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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --extra_scrub
; RUN: llc -mtriple=aarch64 -mattr=+sha3 < %s | FileCheck --check-prefix=SHA3 %s
; RUN: llc -mtriple=aarch64 -mattr=-sha3 < %s | FileCheck --check-prefix=NOSHA3 %s
; RUN: llc -mtriple=aarch64 -mattr=+sve2 < %s | FileCheck --check-prefix=SVE2 %s
; RUN: llc -mtriple=aarch64 -mattr=+sha3,+sve2 < %s | FileCheck --check-prefix=SHA3 %s
define <2 x i64> @bcax_64x2(<2 x i64> %0, <2 x i64> %1, <2 x i64> %2) {
; SHA3-LABEL: bcax_64x2:
; SHA3: // %bb.0:
; SHA3-NEXT: bcax v0.16b, v2.16b, v0.16b, v1.16b
; SHA3-NEXT: ret
;
; NOSHA3-LABEL: bcax_64x2:
; NOSHA3: // %bb.0:
; NOSHA3-NEXT: bic v0.16b, v0.16b, v1.16b
; NOSHA3-NEXT: eor v0.16b, v0.16b, v2.16b
; NOSHA3-NEXT: ret
;
; SVE2-LABEL: bcax_64x2:
; SVE2: // %bb.0:
; SVE2-NEXT: // kill: def $q2 killed $q2 def $z2
; SVE2-NEXT: // kill: def $q1 killed $q1 def $z1
; SVE2-NEXT: // kill: def $q0 killed $q0 def $z0
; SVE2-NEXT: bcax z2.d, z2.d, z0.d, z1.d
; SVE2-NEXT: mov v0.16b, v2.16b
; SVE2-NEXT: ret
%4 = xor <2 x i64> %1, <i64 -1, i64 -1>
%5 = and <2 x i64> %4, %0
%6 = xor <2 x i64> %5, %2
ret <2 x i64> %6
}
define <4 x i32> @bcax_32x4(<4 x i32> %0, <4 x i32> %1, <4 x i32> %2) {
; SHA3-LABEL: bcax_32x4:
; SHA3: // %bb.0:
; SHA3-NEXT: bcax v0.16b, v2.16b, v0.16b, v1.16b
; SHA3-NEXT: ret
;
; NOSHA3-LABEL: bcax_32x4:
; NOSHA3: // %bb.0:
; NOSHA3-NEXT: bic v0.16b, v0.16b, v1.16b
; NOSHA3-NEXT: eor v0.16b, v0.16b, v2.16b
; NOSHA3-NEXT: ret
;
; SVE2-LABEL: bcax_32x4:
; SVE2: // %bb.0:
; SVE2-NEXT: // kill: def $q2 killed $q2 def $z2
; SVE2-NEXT: // kill: def $q1 killed $q1 def $z1
; SVE2-NEXT: // kill: def $q0 killed $q0 def $z0
; SVE2-NEXT: bcax z2.d, z2.d, z0.d, z1.d
; SVE2-NEXT: mov v0.16b, v2.16b
; SVE2-NEXT: ret
%4 = xor <4 x i32> %1, <i32 -1, i32 -1, i32 -1, i32 -1>
%5 = and <4 x i32> %4, %0
%6 = xor <4 x i32> %5, %2
ret <4 x i32> %6
}
define <8 x i16> @bcax_16x8(<8 x i16> %0, <8 x i16> %1, <8 x i16> %2) {
; SHA3-LABEL: bcax_16x8:
; SHA3: // %bb.0:
; SHA3-NEXT: bcax v0.16b, v2.16b, v0.16b, v1.16b
; SHA3-NEXT: ret
;
; NOSHA3-LABEL: bcax_16x8:
; NOSHA3: // %bb.0:
; NOSHA3-NEXT: bic v0.16b, v0.16b, v1.16b
; NOSHA3-NEXT: eor v0.16b, v0.16b, v2.16b
; NOSHA3-NEXT: ret
;
; SVE2-LABEL: bcax_16x8:
; SVE2: // %bb.0:
; SVE2-NEXT: // kill: def $q2 killed $q2 def $z2
; SVE2-NEXT: // kill: def $q1 killed $q1 def $z1
; SVE2-NEXT: // kill: def $q0 killed $q0 def $z0
; SVE2-NEXT: bcax z2.d, z2.d, z0.d, z1.d
; SVE2-NEXT: mov v0.16b, v2.16b
; SVE2-NEXT: ret
%4 = xor <8 x i16> %1, <i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1, i16 -1>
%5 = and <8 x i16> %4, %0
%6 = xor <8 x i16> %5, %2
ret <8 x i16> %6
}
define <16 x i8> @bcax_8x16(<16 x i8> %0, <16 x i8> %1, <16 x i8> %2) {
; SHA3-LABEL: bcax_8x16:
; SHA3: // %bb.0:
; SHA3-NEXT: bcax v0.16b, v2.16b, v0.16b, v1.16b
; SHA3-NEXT: ret
;
; NOSHA3-LABEL: bcax_8x16:
; NOSHA3: // %bb.0:
; NOSHA3-NEXT: bic v0.16b, v0.16b, v1.16b
; NOSHA3-NEXT: eor v0.16b, v0.16b, v2.16b
; NOSHA3-NEXT: ret
;
; SVE2-LABEL: bcax_8x16:
; SVE2: // %bb.0:
; SVE2-NEXT: // kill: def $q2 killed $q2 def $z2
; SVE2-NEXT: // kill: def $q1 killed $q1 def $z1
; SVE2-NEXT: // kill: def $q0 killed $q0 def $z0
; SVE2-NEXT: bcax z2.d, z2.d, z0.d, z1.d
; SVE2-NEXT: mov v0.16b, v2.16b
; SVE2-NEXT: ret
%4 = xor <16 x i8> %1, <i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1, i8 -1>
%5 = and <16 x i8> %4, %0
%6 = xor <16 x i8> %5, %2
ret <16 x i8> %6
}
|
