-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathm_amatvec.alpha
150 lines (126 loc) · 2.44 KB
/
m_amatvec.alpha
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
/* coded for the alpha 21064 */
.ugen
.verstamp 3 11
.text
.align 4
.file 2 "m_amatvec.c"
.globl mult_adj_su3_mat_vec
.loc 2 64
# 64 void mult_adj_su3_mat_vec(a,b,c) su3_matrix *a; su3_vector *b,*c; {
.ent mult_adj_su3_mat_vec 2
mult_adj_su3_mat_vec:
.option O2
ldgp $gp, 0($27)
.frame $sp, 0, $26, 0
.prologue 1
.loc 2 64
.loc 2 67
# 65 int i,j,k;
# 66 register float t,ar,ai,br,bi,cr,ci;
# 67 for(i=0;i<3;i++){
bis $31, $31, $0
bis $16, $16, $19
bis $18, $18, $20
$32:
.loc 2 67
.loc 2 69
# 68
# 69 ar=a->e[0][i].real; ai=a->e[0][i].imag;
lds $f0, 0($19)
.loc 2 69
lds $f1, 4($19)
.loc 2 70
# 70 br=b->c[0].real; bi=b->c[0].imag;
lds $f16, 0($17)
.loc 2 70
lds $f17, 4($17)
.loc 2 71
# 71 cr=ar*br; t=ai*bi; cr += t;
.loc 2 71
.loc 2 71
muls $f0, $f16, $f10
muls $f1, $f17, $f11
adds $f10, $f11, $f18
.loc 2 72
# 72 ci=ar*bi; t=ai*br; ci -= t;
.loc 2 72
.loc 2 72
muls $f0, $f17, $f12
muls $f1, $f16, $f13
subs $f12, $f13, $f19
.loc 2 74
# 73
# 74 ar=a->e[1][i].real; ai=a->e[1][i].imag;
lds $f0, 24($19)
.loc 2 74
lds $f1, 28($19)
.loc 2 75
# 75 br=b->c[1].real; bi=b->c[1].imag;
lds $f16, 8($17)
.loc 2 75
lds $f17, 12($17)
.loc 2 76
# 76 t=ar*br; cr += t; t=ai*bi; cr += t;
.loc 2 76
muls $f0, $f16, $f14
adds $f18, $f14, $f18
.loc 2 76
.loc 2 76
muls $f1, $f17, $f15
adds $f18, $f15, $f18
.loc 2 77
# 77 t=ar*bi; ci += t; t=ai*br; ci -= t;
.loc 2 77
muls $f0, $f17, $f22
adds $f19, $f22, $f19
.loc 2 77
.loc 2 77
muls $f1, $f16, $f23
subs $f19, $f23, $f19
.loc 2 79
# 78
# 79 ar=a->e[2][i].real; ai=a->e[2][i].imag;
lds $f0, 48($19)
.loc 2 79
lds $f1, 52($19)
.loc 2 80
# 80 br=b->c[2].real; bi=b->c[2].imag;
lds $f16, 16($17)
.loc 2 80
lds $f17, 20($17)
.loc 2 81
# 81 t=ar*br; cr += t; t=ai*bi; cr += t;
.loc 2 81
muls $f0, $f16, $f24
adds $f18, $f24, $f18
.loc 2 81
.loc 2 81
muls $f1, $f17, $f25
adds $f18, $f25, $f18
.loc 2 82
# 82 t=ar*bi; ci += t; t=ai*br; ci -= t;
.loc 2 82
muls $f0, $f17, $f26
adds $f19, $f26, $f19
.loc 2 82
.loc 2 82
muls $f1, $f16, $f27
subs $f19, $f27, $f19
.loc 2 84
# 83
# 84 c->c[i].real=cr;
sts $f18, 0($20)
.loc 2 85
# 85 c->c[i].imag=ci;
sts $f19, 4($20)
addl $0, 1, $0
addq $19, 8, $19
addq $20, 8, $20
subq $0, 3, $1
bne $1, $32
.loc 2 87
# 86 }
# 87 }
.livereg 0x007F0002,0x3FC00000
ret $31, ($26), 1
.end mult_adj_su3_mat_vec