forked from OSchip/llvm-project
35 lines
2.3 KiB
LLVM
35 lines
2.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
|
; RUN: opt < %s -mtriple=amdgcn-unknown-amdhsa -cost-model -cost-kind=throughput -analyze | FileCheck %s
|
|
|
|
define i32 @reduce_i1(i32 %arg) {
|
|
; CHECK-LABEL: 'reduce_i1'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 17 for instruction: %V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 33 for instruction: %V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 65 for instruction: %V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 130 for instruction: %V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 10 for instruction: ret i32 undef
|
|
;
|
|
%V1 = call i1 @llvm.vector.reduce.or.v1i1(<1 x i1> undef)
|
|
%V2 = call i1 @llvm.vector.reduce.or.v2i1(<2 x i1> undef)
|
|
%V4 = call i1 @llvm.vector.reduce.or.v4i1(<4 x i1> undef)
|
|
%V8 = call i1 @llvm.vector.reduce.or.v8i1(<8 x i1> undef)
|
|
%V16 = call i1 @llvm.vector.reduce.or.v16i1(<16 x i1> undef)
|
|
%V32 = call i1 @llvm.vector.reduce.or.v32i1(<32 x i1> undef)
|
|
%V64 = call i1 @llvm.vector.reduce.or.v64i1(<64 x i1> undef)
|
|
%V128 = call i1 @llvm.vector.reduce.or.v128i1(<128 x i1> undef)
|
|
ret i32 undef
|
|
}
|
|
|
|
declare i1 @llvm.vector.reduce.or.v1i1(<1 x i1>)
|
|
declare i1 @llvm.vector.reduce.or.v2i1(<2 x i1>)
|
|
declare i1 @llvm.vector.reduce.or.v4i1(<4 x i1>)
|
|
declare i1 @llvm.vector.reduce.or.v8i1(<8 x i1>)
|
|
declare i1 @llvm.vector.reduce.or.v16i1(<16 x i1>)
|
|
declare i1 @llvm.vector.reduce.or.v32i1(<32 x i1>)
|
|
declare i1 @llvm.vector.reduce.or.v64i1(<64 x i1>)
|
|
declare i1 @llvm.vector.reduce.or.v128i1(<128 x i1>)
|