forked from jpowie01/CUDA-DNN-MNIST
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathtensor1d.sm_61.ptx
134 lines (105 loc) · 2.36 KB
/
tensor1d.sm_61.ptx
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
.version 5.0
.target sm_61
.address_size 64
.visible .entry _Z4kAddPfS_i(
.param .u64 _Z4kAddPfS_i_param_0,
.param .u64 _Z4kAddPfS_i_param_1,
.param .u32 _Z4kAddPfS_i_param_2
)
{
.reg .pred %p<2>;
.reg .f32 %f<4>;
.reg .b32 %r<3>;
.reg .b64 %rd<8>;
ld.param.u64 %rd1, [_Z4kAddPfS_i_param_0];
ld.param.u64 %rd2, [_Z4kAddPfS_i_param_1];
ld.param.u32 %r2, [_Z4kAddPfS_i_param_2];
.loc 1 5 1
mov.u32 %r1, %ctaid.x;
.loc 1 6 1
setp.ge.s32 %p1, %r1, %r2;
@%p1 bra BB0_2;
.loc 1 5 1
cvta.to.global.u64 %rd3, %rd2;
.loc 1 7 1
mul.wide.s32 %rd4, %r1, 4;
add.s64 %rd5, %rd3, %rd4;
.loc 1 5 1
cvta.to.global.u64 %rd6, %rd1;
.loc 1 7 1
add.s64 %rd7, %rd6, %rd4;
ld.global.f32 %f1, [%rd7];
ld.global.f32 %f2, [%rd5];
add.vf32 %f3, %f2, %f1;
st.global.f32 [%rd7], %f3;
BB0_2:
.loc 1 9 2
ret;
}
.visible .entry _Z9kSubtractPfS_i(
.param .u64 _Z9kSubtractPfS_i_param_0,
.param .u64 _Z9kSubtractPfS_i_param_1,
.param .u32 _Z9kSubtractPfS_i_param_2
)
{
.reg .pred %p<2>;
.reg .f32 %f<4>;
.reg .b32 %r<3>;
.reg .b64 %rd<8>;
ld.param.u64 %rd1, [_Z9kSubtractPfS_i_param_0];
ld.param.u64 %rd2, [_Z9kSubtractPfS_i_param_1];
ld.param.u32 %r2, [_Z9kSubtractPfS_i_param_2];
.loc 1 13 1
mov.u32 %r1, %ctaid.x;
.loc 1 14 1
setp.ge.s32 %p1, %r1, %r2;
@%p1 bra BB1_2;
.loc 1 13 1
cvta.to.global.u64 %rd3, %rd2;
.loc 1 15 1
mul.wide.s32 %rd4, %r1, 4;
add.s64 %rd5, %rd3, %rd4;
.loc 1 13 1
cvta.to.global.u64 %rd6, %rd1;
.loc 1 15 1
add.s64 %rd7, %rd6, %rd4;
ld.global.f32 %f1, [%rd7];
ld.global.f32 %f2, [%rd5];
sub.vf32 %f3, %f1, %f2;
st.global.f32 [%rd7], %f3;
BB1_2:
.loc 1 17 2
ret;
}
.visible .entry _Z6kScalePffi(
.param .u64 _Z6kScalePffi_param_0,
.param .f32 _Z6kScalePffi_param_1,
.param .u32 _Z6kScalePffi_param_2
)
{
.reg .pred %p<2>;
.reg .f32 %f<4>;
.reg .b32 %r<3>;
.reg .b64 %rd<5>;
ld.param.u64 %rd1, [_Z6kScalePffi_param_0];
ld.param.f32 %f1, [_Z6kScalePffi_param_1];
ld.param.u32 %r2, [_Z6kScalePffi_param_2];
.loc 1 21 1
mov.u32 %r1, %ctaid.x;
.loc 1 22 1
setp.ge.s32 %p1, %r1, %r2;
@%p1 bra BB2_2;
.loc 1 21 1
cvta.to.global.u64 %rd2, %rd1;
.loc 1 23 1
mul.wide.s32 %rd3, %r1, 4;
add.s64 %rd4, %rd2, %rd3;
ld.global.f32 %f2, [%rd4];
mul.vf32 %f3, %f2, %f1;
st.global.f32 [%rd4], %f3;
BB2_2:
.loc 1 25 2
ret;
}
.file 1 "/home/evan/Projects/sim-dl-runner/programs/MLP2/./src/tensor/tensor1d.cu", 1612257611, 1712
.file 2 "/usr/local/cuda-8.0/include/cuda_device_runtime_api.h", 1596964847, 13858