reduce-fmin.ll
8.67 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE2
; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+ssse3 | FileCheck %s --check-prefixes=CHECK,SSE,SSSE3
; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.1 | FileCheck %s --check-prefixes=CHECK,SSE,SSE4,SSE41
; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+sse4.2 | FileCheck %s --check-prefixes=CHECK,SSE,SSE4,SSE42
; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx | FileCheck %s --check-prefixes=CHECK,AVX,AVX1
; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx2 | FileCheck %s --check-prefixes=CHECK,AVX,AVX2
; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512F
; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512bw | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512BW
; RUN: opt < %s -cost-model -mtriple=x86_64-apple-darwin -analyze -mattr=+avx512f,+avx512dq | FileCheck %s --check-prefixes=CHECK,AVX512,AVX512DQ
define i32 @reduce_f64(i32 %arg) {
; SSE-LABEL: 'reduce_f64'
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call double @llvm.experimental.vector.reduce.fmin.v1f64(<1 x double> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call double @llvm.experimental.vector.reduce.fmin.v2f64(<2 x double> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call double @llvm.experimental.vector.reduce.fmin.v4f64(<4 x double> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call double @llvm.experimental.vector.reduce.fmin.v8f64(<8 x double> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V16 = call double @llvm.experimental.vector.reduce.fmin.v16f64(<16 x double> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX-LABEL: 'reduce_f64'
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call double @llvm.experimental.vector.reduce.fmin.v1f64(<1 x double> undef)
; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call double @llvm.experimental.vector.reduce.fmin.v2f64(<2 x double> undef)
; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call double @llvm.experimental.vector.reduce.fmin.v4f64(<4 x double> undef)
; AVX-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call double @llvm.experimental.vector.reduce.fmin.v8f64(<8 x double> undef)
; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16 = call double @llvm.experimental.vector.reduce.fmin.v16f64(<16 x double> undef)
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'reduce_f64'
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call double @llvm.experimental.vector.reduce.fmin.v1f64(<1 x double> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call double @llvm.experimental.vector.reduce.fmin.v2f64(<2 x double> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call double @llvm.experimental.vector.reduce.fmin.v4f64(<4 x double> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call double @llvm.experimental.vector.reduce.fmin.v8f64(<8 x double> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16 = call double @llvm.experimental.vector.reduce.fmin.v16f64(<16 x double> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V1 = call double @llvm.experimental.vector.reduce.fmin.v1f64(<1 x double> undef)
%V2 = call double @llvm.experimental.vector.reduce.fmin.v2f64(<2 x double> undef)
%V4 = call double @llvm.experimental.vector.reduce.fmin.v4f64(<4 x double> undef)
%V8 = call double @llvm.experimental.vector.reduce.fmin.v8f64(<8 x double> undef)
%V16 = call double @llvm.experimental.vector.reduce.fmin.v16f64(<16 x double> undef)
ret i32 undef
}
define i32 @reduce_f32(i32 %arg) {
; SSE-LABEL: 'reduce_f32'
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call float @llvm.experimental.vector.reduce.fmin.v1f32(<1 x float> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call float @llvm.experimental.vector.reduce.fmin.v2f32(<2 x float> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call float @llvm.experimental.vector.reduce.fmin.v4f32(<4 x float> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V8 = call float @llvm.experimental.vector.reduce.fmin.v8f32(<8 x float> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16 = call float @llvm.experimental.vector.reduce.fmin.v16f32(<16 x float> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %V32 = call float @llvm.experimental.vector.reduce.fmin.v32f32(<32 x float> undef)
; SSE-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX-LABEL: 'reduce_f32'
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call float @llvm.experimental.vector.reduce.fmin.v1f32(<1 x float> undef)
; AVX-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call float @llvm.experimental.vector.reduce.fmin.v2f32(<2 x float> undef)
; AVX-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call float @llvm.experimental.vector.reduce.fmin.v4f32(<4 x float> undef)
; AVX-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call float @llvm.experimental.vector.reduce.fmin.v8f32(<8 x float> undef)
; AVX-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V16 = call float @llvm.experimental.vector.reduce.fmin.v16f32(<16 x float> undef)
; AVX-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V32 = call float @llvm.experimental.vector.reduce.fmin.v32f32(<32 x float> undef)
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512-LABEL: 'reduce_f32'
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %V1 = call float @llvm.experimental.vector.reduce.fmin.v1f32(<1 x float> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call float @llvm.experimental.vector.reduce.fmin.v2f32(<2 x float> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V4 = call float @llvm.experimental.vector.reduce.fmin.v4f32(<4 x float> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V8 = call float @llvm.experimental.vector.reduce.fmin.v8f32(<8 x float> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V16 = call float @llvm.experimental.vector.reduce.fmin.v16f32(<16 x float> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V32 = call float @llvm.experimental.vector.reduce.fmin.v32f32(<32 x float> undef)
; AVX512-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
%V1 = call float @llvm.experimental.vector.reduce.fmin.v1f32(<1 x float> undef)
%V2 = call float @llvm.experimental.vector.reduce.fmin.v2f32(<2 x float> undef)
%V4 = call float @llvm.experimental.vector.reduce.fmin.v4f32(<4 x float> undef)
%V8 = call float @llvm.experimental.vector.reduce.fmin.v8f32(<8 x float> undef)
%V16 = call float @llvm.experimental.vector.reduce.fmin.v16f32(<16 x float> undef)
%V32 = call float @llvm.experimental.vector.reduce.fmin.v32f32(<32 x float> undef)
ret i32 undef
}
declare double @llvm.experimental.vector.reduce.fmin.v1f64(<1 x double>)
declare double @llvm.experimental.vector.reduce.fmin.v2f64(<2 x double>)
declare double @llvm.experimental.vector.reduce.fmin.v4f64(<4 x double>)
declare double @llvm.experimental.vector.reduce.fmin.v8f64(<8 x double>)
declare double @llvm.experimental.vector.reduce.fmin.v16f64(<16 x double>)
declare float @llvm.experimental.vector.reduce.fmin.v1f32(<1 x float>)
declare float @llvm.experimental.vector.reduce.fmin.v2f32(<2 x float>)
declare float @llvm.experimental.vector.reduce.fmin.v4f32(<4 x float>)
declare float @llvm.experimental.vector.reduce.fmin.v8f32(<8 x float>)
declare float @llvm.experimental.vector.reduce.fmin.v16f32(<16 x float>)
declare float @llvm.experimental.vector.reduce.fmin.v32f32(<32 x float>)