blob: 2eb63babdc343263460fb48407ef05a54a74669f (
plain)
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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
|
; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -mcpu=pentium4 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=X86 -check-prefix=SSE2
; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -mcpu=corei7 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=X86 -check-prefix=SSE42
; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -mcpu=corei7-avx -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=X86 -check-prefix=AVX
; RUN: opt < %s -mtriple=i686-unknown-linux-gnu -mcpu=core-avx2 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=X86 -check-prefix=AVX2
; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=pentium4 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=X64 -check-prefix=SSE2
; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=X64 -check-prefix=SSE42
; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7-avx -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=X64 -check-prefix=AVX
; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=core-avx2 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=X64 -check-prefix=AVX2
; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=bdver2 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=XOP -check-prefix=XOPAVX
; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -mcpu=bdver4 -cost-model -analyze | FileCheck %s -check-prefix=CHECK -check-prefix=XOP -check-prefix=XOPAVX2
; Verify the cost of scalar bitreverse instructions.
declare i64 @llvm.bitreverse.i64(i64)
declare i32 @llvm.bitreverse.i32(i32)
declare i16 @llvm.bitreverse.i16(i16)
declare i8 @llvm.bitreverse.i8(i8)
define i64 @var_bitreverse_i64(i64 %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_i64':
; X86: Found an estimated cost of 28 for instruction: %bitreverse
; X64: Found an estimated cost of 14 for instruction: %bitreverse
; XOP: Found an estimated cost of 3 for instruction: %bitreverse
%bitreverse = call i64 @llvm.bitreverse.i64(i64 %a)
ret i64 %bitreverse
}
define i32 @var_bitreverse_i32(i32 %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_i32':
; X86: Found an estimated cost of 14 for instruction: %bitreverse
; X64: Found an estimated cost of 14 for instruction: %bitreverse
; XOP: Found an estimated cost of 3 for instruction: %bitreverse
%bitreverse = call i32 @llvm.bitreverse.i32(i32 %a)
ret i32 %bitreverse
}
define i16 @var_bitreverse_i16(i16 %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_i16':
; X86: Found an estimated cost of 14 for instruction: %bitreverse
; X64: Found an estimated cost of 14 for instruction: %bitreverse
; XOP: Found an estimated cost of 3 for instruction: %bitreverse
%bitreverse = call i16 @llvm.bitreverse.i16(i16 %a)
ret i16 %bitreverse
}
define i8 @var_bitreverse_i8(i8 %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_i8':
; X86: Found an estimated cost of 11 for instruction: %bitreverse
; X64: Found an estimated cost of 11 for instruction: %bitreverse
; XOP: Found an estimated cost of 3 for instruction: %bitreverse
%bitreverse = call i8 @llvm.bitreverse.i8(i8 %a)
ret i8 %bitreverse
}
; Verify the cost of vector bitreverse instructions.
declare <2 x i64> @llvm.bitreverse.v2i64(<2 x i64>)
declare <4 x i32> @llvm.bitreverse.v4i32(<4 x i32>)
declare <8 x i16> @llvm.bitreverse.v8i16(<8 x i16>)
declare <16 x i8> @llvm.bitreverse.v16i8(<16 x i8>)
declare <4 x i64> @llvm.bitreverse.v4i64(<4 x i64>)
declare <8 x i32> @llvm.bitreverse.v8i32(<8 x i32>)
declare <16 x i16> @llvm.bitreverse.v16i16(<16 x i16>)
declare <32 x i8> @llvm.bitreverse.v32i8(<32 x i8>)
define <2 x i64> @var_bitreverse_v2i64(<2 x i64> %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_v2i64':
; SSE2: Found an estimated cost of 29 for instruction: %bitreverse
; SSE42: Found an estimated cost of 5 for instruction: %bitreverse
; AVX: Found an estimated cost of 5 for instruction: %bitreverse
; AVX2: Found an estimated cost of 5 for instruction: %bitreverse
; XOP: Found an estimated cost of 1 for instruction: %bitreverse
%bitreverse = call <2 x i64> @llvm.bitreverse.v2i64(<2 x i64> %a)
ret <2 x i64> %bitreverse
}
define <4 x i64> @var_bitreverse_v4i64(<4 x i64> %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_v4i64':
; SSE2: Found an estimated cost of 58 for instruction: %bitreverse
; SSE42: Found an estimated cost of 10 for instruction: %bitreverse
; AVX: Found an estimated cost of 10 for instruction: %bitreverse
; AVX2: Found an estimated cost of 5 for instruction: %bitreverse
; XOP: Found an estimated cost of 4 for instruction: %bitreverse
%bitreverse = call <4 x i64> @llvm.bitreverse.v4i64(<4 x i64> %a)
ret <4 x i64> %bitreverse
}
define <4 x i32> @var_bitreverse_v4i32(<4 x i32> %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_v4i32':
; SSE2: Found an estimated cost of 27 for instruction: %bitreverse
; SSE42: Found an estimated cost of 5 for instruction: %bitreverse
; AVX: Found an estimated cost of 5 for instruction: %bitreverse
; AVX2: Found an estimated cost of 5 for instruction: %bitreverse
; XOP: Found an estimated cost of 1 for instruction: %bitreverse
%bitreverse = call <4 x i32> @llvm.bitreverse.v4i32(<4 x i32> %a)
ret <4 x i32> %bitreverse
}
define <8 x i32> @var_bitreverse_v8i32(<8 x i32> %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_v8i32':
; SSE2: Found an estimated cost of 54 for instruction: %bitreverse
; SSE42: Found an estimated cost of 10 for instruction: %bitreverse
; AVX: Found an estimated cost of 10 for instruction: %bitreverse
; AVX2: Found an estimated cost of 5 for instruction: %bitreverse
; XOP: Found an estimated cost of 4 for instruction: %bitreverse
%bitreverse = call <8 x i32> @llvm.bitreverse.v8i32(<8 x i32> %a)
ret <8 x i32> %bitreverse
}
define <8 x i16> @var_bitreverse_v8i16(<8 x i16> %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_v8i16':
; SSE2: Found an estimated cost of 27 for instruction: %bitreverse
; SSE42: Found an estimated cost of 5 for instruction: %bitreverse
; AVX: Found an estimated cost of 5 for instruction: %bitreverse
; AVX2: Found an estimated cost of 5 for instruction: %bitreverse
; XOP: Found an estimated cost of 1 for instruction: %bitreverse
%bitreverse = call <8 x i16> @llvm.bitreverse.v8i16(<8 x i16> %a)
ret <8 x i16> %bitreverse
}
define <16 x i16> @var_bitreverse_v16i16(<16 x i16> %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_v16i16':
; SSE2: Found an estimated cost of 54 for instruction: %bitreverse
; SSE42: Found an estimated cost of 10 for instruction: %bitreverse
; AVX: Found an estimated cost of 10 for instruction: %bitreverse
; AVX2: Found an estimated cost of 5 for instruction: %bitreverse
; XOP: Found an estimated cost of 4 for instruction: %bitreverse
%bitreverse = call <16 x i16> @llvm.bitreverse.v16i16(<16 x i16> %a)
ret <16 x i16> %bitreverse
}
define <16 x i8> @var_bitreverse_v16i8(<16 x i8> %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_v16i8':
; SSE2: Found an estimated cost of 20 for instruction: %bitreverse
; SSE42: Found an estimated cost of 5 for instruction: %bitreverse
; AVX: Found an estimated cost of 5 for instruction: %bitreverse
; AVX2: Found an estimated cost of 5 for instruction: %bitreverse
; XOP: Found an estimated cost of 1 for instruction: %bitreverse
%bitreverse = call <16 x i8> @llvm.bitreverse.v16i8(<16 x i8> %a)
ret <16 x i8> %bitreverse
}
define <32 x i8> @var_bitreverse_v32i8(<32 x i8> %a) {
; CHECK: 'Cost Model Analysis' for function 'var_bitreverse_v32i8':
; SSE2: Found an estimated cost of 40 for instruction: %bitreverse
; SSE42: Found an estimated cost of 10 for instruction: %bitreverse
; AVX: Found an estimated cost of 10 for instruction: %bitreverse
; AVX2: Found an estimated cost of 5 for instruction: %bitreverse
; XOP: Found an estimated cost of 4 for instruction: %bitreverse
%bitreverse = call <32 x i8> @llvm.bitreverse.v32i8(<32 x i8> %a)
ret <32 x i8> %bitreverse
}
|
