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
|
#include "textflag.h"
#define ROUND()\
ADD.S R2,R0,R0;\
ADC R3,R1,R1;\
EOR R2<<13,R0,R8;\
EOR R3>>19,R8,R8;\
EOR R2>>19,R1,R11;\
EOR R3<<13,R11,R11;\
ADD.S R6,R4,R4;\
ADC R7,R5,R5;\
EOR R6<<16,R4,R2;\
EOR R7>>16,R2,R2;\
EOR R6>>16,R5,R3;\
EOR R7<<16,R3,R3;\
ADD.S R2,R1,R1;\
ADC R3,R0,R0;\
EOR R2<<21,R1,R6;\
EOR R3>>11,R6,R6;\
EOR R2>>11,R0,R7;\
EOR R3<<21,R7,R7;\
ADD.S R8,R4,R4;\
ADC R11,R5,R5;\
EOR R8<<17,R4,R2;\
EOR R11>>15,R2,R2;\
EOR R8>>15,R5,R3;\
EOR R11<<17,R3,R3;\
ADD.S R2,R1,R1;\
ADC R3,R0,R0;\
EOR R2<<13,R1,R8;\
EOR R3>>19,R8,R8;\
EOR R2>>19,R0,R11;\
EOR R3<<13,R11,R11;\
ADD.S R6,R5,R5;\
ADC R7,R4,R4;\
EOR R6<<16,R5,R2;\
EOR R7>>16,R2,R2;\
EOR R6>>16,R4,R3;\
EOR R7<<16,R3,R3;\
ADD.S R2,R0,R0;\
ADC R3,R1,R1;\
EOR R2<<21,R0,R6;\
EOR R3>>11,R6,R6;\
EOR R2>>11,R1,R7;\
EOR R3<<21,R7,R7;\
ADD.S R8,R5,R5;\
ADC R11,R4,R4;\
EOR R8<<17,R5,R2;\
EOR R11>>15,R2,R2;\
EOR R8>>15,R4,R3;\
EOR R11<<17,R3,R3;
// once(d *digest)
TEXT ·once(SB),NOSPLIT,$4-4
MOVW d+0(FP),R8
MOVM.IA (R8),[R0,R1,R2,R3,R4,R5,R6,R7]
MOVW 48(R8),R12
MOVW 52(R8),R14
EOR R12,R6,R6
EOR R14,R7,R7
ROUND()
EOR R12,R0,R0
EOR R14,R1,R1
MOVW d+0(FP),R8
MOVM.IA [R0,R1,R2,R3,R4,R5,R6,R7],(R8)
RET
// finalize(d *digest) uint64
TEXT ·finalize(SB),NOSPLIT,$4-12
MOVW d+0(FP),R8
MOVM.IA (R8),[R0,R1,R2,R3,R4,R5,R6,R7]
MOVW 48(R8),R12
MOVW 52(R8),R14
EOR R12,R6,R6
EOR R14,R7,R7
ROUND()
EOR R12,R0,R0
EOR R14,R1,R1
EOR $255,R4
ROUND()
ROUND()
EOR R2,R0,R0
EOR R3,R1,R1
EOR R6,R4,R4
EOR R7,R5,R5
EOR R4,R0,R0
EOR R5,R1,R1
MOVW R0,ret_lo+4(FP)
MOVW R1,ret_hi+8(FP)
RET
// blocks(d *digest, data []uint8)
TEXT ·blocks(SB),NOSPLIT,$4-16
MOVW d+0(FP),R8
MOVM.IA (R8),[R0,R1,R2,R3,R4,R5,R6,R7]
MOVW p+4(FP),R9
MOVW p_len+8(FP),R11
ADD R9,R11,R11
MOVW R11,endp-4(SP)
AND.S $3,R9,R8
BNE blocksunaligned
blocksloop:
MOVM.IA.W (R9),[R12,R14]
EOR R12,R6,R6
EOR R14,R7,R7
ROUND()
EOR R12,R0,R0
EOR R14,R1,R1
MOVW endp-4(SP),R11
CMP R11,R9
BLO blocksloop
MOVW d+0(FP),R8
MOVM.IA [R0,R1,R2,R3,R4,R5,R6,R7],(R8)
RET
blocksunaligned:
MOVBU.P 8(R9),R12
MOVBU -7(R9),R11
ORR R11<<8,R12,R12
MOVBU -6(R9),R11
ORR R11<<16,R12,R12
MOVBU -5(R9),R11
ORR R11<<24,R12,R12
MOVBU -4(R9),R14
MOVBU -3(R9),R11
ORR R11<<8,R14,R14
MOVBU -2(R9),R11
ORR R11<<16,R14,R14
MOVBU -1(R9),R11
ORR R11<<24,R14,R14
EOR R12,R6,R6
EOR R14,R7,R7
ROUND()
EOR R12,R0,R0
EOR R14,R1,R1
MOVW endp-4(SP),R11
CMP R11,R9
BLO blocksunaligned
MOVW d+0(FP),R8
MOVM.IA [R0,R1,R2,R3,R4,R5,R6,R7],(R8)
RET
|
