; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -S -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve.fp -cost-model -analyze | FileCheck %s

define i32 @masked_gather() {
; CHECK-LABEL: 'masked_gather'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 4, <4 x i1> undef, <4 x double> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 4, <2 x i1> undef, <2 x double> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 4, <16 x i1> undef, <16 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 4, <8 x i1> undef, <8 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 4, <4 x i1> undef, <4 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 4, <2 x i1> undef, <2 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %V16F16 = call <16 x half> @llvm.masked.gather.v16f16.v16p0f16(<16 x half*> undef, i32 2, <16 x i1> undef, <16 x half> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V8F16 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> undef, i32 2, <8 x i1> undef, <8 x half> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %V4F16 = call <4 x half> @llvm.masked.gather.v4f16.v4p0f16(<4 x half*> undef, i32 2, <4 x i1> undef, <4 x half> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %V2F16 = call <2 x half> @llvm.masked.gather.v2f16.v2p0f16(<2 x half*> undef, i32 2, <2 x i1> undef, <2 x half> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 4, <4 x i1> undef, <4 x i64> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 4, <2 x i1> undef, <2 x i64> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 4, <16 x i1> undef, <16 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 4, <8 x i1> undef, <8 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 4, <4 x i1> undef, <4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 4, <2 x i1> undef, <2 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 2, <16 x i1> undef, <16 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 2, <8 x i1> undef, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 2, <4 x i1> undef, <4 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I16 = call <2 x i16> @llvm.masked.gather.v2i16.v2p0i16(<2 x i16*> undef, i32 2, <2 x i1> undef, <2 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %V4I8 = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> undef, i32 1, <4 x i1> undef, <4 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %V2I8 = call <2 x i8> @llvm.masked.gather.v2i8.v2p0i8(<2 x i8*> undef, i32 1, <2 x i1> undef, <2 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %V4I32p = call <4 x i32*> @llvm.masked.gather.v4p0i32.v4p0p0i32(<4 x i32**> undef, i32 4, <4 x i1> undef, <4 x i32*> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
;
  %V4F64 = call <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*> undef, i32 4, <4 x i1> undef, <4 x double> undef)
  %V2F64 = call <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*> undef, i32 4, <2 x i1> undef, <2 x double> undef)

  %V16F32 = call <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*> undef, i32 4, <16 x i1> undef, <16 x float> undef)
  %V8F32 = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> undef, i32 4, <8 x i1> undef, <8 x float> undef)
  %V4F32 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> undef, i32 4, <4 x i1> undef, <4 x float> undef)
  %V2F32 = call <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*> undef, i32 4, <2 x i1> undef, <2 x float> undef)

  %V16F16 = call <16 x half> @llvm.masked.gather.v16f16.v16p0f16(<16 x half*> undef, i32 2, <16 x i1> undef, <16 x half> undef)
  %V8F16 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> undef, i32 2, <8 x i1> undef, <8 x half> undef)
  %V4F16 = call <4 x half> @llvm.masked.gather.v4f16.v4p0f16(<4 x half*> undef, i32 2, <4 x i1> undef, <4 x half> undef)
  %V2F16 = call <2 x half> @llvm.masked.gather.v2f16.v2p0f16(<2 x half*> undef, i32 2, <2 x i1> undef, <2 x half> undef)

  %V4I64 = call <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*> undef, i32 4, <4 x i1> undef, <4 x i64> undef)
  %V2I64 = call <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*> undef, i32 4, <2 x i1> undef, <2 x i64> undef)

  %V16I32 = call <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*> undef, i32 4, <16 x i1> undef, <16 x i32> undef)
  %V8I32 = call <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*> undef, i32 4, <8 x i1> undef, <8 x i32> undef)
  %V4I32 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> undef, i32 4, <4 x i1> undef, <4 x i32> undef)
  %V2I32 = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> undef, i32 4, <2 x i1> undef, <2 x i32> undef)

  %V16I16 = call <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*> undef, i32 2, <16 x i1> undef, <16 x i16> undef)
  %V8I16 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> undef, i32 2, <8 x i1> undef, <8 x i16> undef)
  %V4I16 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> undef, i32 2, <4 x i1> undef, <4 x i16> undef)
  %V2I16 = call <2 x i16> @llvm.masked.gather.v2i16.v2p0i16(<2 x i16*> undef, i32 2, <2 x i1> undef, <2 x i16> undef)

  %V32I8 = call <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*> undef, i32 1, <32 x i1> undef, <32 x i8> undef)
  %V16I8 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> undef, i32 1, <16 x i1> undef, <16 x i8> undef)
  %V8I8 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> undef, i32 1, <8 x i1> undef, <8 x i8> undef)
  %V4I8 = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> undef, i32 1, <4 x i1> undef, <4 x i8> undef)
  %V2I8 = call <2 x i8> @llvm.masked.gather.v2i8.v2p0i8(<2 x i8*> undef, i32 1, <2 x i1> undef, <2 x i8> undef)

  %V4I32p = call <4 x i32*> @llvm.masked.gather.v4p0i32.v4p0p0i32(<4 x i32**> undef, i32 4, <4 x i1> undef, <4 x i32*> undef)

  ret i32 0
}

define i32 @masked_scatter() {
; CHECK-LABEL: 'masked_scatter'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 4, <4 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 4, <2 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 96 for instruction: call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 4, <16 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 4, <8 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 4, <4 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 4, <2 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: call void @llvm.masked.scatter.v16f16.v16p0f16(<16 x half> undef, <16 x half*> undef, i32 2, <16 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> undef, <8 x half*> undef, i32 2, <8 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v4f16.v4p0f16(<4 x half> undef, <4 x half*> undef, i32 2, <4 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: call void @llvm.masked.scatter.v2f16.v2p0f16(<2 x half> undef, <2 x half*> undef, i32 2, <2 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 4, <4 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 4, <2 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 192 for instruction: call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 4, <16 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 80 for instruction: call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 4, <8 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 4, <4 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 4, <2 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 160 for instruction: call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 2, <16 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 2, <8 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 2, <4 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v2i16.v2p0i16(<2 x i16> undef, <2 x i16*> undef, i32 2, <2 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 320 for instruction: call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> undef, <4 x i8*> undef, i32 1, <4 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: call void @llvm.masked.scatter.v2i8.v2p0i8(<2 x i8> undef, <2 x i8*> undef, i32 1, <2 x i1> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret i32 0
;
  call void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double> undef, <4 x double*> undef, i32 4, <4 x i1> undef)
  call void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double> undef, <2 x double*> undef, i32 4, <2 x i1> undef)

  call void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float> undef, <16 x float*> undef, i32 4, <16 x i1> undef)
  call void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float> undef, <8 x float*> undef, i32 4, <8 x i1> undef)
  call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> undef, <4 x float*> undef, i32 4, <4 x i1> undef)
  call void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float> undef, <2 x float*> undef, i32 4, <2 x i1> undef)

  call void @llvm.masked.scatter.v16f16.v16p0f16(<16 x half> undef, <16 x half*> undef, i32 2, <16 x i1> undef)
  call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> undef, <8 x half*> undef, i32 2, <8 x i1> undef)
  call void @llvm.masked.scatter.v4f16.v4p0f16(<4 x half> undef, <4 x half*> undef, i32 2, <4 x i1> undef)
  call void @llvm.masked.scatter.v2f16.v2p0f16(<2 x half> undef, <2 x half*> undef, i32 2, <2 x i1> undef)

  call void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64> undef, <4 x i64*> undef, i32 4, <4 x i1> undef)
  call void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64> undef, <2 x i64*> undef, i32 4, <2 x i1> undef)

  call void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32> undef, <16 x i32*> undef, i32 4, <16 x i1> undef)
  call void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32> undef, <8 x i32*> undef, i32 4, <8 x i1> undef)
  call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> undef, <4 x i32*> undef, i32 4, <4 x i1> undef)
  call void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32> undef, <2 x i32*> undef, i32 4, <2 x i1> undef)

  call void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16> undef, <16 x i16*> undef, i32 2, <16 x i1> undef)
  call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> undef, <8 x i16*> undef, i32 2, <8 x i1> undef)
  call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> undef, <4 x i16*> undef, i32 2, <4 x i1> undef)
  call void @llvm.masked.scatter.v2i16.v2p0i16(<2 x i16> undef, <2 x i16*> undef, i32 2, <2 x i1> undef)

  call void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8> undef, <32 x i8*> undef, i32 1, <32 x i1> undef)
  call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> undef, <16 x i8*> undef, i32 1, <16 x i1> undef)
  call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> undef, <8 x i8*> undef, i32 1, <8 x i1> undef)
  call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> undef, <4 x i8*> undef, i32 1, <4 x i1> undef)
  call void @llvm.masked.scatter.v2i8.v2p0i8(<2 x i8> undef, <2 x i8*> undef, i32 1, <2 x i1> undef)

  ret i32 0
}

define void @gep_v4i32(i32* %base, i16* %base16, i8* %base8, <4 x i32> %ind32, <4 x i16> %ind16, <4 x i1> %mask)  {
; CHECK-LABEL: 'gep_v4i32'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep1 = getelementptr i32, i32* %base, <4 x i32> %ind32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res1 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep1, i32 4, <4 x i1> %mask, <4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res1, <4 x i32*> %gep1, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indzext = zext <4 x i16> %ind16 to <4 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep2 = getelementptr i32, i32* %base, <4 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res2 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep2, i32 4, <4 x i1> %mask, <4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res2, <4 x i32*> %gep2, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indsext = sext <4 x i16> %ind16 to <4 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep3 = getelementptr i32, i32* %base, <4 x i32> %indsext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res3 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep3, i32 4, <4 x i1> %mask, <4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res3, <4 x i32*> %gep3, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepu = getelementptr i32, i32* %base, <4 x i32> %ind32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %resu = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gepu, i32 1, <4 x i1> %mask, <4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resu, <4 x i32*> %gepu, i32 1, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepos = getelementptr i8, i8* %base8, <4 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %geposb = bitcast <4 x i8*> %gepos to <4 x i32*>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %resos = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %geposb, i32 4, <4 x i1> %mask, <4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resos, <4 x i32*> %geposb, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i16, i16* %base16, <4 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <4 x i16*> %gepbs to <4 x i32*>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %resbs = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gepbsb, i32 4, <4 x i1> %mask, <4 x i32> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resbs, <4 x i32*> %gepbsb, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %gep1 = getelementptr i32, i32* %base, <4 x i32> %ind32
  %res1 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep1, i32 4, <4 x i1> %mask, <4 x i32> undef)
  call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res1, <4 x i32*> %gep1, i32 4, <4 x i1> %mask)

  %indzext = zext <4 x i16> %ind16 to <4 x i32>
  %gep2 = getelementptr i32, i32* %base, <4 x i32> %indzext
  %res2 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep2, i32 4, <4 x i1> %mask, <4 x i32> undef)
  call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res2, <4 x i32*> %gep2, i32 4, <4 x i1> %mask)

  %indsext = sext <4 x i16> %ind16 to <4 x i32>
  %gep3 = getelementptr i32, i32* %base, <4 x i32> %indsext
  %res3 = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gep3, i32 4, <4 x i1> %mask, <4 x i32> undef)
  call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %res3, <4 x i32*> %gep3, i32 4, <4 x i1> %mask)

  ; unaligned
  %gepu = getelementptr i32, i32* %base, <4 x i32> %ind32
  %resu = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gepu, i32 1, <4 x i1> %mask, <4 x i32> undef)
  call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resu, <4 x i32*> %gepu, i32 1, <4 x i1> %mask)

  ; 1 scale
  %gepos = getelementptr i8, i8* %base8, <4 x i32> %indzext
  %geposb = bitcast <4 x i8*> %gepos to <4 x i32*>
  %resos = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %geposb, i32 4, <4 x i1> %mask, <4 x i32> undef)
  call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resos, <4 x i32*> %geposb, i32 4, <4 x i1> %mask)

  ; bad scale (but doesn't really matter because i32)
  %gepbs = getelementptr i16, i16* %base16, <4 x i32> %indzext
  %gepbsb = bitcast <4 x i16*> %gepbs to <4 x i32*>
  %resbs = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %gepbsb, i32 4, <4 x i1> %mask, <4 x i32> undef)
  call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %resbs, <4 x i32*> %gepbsb, i32 4, <4 x i1> %mask)
  ret void
}

define void @gep_v4f32(float* %base, i16* %base16, i8* %base8, <4 x i32> %ind32, <4 x i16> %ind16, <4 x i1> %mask)  {
; CHECK-LABEL: 'gep_v4f32'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep1 = getelementptr float, float* %base, <4 x i32> %ind32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res1 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep1, i32 4, <4 x i1> %mask, <4 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res1, <4 x float*> %gep1, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indzext = zext <4 x i16> %ind16 to <4 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep2 = getelementptr float, float* %base, <4 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res2 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep2, i32 4, <4 x i1> %mask, <4 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res2, <4 x float*> %gep2, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indsext = sext <4 x i16> %ind16 to <4 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep3 = getelementptr float, float* %base, <4 x i32> %indsext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res3 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep3, i32 4, <4 x i1> %mask, <4 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res3, <4 x float*> %gep3, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gepu = getelementptr float, float* %base, <4 x i32> %ind32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %resu = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gepu, i32 1, <4 x i1> %mask, <4 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resu, <4 x float*> %gepu, i32 1, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepos = getelementptr i8, i8* %base8, <4 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %geposb = bitcast <4 x i8*> %gepos to <4 x float*>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %resos = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %geposb, i32 4, <4 x i1> %mask, <4 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resos, <4 x float*> %geposb, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i16, i16* %base16, <4 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <4 x i16*> %gepbs to <4 x float*>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %resbs = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gepbsb, i32 4, <4 x i1> %mask, <4 x float> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resbs, <4 x float*> %gepbsb, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %gep1 = getelementptr float, float* %base, <4 x i32> %ind32
  %res1 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep1, i32 4, <4 x i1> %mask, <4 x float> undef)
  call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res1, <4 x float*> %gep1, i32 4, <4 x i1> %mask)

  %indzext = zext <4 x i16> %ind16 to <4 x i32>
  %gep2 = getelementptr float, float* %base, <4 x i32> %indzext
  %res2 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep2, i32 4, <4 x i1> %mask, <4 x float> undef)
  call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res2, <4 x float*> %gep2, i32 4, <4 x i1> %mask)

  %indsext = sext <4 x i16> %ind16 to <4 x i32>
  %gep3 = getelementptr float, float* %base, <4 x i32> %indsext
  %res3 = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gep3, i32 4, <4 x i1> %mask, <4 x float> undef)
  call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %res3, <4 x float*> %gep3, i32 4, <4 x i1> %mask)

  ; unaligned
  %gepu = getelementptr float, float* %base, <4 x i32> %ind32
  %resu = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gepu, i32 1, <4 x i1> %mask, <4 x float> undef)
  call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resu, <4 x float*> %gepu, i32 1, <4 x i1> %mask)

  ; 1 scale
  %gepos = getelementptr i8, i8* %base8, <4 x i32> %indzext
  %geposb = bitcast <4 x i8*> %gepos to <4 x float*>
  %resos = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %geposb, i32 4, <4 x i1> %mask, <4 x float> undef)
  call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resos, <4 x float*> %geposb, i32 4, <4 x i1> %mask)

  ; bad scale (but doesn't really matter because i32)
  %gepbs = getelementptr i16, i16* %base16, <4 x i32> %indzext
  %gepbsb = bitcast <4 x i16*> %gepbs to <4 x float*>
  %resbs = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> %gepbsb, i32 4, <4 x i1> %mask, <4 x float> undef)
  call void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float> %resbs, <4 x float*> %gepbsb, i32 4, <4 x i1> %mask)
  ret void
}

define void @gep_v4i16(i16* %base, <4 x i32> %ind32, <4 x i16> %ind16, <4 x i1> %mask)  {
; CHECK-LABEL: 'gep_v4i16'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep1 = getelementptr i16, i16* %base, <4 x i32> %ind32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %res1 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep1, i32 2, <4 x i1> %mask, <4 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res1, <4 x i16*> %gep1, i32 2, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indzext = zext <4 x i16> %ind16 to <4 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep2 = getelementptr i16, i16* %base, <4 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %res2 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep2, i32 2, <4 x i1> %mask, <4 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res2, <4 x i16*> %gep2, i32 2, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %indsext = sext <4 x i16> %ind16 to <4 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep3 = getelementptr i16, i16* %base, <4 x i32> %indsext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: %res3 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep3, i32 2, <4 x i1> %mask, <4 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 36 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res3, <4 x i16*> %gep3, i32 2, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep5 = getelementptr i16, i16* %base, <4 x i16> %ind16
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res5 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep5, i32 2, <4 x i1> %mask, <4 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res5zext = zext <4 x i16> %res5 to <4 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %res5trunc = trunc <4 x i32> %res5zext to <4 x i16>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res5trunc, <4 x i16*> %gep5, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res6 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep5, i32 2, <4 x i1> %mask, <4 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res6sext = sext <4 x i16> %res6 to <4 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %res6trunc = trunc <4 x i32> %res6sext to <4 x i16>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res6trunc, <4 x i16*> %gep5, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %gep1 = getelementptr i16, i16* %base, <4 x i32> %ind32
  %res1 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep1, i32 2, <4 x i1> %mask, <4 x i16> undef)
  call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res1, <4 x i16*> %gep1, i32 2, <4 x i1> %mask)

  %indzext = zext <4 x i16> %ind16 to <4 x i32>
  %gep2 = getelementptr i16, i16* %base, <4 x i32> %indzext
  %res2 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep2, i32 2, <4 x i1> %mask, <4 x i16> undef)
  call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res2, <4 x i16*> %gep2, i32 2, <4 x i1> %mask)

  %indsext = sext <4 x i16> %ind16 to <4 x i32>
  %gep3 = getelementptr i16, i16* %base, <4 x i32> %indsext
  %res3 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep3, i32 2, <4 x i1> %mask, <4 x i16> undef)
  call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res3, <4 x i16*> %gep3, i32 2, <4 x i1> %mask)

  ; result zext
  %gep5 = getelementptr i16, i16* %base, <4 x i16> %ind16
  %res5 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep5, i32 2, <4 x i1> %mask, <4 x i16> undef)
  %res5zext = zext <4 x i16> %res5 to <4 x i32>
  %res5trunc = trunc <4 x i32> %res5zext to <4 x i16>
  call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res5trunc, <4 x i16*> %gep5, i32 4, <4 x i1> %mask)

  ; result sext
  %res6 = call <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*> %gep5, i32 2, <4 x i1> %mask, <4 x i16> undef)
  %res6sext = sext <4 x i16> %res6 to <4 x i32>
  %res6trunc = trunc <4 x i32> %res6sext to <4 x i16>
  call void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16> %res6trunc, <4 x i16*> %gep5, i32 4, <4 x i1> %mask)

  ret void
}

define void @gep_v4i8(i8* %base, <4 x i8> %ind8, <4 x i1> %mask)  {
; CHECK-LABEL: 'gep_v4i8'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep5 = getelementptr i8, i8* %base, <4 x i8> %ind8
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res5 = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> %gep5, i32 2, <4 x i1> %mask, <4 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res5zext = zext <4 x i8> %res5 to <4 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %res5trunc = trunc <4 x i32> %res5zext to <4 x i8>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> %res5trunc, <4 x i8*> %gep5, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %res6 = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> %gep5, i32 2, <4 x i1> %mask, <4 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %res6sext = sext <4 x i8> %res6 to <4 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %res6trunc = trunc <4 x i32> %res6sext to <4 x i8>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> %res6trunc, <4 x i8*> %gep5, i32 4, <4 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  ; result zext
  %gep5 = getelementptr i8, i8* %base, <4 x i8> %ind8
  %res5 = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> %gep5, i32 2, <4 x i1> %mask, <4 x i8> undef)
  %res5zext = zext <4 x i8> %res5 to <4 x i32>
  %res5trunc = trunc <4 x i32> %res5zext to <4 x i8>
  call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> %res5trunc, <4 x i8*> %gep5, i32 4, <4 x i1> %mask)

  ; result sext
  %res6 = call <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*> %gep5, i32 2, <4 x i1> %mask, <4 x i8> undef)
  %res6sext = sext <4 x i8> %res6 to <4 x i32>
  %res6trunc = trunc <4 x i32> %res6sext to <4 x i8>
  call void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8> %res6trunc, <4 x i8*> %gep5, i32 4, <4 x i1> %mask)

  ret void
}

define void @gep_v8i16(i16* %base, i8* %base8, i32* %base32, <8 x i32> %ind32, <8 x i16> %ind16, <8 x i8> %ind8, <8 x i1> %mask)  {
; CHECK-LABEL: 'gep_v8i16'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep1 = getelementptr i16, i16* %base, <8 x i32> %ind32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %res1 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep1, i32 2, <8 x i1> %mask, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res1, <8 x i16*> %gep1, i32 2, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indzext = zext <8 x i16> %ind16 to <8 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep2 = getelementptr i16, i16* %base, <8 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res2 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep2, i32 2, <8 x i1> %mask, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res2, <8 x i16*> %gep2, i32 2, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indsext = sext <8 x i16> %ind16 to <8 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep3 = getelementptr i16, i16* %base, <8 x i32> %indsext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %res3 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep3, i32 2, <8 x i1> %mask, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res3, <8 x i16*> %gep3, i32 2, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %resu = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep2, i32 1, <8 x i1> %mask, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resu, <8 x i16*> %gep2, i32 1, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepos = getelementptr i8, i8* %base8, <8 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %geposb = bitcast <8 x i8*> %gepos to <8 x i16*>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %resos = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %geposb, i32 2, <8 x i1> %mask, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resos, <8 x i16*> %geposb, i32 2, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i32, i32* %base32, <8 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <8 x i32*> %gepbs to <8 x i16*>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: %resbs = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gepbsb, i32 2, <8 x i1> %mask, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 72 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resbs, <8 x i16*> %gepbsb, i32 2, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indzext4 = zext <8 x i16> %ind16 to <8 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep4 = getelementptr i16, i16* %base, <8 x i32> %indzext4
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %indtrunc = trunc <8 x i32> %ind32 to <8 x i16>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %indtrunc, <8 x i16*> %gep4, i32 2, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep4, i32 2, <8 x i1> %mask, <8 x i16> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %ressext = sext <8 x i16> %res to <8 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %restrunc = trunc <8 x i32> %ressext to <8 x i16>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %restrunc, <8 x i16*> %gep4, i32 4, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  ; no offset ext
  %gep1 = getelementptr i16, i16* %base, <8 x i32> %ind32
  %res1 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep1, i32 2, <8 x i1> %mask, <8 x i16> undef)
  call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res1, <8 x i16*> %gep1, i32 2, <8 x i1> %mask)

  ; offset zext
  %indzext = zext <8 x i16> %ind16 to <8 x i32>
  %gep2 = getelementptr i16, i16* %base, <8 x i32> %indzext
  %res2 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep2, i32 2, <8 x i1> %mask, <8 x i16> undef)
  call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res2, <8 x i16*> %gep2, i32 2, <8 x i1> %mask)

  ; offset sext
  %indsext = sext <8 x i16> %ind16 to <8 x i32>
  %gep3 = getelementptr i16, i16* %base, <8 x i32> %indsext
  %res3 = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep3, i32 2, <8 x i1> %mask, <8 x i16> undef)
  call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %res3, <8 x i16*> %gep3, i32 2, <8 x i1> %mask)

  ; unaligned
  %resu = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep2, i32 1, <8 x i1> %mask, <8 x i16> undef)
  call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resu, <8 x i16*> %gep2, i32 1, <8 x i1> %mask)

  ; 1 scale
  %gepos = getelementptr i8, i8* %base8, <8 x i32> %indzext
  %geposb = bitcast <8 x i8*> %gepos to <8 x i16*>
  %resos = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %geposb, i32 2, <8 x i1> %mask, <8 x i16> undef)
  call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resos, <8 x i16*> %geposb, i32 2, <8 x i1> %mask)

  ; bad scale
  %gepbs = getelementptr i32, i32* %base32, <8 x i32> %indzext
  %gepbsb = bitcast <8 x i32*> %gepbs to <8 x i16*>
  %resbs = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gepbsb, i32 2, <8 x i1> %mask, <8 x i16> undef)
  call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %resbs, <8 x i16*> %gepbsb, i32 2, <8 x i1> %mask)

  ; trunc scatter
  %indzext4 = zext <8 x i16> %ind16 to <8 x i32>
  %gep4 = getelementptr i16, i16* %base, <8 x i32> %indzext4
  %indtrunc = trunc <8 x i32> %ind32 to <8 x i16>
  call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %indtrunc, <8 x i16*> %gep4, i32 2, <8 x i1> %mask)

  ; ext result to <8 x i32>
  %res = call <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*> %gep4, i32 2, <8 x i1> %mask, <8 x i16> undef)
  %ressext = sext <8 x i16> %res to <8 x i32>
  %restrunc = trunc <8 x i32> %ressext to <8 x i16>
  call void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16> %restrunc, <8 x i16*> %gep4, i32 4, <8 x i1> %mask)

  ret void
}

define void @gep_v8f16(half* %base, i8* %base8, i32* %base32, <8 x i32> %ind32, <8 x i16> %ind16, <8 x i1> %mask)  {
; CHECK-LABEL: 'gep_v8f16'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep1 = getelementptr half, half* %base, <8 x i32> %ind32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res1 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep1, i32 2, <8 x i1> %mask, <8 x half> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res1, <8 x half*> %gep1, i32 2, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indzext = zext <8 x i16> %ind16 to <8 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep2 = getelementptr half, half* %base, <8 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res2 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep2, i32 2, <8 x i1> %mask, <8 x half> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res2, <8 x half*> %gep2, i32 2, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %indsext = sext <8 x i16> %ind16 to <8 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %gep3 = getelementptr half, half* %base, <8 x i32> %indsext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %res3 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep3, i32 2, <8 x i1> %mask, <8 x half> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res3, <8 x half*> %gep3, i32 2, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %resu = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep2, i32 1, <8 x i1> %mask, <8 x half> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resu, <8 x half*> %gep2, i32 1, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepos = getelementptr i8, i8* %base8, <8 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %geposb = bitcast <8 x i8*> %gepos to <8 x half*>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %resos = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %geposb, i32 2, <8 x i1> %mask, <8 x half> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resos, <8 x half*> %geposb, i32 2, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i32, i32* %base32, <8 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <8 x i32*> %gepbs to <8 x half*>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: %resbs = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gepbsb, i32 2, <8 x i1> %mask, <8 x half> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 24 for instruction: call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resbs, <8 x half*> %gepbsb, i32 2, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  ; no offset ext
  %gep1 = getelementptr half, half* %base, <8 x i32> %ind32
  %res1 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep1, i32 2, <8 x i1> %mask, <8 x half> undef)
  call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res1, <8 x half*> %gep1, i32 2, <8 x i1> %mask)

  ; offset zext
  %indzext = zext <8 x i16> %ind16 to <8 x i32>
  %gep2 = getelementptr half, half* %base, <8 x i32> %indzext
  %res2 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep2, i32 2, <8 x i1> %mask, <8 x half> undef)
  call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res2, <8 x half*> %gep2, i32 2, <8 x i1> %mask)

  ; offset sext
  %indsext = sext <8 x i16> %ind16 to <8 x i32>
  %gep3 = getelementptr half, half* %base, <8 x i32> %indsext
  %res3 = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep3, i32 2, <8 x i1> %mask, <8 x half> undef)
  call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %res3, <8 x half*> %gep3, i32 2, <8 x i1> %mask)

  ; unaligned
  %resu = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gep2, i32 1, <8 x i1> %mask, <8 x half> undef)
  call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resu, <8 x half*> %gep2, i32 1, <8 x i1> %mask)

  ; 1 scale
  %gepos = getelementptr i8, i8* %base8, <8 x i32> %indzext
  %geposb = bitcast <8 x i8*> %gepos to <8 x half*>
  %resos = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %geposb, i32 2, <8 x i1> %mask, <8 x half> undef)
  call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resos, <8 x half*> %geposb, i32 2, <8 x i1> %mask)

  ; bad scale
  %gepbs = getelementptr i32, i32* %base32, <8 x i32> %indzext
  %gepbsb = bitcast <8 x i32*> %gepbs to <8 x half*>
  %resbs = call <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*> %gepbsb, i32 2, <8 x i1> %mask, <8 x half> undef)
  call void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half> %resbs, <8 x half*> %gepbsb, i32 2, <8 x i1> %mask)

  ret void
}

define void @gep_v8i8(i8* %base, <8 x i8> %ind8, <8 x i1> %mask)  {
; CHECK-LABEL: 'gep_v8i8'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %indzext = zext <8 x i8> %ind8 to <8 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep5 = getelementptr i8, i8* %base, <8 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res5 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> %gep5, i32 2, <8 x i1> %mask, <8 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res5zext = zext <8 x i8> %res5 to <8 x i16>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %res5trunc = trunc <8 x i16> %res5zext to <8 x i8>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> %res5trunc, <8 x i8*> %gep5, i32 4, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %res6 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> %gep5, i32 2, <8 x i1> %mask, <8 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %res6sext = sext <8 x i8> %res6 to <8 x i16>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %res6trunc = trunc <8 x i16> %res6sext to <8 x i8>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> %res6trunc, <8 x i8*> %gep5, i32 4, <8 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  ; result zext
  %indzext = zext <8 x i8> %ind8 to <8 x i32>
  %gep5 = getelementptr i8, i8* %base, <8 x i32> %indzext
  %res5 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> %gep5, i32 2, <8 x i1> %mask, <8 x i8> undef)
  %res5zext = zext <8 x i8> %res5 to <8 x i16>
  %res5trunc = trunc <8 x i16> %res5zext to <8 x i8>
  call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> %res5trunc, <8 x i8*> %gep5, i32 4, <8 x i1> %mask)

  ; result sext
  %res6 = call <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*> %gep5, i32 2, <8 x i1> %mask, <8 x i8> undef)
  %res6sext = sext <8 x i8> %res6 to <8 x i16>
  %res6trunc = trunc <8 x i16> %res6sext to <8 x i8>
  call void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8> %res6trunc, <8 x i8*> %gep5, i32 4, <8 x i1> %mask)

  ret void
}

define void @gep_v16i8(i8* %base, i16* %base16, <16 x i8> %ind8, <16 x i32> %ind32, <16 x i1> %mask)  {
; CHECK-LABEL: 'gep_v16i8'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep1 = getelementptr i8, i8* %base, <16 x i32> %ind32
; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %res1 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep1, i32 1, <16 x i1> %mask, <16 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res1, <16 x i8*> %gep1, i32 2, <16 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %indzext = zext <16 x i8> %ind8 to <16 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep2 = getelementptr i8, i8* %base, <16 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %res2 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep2, i32 2, <16 x i1> %mask, <16 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res2, <16 x i8*> %gep2, i32 2, <16 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %indsext = sext <16 x i8> %ind8 to <16 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep3 = getelementptr i8, i8* %base, <16 x i32> %indsext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %res3 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep3, i32 2, <16 x i1> %mask, <16 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res3, <16 x i8*> %gep3, i32 2, <16 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i16, i16* %base16, <16 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbsb = bitcast <16 x i16*> %gepbs to <16 x i8*>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbsb, i32 2, <16 x i1> %mask, <16 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbsb, i32 2, <16 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 74 for instruction: %indzext4 = zext <16 x i8> %ind8 to <16 x i32>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gep4 = getelementptr i8, i8* %base, <16 x i32> %indzext
; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %indtrunc = trunc <16 x i32> %ind32 to <16 x i8>
; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %indtrunc, <16 x i8*> %gep4, i32 2, <16 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  ; no offset ext
  %gep1 = getelementptr i8, i8* %base, <16 x i32> %ind32
  %res1 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep1, i32 1, <16 x i1> %mask, <16 x i8> undef)
  call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res1, <16 x i8*> %gep1, i32 2, <16 x i1> %mask)

  ; offset zext
  %indzext = zext <16 x i8> %ind8 to <16 x i32>
  %gep2 = getelementptr i8, i8* %base, <16 x i32> %indzext
  %res2 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep2, i32 2, <16 x i1> %mask, <16 x i8> undef)
  call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res2, <16 x i8*> %gep2, i32 2, <16 x i1> %mask)

  ; offset sext
  %indsext = sext <16 x i8> %ind8 to <16 x i32>
  %gep3 = getelementptr i8, i8* %base, <16 x i32> %indsext
  %res3 = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gep3, i32 2, <16 x i1> %mask, <16 x i8> undef)
  call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %res3, <16 x i8*> %gep3, i32 2, <16 x i1> %mask)

  ; Bad scale
  %gepbs = getelementptr i16, i16* %base16, <16 x i32> %indzext
  %gepbsb = bitcast <16 x i16*> %gepbs to <16 x i8*>
  %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbsb, i32 2, <16 x i1> %mask, <16 x i8> undef)
  call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbsb, i32 2, <16 x i1> %mask)

  ; trunc scatter
  %indzext4 = zext <16 x i8> %ind8 to <16 x i32>
  %gep4 = getelementptr i8, i8* %base, <16 x i32> %indzext
  %indtrunc = trunc <16 x i32> %ind32 to <16 x i8>
  call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %indtrunc, <16 x i8*> %gep4, i32 2, <16 x i1> %mask)

  ret void
}

define void @gep_v16i8p(<16 x i8*> %base, i32 %off, <16 x i1> %mask)  {
; CHECK-LABEL: 'gep_v16i8p'
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %gepbs = getelementptr i8, <16 x i8*> %base, i32 %off
; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbs, i32 2, <16 x i1> %mask, <16 x i8> undef)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 144 for instruction: call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbs, i32 2, <16 x i1> %mask)
; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
;
  %gepbs = getelementptr i8, <16 x i8*> %base, i32 %off
  %resbs = call <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*> %gepbs, i32 2, <16 x i1> %mask, <16 x i8> undef)
  call void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8> %resbs, <16 x i8*> %gepbs, i32 2, <16 x i1> %mask)
  ret void
}

declare <4 x double> @llvm.masked.gather.v4f64.v4p0f64(<4 x double*>, i32, <4 x i1>, <4 x double>)
declare <2 x double> @llvm.masked.gather.v2f64.v2p0f64(<2 x double*>, i32, <2 x i1>, <2 x double>)

declare <16 x float> @llvm.masked.gather.v16f32.v16p0f32(<16 x float*>, i32, <16 x i1>, <16 x float>)
declare <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*>, i32, <8 x i1>, <8 x float>)
declare <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*>, i32, <4 x i1>, <4 x float>)
declare <2 x float> @llvm.masked.gather.v2f32.v2p0f32(<2 x float*>, i32, <2 x i1>, <2 x float>)

declare <16 x half> @llvm.masked.gather.v16f16.v16p0f16(<16 x half*>, i32, <16 x i1>, <16 x half>)
declare <8 x half> @llvm.masked.gather.v8f16.v8p0f16(<8 x half*>, i32, <8 x i1>, <8 x half>)
declare <4 x half> @llvm.masked.gather.v4f16.v4p0f16(<4 x half*>, i32, <4 x i1>, <4 x half>)
declare <2 x half> @llvm.masked.gather.v2f16.v2p0f16(<2 x half*>, i32, <2 x i1>, <2 x half>)

declare <4 x i64> @llvm.masked.gather.v4i64.v4p0i64(<4 x i64*>, i32, <4 x i1>, <4 x i64>)
declare <2 x i64> @llvm.masked.gather.v2i64.v2p0i64(<2 x i64*>, i32, <2 x i1>, <2 x i64>)

declare <16 x i32> @llvm.masked.gather.v16i32.v16p0i32(<16 x i32*>, i32, <16 x i1>, <16 x i32>)
declare <8 x i32> @llvm.masked.gather.v8i32.v8p0i32(<8 x i32*>, i32, <8 x i1>, <8 x i32>)
declare <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*>, i32, <4 x i1>, <4 x i32>)
declare <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*>, i32, <2 x i1>, <2 x i32>)
declare <4 x i32*> @llvm.masked.gather.v4p0i32.v4p0p0i32(<4 x i32**>, i32, <4 x i1>, <4 x i32*>)

declare <16 x i16> @llvm.masked.gather.v16i16.v16p0i16(<16 x i16*>, i32, <16 x i1>, <16 x i16>)
declare <8 x i16> @llvm.masked.gather.v8i16.v8p0i16(<8 x i16*>, i32, <8 x i1>, <8 x i16>)
declare <4 x i16> @llvm.masked.gather.v4i16.v4p0i16(<4 x i16*>, i32, <4 x i1>, <4 x i16>)
declare <2 x i16> @llvm.masked.gather.v2i16.v2p0i16(<2 x i16*>, i32, <2 x i1>, <2 x i16>)

declare <32 x i8> @llvm.masked.gather.v32i8.v32p0i8(<32 x i8*>, i32, <32 x i1>, <32 x i8>)
declare <16 x i8> @llvm.masked.gather.v16i8.v16p0i8(<16 x i8*>, i32, <16 x i1>, <16 x i8>)
declare <8 x i8> @llvm.masked.gather.v8i8.v8p0i8(<8 x i8*>, i32, <8 x i1>, <8 x i8>)
declare <4 x i8> @llvm.masked.gather.v4i8.v4p0i8(<4 x i8*>, i32, <4 x i1>, <4 x i8>)
declare <2 x i8> @llvm.masked.gather.v2i8.v2p0i8(<2 x i8*>, i32, <2 x i1>, <2 x i8>)

declare void @llvm.masked.scatter.v4f64.v4p0f64(<4 x double>, <4 x double*>, i32, <4 x i1>)
declare void @llvm.masked.scatter.v2f64.v2p0f64(<2 x double>, <2 x double*>, i32, <2 x i1>)

declare void @llvm.masked.scatter.v16f32.v16p0f32(<16 x float>, <16 x float*>, i32, <16 x i1>)
declare void @llvm.masked.scatter.v8f32.v8p0f32(<8 x float>, <8 x float*>, i32, <8 x i1>)
declare void @llvm.masked.scatter.v4f32.v4p0f32(<4 x float>, <4 x float*>, i32, <4 x i1>)
declare void @llvm.masked.scatter.v2f32.v2p0f32(<2 x float>, <2 x float*>, i32, <2 x i1>)

declare void @llvm.masked.scatter.v16f16.v16p0f16(<16 x half>, <16 x half*>, i32, <16 x i1>)
declare void @llvm.masked.scatter.v8f16.v8p0f16(<8 x half>, <8 x half*>, i32, <8 x i1>)
declare void @llvm.masked.scatter.v4f16.v4p0f16(<4 x half>, <4 x half*>, i32, <4 x i1>)
declare void @llvm.masked.scatter.v2f16.v2p0f16(<2 x half>, <2 x half*>, i32, <2 x i1>)

declare void @llvm.masked.scatter.v4i64.v4p0i64(<4 x i64>, <4 x i64*>, i32, <4 x i1>)
declare void @llvm.masked.scatter.v2i64.v2p0i64(<2 x i64>, <2 x i64*>, i32, <2 x i1>)

declare void @llvm.masked.scatter.v16i32.v16p0i32(<16 x i32>, <16 x i32*>, i32, <16 x i1>)
declare void @llvm.masked.scatter.v8i32.v8p0i32(<8 x i32>, <8 x i32*>, i32, <8 x i1>)
declare void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32>, <4 x i32*>, i32, <4 x i1>)
declare void @llvm.masked.scatter.v2i32.v2p0i32(<2 x i32>, <2 x i32*>, i32, <2 x i1>)

declare void @llvm.masked.scatter.v16i16.v16p0i16(<16 x i16>, <16 x i16*>, i32, <16 x i1>)
declare void @llvm.masked.scatter.v8i16.v8p0i16(<8 x i16>, <8 x i16*>, i32, <8 x i1>)
declare void @llvm.masked.scatter.v4i16.v4p0i16(<4 x i16>, <4 x i16*>, i32, <4 x i1>)
declare void @llvm.masked.scatter.v2i16.v2p0i16(<2 x i16>, <2 x i16*>, i32, <2 x i1>)

declare void @llvm.masked.scatter.v32i8.v32p0i8(<32 x i8>, <32 x i8*>, i32, <32 x i1>)
declare void @llvm.masked.scatter.v16i8.v16p0i8(<16 x i8>, <16 x i8*>, i32, <16 x i1>)
declare void @llvm.masked.scatter.v8i8.v8p0i8(<8 x i8>, <8 x i8*>, i32, <8 x i1>)
declare void @llvm.masked.scatter.v4i8.v4p0i8(<4 x i8>, <4 x i8*>, i32, <4 x i1>)
declare void @llvm.masked.scatter.v2i8.v2p0i8(<2 x i8>, <2 x i8*>, i32, <2 x i1>)