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
|
//
// Generated by NVIDIA NVVM Compiler
// Compiler built on Sat Mar 30 20:51:33 2013 (1364691093)
// Cuda compilation tools, release 5.5, V5.5.0
//
.version 3.2
.target sm_20
.address_size 64
.visible .entry _Z8myKernelPi(
.param .u64 _Z8myKernelPi_param_0
)
{
.reg .s32 %r<5>;
.reg .s64 %rd<5>;
ld.param.u64 %rd1, [_Z8myKernelPi_param_0];
cvta.to.global.u64 %rd2, %rd1;
.loc 1 3 1
mov.u32 %r1, %ntid.x;
mov.u32 %r2, %ctaid.x;
mov.u32 %r3, %tid.x;
mad.lo.s32 %r4, %r1, %r2, %r3;
mul.wide.s32 %rd3, %r4, 4;
add.s64 %rd4, %rd2, %rd3;
.loc 1 4 1
st.global.u32 [%rd4], %r4;
.loc 1 5 2
ret;
}
|
