1; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
2; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -passes='print<cost-model>' -cost-kind=throughput 2>&1 -disable-output | FileCheck %s
3
4define void @reduce() {
5; CHECK-LABEL: 'reduce'
6; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V1i8 = call i8 @llvm.vector.reduce.add.v1i8(<1 x i8> undef)
7; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V3i8 = call i8 @llvm.vector.reduce.add.v3i8(<3 x i8> undef)
8; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4i8 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
9; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i8 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
10; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V16i8 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
11; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V32i8 = call i8 @llvm.vector.reduce.add.v32i8(<32 x i8> undef)
12; CHECK-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %V64i8 = call i8 @llvm.vector.reduce.add.v64i8(<64 x i8> undef)
13; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2i16 = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> undef)
14; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4i16 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> undef)
15; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V8i16 = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> undef)
16; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V16i16 = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> undef)
17; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2i32 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> undef)
18; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V4i32 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> undef)
19; CHECK-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %V8i32 = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> undef)
20; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %V2i64 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
21; CHECK-NEXT:  Cost Model: Found an estimated cost of 9 for instruction: %V4i64 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
22; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
23;
24  %V1i8 = call i8 @llvm.vector.reduce.add.v1i8(<1 x i8> undef)
25  %V3i8 = call i8 @llvm.vector.reduce.add.v3i8(<3 x i8> undef)
26  %V4i8 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
27  %V8i8 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
28  %V16i8 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
29  %V32i8 = call i8 @llvm.vector.reduce.add.v32i8(<32 x i8> undef)
30  %V64i8 = call i8 @llvm.vector.reduce.add.v64i8(<64 x i8> undef)
31  %V2i16 = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> undef)
32  %V4i16 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> undef)
33  %V8i16 = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> undef)
34  %V16i16 = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> undef)
35  %V2i32 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> undef)
36  %V4i32 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> undef)
37  %V8i32 = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> undef)
38  %V2i64 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
39  %V4i64 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
40  ret void
41}
42
43declare i8 @llvm.vector.reduce.add.v1i8(<1 x i8>)
44declare i8 @llvm.vector.reduce.add.v3i8(<3 x i8>)
45declare i8 @llvm.vector.reduce.add.v4i8(<4 x i8>)
46declare i8 @llvm.vector.reduce.add.v8i8(<8 x i8>)
47declare i8 @llvm.vector.reduce.add.v16i8(<16 x i8>)
48declare i8 @llvm.vector.reduce.add.v32i8(<32 x i8>)
49declare i8 @llvm.vector.reduce.add.v64i8(<64 x i8>)
50declare i16 @llvm.vector.reduce.add.v2i16(<2 x i16>)
51declare i16 @llvm.vector.reduce.add.v4i16(<4 x i16>)
52declare i16 @llvm.vector.reduce.add.v8i16(<8 x i16>)
53declare i16 @llvm.vector.reduce.add.v16i16(<16 x i16>)
54declare i32 @llvm.vector.reduce.add.v2i32(<2 x i32>)
55declare i32 @llvm.vector.reduce.add.v4i32(<4 x i32>)
56declare i32 @llvm.vector.reduce.add.v8i32(<8 x i32>)
57declare i64 @llvm.vector.reduce.add.v2i64(<2 x i64>)
58declare i64 @llvm.vector.reduce.add.v4i64(<4 x i64>)
59