xref: /llvm-project/llvm/test/Analysis/CostModel/AArch64/splice.ll (revision bfc0317153dca75137fba00b5c28758d6f720963) 
1; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
2; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=aarch64--linux-gnu | FileCheck %s
3
4target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
5
6define void @vector_splice() #0 {
7; CHECK-LABEL: 'vector_splice'
8; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v16i8 = call <16 x i8> @llvm.vector.splice.v16i8(<16 x i8> zeroinitializer, <16 x i8> zeroinitializer, i32 1)
9; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice.v32i8 = call <32 x i8> @llvm.vector.splice.v32i8(<32 x i8> zeroinitializer, <32 x i8> zeroinitializer, i32 1)
10; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v2i16 = call <2 x i16> @llvm.vector.splice.v2i16(<2 x i16> zeroinitializer, <2 x i16> zeroinitializer, i32 1)
11; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v4i16 = call <4 x i16> @llvm.vector.splice.v4i16(<4 x i16> zeroinitializer, <4 x i16> zeroinitializer, i32 1)
12; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v8i16 = call <8 x i16> @llvm.vector.splice.v8i16(<8 x i16> zeroinitializer, <8 x i16> zeroinitializer, i32 1)
13; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice.v16i16 = call <16 x i16> @llvm.vector.splice.v16i16(<16 x i16> zeroinitializer, <16 x i16> zeroinitializer, i32 1)
14; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v4i32 = call <4 x i32> @llvm.vector.splice.v4i32(<4 x i32> zeroinitializer, <4 x i32> zeroinitializer, i32 1)
15; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice.v8i32 = call <8 x i32> @llvm.vector.splice.v8i32(<8 x i32> zeroinitializer, <8 x i32> zeroinitializer, i32 1)
16; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v2i64 = call <2 x i64> @llvm.vector.splice.v2i64(<2 x i64> zeroinitializer, <2 x i64> zeroinitializer, i32 1)
17; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice.v4i64 = call <4 x i64> @llvm.vector.splice.v4i64(<4 x i64> zeroinitializer, <4 x i64> zeroinitializer, i32 1)
18; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v2f16 = call <2 x half> @llvm.vector.splice.v2f16(<2 x half> zeroinitializer, <2 x half> zeroinitializer, i32 1)
19; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v4f16 = call <4 x half> @llvm.vector.splice.v4f16(<4 x half> zeroinitializer, <4 x half> zeroinitializer, i32 1)
20; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v8f16 = call <8 x half> @llvm.vector.splice.v8f16(<8 x half> zeroinitializer, <8 x half> zeroinitializer, i32 1)
21; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice.v16f16 = call <16 x half> @llvm.vector.splice.v16f16(<16 x half> zeroinitializer, <16 x half> zeroinitializer, i32 1)
22; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v2f32 = call <2 x float> @llvm.vector.splice.v2f32(<2 x float> zeroinitializer, <2 x float> zeroinitializer, i32 1)
23; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v4f32 = call <4 x float> @llvm.vector.splice.v4f32(<4 x float> zeroinitializer, <4 x float> zeroinitializer, i32 1)
24; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice.v8f32 = call <8 x float> @llvm.vector.splice.v8f32(<8 x float> zeroinitializer, <8 x float> zeroinitializer, i32 1)
25; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v2f64 = call <2 x double> @llvm.vector.splice.v2f64(<2 x double> zeroinitializer, <2 x double> zeroinitializer, i32 1)
26; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice.v4f64 = call <4 x double> @llvm.vector.splice.v4f64(<4 x double> zeroinitializer, <4 x double> zeroinitializer, i32 1)
27; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v2bf16 = call <2 x bfloat> @llvm.vector.splice.v2bf16(<2 x bfloat> zeroinitializer, <2 x bfloat> zeroinitializer, i32 1)
28; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v4bf16 = call <4 x bfloat> @llvm.vector.splice.v4bf16(<4 x bfloat> zeroinitializer, <4 x bfloat> zeroinitializer, i32 1)
29; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v8bf16 = call <8 x bfloat> @llvm.vector.splice.v8bf16(<8 x bfloat> zeroinitializer, <8 x bfloat> zeroinitializer, i32 1)
30; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %splice.v16bf16 = call <16 x bfloat> @llvm.vector.splice.v16bf16(<16 x bfloat> zeroinitializer, <16 x bfloat> zeroinitializer, i32 1)
31; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v16i1 = call <16 x i1> @llvm.vector.splice.v16i1(<16 x i1> zeroinitializer, <16 x i1> zeroinitializer, i32 1)
32; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v8i1 = call <8 x i1> @llvm.vector.splice.v8i1(<8 x i1> zeroinitializer, <8 x i1> zeroinitializer, i32 1)
33; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v4i1 = call <4 x i1> @llvm.vector.splice.v4i1(<4 x i1> zeroinitializer, <4 x i1> zeroinitializer, i32 1)
34; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %splice.v2i1 = call <2 x i1> @llvm.vector.splice.v2i1(<2 x i1> zeroinitializer, <2 x i1> zeroinitializer, i32 1)
35; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: %splice.v2i128 = call <2 x i128> @llvm.vector.splice.v2i128(<2 x i128> zeroinitializer, <2 x i128> zeroinitializer, i32 1)
36; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
37;
38  %splice.v16i8 = call <16 x i8> @llvm.vector.splice.v16i8(<16 x i8> zeroinitializer, <16 x i8> zeroinitializer, i32 1)
39  %splice.v32i8 = call <32 x i8> @llvm.vector.splice.v32i8(<32 x i8> zeroinitializer, <32 x i8> zeroinitializer, i32 1)
40  %splice.v2i16 = call <2 x i16> @llvm.vector.splice.v2i16(<2 x i16> zeroinitializer, <2 x i16> zeroinitializer, i32 1)
41  %splice.v4i16 = call <4 x i16> @llvm.vector.splice.v4i16(<4 x i16> zeroinitializer, <4 x i16> zeroinitializer, i32 1)
42  %splice.v8i16 = call <8 x i16> @llvm.vector.splice.v8i16(<8 x i16> zeroinitializer, <8 x i16> zeroinitializer, i32 1)
43  %splice.v16i16 = call <16 x i16> @llvm.vector.splice.v16i16(<16 x i16> zeroinitializer, <16 x i16> zeroinitializer, i32 1)
44  %splice.v4i32 = call <4 x i32> @llvm.vector.splice.v4i32(<4 x i32> zeroinitializer, <4 x i32> zeroinitializer, i32 1)
45  %splice.v8i32 = call <8 x i32> @llvm.vector.splice.v8i32(<8 x i32> zeroinitializer, <8 x i32> zeroinitializer, i32 1)
46  %splice.v2i64 = call <2 x i64> @llvm.vector.splice.v2i64(<2 x i64> zeroinitializer, <2 x i64> zeroinitializer, i32 1)
47  %splice.v4i64 = call <4 x i64> @llvm.vector.splice.v4i64(<4 x i64> zeroinitializer, <4 x i64> zeroinitializer, i32 1)
48  %splice.v2f16 = call <2 x half> @llvm.vector.splice.v2f16(<2 x half> zeroinitializer, <2 x half> zeroinitializer, i32 1)
49  %splice.v4f16 = call <4 x half> @llvm.vector.splice.v4f16(<4 x half> zeroinitializer, <4 x half> zeroinitializer, i32 1)
50  %splice.v8f16 = call <8 x half> @llvm.vector.splice.v8f16(<8 x half> zeroinitializer, <8 x half> zeroinitializer, i32 1)
51  %splice.v16f16 = call <16 x half> @llvm.vector.splice.v16f16(<16 x half> zeroinitializer, <16 x half> zeroinitializer, i32 1)
52  %splice.v2f32 = call <2 x float> @llvm.vector.splice.v2f32(<2 x float> zeroinitializer, <2 x float> zeroinitializer, i32 1)
53  %splice.v4f32 = call <4 x float> @llvm.vector.splice.v4f32(<4 x float> zeroinitializer, <4 x float> zeroinitializer, i32 1)
54  %splice.v8f32 = call <8 x float> @llvm.vector.splice.v8f32(<8 x float> zeroinitializer, <8 x float> zeroinitializer, i32 1)
55  %splice.v2f64 = call <2 x double> @llvm.vector.splice.v2f64(<2 x double> zeroinitializer, <2 x double> zeroinitializer, i32 1)
56  %splice.v4f64 = call <4 x double> @llvm.vector.splice.v4f64(<4 x double> zeroinitializer, <4 x double> zeroinitializer, i32 1)
57  %splice.v2bf16 = call <2 x bfloat> @llvm.vector.splice.v2bf16(<2 x bfloat> zeroinitializer, <2 x bfloat> zeroinitializer, i32 1)
58  %splice.v4bf16 = call <4 x bfloat> @llvm.vector.splice.v4bf16(<4 x bfloat> zeroinitializer, <4 x bfloat> zeroinitializer, i32 1)
59  %splice.v8bf16 = call <8 x bfloat> @llvm.vector.splice.v8bf16(<8 x bfloat> zeroinitializer, <8 x bfloat> zeroinitializer, i32 1)
60  %splice.v16bf16 = call <16 x bfloat> @llvm.vector.splice.v16bf16(<16 x bfloat> zeroinitializer, <16 x bfloat> zeroinitializer, i32 1)
61  %splice.v16i1 = call <16 x i1> @llvm.vector.splice.v16i1(<16 x i1> zeroinitializer, <16 x i1> zeroinitializer, i32 1)
62  %splice.v8i1 =  call <8 x i1> @llvm.vector.splice.v8i1(<8 x i1> zeroinitializer, <8 x i1> zeroinitializer, i32 1)
63  %splice.v4i1 = call <4 x i1> @llvm.vector.splice.v4i1(<4 x i1> zeroinitializer, <4 x i1> zeroinitializer, i32 1)
64  %splice.v2i1 = call <2 x i1> @llvm.vector.splice.v2i1(<2 x i1> zeroinitializer, <2 x i1> zeroinitializer, i32 1)
65  %splice.v2i128 = call <2 x i128> @llvm.vector.splice.v2i128(<2 x i128> zeroinitializer, <2 x i128> zeroinitializer, i32 1)
66  ret void
67}
68
69declare <2 x i1> @llvm.vector.splice.v2i1(<2 x i1>, <2 x i1>, i32)
70declare <4 x i1> @llvm.vector.splice.v4i1(<4 x i1>, <4 x i1>, i32)
71declare <8 x i1> @llvm.vector.splice.v8i1(<8 x i1>, <8 x i1>, i32)
72declare <16 x i1> @llvm.vector.splice.v16i1(<16 x i1>, <16 x i1>, i32)
73declare <2 x i8> @llvm.vector.splice.v2i8(<2 x i8>, <2 x i8>, i32)
74declare <16 x i8> @llvm.vector.splice.v16i8(<16 x i8>, <16 x i8>, i32)
75declare <32 x i8> @llvm.vector.splice.v32i8(<32 x i8>, <32 x i8>, i32)
76declare <2 x i16> @llvm.vector.splice.v2i16(<2 x i16>, <2 x i16>, i32)
77declare <4 x i16> @llvm.vector.splice.v4i16(<4 x i16>, <4 x i16>, i32)
78declare <8 x i16> @llvm.vector.splice.v8i16(<8 x i16>, <8 x i16>, i32)
79declare <16 x i16> @llvm.vector.splice.v16i16(<16 x i16>, <16 x i16>, i32)
80declare <4 x i32> @llvm.vector.splice.v4i32(<4 x i32>, <4 x i32>, i32)
81declare <8 x i32> @llvm.vector.splice.v8i32(<8 x i32>, <8 x i32>, i32)
82declare <2 x i64> @llvm.vector.splice.v2i64(<2 x i64>, <2 x i64>, i32)
83declare <4 x i64> @llvm.vector.splice.v4i64(<4 x i64>, <4 x i64>, i32)
84declare <2 x half> @llvm.vector.splice.v2f16(<2 x half>, <2 x half>, i32)
85declare <4 x half> @llvm.vector.splice.v4f16(<4 x half>, <4 x half>, i32)
86declare <8 x half> @llvm.vector.splice.v8f16(<8 x half>, <8 x half>, i32)
87declare <16 x half> @llvm.vector.splice.v16f16(<16 x half>, <16 x half>, i32)
88declare <2 x bfloat> @llvm.vector.splice.v2bf16(<2 x bfloat>, <2 x bfloat>, i32)
89declare <4 x bfloat> @llvm.vector.splice.v4bf16(<4 x bfloat>, <4 x bfloat>, i32)
90declare <8 x bfloat> @llvm.vector.splice.v8bf16(<8 x bfloat>, <8 x bfloat>, i32)
91declare <16 x bfloat> @llvm.vector.splice.v16bf16(<16 x bfloat>, <16 x bfloat>, i32)
92declare <2 x float> @llvm.vector.splice.v2f32(<2 x float>, <2 x float>, i32)
93declare <4 x float> @llvm.vector.splice.v4f32(<4 x float>, <4 x float>, i32)
94declare <8 x float> @llvm.vector.splice.v8f32(<8 x float>, <8 x float>, i32)
95declare <16 x float> @llvm.vector.splice.v16f32(<16 x float>, <16 x float>, i32)
96declare <2 x double> @llvm.vector.splice.v2f64(<2 x double>, <2 x double>, i32)
97declare <4 x double> @llvm.vector.splice.v4f64(<4 x double>, <4 x double>, i32)
98declare <2 x i128> @llvm.vector.splice.v2i128(<2 x i128>, <2 x i128>, i32)
99
100attributes #0 = { "target-features"="+bf16" }
101