masked.scatter.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i32*>, i32, <vscale x 2 x i1>)
declare void @llvm.masked.scatter.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64*>, i32, <vscale x 2 x i1>)
declare void @llvm.masked.scatter.nxv2i8(<vscale x 2 x i8>, <vscale x 2 x i8*>, i32, <vscale x 2 x i1>)
declare void @llvm.masked.scatter.nxv4i32.nxv4p0i32(<vscale x 4 x i32>, <vscale x 4 x i32*>, i32, <vscale x 4 x i1>)
attributes #0 = { "target-features"="+sve,+bf16" }