1 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
2 ; RUN: opt < %s -mtriple=armv8a-linux-gnueabihf -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck %s
4 target datalayout = "e-m:e-p:32:32-Fi8-i64:64-v128:64:128-a:0:32-n32-S64"
6 define i32 @reduce_i1(i32 %arg) {
7 ; CHECK-LABEL: 'reduce_i1'
8 ; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
9 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
10 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
11 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
12 ; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
13 ; CHECK-NEXT: Cost Model: Found an estimated cost of 97 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
14 ; CHECK-NEXT: Cost Model: Found an estimated cost of 193 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
15 ; CHECK-NEXT: Cost Model: Found an estimated cost of 385 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
16 ; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
18 %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
19 %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
20 %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
21 %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
22 %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
23 %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
24 %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
25 %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
29 declare i1 @llvm.vector.reduce.or.v1i1(<1 x i1>)
30 declare i1 @llvm.vector.reduce.or.v2i1(<2 x i1>)
31 declare i1 @llvm.vector.reduce.or.v4i1(<4 x i1>)
32 declare i1 @llvm.vector.reduce.or.v8i1(<8 x i1>)
33 declare i1 @llvm.vector.reduce.or.v16i1(<16 x i1>)
34 declare i1 @llvm.vector.reduce.or.v32i1(<32 x i1>)
35 declare i1 @llvm.vector.reduce.or.v64i1(<64 x i1>)
36 declare i1 @llvm.vector.reduce.or.v128i1(<128 x i1>)